Compare commits

...

867 Commits

Author SHA1 Message Date
João Moura
3932d3fea6 [docs-freeze] docs: snapshot and changelog for v1.15.10 (#6756) 2026-07-31 14:57:21 +00:00
João Moura
f262ac214e feat: bump versions to 1.15.10 (#6753) 2026-07-31 14:45:28 +00:00
João Moura
ebe0082aca feat(tracing): collect skill usage events (#6727)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* feat(tracing): collect skill usage events

PR #6652 added SkillUsedEvent but deliberately shipped no listener wiring,
so the event reached no collector. The trace listener subscribed to the five
setup events -- discovery, load, activation, failure -- and none of them can
answer the question skills observability is for: activation is idempotent and
fires once at setup, so an agent using a skill across twenty turns produces
exactly one event.

SkillUsedEvent is the only runtime signal and the only one that re-fires per
execution. Subscribing to it lets a trace attribute skill usage to an agent
and a task.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(tests): scope the trace-listener handlers, assert the forwarded event

CrewAIEventsBus is a singleton, so constructing one in the fixture still
registered against the process-wide bus. _register_action_event_handlers
attached every action handler with no cleanup, leaving them live after the
patch ended -- firing against a listener built with __new__, which has no
batch_manager, in whatever test ran next. scoped_handlers clears them.

Also assert the event object itself is forwarded, not just its type: the
collector serializes the event, so dropping or replacing it would lose every
attribution field while still passing a type-only check.

Both raised in review on #6727.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* test: assert the forwarded skill event by identity

Comparing field values would still pass if a handler forwarded a
reconstructed copy rather than the event itself. Bind the event and assert
`forwarded is event`.

Raised in review on #6727.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-30 18:17:13 +00:00
Gui Vieira
3266932f00 [COR-636] Remove migrated AMP documentation (#6730) 2026-07-30 13:14:34 -03:00
Rip&Tear
ceed4a3ff7 Update security reporting guidelines (#6728) 2026-07-30 21:46:28 +08:00
João Moura
112762a7fa [docs-freeze] docs: snapshot and changelog for v1.15.9 (#6726)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-07-30 05:45:17 +00:00
João Moura
bfe8df4471 feat: bump versions to 1.15.9 (#6725) 2026-07-29 22:40:32 -07:00
João Moura
453676c61a feat(tools): surface tool failures instead of reporting them as success (#6712)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* feat(tools): surface tool failures instead of reporting them as success

A tool can finish without raising and still fail to do what it was asked.
Slack answers HTTP 200 with `{"ok": false, "error": "channel_not_found"}`;
an MCP server sets `isError`; a CrewAI AMP action returns
`API request failed: ...`. In every case the call "worked", so the error
text reached the agent as an ordinary result, the agent narrated the
problem in prose, and the run was recorded as a success.

Concretely: five failed `slackbot_send_message` calls each rendered as
"Tool Execution Completed", the task passed, and the crew passed -- with
the only evidence being a sentence in the final answer. Nothing
downstream could tell the difference, and an agent that keeps going on a
step that silently did nothing builds the rest of its work on it.

Give that outcome a type and a reaction:

- `ToolFailure` -- what a tool returns instead of an error string. The
  agent still reads prose via `as_agent_message()`, so model behavior is
  unchanged; the framework now knows the call failed.
- `ToolFailurePolicy` -- `ignore` (previous behavior), `warn` (default:
  record + emit, keep going), `raise` (abort with
  `ToolExecutionFailedError`). Resolved most-specific-first: tool, task,
  agent, crew.
- `ToolFailureDetectedEvent` -- emitted before a `raise` aborts, so
  subscribers always observe the failure. `ToolUsageFinishedEvent` also
  carries a `failure` field so a trace UI can mark the call failed
  without correlating two events.
- `tool_failures` on `TaskOutput`, `CrewOutput` and `LiteAgentOutput`,
  plus `has_tool_failures`, so consumers never parse a string.

Detection is strictly declarative -- no string sniffing, so a tool that
legitimately returns text about an error is never misread as failing.
Failures come from a returned `ToolFailure`, a raised exception, MCP
`isError`, a spent `max_usage_count`, or an unknown tool.

Wired into all four tool-execution paths (the ReAct path and the three
native function-calling implementations). Sources updated to report
structurally: `MCPClient.call_tool_result()` preserves `isError` that
`call_tool()` dropped, and `CrewAIPlatformActionTool` returns a
`ToolFailure` for non-2xx and for caught exceptions.

Two latent bugs fixed along the way: `ToolUsage` assumed every agent has
a `fingerprint` (LiteAgent does not), and policy resolution now tolerates
malformed values rather than letting telemetry take down a tool call.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): address review round 1 on tool-failure signalling

Five real defects from Bugbot, none of them cosmetic.

Tool-scoped policy never applied (high). `resolve_tool_failure_policy`
read `tool_failure_policy` off the object handed to it, but every
execution path passes the `CrewStructuredTool` wrapper, which never
carried the attribute -- and `BaseTool` never declared it in the first
place. A tool-scoped `raise`/`ignore` was silently ignored while the
docs and a unit test claimed otherwise; the test passed only because it
called the resolver directly with an authored tool. Declared the field on
`BaseTool`, propagated it through `to_structured_tool()` and
`CrewStructuredTool`, and made resolution fall back through
`_original_tool` so either shape works.

A failed call still printed the green "Completed" panel, then the red
one. That is the terminal version of the exact bug this PR is about.
Suppressed the success panel when the call reported failure.

A raised tool printed twice: `ToolUsageErrorEvent` already renders a red
panel, and the new failure panel repeated it. The event is still emitted
-- policy and traces need it -- but the duplicate console output is gone.
Both decisions now live in named predicates on `ConsoleFormatter` rather
than inline in the listener closure, so they are directly testable.

Unknown tools were reported on the ReAct path but silently ignored on all
three native paths, so the same miss was loud or silent depending on
executor style. Native paths now record `UNKNOWN_TOOL` too. This also
surfaced a live `NameError`: ruff had pruned `ToolFailureReason` from
`agent_utils` as unused, so the new branch would have crashed at runtime.

`LiteAgentOutput` had `tool_failures` but not `has_tool_failures`, which
the PR promised on all three output types -- an `AttributeError` for any
caller sharing one check across result types.

Testing: 16 further tests, 45 total. Two console tests were passing
vacuously because `emit()` dispatches sync handlers on a thread pool, so
the assertions raced the handler; they now assert on the predicates
directly, and the native-path test drains the bus with `flush()` and
checks the synchronously-written record. Full suite still matches
baseline exactly at 377 pre-existing failures.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* chore: update tool specifications

* fix(tools): address review round 2 and fix CI type failure

CI caught a type error I should have: widening `agent` to accept a
`LiteAgent` (so a standalone LiteAgent resolves its own policy) left the
declared signatures behind. Widened `execute_tool_and_check_finality`,
its async twin, and `ToolCallHookContext` to `Agent | BaseAgent |
LiteAgent | None`, which is what those actually receive now.

Seven CodeRabbit findings, all verified against the code first:

`raise` was being downgraded by three enclosing handlers. With
`max_execution_time` set, `_execute_with_timeout` wrapped every exception
in `RuntimeError`, so `_check_execution_error` no longer recognized the
passthrough and sent the task through the retry loop instead of aborting.
`StepExecutor.execute` turned it into `StepResult(success=False)` and let
the plan continue. `LiteAgent.kickoff` ran it through
`handle_unknown_error` and printed "This is likely a bug - please report
it" for what is a deliberate, configured stop.

Failure records were dropped on two paths. `reset_tool_failures()` only
ran in `_prepare_task_execution`, so `Agent.kickoff()` / `kickoff_async()`
— which enter through `_prepare_kickoff` — accumulated records across
runs. And a guardrail retry calls `execute_task` again, which resets the
agent, so a tool that failed on a blocked attempt vanished from the final
output entirely: a run could report zero failures having demonstrably
failed one. Failures now accumulate across guardrail attempts.

Writing the tests for that surfaced a further miss of my own:
`Agent.kickoff()` builds its `LiteAgentOutput` in `agent/core.py` via
`AgentExecutor`, not through `LiteAgent`, so `tool_failures` was always
empty there regardless of the recording fix. Wired up, and the LiteAgent
path now reads from whichever agent the executor was handed
(`original_agent` under kickoff, `self` standalone) rather than assuming.

`last_tool_failures` returns a copy, so a caller cannot mutate the
agent's record or watch it shift mid-run.

Testing: 7 further tests, 52 total, covering the timeout wrapper, the
retry limit, kickoff reset, the kickoff output path, copy semantics and
guardrail accumulation. Full suite matches baseline exactly at 377
pre-existing failures; mypy clean on every changed file.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): make crew-scoped policy real and close the last raise leak

Two findings, and the first was a documented feature that never worked.

`resolve_tool_failure_policy` consulted a crew, and the docs advertised
crew as a scope, but `Crew` had no `tool_failure_policy` field at all --
and even with one it was unreachable, because `BaseAgent` defaulted the
policy to `WARN` rather than `None`, so resolution always stopped at the
agent. Crew-level configuration was silently ignored.

Fixed by making "inherit" the default everywhere instead of baking `warn`
into one layer: `Crew` gains the field, and `BaseAgent`/`LiteAgent`
default to `None` like `Task` and `BaseTool` already did. The resolver
owns the single fallback, so the chain is genuinely
tool > task > agent > crew > warn and the effective default with nothing
configured is still `warn`. Reading `agent.tool_failure_policy` now
returns `None` (meaning "inherit") rather than `WARN`.

The other: `StepExecutor` re-raised `ToolExecutionFailedError` from its
outer handler, but the nested handler around the native-to-text tooling
fallback still caught it and returned `StepResult(success=False)`. An
agent whose LLM lacked native tool calling would therefore not abort
under `raise`. That is the third distinct place this exception was being
downgraded; it now re-raises there too.

Testing: 8 further tests, 60 total, including the full precedence chain
walked one level at a time and crew-scoped `raise`/`ignore` driven
end-to-end through `kickoff()` rather than only through the resolver --
the gap that let the original crew bug pass review. Full suite matches
baseline exactly at 377 pre-existing failures; mypy clean on every
changed file.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* docs: trim comments and docstrings on tool-failure signalling

Prose only -- no behavior change. Cut the module docstring, the longer
class and method docstrings, the multi-line inline comments, and the
verbose Field descriptions down to what actually earns its place. Net 87
lines lighter.

Kept the "why" in every case where the reason is non-obvious (why the
event fires before a raise, why the policy reads through the tool wrapper,
why the bus needs draining in tests) and dropped the restatements of what
the code already says.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): make ignore truly silent, stop caching failures, close 4 gaps

Six findings from the latest review round, all verified against the code
before touching it.

`ignore` was not silent. `ToolUsageFinishedEvent.failure` was set before
the policy ran, so traces still saw a failed call under a policy documented
as surfacing nothing. Worse, the console then showed *no* panel at all:
green was suppressed because `failure` was present, red was skipped because
`ignore` never emits `ToolFailureDetectedEvent`. New `reportable_failure()`
resolves the policy before the finished event and drops the flag under
`ignore`; wired into all four execution paths.

Failures were being cached. `CacheHandler.add` stored a `ToolFailure` like
any other result, so a transient error became permanent for the rest of the
run and every later hit re-reported a call that never re-ran. The cache now
refuses to store declared failures -- fixed at the single choke point rather
than at each of the four call sites.

A spent `max_usage_count` was invisible on the shared native path.
`BaseTool._claim_usage` returned a bare string that only the executors
recognising that exact message treated as a failure. It now returns a
`ToolFailure` with `USAGE_LIMIT`, so every path records it.

A guardrail returning a whole `TaskOutput` replaced the output without
carrying accumulated failures over, so earlier attempts vanished from
`CrewOutput.tool_failures`. New `merge_tool_failures()` combines and
deduplicates, and the retry-rebuild path uses it too.

A hook-blocked call inherited a cached failure and attributed it to a call
that never ran. Now cleared. Not reachable through the built-in cache once
failures stop being cached, so the test injects a custom cache handler that
does retain them -- verified to fail without the guard.

Also removed a `datetime` import left unused by the earlier console-test
rewrite.

Testing: 13 further tests, 73 total. Full suite matches baseline exactly at
377 pre-existing failures; the usage-limit suites that `_claim_usage`
touches pass unchanged; mypy clean on every changed file.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): let raise through the parallel native path, guard all handlers

Chasing down CodeRabbit's note about callers of
execute_single_native_tool_call turned up a fifth place this exception was
being downgraded: the experimental executor's parallel branch wrapped
future.result() in a broad except and folded the abort into a fake tool
result, so the remaining parallel calls carried on. The sequential path and
crew_agent_executor's parallel branch were already fine.

Five separate handlers have swallowed this during review, so added a guard
test asserting the passthrough at every site rather than trusting the next
one gets spotted.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): keep a failed tool out of the final answer, finish crew scope

Three more findings, all confirmed against the code.

A failed `result_as_answer` tool still became the task's output. The native
paths already excluded raised errors and hook blocks from short-circuiting,
but not declared failures -- so an error message silently became the answer,
which is the exact shape of bug this PR exists to prevent. Fixed on all
paths, and there were three independent override points, not one:
`ToolResult.result_as_answer` in tool_utils, the `execution_result`
finality checks in both executors, and `process_tool_results()`, which
reads `agent.tools_results` back separately. The first two fixes alone left
the behavior unchanged; only the third made the test pass.

`ToolUsage` never received a crew, so a crew-level `ignore` half-applied:
recording and `ToolFailureDetectedEvent` stayed quiet, but the flag was
still attached to `ToolUsageFinishedEvent`. It now takes and stores `crew`.

`CrewAgentExecutor.invoke`/`ainvoke` routed a deliberate stop through
`handle_unknown_error`, printing "An unknown error occurred" on verbose
runs. LiteAgent already special-cased this; both now do.

Testing: 5 further tests, 79 total, including that a *successful*
`result_as_answer` tool still short-circuits. Full suite matches baseline
exactly at 377 pre-existing failures; mypy clean on every changed file.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): report malformed tool args, correlate the failure event

Two findings from the latest round.

Malformed native tool arguments returned early with a plain error dict and
never reported a failure, so `ToolFailureReason.INVALID_INPUT` was declared
but unreferenced -- a bad tool call was absent from records, events and
`raise` aborts. `parse_tool_call_args` now carries an INVALID_INPUT failure
on the error dict and both executors report it before returning.

`ToolFailureDetectedEvent` never set `agent_id`, so a trace could not tie it
to a specific agent instance. Fixing that exposed the same gap running the
other way: `ToolUsage`'s own started/finished/error events never set
`agent_id` either, so on the ReAct path the paired finished event had
nothing to correlate against. Both now set it.

Set explicitly rather than via `from_agent`, which would also overwrite
`agent_role` and lose the `_original_role` preference those events already
apply -- a behavior change that has nothing to do with correlation.

Testing: 5 further tests, 84 total, asserting the ids match between the
failure event and its paired finished event. One existing test pinned the
exact key set of the parse-error dict and was updated for the new key. Full
suite matches baseline at 377 pre-existing failures; the one apparent
addition was the known `test_trace_enable_disable` order-flake, confirmed by
re-running rather than assumed.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): scope failure accumulation per execution, drop deprecated executor

Two review requests from @lorenzejay.

Accumulation no longer lives as mutable state on the shared agent. A
ContextVar collector is opened around each execution -- task, kickoff, and
each guardrail retry -- and the output reads that collector directly instead
of copying the agent's list. ContextVars are copied per asyncio task and per
thread, so concurrent executions cannot see each other's records, and
nesting is safe for retries. `last_tool_failures` prefers the active
collector and falls back to the last completed execution, so the accessor is
correct during a run too. The per-execution reset that caused the erasure is
gone.

Reproducing this took some digging and the finding is worth recording: crew
tasks *cannot* hit it, because `AgentExecutor` refuses concurrent reuse of
one instance and raises. `agent.kickoff()` has no such guard, and there the
bug reproduces exactly as reported -- two concurrent kickoffs each returned
two records. The regression test forces the overlap with a barrier so it is
deterministic rather than timing-dependent, and I verified it reports [2, 2]
against the old behavior and [1, 1] now.

Removed the tool-failure integration from `CrewAgentExecutor` entirely; that
file is back to its state on main. Note the shared ReAct helper it calls
still records failures, since that is common code rather than new behavior in
the deprecated file -- so a `raise` policy will be swallowed by that
executor's generic handler. Flagged on the PR rather than papered over.

Testing: 89 total. Two tests I wrote for this were vacuous on the first
attempt -- they passed against the simulated pre-fix code -- so each
concurrency test was checked against the old behavior before being kept.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): report malformed calls everywhere, drop the unused block reason

Four findings.

`execute_single_native_tool_call` swallowed a JSON decode error into an empty
args dict and ran the tool with no input at all -- worse than not reporting
it. It now routes through `parse_tool_call_args` like the executors do, so
the StepExecutor/planning path reports INVALID_INPUT and returns instead of
executing. That also removes a duplicated inline parse.

The ReAct path returned a `ToolUsageError` message as an ordinary result
without reporting it, so a malformed call there was invisible while the
equivalent native failure was recorded. Now reported as INVALID_INPUT too.

`Agent.kickoff` opened a collector but no longer reset the agent-level list,
so `last_tool_failures` grew across kickoffs. Reset restored, matching task
execution.

`ToolFailureReason.BLOCKED_BY_HOOK` was declared and never produced. Rather
than start reporting hook blocks as failures, the member is removed: a block
is a deliberate decision by the hook author, and treating it as a failure
would make `raise` abort on an intentional veto. Added a guard test that every
remaining reason is actually produced somewhere, so a dead member cannot
reappear -- the same smell that flagged INVALID_INPUT last round.

Also switched the deprecation guard test to a single import style.

Testing: 6 further tests, 95 total, including that the tool does not run when
its args fail to parse. Full suite matches baseline at 377 pre-existing
failures; mypy clean.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

* fix(tools): merge failures across kickoff guardrail retries, cancel siblings

Kickoff guardrail retries discarded the blocked attempt's failures. Each
retry calls `_execute_and_build_output`, which opens a fresh collector and
builds a new output, so a run could report zero failures having demonstrably
failed one -- the same bug already fixed on the task guardrail path, which
merges. Now merged there too. Verified the test fails without the fix.

Under `raise`, one parallel native tool aborting left its siblings running:
the pool waited for them and pending ones still started. It now shuts the
pool down with `cancel_futures=True` so a not-yet-started sibling never runs.
Threads already in flight cannot be interrupted in Python, so a concurrent
tool may still complete before the abort surfaces; that is noted at the call
site rather than left implied.

Also satisfied CodeQL by materialising the enum in the guard test's loop.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ETacm2dMASfpMAYUiDu5YG

---------

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-07-29 19:30:14 -07:00
Lucas Gomide
d52d0a1628 feat: emit FlowFailedEvent when a flow execution fails (#6718)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* feat: emit FlowFailedEvent when a flow execution fails

A failed flow never emitted a terminal lifecycle event, so the
`flow_started` scope stayed open and consumers such as tracing closed the
root span with a generic orphaned message instead of the real error.
`kickoff_async` and the resume path now emit `FlowFailedEvent`, paired
with `flow_started` and carrying the exception, after draining pending
handlers and background memory writes. The resume path also emits the
`MethodExecutionStartedEvent` it was missing for the method being resumed,
so its finished or failed event pairs with its own scope instead of
popping the flow's.

* fix: skip FlowFailedEvent when the run never opened a scope

The `kickoff_async` try block starts before `FlowStartedEvent` is emitted,
so an abort in the execution-start hooks, in input handling or in state
restore emitted a `flow_failed` with no opener, which pops an unrelated
scope and warns about an empty scope stack. The failure event is now
gated on the flow scope actually being open, either from this kickoff's
`flow_started` or from a restored deferred session scope.
2026-07-29 14:44:55 -04:00
Lorenze Jay
f15844b219 Lorenze/imp/skills progressive disclosure (#6675)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* skills progressive disclosure

* skills progressive disclosure

* improving progressive disclosure

* addressed comment

* fix test

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2026-07-28 09:33:43 -07:00
João Moura
e9caf1e1b8 [docs-freeze] docs: snapshot and changelog for v1.15.8 (#6703) 2026-07-28 15:05:44 +00:00
João Moura
133baf39b8 feat: bump versions to 1.15.8 (#6702) 2026-07-28 14:59:36 +00:00
João Moura
2e95bfb4e8 fix(tools): sandbox FileWriterTool writes and fix file tool rough edges (#6692)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix(tools): sandbox FileWriterTool writes and fix file tool rough edges

FileReadTool confined reads to the working directory, but FileWriterTool
only checked that `filename` stayed inside `directory` — and `directory`
itself is an LLM-supplied schema field. An agent could therefore write
anywhere the process had permission to, including ~/.ssh and site-packages,
while the reader refused to read back what the writer had just written.
FileWriterTool was the only filesystem tool in the package that did not go
through validate_file_path; files_compressor_tool validates even its
output path.

Writes are now confined to base_dir (the working directory by default):
the resolved directory must sit inside base_dir, and the resolved file
must sit inside that directory. The pre-existing filename containment
check is kept as-is and still applies even when the unsafe-paths escape
hatch is on, so no existing guarantee is weakened.

Both tools gain a base_dir field so a developer can widen the sandbox
deliberately instead of reaching for the process-wide
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS kill switch. FileReadTool also stops
rejecting a file_path given to its own constructor: that is
developer-declared intent, and declaring one file does not expose its
siblings.

Also fixed:

- FileReadTool scanned the whole file when reading a line window; it now
  stops via islice once the requested lines are collected.
- FileWriterTool._run(**kwargs) made the documented positional call
  signature raise TypeError and turned a missing overwrite into
  "error accessing key". It now takes named parameters in the documented
  (filename, content, directory) order.
- A directory naming an existing file reported "already exists and
  overwrite option was not passed" even with overwrite=True; it now
  explains the real problem.
- Subdirectories inside filename are created, matching what passing
  directory already did.
- Both tools now write and decode UTF-8 by default instead of the
  platform locale encoding, with an encoding field to override. The docs
  already claimed UTF-8 and recommended the writer to Windows users.
- The writer's schema fields had no descriptions for the LLM.
- Docs claimed FileReadTool parses JSON into a dict (it never has),
  shipped a snippet that raised TypeError, and did not mention the path
  sandbox. The writer README also began with a stray "Here's the
  rewritten README" preamble.

BREAKING CHANGE: FileWriterTool no longer writes outside the working
directory. Pass base_dir to authorize a different tree.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* chore: update tool specifications

* fix(tools): make the declared FileReadTool file reachable by agents

Addresses review feedback on #6692.

The constructor-path exemption did not actually work the way an agent
calls the tool. The description only advertises a redacted label (the
basename, when the file sits outside the sandbox), but resolution
required the exact absolute path, so the model's call was sandboxed and
the declared file was never read. Worse, file_path was a required schema
field, so the long-documented "call with no arguments to read the default
file" raised a validation error instead:

    FileReadTool(file_path="/outside/declared.txt")
    .run()                          -> ValueError: validation failed
    .run(file_path="declared.txt")  -> Error: File not found
    .run(file_path="/outside/declared.txt") -> works, but the model was
                                               never told this path

file_path is now optional in the schema, so omitting it reads the default,
and the declared file is addressable by the label the description shows
the model as well as by its real path. Declaring one file still does not
expose its siblings.

The declared path is also pinned to its real path at construction, so a
later chdir cannot silently repoint it at a different file — previously a
relative constructor path re-resolved against the new working directory
on every call.

Also guards the writer's filepath resolution, which could raise
ValueError out of _run for a filename containing a null byte, breaking
the contract of always returning a descriptive string. The directory and
read paths were already guarded.

Adds docstrings to strtobool and both _run methods, corrects an Arabic
tanween spelling and a kaf-as-descriptor calque in the localized read
docs, and regenerates tool.specs.json for the schema change.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(tools): anchor the declared read path to base_dir, not the cwd

Addresses the second round of review feedback on #6692.

The previous commit pinned a relative constructor file_path with
os.path.realpath, which anchors to the working directory, while both
format_path_for_display and validate_file_path anchor a relative path to
base_dir. With the two roots disagreeing, the same relative string meant
two different files — and the tool served the cwd one under a label that
looks like it belongs to the sandbox:

    FileReadTool(file_path="data.txt", base_dir="/allowed")   # cwd=/work
    label advertised to the model -> "data.txt"
    run(file_path="data.txt")     -> contents of /work/data.txt

That reads a file from outside base_dir, so it was a sandbox escape
introduced by the exemption itself, not just a wrong-file bug.

Resolution now goes through a single _resolve_against_base helper that
anchors relative paths exactly the way the sandbox does, so the pinned
path, the advertised label and the containment check all agree. Covered
by test_relative_declared_path_anchors_to_base_dir.

Also softens "always readable" to "always allowed past the containment
check" in the docstring, README and docs, since bypassing containment
does not guarantee the read succeeds — it can still fail on a missing
file, a directory, or permissions.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(tools): tell the LLM about the path sandbox in tool descriptions

Addresses the low-confidence notes from the Copilot review on #6692.

Both tools' descriptions were pre-sandbox wording, so the model learned
about containment only by attempting a path and reading the error back.
Both now state that access is confined to the tool's allowed directory
and that a path resolving outside it is rejected.

The wording deliberately says "the tool's allowed directory" rather than
"the working directory", because the root is base_dir when one is set,
and naming the absolute root would leak it into the prompt — the same
reason paths are redacted in errors.

Not changed: the notes also suggested advertising `encoding`. That is a
constructor-only field the model cannot set, so describing it to the LLM
would be misleading.

Also fixes a test docstring that contradicted its own assertion — the
public run() path does raise on schema validation failure, which is what
the test asserts.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(tools): anchor base_dir at construction so the sandbox cannot move

Addresses the third review round on #6692.

Both remaining findings came from the same habit: storing an unanchored
string and re-resolving it later.

A relative base_dir was kept verbatim and re-resolved against getcwd() on
every call, while the declared file was pinned once at construction. After
a chdir the sandbox root moved but the declared default did not, so one
tool applied two different roots. base_dir is now resolved once — in the
reader's __init__, and via a field_validator on the writer so it also
applies on the model_validate path.

That also covers the serialization concern. model_dump drops the private
pin, and __init__ re-runs on restore, so a relative file_path was
re-anchored against whatever the working directory happened to be at load
time. With base_dir anchored, restore rebuilds the identical pin.

The residual case is a relative file_path with no base_dir, where the
sandbox root is the working directory too — so both move together and the
tool stays self-consistent. Covered by
test_declared_path_survives_a_serialization_round_trip and
test_relative_base_dir_is_anchored_at_construction on both tools.

Also corrects the writer's 'directory' description, README and docs: the
default resolves inside the tool's allowed directory, which is base_dir
when one is set, not always the working directory.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-07-28 02:20:26 -07:00
João Moura
97981ed31b feat(tools): add WaitTool for pausing on long-running jobs (#6690)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* feat(tools): add WaitTool for pausing on long-running jobs

Agents that kick off out-of-band work (a sandbox build, a deployment, an
async API job) have no way to let clock time pass: they either poll in a
tight loop or give up before the work finishes.

WaitTool pauses for a given number of seconds, with an optional reason
echoed back for traces. A single call waits at most max_seconds (default
300, configurable). Longer requests are clamped to the cap and the result
says so, so the model calls again rather than failing. Sync and async
execution are both implemented; stdlib only, no new dependencies.

The tool description spells out when to reach for it (builds, deploys,
batch jobs, async polling, backoff) and when not to, so models pick it up
for the right reason.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(tools): enforce non-negative wait on positional calls, fix doc snippets

BaseTool.run() skips args_schema validation when called with positional
arguments, so tool.run(-5) reached time.sleep(-5) and failed with an
unrelated error. _resolve_duration now enforces the seconds >= 0 contract
itself, covered for both run() and arun().

Docs and README examples are now self-contained: check_build_status_tool
is defined with the @tool decorator instead of referenced out of nowhere,
and the async example awaits inside asyncio.run() rather than at top level.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* docs: point the wait tool card at the edge path

Unprefixed links resolve against the default docs version (v1.15.7),
where the wait tool page does not exist, so the card 404'd in the broken
link check. Prefixing with /edge matches how other edge pages link.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(tools): never cache waits and keep the advertised cap accurate

Two issues from review, both confirmed against the code.

Waits inherited the default cache_function, which always allows caching.
With crew cache enabled, a repeat call with the same arguments returned
"Waited N seconds." straight from the cache without sleeping, turning a
poll-wait-check loop into a busy loop. WaitTool now declares a
cache_function that always refuses.

The description advertising the cap was only rebuilt when max_seconds
reached __init__ without an explicit description. Passing both (as a
platform building from tool.specs.json init params would), calling
model_validate, or assigning max_seconds left the text claiming 300
seconds while clamping to something else. A model_validator now derives
the description from max_seconds on construction, validation, and
assignment, and leaves a caller-supplied description untouched.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(tools): reject NaN waits and pluralize single-second results

_resolve_duration now rejects NaN with its own message instead of letting
time.sleep raise "Invalid value NaN (not a number)" from a positional
call. Infinity keeps clamping to the cap like any other oversized wait.

Result and description text no longer says "1 seconds". Tests use the
public WaitTool().description as the baseline rather than reaching for
module-private helpers.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-27 17:12:27 -07:00
Thiago Moretto
e2c8d7ca88 fix: mark E2B_API_KEY as a required env var for E2B tools (#6688)
E2B_API_KEY was declared with required=False on the shared E2B tool
base (E2BExecTool, E2BFileTool, E2BPythonTool), even though none of
the three tools can create or attach to a sandbox without it.
E2B_DOMAIN stays optional since it genuinely defaults to e2b.dev.

Regenerated lib/crewai-tools/tool.specs.json via
generate_tool_specs.py to reflect the change.
2026-07-27 18:31:51 +00:00
Lucas Gomide
ca5ef810be ci: check doc links only on edge and latest versions (#6633)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
`mintlify broken-links` walks every frozen version snapshot under
`docs/` (currently 22 of them), pushing docs PR checks past 14 minutes
and growing with each release. Prune the immutable snapshots — keeping
`edge` and the default (latest) version, which unprefixed links resolve
against — before running the checker, cutting the run to ~30 seconds.
`workflow_dispatch` still checks the full tree, and the deprecated
`mintlify` CLI is swapped for `mint`, which drops the `yes` prompt hack.
2026-07-27 08:22:01 -04:00
Ossama Alami
daa7019898 docs(llms): refresh model availability guidance (#6676)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* docs(llms): refresh model availability guidance

* docs: clarify structured output support

* docs: address LLM guide review feedback

* docs: refresh streaming model examples
2026-07-26 16:13:36 -07:00
João Moura
1870b444e7 [docs-freeze] docs: snapshot and changelog for v1.15.7 (#6673) 2026-07-26 11:19:47 -07:00
João Moura
38ca5edce2 feat: bump versions to 1.15.7 (#6672) 2026-07-26 18:07:46 +00:00
Lorenze Jay
213d9485fe docs: snapshot and changelog for v1.15.7a1 (#6665)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-07-26 14:04:16 -03:00
Lorenze Jay
c459d01c35 feat: bump versions to 1.15.7a1 (#6661) 2026-07-26 13:47:11 -03:00
João Moura
cc0759854d fix(skills): resolve registry skills through the runtime's CrewAI+ client (#6658)
* fix(skills): resolve registry skills through the installed AMP client

Skill downloads built their own `PlusAPI` and authenticated it from
`CREWAI_USER_PAT`, the platform integration token, or the saved CLI login.
Managed runtimes have no user credential to offer: they install a client of
their own, which `load_agent_from_repository` already resolves through, so
Agent Repository lookups worked while the skill downloads beside them failed
with 401.

Skills now resolve their client the same way, via `resolve_plus_client()` next
to the hook it reads. A client that can't fetch skills falls back to
environment credentials and warns, so older runtimes behave as they do today.
`resolve_plus_response()` shares the sync/async bridging both lookups need,
since `PlusAPI` is synchronous while managed clients are not.

Version pinning, which the same bug was hiding:

- Registry refs accept `@org/name@version`, and `@org/name@v1.2.0` since people
  write it both ways. `parse_skill_ref()` returns a `SkillRef(org, name,
  version)`; `parse_registry_ref()` keeps its `(org, name)` shape and drops the
  pin, so existing callers are unaffected
- Agent Repository agents record a version per skill, which was parsed off the
  response and dropped. Those pins now travel with the refs, so publishing a
  new version of a skill no longer changes every agent that uses it
- A pinned ref only accepts a project-local copy declaring that version in its
  `metadata.version` frontmatter, and the cache reports a miss when the version
  it recorded differs — so a pin re-resolves rather than loading another
  version. Unpinned refs keep hitting the cache as before
- An unknown pin fails instead of quietly falling back to the newest version

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(skills): reject a blank version pin instead of floating to latest

A blank `version` passed to `download_skill` read as "unpinned" and quietly
resolved the latest version, which is not what a caller supplying one asked
for — and it disagreed with `parse_skill_ref`, which already rejects empty
pins. Not reachable through `resolve_registry_ref` or the Agent Repository
auto-pinning, both of which only ever pass a non-empty version.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(skills): carry the caller's context into the worker thread

When resolve_plus_response bridges an async client from inside a running loop
it runs the coroutine on a worker thread, which starts with empty ContextVars.
A client reading runtime state there — the platform integration token, flow
context — would see defaults rather than the caller's values, which is hard to
diagnose from the resulting auth or routing failure.

Copy the context across, matching how the parallel-summarization bridge in this
module already does it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-26 13:27:29 -03:00
alex-clawd
bd2cb0f23e fix(openai): recover from the GPT-5.6 tools + reasoning_effort 400 (#6660)
An ordinary agent with a tool fails on the whole GPT-5.6 family:

    Agent(role=..., goal=..., backstory=...,
          llm=LLM(model="openai/gpt-5.6-sol"), tools=[multiply])

    Function tools with reasoning_effort are not supported for gpt-5.6-sol in
    /v1/chat/completions. To use function tools, use /v1/responses or set
    reasoning_effort to 'none'.

Nothing sets reasoning_effort -- not the user, not CrewAI. The family applies a
server-side default and then refuses it once tools are present. Confirmed with
raw HTTP, no CrewAI involved, on a payload with no reasoning_effort key at all:

    gpt-5.6-sol  tools, no reasoning_effort key   -> 400
    gpt-5.6-sol  tools, reasoning_effort="none"   -> OK
    gpt-5.5      tools, no reasoning_effort key   -> OK
    gpt-5.4      tools, no reasoning_effort key   -> OK
    gpt-5.2      tools, no reasoning_effort key   -> OK

So this is GPT-5.6 only, and it needs an explicit "none" -- dropping the key is
what the rejected request already looked like.

Recovered from the error rather than a model list: catch the 400, resend with
reasoning_effort="none", once. No model names, so a family OpenAI restricts later
works without a release here. Detection matches the structured `param` field plus
the message, so the unrelated "Unsupported value" 400 that o1/o3 return for
"none" isn't mistaken for this one, and the retry can't loop.

Verified against main with real agents (no reasoning_effort anywhere):

    model          no tools   tools        tools + reasoning=True
    gpt-5.6-sol    ok / ok    400 / ok     hang / ok
    gpt-5.6-terra  ok / ok    400 / ok        - / ok
    gpt-5.6-luna   ok / ok    400 / ok        - / ok
    gpt-5.5        ok         ok              -
    gpt-5.2        ok         ok           ok / ok
    gpt-4o         ok         ok              -

On main, tools + Agent(reasoning=True) produced no output and no error and was
killed at 420s; gpt-5.2 with the same config finishes in ~40s. Both the 400 and
that hang are fixed.

Tests: 15 cases, including agent definitions with tools, with tools plus
reasoning=True, and without tools. tests/llms + tests/agents -> 961 passed
(1 pre-existing unrelated failure from a local OLLAMA_API_KEY env leak).
Ruff + mypy clean.
2026-07-26 12:48:17 -03:00
alex-clawd
c52d0d9530 fix(openai): make tool calling work on the Responses API path (#6657)
* fix(openai): make tool calling work on the Responses API path

An agent with tools on api="responses" never produced an answer. It returned the
raw tool-call list instead:

    [{'id': 'call_...', 'name': 'multiply', 'arguments': '{"a":17,"b":23}'}]

Three defects in the chain, all on the Responses side only:

1. `is_tool_call_list()` knew the OpenAI-nested, Anthropic, Bedrock and Gemini
   shapes but not the Responses one ({"id", "name", "arguments"} -- no nested
   "function", no "input"). The list wasn't recognized as tool calls, so the
   executor handed it back verbatim as the final answer.

2. `extract_tool_call_info()` read "arguments" only from a nested "function"
   object, falling back to "input". For the Responses shape both missed and the
   arguments silently became {}, so the tool would have run with no input.

3. With those fixed the tool ran, then the follow-up request 400'd:

       Invalid type for 'input[1].content': expected one of an array of objects
       or string, but got null instead.

   Tool calling is expressed differently by the two APIs. Chat Completions uses an
   assistant message carrying `tool_calls` with content: None, then role: "tool"
   results. The Responses API uses flat function_call / function_call_output items
   keyed by call_id. Those messages were passed through untranslated.

`_to_responses_input()` now converts them. Messages without tool calls pass
through unchanged, so nothing else moves.

Verified end to end against the live API:

    api="responses" + tools           -> 391   (was raw tool-call JSON)
    chained multi-step tool calls     -> 400   (17*23, then +9)
    completions path (control)        -> 391   (unchanged)

The generated `input` payload was also posted to /v1/responses directly and
accepted, and the pre-fix chat-shaped payload confirmed as a 400.

This is why api="responses" never worked for agents: the provider side has had a
full Responses implementation since #4258/c4c9208, but the executor never learned
the shape it emits. Fixing it also unblocks routing gpt-5.4+ tool calls to the
Responses API instead of dropping reasoning_effort.

Tests: 12 cases covering recognition, extraction (including that the Chat
Completions and Bedrock shapes are unaffected), translation of assistant/tool
messages, parallel calls, assistant text alongside tool calls, non-string tool
output, and the full prepared `input` list.

* fix(openai): prefer Responses "call_id" over the item's own "id"

Per CodeRabbit review. A raw Responses function_call item carries both keys with
different values, confirmed against the live API:

    keys    ['arguments', 'call_id', 'id', 'name', 'status', 'type']
    id      fc_0adeb715c5d740c7006a65ccb72b948199872ad8b5a5c53108
    call_id call_dEoHFrYnOgWYvk17FymdcDZ5

function_call_output must reference call_id. Reading the item's own "id" would
produce a tool result the model can't correlate back to its invocation.

Our own _extract_function_calls_from_response already maps item.call_id into "id",
so the normal path was correct and the existing tests passed. But
extract_tool_call_info is a shared helper reached from every provider's tool loop,
and a raw Responses item is a plausible thing to hand it -- silently picking the
wrong identifier is a bad trap to leave in place for one line of guard.

Tests: raw item extraction asserting call_id is chosen over id, and a round-trip
check that the id extracted from a call is the one sent back with its result.
997 passed across tests/llms, test_agent_utils and tests/agents (1 pre-existing
unrelated failure from a local OLLAMA_API_KEY env leak). Real two-agent chained-tool
run still returns the correct answer.

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2026-07-26 06:18:20 -03:00
alex-clawd
b64c92c87b fix(openai): route responses-only models instead of failing with 404 (#6656)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
The pro tier is not served by /v1/chat/completions. Probing the live endpoints:

    model         /v1/chat/completions   /v1/responses
    gpt-5-pro     404                    OK
    gpt-5.5-pro   404                    OK
    gpt-5.4-pro   404                    OK
    gpt-5.2-pro   404                    OK
    o1-pro        404                    OK
    o3-pro        404                    OK

Since api defaults to "completions", LLM(model="openai/gpt-5-pro") fails with
"Model ... not found", which is misleading -- the model exists, the endpoint is
wrong. OpenAI's own 404 text ("This is not a chat model") doesn't make the fix
obvious either.

These requests now route to the Responses API automatically, which is verified to
work for every model above. An explicit api= setting is always honoured.

Model matching normalizes the configured string first, so "openai/gpt-5-pro" and
"gpt-5-pro-2025-10-06" both resolve to "gpt-5-pro". It's an exact list rather
than a "-pro" substring, so a custom deployment named "gpt-4-pro-custom" isn't
swept up.

The chat-completions 404 handler also gained an actionable message: when the
response says responses-only, or the model is a known pro model, the error names
api="responses" instead of just reporting "not found".

Tests: 29 cases covering name normalization, detection, routing (including that
call() reaches the Responses handler), and both 404 message paths.
2026-07-26 06:03:09 -03:00
alex-clawd
80fa0295c4 Emit skill usage events at runtime for observability (#6652)
* feat: emit skill usage events at runtime

* test: cover skill events via execute_task paths
2026-07-26 05:04:19 -03:00
alex-clawd
728183e420 fix(deps): bump bedrock-agentcore to patch CVE-2026-16796 (#6654)
bedrock-agentcore 1.7.0 has GHSA-j6g5-3hh3-pgw8 (CVE-2026-16796, high):
argument-delimiter injection in CodeInterpreter.install_packages(). It fails
the pip-audit vulnerability scan on every PR in the repo.

The patch is 1.18.1, which requires boto3>=1.43.31. The old <1.8.0 cap plus
aiobotocore~=3.5.0 (botocore<1.42.92) made that unsatisfiable, so the AWS
stack moves together:

- bedrock-agentcore >=1.7.0,<1.8.0 -> >=1.18.1,<2.0.0
- boto3 ~=1.42.90 -> ~=1.43.46  (aws + bedrock extras)
- aiobotocore ~=3.5.0 -> ~=3.8.0 (aws + bedrock extras)

aiobotocore 3.8.0 allows botocore <1.43.47 and boto3 1.43.46 pins botocore
1.43.46, so the ranges overlap.

Verified: uv lock resolves, pip-audit reports no vulnerabilities (3 existing
ignores, none new), 48 bedrock tests pass, and both bedrock toolkits import
cleanly. BrowserClient.{start,stop,generate_ws_headers} and
CodeInterpreter.{start,stop,invoke} are unchanged in 1.18.1.
2026-07-26 04:55:05 -03:00
Lorenze Jay
b3aaaab023 [docs-freeze] docs: snapshot and changelog for v1.15.6 (#6632)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-07-24 20:30:21 +00:00
Lorenze Jay
a4cbeacca5 feat: bump versions to 1.15.6 (#6631) 2026-07-24 20:21:58 +00:00
alex-clawd
c528e8bdee fix: detect Anthropic preview tool-use blocks (#6629)
* fix: detect anthropic preview tool-use blocks

* fix: preserve typed Anthropic tool-use blocks

* fix: bump gitpython for vulnerability scan

* docs: clarify gitpython advisory ranges

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-07-24 15:32:38 -03:00
alex-clawd
c06043f7e8 fix: preserve strict tool schema property names (#6628) 2026-07-24 09:49:05 -07:00
Rip&Tear
b14d36bfe4 chore: bump json-repair to 0.60.1, drop fixed vuln ignores in scan (#6612)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* chore: bump json-repair to 0.60.1 and un-ignore fixed vulns in scan

- json-repair 0.25.3 -> 0.60.1 (fixes GHSA-xf7x-x43h-rpqh)
- pyOpenSSL already at 26.2.0 in lock (covers CVE-2026-27448, CVE-2026-27459)
- remove the corresponding --ignore-vuln flags from vulnerability-scan.yml

* fix: adapt _safe_repair_json to json-repair 0.60 semantics

json-repair >= 0.60 returns an empty string for plain-text input and
wraps brace-enclosed junk in a single-element list instead of the old
""/{} sentinel values. Treat both as unrepairable so the original
tool input is preserved.

* chore: fix CI - bump gitpython/pyasn1, drop stale type ignores

- gitpython 3.1.50 -> 3.1.52 (GHSA-2f96-g7mh-g2hx, GHSA-v396-v7q4-x2qj,
  GHSA-956x-8gvw-wg5v; fixed in 3.1.51)
- pyasn1 0.6.3 -> 0.6.4 (GHSA-8ppf-4f7h-5ppj, GHSA-hm4w-wwcw-mr6r)
- json-repair 0.60 ships type stubs; remove now-unused
  type: ignore[import-untyped] comments flagged by mypy
2026-07-22 16:47:33 -07:00
Lucas Gomide
3bb87532da fix: dispatch execution_end hook on failed crew and flow executions (#6607)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: dispatch execution_end hook on failed crew and flow executions

The `execution_end` interception point only fired after a successful
kickoff, so consumers never learned about failed runs. Crew kickoff
paths (`kickoff`/`akickoff`) and the flow runtime (`kickoff_async`,
`resume_async`) now dispatch it on the failure path too, with new
additive `status` ("completed"/"failed") and `error` fields on
`ExecutionEndContext`. Pairing flags guarantee exactly-once dispatch,
keep the start/end pairing invariant, and the original exception
propagates unchanged.

* fix: track execution_end pairing per invocation for reentrant flows

Reentrant kickoffs on the same Flow instance are supported (usage
aggregation already accommodates them), but the instance-level pairing
booleans let an inner kickoff's completion mark the outer execution as
ended, skipping the outer failure's `execution_end`. The pairing state
now lives in each `kickoff_async` invocation's locals, and the resume
path passes a per-invocation holder into `_resume_async_body`. Crew
keeps its instance flags since crew kickoffs are not reentrant on the
same instance (`kickoff_for_each` copies the crew).
2026-07-21 15:25:06 -04:00
iris-clawd
6d496f799b fix: handle async get_agent in load_agent_from_repository (#6608)
* fix: handle async get_agent in load_agent_from_repository

The enterprise PlusClient.get_agent() is async, but
load_agent_from_repository() calls it synchronously. When the enterprise
client is hooked in, client.get_agent() returns a coroutine instead of a
response, causing "'coroutine' object has no attribute 'status_code'".

This adds an inspect.isawaitable() check after the call: if the response
is a coroutine, it is properly awaited via asyncio.run() (or via a
thread-pool executor if an event loop is already running).

Co-authored-by: Joe Moura <joao@crewai.com>

* fix: resolve mypy type-checker errors for async awaitable handling

* fix: remove unused type: ignore comment

---------

Co-authored-by: Joe Moura <joao@crewai.com>
2026-07-21 15:21:41 -03:00
Lorenze Jay
40279e3152 fix dep resolution (#6605)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-07-21 08:37:08 -03:00
Vinicius Brasil
ce739e28c7 [docs-freeze] docs: snapshot and changelog for v1.15.5 (#6602)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-07-20 12:33:16 -04:00
Vinicius Brasil
4c7e483936 feat: bump versions to 1.15.5 (#6601) 2026-07-20 16:20:33 +00:00
Vinicius Brasil
fa255387a3 Authenticate skill registry downloads (#6600)
Registry downloads initialized PlusAPI without credentials, so uncached skills failed outside CLI-authenticated flows and were blocked entirely in non-interactive environments.

Use CREWAI_USER_PAT first, then the platform integration token, then the saved login token, and pass CREWAI_ORGANIZATION_UUID. Remove the non-interactive cache-only restriction so runtime downloads work.
2026-07-20 12:43:03 -03:00
Vinicius Brasil
69c0308f2c [docs-freeze] docs: snapshot and changelog for v1.15.4 (#6583)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-07-17 14:33:07 +00:00
Vinicius Brasil
e0bd967484 feat: bump versions to 1.15.4 (#6582) 2026-07-17 14:27:15 +00:00
João Moura
f0704ebb22 feat(skills)!: promote Skills Repository out of experimental (#6579)
* feat(skills)!: promote Skills Repository out of experimental

The registry-backed Skills Repository (crewai skill create/publish/
install/list, @org/name refs, global cache) is now mainline:

- CLI: `crewai skill ...` is a top-level group; the CREWAI_EXPERIMENTAL
  gate and the now-empty `crewai experimental` group are removed.
- Runtime: registry.py, cache.py, and events.py move from
  crewai.experimental.skills into crewai.skills next to the loader;
  the require_experimental_skills() gate is gone.
  crewai.experimental.skills remains as a deprecated re-export shim.
- Docs: concepts/skills now leads with the CLI workflow and documents
  the create -> publish -> install lifecycle.

Linear: n/a (requested promotion)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(skills): org-scoped publish only + docs in all languages

Skills are always scoped to the publishing organization, like tools:
drop the --public/--private flags from `crewai skill publish` and
always send is_public=False to the registry. CLI tests assert the flag
is rejected and the API never receives a public publish.

Translate the new CLI-first Quick Start and the create -> publish ->
install lifecycle section into ar, pt-BR, and ko concepts/skills docs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(skills): address review comments on the promotion PR

- Back-compat shim now aliases the old submodules in sys.modules so
  `crewai.experimental.skills.registry/cache/events` imports (and patch
  targets) resolve to the real crewai.skills modules, not just the
  package-root re-exports.
- `crewai skill publish` actually enforces the git-state check that
  --force claims to skip: unsynced repos block publishing (mirroring
  tool publish); standalone skill dirs outside any git repo publish
  without a check.
- Explicit UTF-8 encoding on SKILL.md and cache-metadata reads/writes.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(skills): fail closed when git state cannot be validated on publish

Follow deploy's pattern: construct git.Repository(fetch=False) and only
treat "not a Git repository" as skippable — any other git error
(fetch/auth/misconfiguration) now blocks publish with a --force escape
hatch instead of silently bypassing the sync check.

Also single-style imports in the shim test (CodeQL) with the dotted
shim import covered via importlib.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(skills): fetch before sync check on publish; bump mcp past advisories

Publish now refreshes remote-tracking refs (repository.fetch()) before
is_synced(), so ahead/behind is judged against the actual remote rather
than stale local refs; a failing fetch blocks publish with the --force
escape hatch. Adds a fail-closed test for fetch errors.

Raise mcp to >=1.28.1,<2 (locks 1.28.1): the ~=1.26.0 pin blocked
GHSA-hvrp-rf83-w775 / GHSA-jpw9-pfvf-9f58 (fixed 1.27.2) and
GHSA-vj7q-gjh5-988w (fixed 1.28.1), which were failing pip-audit on
this PR.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Vinicius Brasil <vini@hey.com>
2026-07-17 14:21:15 +00:00
Vinicius Brasil
4e23bf6d45 Update dependencies with security fixes (#6580)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* Pillow 12.1.1 → 12.3.0 (CVE-2026-55798, CVE-2026-54059, CVE-2026-54060,
  CVE-2026-55379, CVE-2026-55380, CVE-2026-59197, CVE-2026-59203)
* mcp 1.26.0 → 1.28.1 (CVE-2026-59950)
* couchbase 4.3.5 → 4.6.0
2026-07-17 09:12:45 -03:00
Jesse Miller
df2e68fe0a docs: add Flows in Studio documentation (#6575)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* docs: add Flows in Studio documentation

Documents the new Flows build mode in Studio: why deterministic
workflows with agentic steps matter, the three core node types
(Single Agent, Crews, Router), and Agent Repository publish/pull
sync across organizations.

Includes a rollout banner for the week of July 20th, English source
plus pt-BR, Korean, and Arabic translations, and nav entries for
both edge and v1.15.2 (Crew Studio group renamed to Studio).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: limit Flows in Studio docs to edge version

Versioned snapshots are updated by a separate script, so remove the
v1.15.2 copies and revert its nav changes; the page now lives only
under edge.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-16 20:05:59 +00:00
Vinicius Brasil
475ce6cb6a [docs-freeze] docs: snapshot and changelog for v1.15.3 (#6577) 2026-07-16 19:42:53 +00:00
Vinicius Brasil
cbb8c982f8 feat: bump versions to 1.15.3 (#6576) 2026-07-16 19:26:14 +00:00
Vinicius Brasil
a2b0af6bc8 docs: snapshot and changelog for v1.15.3a2 (#6574) 2026-07-16 18:55:47 +00:00
Vinicius Brasil
a1021de7f3 feat: bump versions to 1.15.3a2 (#6573) 2026-07-16 15:43:38 -03:00
Lucas Gomide
9a49af098b fix: sync kickoff-completed event with OUTPUT hook result (#6571)
* fix: sync kickoff-completed event with OUTPUT hook result

`CrewKickoffCompletedEvent` still carried the pre-hook `TaskOutput`, so
AMP/OTEL consumers never saw `OUTPUT` mutations even though the returned
`CrewOutput` was updated. Sync `final_task_output.raw` from the post-hook
payload before emit, matching `FlowFinishedEvent`.

* style: drop OUTPUT sync comment and rename crew output test
2026-07-16 14:37:56 -04:00
Vinicius Brasil
5dba2ef623 Bump setuptools to 0.83.0 to fix PYSEC-2026-3447 (#6570) 2026-07-16 15:08:28 -03:00
Vinicius Brasil
c5ac2d93b4 docs: snapshot and changelog for v1.15.3a1 (#6567) 2026-07-16 14:22:06 -03:00
Vinicius Brasil
79da292d79 feat: bump versions to 1.15.3a1 (#6566) 2026-07-16 13:56:31 -03:00
Vinicius Brasil
999bee8344 Add organization ID param to PlusAPI client (#6561)
This commit adds the organization ID parameter to the PlusAPI client, in
addition to the settings file. This allows for settings the organization
programmatically.
2026-07-16 12:12:29 -03:00
Vinicius Brasil
985cf52028 Fix null repository agent attributes (#6560)
Repository responses can include null optional fields such as
`reasoning`. Treat them as omitted so Agent defaults apply instead of
failing validation.
2026-07-16 10:13:45 -03:00
Lucas Gomide
da9902da4f docs: group execution hooks and document all hook contexts (#6548)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* docs: group execution hooks and document all hook contexts

The hooks pages sat flat in the learn nav and only documented the LLM
and tool call contexts, with examples built on the legacy decorators.
Groups them under a collapsible "Execution Hooks" section, adds
`step-hooks` and `execution-boundary-hooks` pages covering every hook
context from source, reworks the LLM and tool pages to lead with `@on`
while keeping the decorators, and links the orphaned
`before-and-after-kickoff-hooks` page into the group.

* docs: prefix hook cross-links with /en so they resolve in edge

The new edge-only hooks pages linked each other with versionless paths
like `/learn/step-hooks`, which mintlify resolves against the frozen
default version where those pages do not exist, breaking the CI link
check. Uses the `/en/learn/...` form the other edge pages already use.

* docs: use /edge prefix for links to edge-only hooks pages

The `/en/learn/...` form still resolves against the default frozen
version, where `step-hooks` and `execution-boundary-hooks` do not exist
yet, so the link checker kept failing. Links now use the explicit
`/edge/en/learn/...` form, matching how `consuming-streams.mdx` linked
to edge-only streaming pages before they were frozen.
2026-07-15 08:17:52 -04:00
Lucas Gomide
0e5d0ecfb9 feat: add step interception points and rework execution hooks docs around @on (#6518)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* feat: add pre_step and post_step interception points on task execution

Introduces `StepContext` and the two step points in the dispatcher, and
wires them around agent execution in `task.py` (sync and async paths):
`pre_step` fires after `TaskStartedEvent` with the task context as
payload, `post_step` fires before `TaskCompletedEvent` with the
`TaskOutput`, and hook replacements are rebound in both directions.

* feat: wire pre_step and post_step on flow method execution

Dispatches the step points around each flow method with
kind="flow_method": `pre_step` receives the dumped call params and maps
returned edits back onto args/kwargs, `post_step` can rewrite the method
result before it is recorded. Conformance tests cover per-method firing
and output rewriting.

* docs: rework execution hooks page around the @on api

Replaces the standalone interception hooks catalog with a single
`execution-hooks.mdx` page that teaches `@on` as the primary way to
write hooks, covering the full ten-point catalog across task, flow, and
LLM execution. The legacy per-point decorators stay documented in a
closing section, and the `docs.json` navigation drops the removed page.
2026-07-14 14:47:18 -04:00
Lucas Gomide
a194f3867a feat: wire execution-boundary interception points (#6517)
* feat: wire execution-boundary interception points

Adds the typed interception contexts (`crewai/hooks/contexts.py`) and wires
the `execution_start`, `input`, `output`, and `execution_end` points for both
crews and flows through the dispatcher. `prepare_kickoff` and
`Flow.kickoff_async` fire `execution_start`/`input` so a hook can rewrite
resolved inputs before the run, while `Crew._create_crew_output` and the flow
tail fire `output`/`execution_end` so the final result can be observed or
replaced. Closes the eight critical-path points without touching the legacy
hooks.

* fix: correct execution-boundary hook ordering and input aliasing

Reworks the crew and flow boundary seams flagged in review. `OUTPUT` and
`EXECUTION_END` now run before the completion event (`CrewKickoffCompletedEvent`
and `FlowFinishedEvent`) so a `HookAborted` no longer leaves a spurious
completed signal and a returned payload replacement is honored on the emitted
and returned result. Boundary contexts alias `inputs` to the same object as
`payload` instead of a fresh dict from `or`, so in-place edits survive
read-back. Flows re-publish the resolved inputs into `flow_inputs` baggage
after the `INPUT` hook so trigger-payload injection observes hook rewrites, and
a resumed flow now dispatches `OUTPUT`/`EXECUTION_END` on its completion path.

* chore: drop redundant seam comments from execution-boundary wiring

Removes two inline comments narrating the OUTPUT/EXECUTION_END dispatch
ordering in `crew.py` and the flow runtime, plus a stray sentence about
enterprise adapters in the conformance-suite docstring. Comment-only
cleanup, no behavior change.

* fix: keep crew output typed across boundary hook dispatch

`_create_crew_output` reassigned `crew_output` from the hook contexts'
`payload`, which is typed `Any`, so mypy flagged `no-any-return` at the
function's return. Cast the payload back to `CrewOutput` after each
dispatch and split the `ExecutionEndContext` construction to satisfy
`ruff format`'s line-length limit.
2026-07-14 10:43:18 -04:00
Lucas Gomide
7d21283630 feat: add generic interception-hook dispatcher (#6516)
* feat: add generic interception-hook dispatcher

Introduces `crewai/hooks/dispatch.py` as a single engine behind every
interception point: a hook receives a typed context, may mutate or replace
its `payload`, or raise `HookAborted(reason, source)` to stop the operation.
The full `InterceptionPoint` catalog is frozen from day zero, with global and
contextvar-scoped registries, an `@on` decorator, a no-op fast path, and a
`HookDispatchedEvent` for telemetry. The four existing `before/after_llm_call`
and `before/after_tool_call` hooks become adapters over the dispatcher, so the
legacy dialect and `return False` semantics keep working unchanged while
gaining the new contract.

* fix: harden interception dispatcher against review findings

Corrects several dispatcher edge cases surfaced in review. `_default_reducer`
now reports a modification only when a `payload` is actually applied, the
`agents=` filter falls back to `agent_role` for contexts without an `agent`
object, and `unregister` resolves the filter wrapper stashed by `on` so a
filtered hook can be removed. The tool-hook runners honor the executing
agent's `verbose` flag instead of silently swallowing hook errors, and the
ReAct tool path now runs `POST_TOOL_CALL` on blocked calls to match the
native paths. Also adds abort-telemetry coverage and replaces the flaky
absolute no-op timing budget with a relative one.

* fix: honor scoped hooks on direct llm calls and register @on crew methods

Direct agent-less LLM calls short-circuited on the empty global hook list,
so hooks registered only for the current `scoped_hooks()` context never
ran; the direct-call helpers now defer to `dispatch`, which resolves
scoped hooks behind its own no-op fast path. `CrewBase` likewise only
scanned the legacy `is_*_hook` markers, so `@on(InterceptionPoint.X)`
methods were silently dropped — it now registers them on the dispatcher
with filters applied and `self` bound. Also tightens result typing across
the tool-call seams so `mypy` stays green.

* refactor: scope InterceptionPoint to the points this layer wires

The dispatcher only fires the model- and tool-call boundaries, so
`InterceptionPoint` now lists just those four rather than the full future
catalog. New points are introduced alongside the seams that dispatch them,
keeping every layer free of enum members with no live consumer. The
dispatcher unit tests that borrowed unused points as generic examples are
remapped onto the four kept points.

* test: pin per-hook fail-open at the LLM and tool seams

The dispatcher swallows a hook's exception per hook rather than around the
whole loop, so one buggy hook no longer silently skips every hook registered
after it. These seam-level tests pin that behavior through
`_setup_before_llm_call_hooks` and `run_before/after_tool_call_hooks`, and
confirm an intentional `return False` block still short-circuits later hooks.

* fix: run execution-scoped hooks on the agent executor model seams

`_setup_before/after_llm_call_hooks` only ran the executor's snapshot
hook lists, so hooks registered via `scoped_hooks()` never fired on
`PRE/POST_MODEL_CALL` during normal agent execution, while the tool
seams (which go through `dispatch`) merged them. The seams now append
the current scope's hooks after the snapshot via `get_scoped_hooks`,
matching dispatch's global-then-scoped ordering, and a scoped-only
registration no longer short-circuits the seam.
2026-07-14 10:27:34 -04:00
Lucas Gomide
6452608724 fix: after_llm_call hooks no longer break native tool execution (#6531)
* fix: don't clobber native tool-call responses in after-LLM hooks

Registering any `after_llm_call` hook broke native tool execution: the
executor invokes `_setup_after_llm_call_hooks` on the intermediate
response that carries the model's tool calls, the non-str payload was
stringified for the response-rewrite pass, and the executor then treated
that string as a final answer instead of executing the tools. Structured
payloads (neither `str` nor `BaseModel`) now pass through untouched,
mirroring the isinstance guard `_invoke_after_llm_call_hooks` already
applies on the direct-call path; hooks still fire on the follow-up
textual response.

Fixes #6529

* style: shorten the tool-call guard comment
2026-07-14 09:49:21 -04:00
Lucas Gomide
5f4ac9f407 chore: resolve pip-audit failures for click, pillow, and json-repair (#6542)
The vulnerability scan started failing when PYSEC-2026-2132 (click) and
PYSEC-2026-2253..2257 (pillow) were published on Jul 12. Both have fixed
releases within our constraints, so `uv.lock` upgrades click to 8.4.2 and
pillow to 12.3.0. A newer json-repair advisory (GHSA-xf7x-x43h-rpqh) also
surfaced; its fix is outside the `json-repair~=0.25.2` pin and 0.25.x lacks
the vulnerable `schema_repair` module, so it joins the ignore list in
`vulnerability-scan.yml` with a justification.
2026-07-14 08:34:56 -04:00
Vinicius Brasil
9d72e269e4 Remove redundant CEL text helper (#6528)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
This commit removes the redundant CEL text helper, in favor of the
easier interpolation syntax.
2026-07-13 14:29:36 -04:00
João Moura
fb8e93be25 fix(flow): don't double-append the turn reply when a handler trims history (#6510)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
handle_turn() (and stream_turn) decided "did the handler append its
reply?" by snapshotting the assistant-message count before kickoff and
appending the stringified result when the count came back unchanged. A
handler that appends its reply and then trims state.messages to a cap —
a normal bounded-context pattern — left the count unchanged, so the
fallback appended the reply a second time on every turn once trimming
engaged, and the duplicates then crowded real turns out of the capped
window.

Replace the count heuristic with an explicit per-turn flag:
append_assistant_message() sets _assistant_reply_appended, handle_turn
and stream_turn clear it before kickoff and only fall back when no
assistant message was appended during the turn. The now-unused
_assistant_message_count() helper is removed.

Fixes EPD-181.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 20:01:07 -07:00
João Moura
4fdb7f2bfb fix(tools)!: make tool-result caching opt-in instead of on by default (#6509)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* fix(tools)!: make tool-result caching opt-in instead of on by default

Tool-result caching defaulted to on (Crew.cache=True, and standalone
agents self-wired a CacheHandler at construction), so an LLM calling
the same tool with identical arguments twice in one run silently got
the first result back without the tool executing. For live-data tools
that is a confidently stale answer; for state-mutating tools the second
action is silently dropped.

Caching is now opt-in with the machinery unchanged:
- Crew.cache defaults to False; Crew(cache=True) restores today's
  behavior exactly (agents still default to participating when a crew
  offers its handler, and Agent(cache=False) still opts an agent out).
- Standalone agents no longer self-wire a cache; Agent(cache=True) or
  an explicit cache_handler opts in. Previously even Crew(cache=False)
  agents cached via this self-wired handler.
- Per-tool cache_function write gating is unchanged once opted in.

Existing tests that exercised the caching machinery now opt in
explicitly; new regression tests cover the default (both identical
calls execute), crew-level opt-in dedup, and agent-level wiring.

Fixes EPD-180.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(agent): don't let copy() turn the cache default into an explicit opt-in

Agent.copy() rebuilds from model_dump(), which includes the field
default cache=True, so the copy's model_fields_set contained "cache"
and _setup_agent_executor wired a CacheHandler the source agent never
opted into (Bugbot review finding). Drop "cache" from the dump when it
was not explicitly set on the source; explicit opt-ins still survive
copying.

Also sync the Crew and BaseAgent class docstrings with the new opt-in
cache semantics (CodeRabbit review findings).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(agent): preserve cache_handler-only opt-in across Agent.copy()

copy() excludes cache_handler from the rebuilt agent, so an agent that
opted into tool-result caching solely via an explicit cache_handler
lost caching after copy() (Bugbot review finding). Carry the consent as
cache=True on the copy when the source has a handler wired and hasn't
explicitly disabled caching — the copy wires its own fresh handler,
matching pre-change copy semantics (copies never shared the source's
handler instance).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(crew): offer the crew cache handler to the hierarchical manager

The hierarchical manager agent is created in _create_manager_agent,
outside the validation-time agents loop that offers the crew's cache
handler — and managers no longer self-wire a handler — so
Crew(cache=True) hierarchical runs never cached the manager's
delegation tool calls (Bugbot review finding). Offer the shared crew
handler when the crew opted in; a user-provided manager with
cache=False stays excluded via the existing set_cache_handler gate.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(agent): only construction-time cache opt-ins survive Agent.copy()

The previous copy() fix treated any wired cache_handler as consent, but
agents that merely received the crew's shared handler at kickoff
(set_cache_handler from Crew(cache=True)) never opted in themselves —
their copies must not become standalone cachers (Bugbot review
finding). Record the opt-in signal in _setup_agent_executor, which runs
at construction before any crew wiring can happen, and have copy()
consult that flag instead of inspecting cache_handler after the fact.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 17:37:36 -07:00
João Moura
bfa652a7be fix(tools): stop rewriting the authored tool description at construction (#6508)
* fix(tools): stop rewriting the authored tool description at construction

BaseTool.model_post_init silently replaced the public description field
with the LLM-facing composite ("Tool Name: ...\nTool Arguments: ...\n
Tool Description: <authored>"), breaking equality assertions on authored
text and hiding the extra prompt tokens from token-careful authors.

The authored description now survives construction as written. The
composite is composed on demand via a new formatted_description property
on BaseTool and CrewStructuredTool (shared format_description_for_llm
helper), and every prompt path that relied on the baked-in composite —
render_text_description_and_args, ToolUsage._render, and tool-usage
error messages — now renders through it, so the text the LLM sees is
unchanged.

The helper strips any pre-existing composite block before composing, so
tools deserialized from old checkpoints and adapters that still bake the
composite into the field (e.g. the crewai-tools MCP adapter) don't get
double-wrapped. BaseTool._generate_description remains as a no-op hook
because subclasses override it and model_post_init still calls it.

Fixes EPD-179.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(tools): harden composite-description handling after review

- Anchor the pre-baked-composite check to the actual three-line block
  shape instead of a naive substring match, so authored prose that
  merely mentions "Tool Description:" is never truncated (CodeRabbit /
  Bugbot review finding). Shared as
  strip_composite_description_prefix() and reused by the function-
  calling schema builder, which had the same naive split.
- Make render_text_description_and_args tolerate duck-typed tools
  without a real formatted_description string (fixes CI: step-executor
  tests pass Mock tools whose auto-created attribute is not a str).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-07-10 20:33:57 -03:00
João Moura
b65c8487d2 fix(output): expose token usage under both names on agent and crew results (#6507)
Agent.kickoff() returned LiteAgentOutput with a plain dict at
.usage_metrics and no token_usage attribute, while Crew.kickoff()
returned CrewOutput with a UsageMetrics object at .token_usage and no
usage_metrics attribute — so a usage accessor written for one path
raised AttributeError on the other, and every consumer had to
duck-type both shapes.

Give both result types both surfaces, each name with one consistent
shape everywhere: .token_usage is a UsageMetrics object and
.usage_metrics is a plain dict, on both LiteAgentOutput and CrewOutput.
Added as read-only properties, so existing fields, serialization, and
constructors are unchanged.

Fixes EPD-178.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 20:29:34 -03:00
João Moura
a8b3ecb723 fix(agent): report per-call usage metrics on kickoff results (#6506)
* fix(agent): report per-call usage metrics on kickoff results

Agent.kickoff() populated result.usage_metrics from the LLM instance's
lifetime token accumulator, so counts grew across calls and pooled
across agents sharing one LLM object — a second agent's first turn
appeared to cost the whole preceding session.

Snapshot the accumulator when a kickoff starts and report the delta on
the result (guardrail retries included), via the new
UsageMetrics.delta_since(). The LLM instance's cumulative counters are
untouched: get_token_usage_summary() keeps lifetime totals for
crew-level aggregation, and its docstring now states that scope
explicitly. Applies to both Agent and the deprecated LiteAgent, sync
and async paths.

Fixes EPD-177.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor(agent): drop lite_agent.py diff, add guardrail-retry usage test

Per review: LiteAgent's kickoff path is no longer used, so the per-call
usage snapshot only needs to live in agent/core.py — revert the
lite_agent.py changes entirely. This also removes the duplicated
_current_usage_summary helper and the instance-attr baseline CodeRabbit
flagged.

Add the requested guardrail-retry regression test: a guardrail that
rejects the first attempt and accepts the second must yield
usage_metrics covering both attempts (2x a single-attempt kickoff).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 14:17:45 -07:00
João Moura
7967b19057 fix(flow): stop replaying previous turn's intent when route_turn() returns falsy (#6505)
In conversational flows, a falsy return from an overridden route_turn()
fell back to the sticky state.last_intent from a previous turn, silently
re-running the prior turn's handler for an unhandled input.

The fallback exists for the legacy default_intents path, where
receive_user_message() classifies the intent fresh each turn. Track that
per-turn classification in _turn_classified_intent (cleared on every turn
reset) and route on it instead, so a falsy route_turn() now falls through
to the built-in answer_from_history/converse defaults and never reuses
stale routing state.

Fixes EPD-176.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-07-10 11:44:57 -07:00
João Moura
85c467dfe2 feat(cli): run declarative flows on the TUI (headless terminal fallback) (#6484)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* feat(cli): run declarative flows on the TUI with a headless terminal fallback

Declarative flows now run on the CrewRunApp TUI when interactive, matching
declarative crews and conversational flows. Headless contexts — CREWAI_DMN
(deploy), piped output, CI, any non-TTY — fall back to the direct-terminal
kickoff, gated by is_interactive() (folds in the CREWAI_DMN check and requires
a real TTY).

The TUI shows per-method progress: a new STEPS panel driven by flow method
events (FlowStarted / MethodExecutionStarted/Finished/Failed), each labeled
with its declarative call type (crew/agent/expression/…) read from the flow
definition. Crews/agents inside a method keep streaming in the main panel via
the existing crew/task/LLM handlers.

- crew_run_tui.py: _run_flow_worker (flow.kickoff in a thread worker; reuses
  _on_crew_done/_on_crew_failed + _stringify_output), _is_flow_run gate so crew
  rendering is byte-identical, flow-event subscriptions building _flow_steps,
  and the STEPS sidebar + flow-aware header.
- run_declarative_flow.py: is_interactive() branch → _run_declarative_flow_tui
  (EventListener, method-type map from flow._definition, crew-parity exit codes
  and deploy chaining) or the existing terminal path.

Deviation from the approved plan: gate on is_interactive() rather than
is_dmn_mode_enabled() alone, so non-TTY runs (CI/pipes/CliRunner) never launch
a TUI — this also keeps existing headless flow tests green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): force flow events on for the TUI so STEPS renders under suppress_flow_events

Review follow-up: the STEPS panel and header are driven by flow method events
(FlowStarted / MethodExecution*), but the declarative runtime skips emitting
those when the flow declared config.suppress_flow_events. Interactive TUI runs
would then keep STEPS on "waiting…" and the header on "Starting flow…" while
nested crews still execute.

_run_declarative_flow_tui now forces flow.suppress_flow_events = False for the
interactive run (mirroring how the conversational path mutates the flow for the
TUI). The headless/terminal path never reaches this and keeps the flow's
declared setting. Regression test: test_run_declarative_flow_tui_enables_flow_events.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): clear flow header's current method when a method ends

Review follow-up: the flow header keys off _current_method, which was set on
MethodExecutionStarted but never cleared on Finished/Failed. Between steps (or
after a failed method before kickoff exits) the header kept spinning the old
method name while the STEPS sidebar already showed it done/failed.

_clear_current_method now drops the header's active method when it ends,
falling back to another still-active step (methods can overlap) or none. The
header's idle fallback shows "Working…" once a step has run and "Starting
flow…" only before the first method.

Tests: test_current_method_clears_and_falls_back_across_overlap, plus a
_current_method assertion in test_flow_method_events_build_steps.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix: suppress flow console panels in TUI mode; clear header agent on method change

Two review follow-ups:

1) Method panels break Textual TUI (Cursor): forcing suppress_flow_events off
   so the STEPS panel receives events also un-gated the EventListener's Rich
   flow/method panels (ConsoleFormatter.print_panel prints is_flow=True panels
   regardless of verbose), which interleave with Textual and corrupt the TUI.
   print_panel now skips is_flow panels when is_tui_mode() is set (the same
   context the TUI worker already establishes and the tracing listeners already
   honor). Non-TUI/headless flow runs are unaffected. Test:
   test_console_formatter_tui_mode.

2) Flow header showed a stale agent (CodeRabbit): _current_agent persisted
   across methods. It's now cleared when a method starts and when the active
   method changes, so the header never shows the previous method's agent until
   a new agent event arrives. Test: test_flow_method_transitions_clear_current_agent.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): keep flow name over nested crews; show paused flow methods

Two review follow-ups on the flow TUI:

1) Crew kickoff renamed the flow (Cursor): CrewKickoffStartedEvent overwrote
   _crew_name / the app title with a nested `call: crew` step's crew name, so
   the post-run summary could be labeled with a child crew. The rename is now
   gated on `not _is_flow_run`, preserving the flow's name; crew runs still
   adopt the crew name. Tests: test_crew_kickoff_does_not_rename_flow_run,
   test_crew_kickoff_renames_in_crew_mode.

2) Paused methods showed active (Cursor): the TUI didn't handle
   MethodExecutionPausedEvent, so a @human_feedback pause left the STEPS
   spinner running (flow status panels are suppressed in TUI mode). It now
   marks the step "paused" (⏸, teal) and the header shows "waiting for
   feedback" instead of a spinner. Test: test_method_paused_marks_step_paused.

Note: interactively *providing* human feedback from the flow TUI is a separate
follow-up; this only makes the pause visible instead of a silent stuck spinner.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): run human-feedback declarative flows on the terminal, not the TUI

Two review follow-ups, both rooted in @human_feedback methods:

- Paused flow marked complete (Cursor): async human feedback makes kickoff
  RETURN a HumanFeedbackPending marker (not raise), which _run_flow_worker
  would stringify and report as a successful completion with exit 0.
- Sync feedback breaks TUI (Cursor): default (sync) @human_feedback collects
  input via the flow runtime's Rich console.print + blocking input(), which
  interleaves with Textual and leaves the user unable to review output or
  submit feedback.

run_declarative_flow now routes any flow whose declarative definition declares
human feedback (_flow_uses_human_feedback) to the terminal path, where blocking
input and Rich prompts work natively — regardless of interactivity. Non-feedback
flows still get the TUI. Tests: test_flow_uses_human_feedback_detection,
test_human_feedback_flow_uses_terminal_even_when_interactive.

Fully interactive human feedback inside the TUI remains a separate follow-up.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* refactor(cli): address review — Flow typing, debug logging, flow-vs-crew naming

Review follow-ups from @lucasgomide:

- Type flow helpers as Flow[Any] (via TYPE_CHECKING import) instead of Any and
  drop the defensive getattr chains — _definition is a typed PrivateAttr and
  name/suppress_flow_events are typed fields, so attribute access is safe.
- Replace the silent `except Exception: pass` blocks with logger.debug(...,
  exc_info=True) so unexpected failures are diagnosable in the field
  (_flow_method_types, _flow_uses_human_feedback, suppress_flow_events toggle).
- Flow-vs-crew naming: the flow worker now uses group="flow" (was the
  misleading "crew"), and the shared completion/failure handlers report the
  run with an entity-aware noun ("flow" vs "crew") via _run_noun.

Deferred (separate PR): the os._exit(130) hard-kill on user quit is kept as-is
to match the existing crew convention (run_crew._run_json_crew).

Tests: test_flow_done_uses_flow_wording_for_unfinished_tool; existing crew
wording tests unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-10 11:42:12 -03:00
Lorenze Jay
7baf8f9ba1 improving custom OpenAI urls (#6490)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* Support legacy OpenAI base URL env var

* Add custom OpenAI-compatible endpoint support

* Refactor OpenAI completion module test to restore original module state

- Added logic to save and restore the original OpenAI completion module during the test to prevent issues with class re-imports affecting subsequent tests.
- Ensured that the test checks for the presence of the module and its attributes only after the module is properly reloaded.
- Improved test reliability by avoiding potential failures due to module state changes across tests.

* addressing comments
2026-07-09 15:30:16 -07:00
Lucas Gomide
860817cbcd Drain memory writes before kickoff and flow completion events (#6497)
* fix: drain memory writes before kickoff and flow completion events

Background memory saves from the final task could still be in flight
when `CrewKickoffCompletedEvent`/`FlowFinishedEvent` fired, so telemetry
listeners tore down before `MemorySaveCompletedEvent` arrived and the
save span surfaced as "Span orphaned" errors in traces despite the
record persisting. `Crew` now drains all pending saves — including
per-agent `agent.memory` pools, which the old `finally`-only drain
missed entirely — before emitting the completion event, with the same
ordering applied to both `FlowFinishedEvent` emit paths in the flow
runtime.

* fix: address review findings on the memory drain paths

Bugbot and CodeRabbit flagged gaps in the drain coverage: the
hierarchical `manager_agent` memory pool was never drained,
`Crew.akickoff` lacked the exception-path safety net that sync
`kickoff` has, and `finalize_session_traces` emitted the deferred
session-end `FlowFinishedEvent` without draining first. Also offloads
the pre-emit drains in the flow runtime to `asyncio.to_thread` so the
blocking wait doesn't stall other coroutines sharing the event loop.

* fix: flush event bus after memory drain in flow completion paths

Bugbot flagged that flow paths went straight from the memory drain to
`FlowFinishedEvent`, while crew kickoff flushes the bus in between.
Save completion events emitted during the drain could still have
pending async handlers when flow-finished triggered trace teardown.
Adds a `crewai_event_bus.flush()` after the drain at both flow runtime
emit sites and in `finalize_session_traces`, mirroring
`Crew._create_crew_output`.
2026-07-09 15:01:14 -04:00
Lorenze Jay
289686ab49 [docs-freeze] docs: snapshot and changelog for v1.15.2 (#6479)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-07-07 19:05:05 -07:00
Lorenze Jay
589baa3e7f feat: bump versions to 1.15.2 (#6477) 2026-07-07 18:59:59 -07:00
João Moura
835b93d8c8 fix(cli): key model-catalog cache by exact API key, shorten TTL, skip Ollama (#6468)
Follow-ups to #6462's caching:

1. Key the catalog cache by the exact API key (via a short, non-reversible
   sha256 digest — never the key itself), not just key-present vs absent.
   Switching to a different key for the same provider now misses the previous
   account's entry and refetches, instead of showing the old account's models.

2. Never cache local providers (Ollama). /api/tags is fast and installed
   models change out-of-band, so caching could keep offering a model the user
   just deleted until the entry expired. _is_cacheable() gates both cache read
   and write; the picker now re-probes every call and reflects what's installed.

3. Shorten the dynamic catalog TTL from 6h to 5m — a stale list (new/removed
   models, account changes) is worse than a ~1s refetch, and the cache only
   needs to spare repeated fetches within a wizard session.

Tests: distinct-key cache entries, digest never stores the raw key, Ollama not
cached (reflects deletions / never written), and dynamic TTL expiry.


Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 18:47:19 -07:00
João Moura
3246cb30f5 fix(cli): unify crewai run flow input resolution and prompt from the state schema (#6466)
* fix(cli): unify `crewai run` flow input resolution; prompt from state schema

`crewai run` resolved the configured [tool.crewai] flow, but `--inputs` was
hard-gated behind `--definition` and routed through a separate branch — the two
ways of pointing at the same flow didn't share resolution, and required inputs
were never detected, prompted, or validated (a missing field only blew up at
runtime).

Now inputs and definition come from one place:

- Remove the "--inputs requires --definition" gate (cli.py, run_crew.py,
  run_declarative_flow.py). `--inputs` alone resolves the configured flow,
  exactly like a bare `crewai run`; `--definition` is purely an override. The
  project-env re-exec forwards `--inputs` instead of rejecting it.
- Read the flow's state schema from the runtime Flow instance
  (`type(flow.state).model_json_schema()`), which is reliable for both inline
  `json_schema` and ref-imported `pydantic` state (the static definition's
  json_schema is None for the common ref case).
- Plain `crewai run` detects required state fields (minus those satisfied by
  state defaults) and prompts for them interactively, showing each field's
  description; skipped in non-interactive / CREWAI_DMN mode.
- Validate against the schema before kickoff: pointed
  "Missing required input 'x' — <description>" errors, and warn on unknown keys
  with a did-you-mean suggestion (catches typos like `prospect_emai`).

`--inputs` on a non-flow project now errors clearly ("only supported for
declarative flows") instead of the old confusing gate.

Tests: schema-driven prompt/validate/override paths, unknown-key warning,
defaults-satisfy-required, type validation, and re-exec input forwarding.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): forward reserved `id` input to flow kickoff; ruff format

- Cursor: the schema filter treated an `id` key in --inputs as unknown and
  dropped it, regressing kickoff's persistence-restore support (inputs["id"]).
  Let `id` pass through untouched (test: reserved_id_input_is_forwarded).
- Apply ruff format to run_declarative_flow.py (fixes the lint-run
  `ruff format --check` step).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): don't block persistence-restore resume on schema validation

Cursor (High): `crewai run --inputs '{"id":"…"}'` is a persistence resume —
kickoff hydrates full state from storage, so schema-required fields may come
from the restored state rather than --inputs. The new required-field
prompt/validation was erroring/prompting before kickoff, breaking resume. When
`id` is present in --inputs, forward the inputs unchanged and skip the
prompt/validation. Test: test_id_only_input_skips_required_validation.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): load project .env in the declarative-flow runner

The declarative-flow path never loaded .env — flow projects (type = "flow")
missed API keys/config that crew projects pick up. The JSON-crew path loads
Path.cwd()/.env with override=True (run_crew._run_json_crew); mirror that at
the top of run_declarative_flow() so flow projects behave the same regardless
of where crewai is installed. Test: run_declarative_flow_loads_project_env.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* feat(cli): unify runtime-input prompting across declarative flows and crews

Declarative (JSON) crews now resolve inputs the same way declarative flows
do, via a shared crewai_cli.input_prompt module (prompt_for_inputs,
parse_inputs_json, closest_name, is_interactive):

- accept --inputs (previously rejected for crews), forwarded to the crew
  subprocess via CREWAI_JSON_CREW_INPUTS and validated before spinning up uv
- layer --inputs over the crew's declared `inputs` defaults
- prompt for missing {placeholder}s with the same UX as flows, and error
  cleanly with a pointed per-name message when non-interactive
- warn on unknown keys with a "did you mean" suggestion

Unlike flows — whose state schema is authoritative, so unknown keys are
dropped — the crew placeholder scan is heuristic (agent/task text fields
only), so unrecognized keys are warned about but kept, to avoid discarding a
value a field the scan doesn't cover may rely on.

--inputs remains rejected for classic (Python/YAML) crews, which take their
inputs from main.py. run_declarative_flow's private input helpers move to the
shared module with no behavior change.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* test(crewai): update mirrored CLI test after run_crew input refactor

lib/crewai/tests/cli/test_run_crew.py imports crewai_cli internals and is
collected by the lib/crewai test job (Run Tests). It still imported
_prompt_for_missing_inputs, which was replaced by _resolve_crew_inputs, so
the module failed to import — erroring pytest at collection and cancelling
the rest of the matrix via fail-fast.

Point it at _resolve_crew_inputs and patch the prompt in the shared
crewai_cli.input_prompt module where prompting now lives.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): filter unknown --inputs keys even on flow persistence restore

Review follow-up: the `id` (persistence-restore) branch of
_resolve_flow_inputs returned the raw payload, so typo keys passed alongside
`id` skipped the unknown-key warning/drop and reached kickoff — which can
fail strict (extra="forbid") flow state models. The restore path now still
warns on and drops unknown keys (keeping `id` and known state fields); it
only skips the required-field prompt and pre-kickoff validation, which
persistence hydrates. Regression test: test_id_restore_still_drops_unknown_keys.

Also drop the duplicate module import in test_input_prompt.py (both `import`
and `from ... import` of crewai_cli.input_prompt) flagged by the code-quality
bot; monkeypatching now uses the string target form.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 22:17:09 -03:00
Renato Nitta
fc41c42773 docs: update language from Rules to Policies to match the new dashboard changes (#6471)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* docs: rename ACP rules to policies across edge and v1.15.1 locales with redirects

* docs: point ACP policies pages at the new policy screenshots

* docs: address review — revert frozen v1.15.1 edits and fix redirect ordering

* docs: prefix edge policies cross-links so they resolve until the next version cut

* docs: move policies redirects above all wildcard redirects
2026-07-07 15:43:51 -03:00
Renato Nitta
792b58f46b fix: resolve pip-audit failures (onnx 1.22.0, nltk PYSEC-2026-597) (#6472)
* fix: upgrade onnx to 1.22.0 and ignore unfixed nltk advisory in pip-audit

* fix: sync pip-audit ignore list in pre-commit config with the workflow
2026-07-07 14:09:19 -03:00
Lorenze Jay
799ab0f548 ensure we are writing version for flows (#6467)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-07-06 18:47:27 -07:00
João Moura
2b56dab813 feat(cli): pull latest LLM models dynamically in the crew wizard (#6462)
* feat(cli): pull latest LLM models dynamically in the crew wizard

The JSON-crew creation wizard hardcoded a short model list per provider,
which goes stale as vendors ship new models every few weeks. Add a
three-tier resolver that prefers live data and falls back to a curated list.

- New `model_catalog.get_provider_models(provider, fallback)`:
  1. Vendor API (openai/anthropic/gemini/groq/cerebras/ollama) when the
     provider key is already in the environment — the only reliably-fresh
     source (real release dates / display names).
  2. Curated hardcoded fallback — hand-verified, used when no key is set.
  3. LiteLLM feed — only for providers with no curated list; it lags real
     releases, so it must never preempt the curated fallback.
- Rank by date/version parsed from model ids, humanize labels, 6h cache,
  short timeouts, silent fallback on any error.
- Wire it into `create_json_crew._select_model()` (picker only).
- Refresh the curated fallback against each vendor's official model docs
  (Anthropic Fable 5 / Opus 4.8 / Sonnet 5; OpenAI GPT-5.5(+pro); Gemini
  3.5 Flash / 3.1 Pro preview / 3 Flash preview; Groq Llama 4 / GPT-OSS).
- Tests for ranking, chat filtering, caching, and the tier order (17 tests).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): address model_catalog review findings

- Key the Ollama catalog cache by its base URL so a changed OLLAMA_API_BASE /
  API_BASE no longer serves the previous host's models for up to the TTL.
- Negatively cache the curated fallback after a failed/empty fetch (short
  _NEGATIVE_TTL) so the picker doesn't repeat a timeout-prone vendor/LiteLLM
  request on every call — most impactful for a down local Ollama server.
- Guard _read_catalog_cache / _write_catalog_cache against a non-dict cache
  root (corrupt JSON array no longer raises AttributeError).
- Replace the two empty `except OSError: pass` blocks with
  contextlib.suppress(OSError) plus an explanatory comment (CodeQL empty-except).
- Tests: negative cache, base-keyed Ollama cache, corrupt-cache no-crash (20 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): guard null litellm_provider and paginate Gemini models

- _from_litellm: coerce a present-but-null `litellm_provider` before string
  ops so it's skipped instead of raising AttributeError (keeps the documented
  "never raises" contract).
- _fetch_gemini: walk models.list pages via nextPageToken (bounded to 10) —
  the API is paginated and not guaranteed newest-first, so a single page could
  drop models the ranking should consider.
- Tests for both (22 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* ci: ignore nltk PYSEC-2026-597 in pip-audit (no fix, not reachable)

pip-audit newly flags nltk 3.9.4 for PYSEC-2026-597 (CVE-2026-12243), a path
traversal via percent-encoded `..%2f` in nltk.data.load()/find(). It affects
all nltk versions <=3.9.4 with no patched release, so it can't be resolved by a
version bump — same situation as the already-ignored PYSEC-2026-97.

nltk is a transitive dependency (unstructured[local-inference, all-docs] in
crewai-tools) used for text tokenization; we never pass untrusted resource
URLs/paths to nltk.data, so the traversal is not reachable. Add it to the
curated --ignore-vuln list with a justification, matching the existing pattern.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): address second Cursor review round on model_catalog

- Cache ignores new API keys: include API-key presence in the cache key
  (`<provider>#key|#nokey`), so a key added after a no-key/negative-cached
  lookup triggers a fresh live fetch instead of serving the stale fallback.
- Bad LiteLLM cache crashes picker: `_from_litellm` now requires a dict from
  `_load_litellm_data` (a non-mapping JSON root is skipped, not `.items()`'d).
- Stale LiteLLM refetch loop: memoize the feed load once per process
  (`_litellm_memo` + `_reset_litellm_memo` test hook) so repeated uncurated-
  provider lookups don't each re-attempt a timed download when offline.
- Tests: new-key bypass, corrupt-litellm-cache no-crash, one-fetch-per-process
  (25 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): keep partial Gemini results on later-page fetch error

_fetch_gemini paginates; a network/HTTP error on page 2+ previously raised out
through _from_vendor, discarding models already parsed from earlier pages and
forcing the curated fallback. Catch per-page fetch errors and return the
partial set instead (a first-page failure still yields an empty list -> fallback).
Test: test_vendor_gemini_keeps_partial_on_later_page_error (26 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): don't let an invalid fresh LiteLLM cache block download

_fetch_litellm_data treated any truthy JSON root in a fresh provider_cache.json
as the feed and returned it, so a non-mapping root (e.g. a JSON array) was
memoized and the tier never re-downloaded until the file aged out — leaving
uncurated providers with an empty picker despite a recoverable cache. Only
short-circuit on a usable dict; otherwise fall through to the download.
Test renamed to test_invalid_litellm_cache_falls_through_to_download (asserts
recovery via refetch).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): honor OLLAMA_HOST and treat empty vendor list as authoritative

- Ollama host mismatch: _ollama_base now also reads OLLAMA_HOST (the Ollama
  runtime convention) after OLLAMA_API_BASE/API_BASE, normalizing a scheme-less
  value (e.g. "127.0.0.1:11434" -> "http://127.0.0.1:11434"), so users who set
  only OLLAMA_HOST see models from the server the crew will actually use.
- Empty vendor list: a successful vendor fetch returning no models is now
  authoritative instead of collapsing to the curated fallback. A reachable
  Ollama with nothing installed yields an empty list (the picker prompts for
  manual entry) rather than offering hardcoded models that aren't installed; a
  failed fetch still falls back. _from_vendor now returns [] on success-empty
  and None only when the tier is unavailable.
- Tests: ollama empty->manual, ollama down->fallback, OLLAMA_HOST resolution
  (29 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): Gemini first-page failure falls back instead of showing empty

Interaction from the prior two fixes: _fetch_gemini swallowed a first-page
error and returned [], which _from_vendor reported as a successful-empty result
and get_provider_models treated as authoritative — skipping the curated Gemini
fallback and jumping to manual entry. Now a first-page failure (nothing gathered
yet) re-raises so _from_vendor returns None and the curated list is used; a
later-page failure still keeps the partial results.
Test: test_vendor_gemini_first_page_error_uses_fallback (30 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): Gemini GOOGLE_API_KEY + Ollama recovery not blocked by cache

- Gemini ignores GOOGLE_API_KEY: _PROVIDER_KEY_ENV now maps each provider to a
  tuple of accepted env vars; Gemini accepts GEMINI_API_KEY or GOOGLE_API_KEY
  (matching crewai's own Gemini provider). A new _provider_api_key() resolver
  is used by both _from_vendor and the cache key, so a GOOGLE_API_KEY user gets
  the live models API instead of the stale curated fallback.
- Ollama recovery blocked by cache: skip the negative (fallback) cache for
  Ollama. It's a local, fast-failing server, so re-probing each call is cheap
  and lets the picker pick up real installed models as soon as the server comes
  up, instead of serving suggestions for the negative-cache TTL.
- Tests: GOOGLE_API_KEY live fetch, Ollama down->recover (32 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* style(cli): ruff format model_catalog.py

Add the blank line ruff format expects after _provider_api_key; no behavior
change. Fixes the lint-run `ruff format --check lib/` step.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): don't treat 'search' substring as a non-chat model marker

The 'search' entry in _NON_CHAT_MARKERS matched anywhere in a model id, dropping
legitimate completion models like gpt-4o-search-preview and anything containing
'research' (e.g. o3-deep-research, since 'search' is a substring). Remove it;
the remaining markers (embedding/audio/image/moderation/etc.) still filter
genuine non-chat models. Test: test_search_substring_not_treated_as_non_chat (33).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* Revert "ci: ignore nltk PYSEC-2026-597 in pip-audit"

Do not suppress an unpatched security advisory to make CI green. Remove
PYSEC-2026-597 from the pip-audit ignore list; leave the scan failing so it
keeps surfacing the nltk path traversal (CVE-2026-12243). This PR should not be
merged until nltk ships a fix (or the vulnerable transitive dep is otherwise
resolved).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): exclude fine-tuned models and checkpoints from the picker

With a live OPENAI_API_KEY, /v1/models returns the user's fine-tunes and
training checkpoints (ft:..., ...:ckpt-step-N). Their recent `created`
timestamps ranked them above the base models and filled every slot, so the
picker showed a wall of `ft:gpt-4o-mini-...:crewai::...` with mangled labels and
no foundation models at all. Skip fine-tunes/checkpoints in the OpenAI-shaped
fetcher so clean base models surface; a user who wants a fine-tune can still
enter it via the picker's "Other" option. Test:
test_openai_excludes_fine_tunes_and_checkpoints (34 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

* fix(cli): cleaner model labels + filter Ollama non-chat models

Anthropic/Gemini already use vendor display names; OpenAI/Groq/Cerebras/Ollama
fall to _humanize for anything outside the curated map, which produced mediocre
labels ("GPT Oss 120b", "qwen3 32b", "Deepseek r1", "llama3.3:70b").

Improve _humanize:
- split on ':' too (Ollama tags: llama3.3:70b -> "Llama3.3 70B")
- uppercase size suffixes (70b -> 70B), acronyms OSS/IT, brand casing
  (DeepSeek, ChatGPT, QwQ)
- capitalize the leading letter of fused family+version tokens (qwen3 -> Qwen3)
  while preserving OpenAI o-series lowercase (o3, o1-mini)

Also fix _fetch_ollama: /api/tags lists everything installed, so filter
non-chat (embedding) and fine-tune entries the same way the other tiers do.

Tests: expanded test_humanize + test_ollama_excludes_embedding_models (35 total).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBYGqJHC2TMC6fonFziuuh

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-07-06 20:49:52 -03:00
Lorenze Jay
e55e710df0 Implement message setup and feedback handling in AgentExecutor (#6465)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* Implement message setup and feedback handling in AgentExecutor

- Added  method to streamline message preparation for agent execution, allowing for integration with human input providers.
- Introduced  and  methods to manage the state during feedback processing.
- Enhanced  and  methods to re-run the executor flow using existing feedback messages.
- Updated tests to verify the new message setup and feedback handling functionality, ensuring compatibility with human input providers.

* dont commit runner

* Remove xfail marker from test_crew_train_success as training feedback migration to AgentExecutor is complete.

* fix runtype errors

* fix test

* revert

* mypy fix

* handled reset iterations
2026-07-06 15:28:37 -07:00
Mani
56edf1f95f Added client name header (#6413)
- added client_name header to the 4 tavily tools to classify incoming requests as 'crewai' requests.

- This is for internal analysis

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-07-06 14:20:59 -07:00
Vinicius Brasil
2b90117e88 Add repository agents to flow definitions (#6437)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Inline agent and crew actions can now use repository-backed agents
without duplicating role, goal, and backstory in each definition.

Examples:
* `agent.with.from_repository: support_specialist`
* `crew.with.agents.researcher.from_repository: researcher`

`PlusAPI.get_agent` now uses the shared synchronous request path so
project loaders can fetch repository agents without nested event loops.
2026-07-02 14:28:01 -07:00
Vinicius Brasil
24901cd4f6 Support templated Flow action inputs (#6426)
Flow action inputs now support `${...}` inside strings, not only
strings that are fully wrapped in one expression. This lets authored
flows use simple prompt-like values such as:

* `query: "News about ${state.topic}"`
* `input: "Ticket ${text(state, "ticket.id", "unknown")}"`
* `sources: ["${state.primary_source}", "archive-${state.topic}"]`

Whole-expression values still preserve their runtime type, so
`${state.limit}` remains a number and `${state.domains}` remains a list.
Mixed literal and expression strings render as text.

This removes the need to build labeled strings with CEL concatenation,
which was hard to read, easy to quote incorrectly in YAML, and a poor
fit for the Flow authoring skill examples.
2026-07-02 08:57:50 -07:00
Lorenze Jay
559a9c65c4 docs: snapshot and changelog for v1.15.2a2 (#6422)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-07-01 15:14:56 -07:00
Lorenze Jay
6244738d2a feat: bump versions to 1.15.2a2 (#6421) 2026-07-01 14:55:27 -07:00
Tiago Freire
8b197a7ca8 fix: include aiobotocore in the bedrock extra (#6419)
### Overview

`BedrockCompletion.acall()` (the async completion path used when a crew is kicked off asynchronously) requires `aiobotocore` to build its async client. The `bedrock` extra, however, only declared `boto3`. Crews configured with an AWS Bedrock model work fine under a synchronous `kickoff()`, since that path only needs `boto3`, but raise `NotImplementedError: Async support for AWS Bedrock requires aiobotocore` as soon as they're kicked off asynchronously, since `aiobotocore` was never installed.

The fix adds `aiobotocore` to the `bedrock` extra, so `crewai[bedrock]` installs both the sync (`boto3`) and async (`aiobotocore`) dependencies the native Bedrock provider needs. The lockfile is regenerated to match. The exception message is also corrected — it previously pointed to a `bedrock-async` extra that never existed in `pyproject.toml`.

### Changes

- `lib/crewai/pyproject.toml`: add `aiobotocore~=3.5.0` to the `bedrock` extra
- `uv.lock`: regenerated to reflect the updated `bedrock` extra
- `lib/crewai/src/crewai/llms/providers/bedrock/completion.py`: fix the install hint in the `NotImplementedError` message to reference the real `bedrock` extra instead of the nonexistent `bedrock-async`
2026-07-01 17:30:59 -04:00
Vinicius Brasil
f630c471cf Document flow agent options (#6420)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* Document flow agent options

Document and type inline Flow agent options so authored flows can set:
* `llm.model`, `llm.max_tokens`, and `llm.max_completion_tokens`
* `planning_config.max_attempts`
* `allow_delegation`
* `max_iter`
* `max_rpm`
* `max_execution_time` in seconds

Also tell the flow skill to omit optional fields unless needed.

* Potential fix for pull request finding 'Unused import'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

---------

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-07-01 14:08:44 -07:00
Vinicius Brasil
31a4a4e162 Squeeze AGENTS.md file (#6416) 2026-07-01 11:14:36 -07:00
Vinicius Brasil
1452ee2021 Add text helper to flow skill example (#6406)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-06-30 21:18:58 -07:00
Vinicius Brasil
629f5d537b Reject self-listening flow methods (#6405)
A method that listens to its own name can re-trigger itself or collide
with router events. Rejecting that definition keeps declarative and
Python-authored flows aligned before kickoff.
2026-06-30 19:42:01 -07:00
Vinicius Brasil
ba2dafdeda Add text helper for flow CEL prompts (#6404)
CEL string concatenation currently fails when prompt builders read
missing or null fields. This commit adds `text(root, "path", "default")`
custom CEL helper so prompt text can safely read nested state/output
values.
2026-06-30 16:45:39 -07:00
Lorenze Jay
b37505bcf9 Add streaming docs to the navigation (#6403) 2026-06-30 16:00:38 -07:00
Lorenze Jay
694881c7bf docs: snapshot and changelog for v1.15.2a1 (#6398)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-06-30 13:17:53 -07:00
Lorenze Jay
958d8270db feat: bump versions to 1.15.2a1 (#6397) 2026-06-30 11:43:14 -07:00
Daniel Barreto
ba855bae2b feat: repoint template commands to crewAIInc-fde org (#6394)
Point `crewai template list`/`template add` at the crewAIInc-fde GitHub
org so the FDE template_* repos are listed and installed instead of the
crewAIInc ones.

Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-06-30 11:32:54 -07:00
Vinicius Brasil
c157199065 Support inline skill definitions (#6396)
* Support inline skill definitions

This commit adds inline skill loading without a need for a file. It also
DRYs the skill loading feature.

* Address code review suggestions
2026-06-30 11:22:05 -07:00
Lorenze Jay
8eed457e70 Define stream frame protocol for flows (#6391)
* Define stream frame protocol for flows

* Add direct LLM streaming helpers

* Unify flow streaming frame items

* Update flow streaming integration properties

* Drop stream frame debug runner example

* Address streaming contract review feedback

* Replay cached stream frame projections

* Remove stream frame version field

* Fix streaming contract docs link

* Preserve LLM instance state for stream events

* Address streaming review cleanup
2026-06-30 10:53:48 -07:00
Vinicius Brasil
04fec31f1e Type tool and app in CrewDefinition (#6395)
* Type tool and app in CrewDefinition

This commit fixes a bug in the CrewDefinition class where the tool and
app were not being added.

* Type mcps= parameter
2026-06-30 10:24:21 -07:00
Vinicius Brasil
1556dbea3e Add generated Flow Definition authoring skill (#6393)
* Add generated Flow Definition authoring skill

Generate a portable skill from the Flow Definition schema so agents can
author valid declarative flows with the same reference CrewAI uses to
validate them. New declarative flow projects now write this skill.

```python
from crewai.flow.flow_definition import FlowDefinition
skill = FlowDefinition.skill(skips=(), examples_format="yaml")
```

* `examples_format` accepts `"yaml"` or `"json"`.
* Supported skips: `conversational`, `non_linear_flows`, `each`, `hitl`, `persistence`, `config`, `expression_action`, `script_action`, `tool_action`

The generated skill includes authoring rules, a routed crew example, and
an API reference extracted from the Flow, action, state, agent, crew,
and task Pydantic schemas.

* Fix declarative flow scaffold without framework import

* Fix skipped expression action guidance

* Fix markdown links in skill
2026-06-30 09:13:33 -07:00
Lucas Gomide
e8dced8a2d docs: document Cost Limit rule type in Agent Control Plane (#6387)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-06-29 14:56:13 -03:00
Lucas Gomide
2b87098279 fix: cut docs version nav from Edge so new pages aren't dropped (#6349)
* fix: freeze docs version nav from Edge instead of previous release

The docs cut copied every Edge file into the new `docs/v<X.Y.Z>/`
snapshot but built that version's `docs.json` navigation by cloning the
previous frozen release and only rewriting path prefixes. Pages added to
Edge since the last release were therefore copied to disk yet never
linked in the version selector, which is why the v1.15.0 cut shipped
without the Datadog guide. `_build_new_entry` now clones the Edge nav
entry and rewrites `edge/<locale>/` to `v<new>/<locale>/`, so promoting
Edge to Latest carries every current page and nav restructuring.

* docs: link the v1.15.0 Datadog guide dropped during the cut

The v1.15.0 freeze copied `enterprise/guides/datadog` into the snapshot
for every locale but never linked it in `docs.json`, because the cut
cloned the v1.14.7 nav instead of Edge. This backfills the missing nav
reference in the `en`, `pt-BR`, `ko`, and `ar` v1.15.0 blocks so the
already-shipped page is reachable from the version selector. Pairs with
the `_build_new_entry` fix that prevents future cuts from dropping pages.

* docs: link the v1.15.1 Datadog guide dropped during the cut

The v1.15.1 cut ran before the freeze-from-Edge fix landed, so it
inherited the same bug as v1.15.0: `enterprise/guides/datadog` was
copied into the snapshot for every locale but never linked in
`docs.json`. This backfills the missing nav reference in the `en`,
`pt-BR`, `ko`, and `ar` v1.15.1 blocks so the page is reachable from the
version selector.
2026-06-29 10:03:26 -04:00
Lucas Gomide
4379c45804 docs: drop CREWAI_LOG_FORMAT references from Datadog guide (#6307)
JSON-formatted stdout is now the only supported log shape in CrewAI
Enterprise — the `CREWAI_LOG_FORMAT=json` opt-in env var is gone and
no longer needs to be configured in AMP. Removes the "Enabling JSON
output" section, the env-var setup step, the troubleshooting check,
and the `legacy text mode` comparison across the four locale copies
(`en`, `ko`, `pt-BR`, `ar`) of `docs/edge/<lang>/enterprise/guides/datadog.mdx`.
2026-06-29 09:04:49 -04:00
João Moura
6491f5a663 [docs-freeze] docs: snapshot and changelog for v1.15.1 (#6367)
Some checks failed
Mark stale issues and pull requests / stale (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-06-27 03:50:32 -03:00
João Moura
340f6ad5b8 feat: bump versions to 1.15.1 (#6366) 2026-06-27 03:48:21 -03:00
João Moura
04adff1e0e Fix deployment page link id resolution (#6365) 2026-06-27 03:19:46 -03:00
Vinicius Brasil
e1ddb32e56 Initialize Git repositories for generated projects (#6364)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-06-26 16:29:49 -07:00
Ossama Alami
05ab1ece8e docs(readme): improve open source positioning (#6363) 2026-06-26 16:06:16 -07:00
Lorenze Jay
e716f3de8b docs: snapshot and changelog for v1.15.1a1 (#6362) 2026-06-26 15:16:43 -07:00
Lorenze Jay
1e2c965a75 feat: bump versions to 1.15.1a1 (#6361) 2026-06-26 15:12:37 -07:00
Vinicius Brasil
a149a30bc0 Fix JSON crew template rendering (#6359)
JSON crews were not using existing CLI templates.
2026-06-26 13:48:48 -07:00
João Moura
8eaae40acf Track TUI button telemetry (#6346)
* feat(cli): track TUI button telemetry

* fix(cli): use feature usage telemetry for TUI buttons

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-06-26 12:28:47 -07:00
Vinicius Brasil
596150188b Require explicit CrewAI project definitions (#6358)
* Require explicit CrewAI project definitions

JSON crews and declarative flows now resolve from `[tool.crewai]`
metadata instead of implicit filename discovery. This makes project type
selection deterministic, prevents stray `crew.json(c)` files from changing
CLI behavior, and centralizes definition path validation for run, install,
deploy validation, plotting, and memory reset paths.

`[tool.crewai].definition` must be a project-local file path. Absolute
paths, `~`, missing files, directories, and paths escaping the project root
are rejected so deploy and runtime commands use the same contract.

Breaking changes and migration paths:

* JSON crew projects are no longer discovered from `crew.json` or
  `crew.jsonc` alone. Add explicit metadata:

  ```toml
  [tool.crewai]
  type = "crew"
  definition = "crew.jsonc"
  ```

* Declarative flow projects must use a valid project-local definition path:

  ```toml
  [tool.crewai]
  type = "flow"
  definition = "flows/research.yaml"
  ```

* `Flow.from_definition(definition)` is removed. Use:

  ```python
  Flow.from_declaration(contents=definition)
  ```

* `FlowDefinition.to_json()` and `FlowDefinition.to_yaml()` are removed.
  Use `FlowDefinition.to_dict()` and serialize with the caller's JSON or
  YAML library.

* `FlowDefinition.from_dict()` is removed. Use:

  ```python
  FlowDefinition.from_declaration(contents=data)
  ```

* `FlowDefinition.json_schema()` is removed. Use Pydantic's schema API only
  where schema generation is intentionally needed:

  ```python
  FlowDefinition.model_json_schema(by_alias=True)
  ```

* `crewai_cli.run_crew.find_crew_json_file()` and `_has_json_crew()` are
  removed. Use `configured_project_json_crew()` or the shared
  `crewai_core.project.configured_project_definition("crew")` helper.

* `crewai reset-memories` now only loads JSON crews declared through
  `[tool.crewai].definition`, and invalid declared JSON crew definitions
  fail instead of silently falling back to classic crew discovery.

* Address code review comments
2026-06-26 12:07:03 -07:00
João Moura
e10c17fcf6 Open deployment page after CLI deploy (#6343)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* Open deployment page after CLI deploy

* Format deploy browser URL helper

* Handle browser launch failures

* Prefer nested deployment identifiers
2026-06-26 14:34:07 -03:00
João Moura
f364a7d988 Fix JSON crew version pin (#6342)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* Fix JSON crew version pin

* Use bounded CrewAI dependency range
2026-06-26 05:19:14 -03:00
João Moura
2771c02f45 docs: improve coding agent setup CTA (#6344)
* docs: improve coding agent setup CTA

* docs: move home CTA to published index

* docs: address CTA review feedback
2026-06-26 05:10:55 -03:00
Rip&Tear
5d4851eac7 Fix SSRF redirect bypass in scraping fetches (#6331)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* Validate redirects for scraping URL fetches

* Prevent credential forwarding across redirects
2026-06-25 17:42:49 -07:00
Lorenze Jay
b6fbe078d6 [docs-freeze] docs: snapshot and changelog for v1.15.0 (#6340) 2026-06-25 16:17:40 -07:00
Lorenze Jay
54e28c155e feat: bump versions to 1.15.0 (#6339) 2026-06-25 16:10:48 -07:00
Lorenze Jay
9b31226494 Track conversational flow turn usage in telemetry (#6324)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* Track conversational flow turn usage in telemetry

* adjusted name to flow:conversation_turn

* only mark on turn completed event

* ensure tui also emits these events
2026-06-25 11:02:07 -07:00
Rip&Tear
654abcb40d fix: enforce owner-only permissions on credential files (#6242)
* fix: enforce owner-only permissions on credential files

Credentials stored at rest were left world-readable on multi-user hosts:

- TokenManager._get_secure_storage_path() documented its credential dir as
  mode 0o700 but created it via mkdir() with default perms (0o755), leaving
  the Fernet secret.key and encrypted tokens.enc in a traversable dir.
- Settings.dump() persisted tool_repository_password (plaintext) to
  settings.json via open("w"), producing a 0o644 file, and created the
  config dir at 0o755 — despite the sibling token_manager already writing
  secrets atomically at 0o600.

Fixes:
- TokenManager: chmod the credential dir to 0o700 after mkdir (robust against
  umask and pre-existing dirs).
- Settings: write settings.json atomically at 0o600 (mkstemp + chmod +
  os.replace) and chmod the dedicated config dir to 0o700. The /tmp and cwd
  fallback parents are deliberately not chmod'd; the 0o600 file mode protects
  the credential there.

Adds regression tests asserting 0o600 files and 0o700 dirs, and that shared
fallback dirs are not globally tightened.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* Potential fix for pull request finding 'Empty except'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* Potential fix for pull request finding 'Empty except'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* Close temp fd on secure settings write failure

* Log secure settings fd close failures

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-06-26 01:36:48 +08:00
Rip&Tear
01fc389d4a Restrict docs broken-links workflow permissions (#6330)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-06-25 10:52:33 +08:00
Vinicius Brasil
178c2d212c docs: snapshot and changelog for v1.14.8a5 (#6329)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-06-24 17:31:32 -07:00
Vinicius Brasil
563b55f7ca feat: bump versions to 1.14.8a5 (#6328) 2026-06-24 17:25:08 -07:00
Vinicius Brasil
340d23ae5d Remove StateProxy from flow state access (#6327)
`StateProxy` looked like a thread-safety boundary, but it only protected
a small slice of state operations. Some examples of operations that were
not covered:

- `self.state.counter += 1`, `self.state["counter"] += 1` (increments)
- `self.state.user.profile.score += 1` (nested object mutations)
- `self.state.config["limits"]["max"] = 10` (mutation through model fields)
- `self.state.items[0].status = "done"` (list/container mutations)

This commit decided to remove it completely for simplicity and
performance:

- Simpler runtime code
- attr read: 24x faster, attr write: 27x faster, list append: 19x faster (local benchmark)
- Clearer concurrency contract (lifecycle locks remain, but arbitrary
  shared state mutation is not presented as thread-safe)
2026-06-24 16:37:51 -07:00
Vinicius Brasil
7738a1d30c Make declarative refs work across flows and crews (#6326)
Declarative flows already used `module:qualname` refs for runtime
objects, but crew JSON tools still had their own lookup path. That meant
examples like `project_tools:LookupTool` were treated as named
`crewai_tools` lookups and failed with guidance that only mentioned
`SerperDevTool` or `custom:<name>`. Invalid refs such as
`not_tools:NotATool` also missed the same BaseTool validation used by
flow tool actions.

Move ref resolution into a shared declarative helper, use it from flow
tool actions and crew JSON loading, and require tool refs to resolve to
`BaseTool` classes before instantiation. Validation still checks tool
refs structurally, so validating a crew does not import or execute
project code.
2026-06-24 15:11:59 -07:00
Vinicius Brasil
156b3500b4 Fix JSON schema flow state kickoff inputs (#6325)
Allow required JSON schema state fields to be supplied by kickoff inputs
instead of requiring every field to exist in state.default before
runtime.

Example: a flow with required lead_name and no state.default can now run
with kickoff inputs={"lead_name": "Ada Lovelace"}.
2026-06-24 13:55:38 -07:00
Jesse Miller
5827abbc17 docs: nest One Card per Step under Crew Studio and drop rollout banner (AGE-107) (#6317)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
The page itself already landed on main via #6247. This rebases onto main
and applies the two remaining changes:

- Nest crew-studio + merged-step-card into a collapsible "Crew Studio"
  nav group (pencil icon), across edge and v1.14.7 in en, pt-BR, ko, ar.
- Remove the temporary "Rolling out" Note banner (feature ships today).

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 13:36:49 -04:00
Vinicius Brasil
9d0e3a841b docs: snapshot and changelog for v1.14.8a4 (#6319) 2026-06-24 09:19:33 -07:00
Vinicius Brasil
12a5e91efb feat: bump versions to 1.14.8a4 (#6318) 2026-06-24 09:14:14 -07:00
Rip&Tear
fac3e3579b Fix symlink path traversal in skill archive extraction (#6235)
* Fix symlink path traversal in skill archive extraction

`_safe_extractall` (the Python < 3.12 fallback used by `crewai skills`
archive unpacking) validated each member's *name* against the destination
but never validated symlink/hardlink *targets*. A malicious skill tarball
could plant a symlink escaping the destination (e.g. `link -> /home/user/.ssh`)
followed by a regular member written through it (`link/authorized_keys`),
escaping `dest` even though every member name resolves inside it — the
classic symlink-extraction traversal.

The 3.12+ path (`extractall(..., filter="data")`) already blocks this; the
fallback now mirrors it by rejecting absolute link targets and any link
target that resolves outside the destination directory.

Adds regression tests covering absolute and relative escaping symlinks plus
benign in-tree symlinks and ordinary archives.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* Harden skill cache archive extraction

* Reject special skill archive members

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-24 08:50:41 -07:00
Vinicius Brasil
a046e6a50b Validate declarative flow definition paths (#6311)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-06-23 19:28:35 -07:00
Lorenze Jay
1862ff8f6c Support conversational flows in the CLI TUI (#6293)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* Add conversational flow TUI support

* properly support tui
2026-06-23 18:04:09 -07:00
Vinicius Brasil
f2a074e35b docs: snapshot and changelog for v1.14.8a3 (#6310) 2026-06-23 14:11:31 -07:00
Vinicius Brasil
658b8ee8b9 feat: bump versions to 1.14.8a3 (#6309) 2026-06-23 14:05:23 -07:00
Vinicius Brasil
3452e5c187 Add unified declarative flow loading (#6308)
Add a single declaration loader shared by API and CLI callers.

- Add FlowDefinition.from_declaration for FlowDefinition instances, dictionaries, YAML/JSON strings, and file paths
- Add Flow.from_declaration to build runnable flows directly from the same inputs
- Route declarative flow CLI loading through Flow.from_declaration so path handling and validation stay centralized

```
# Load just the serializable definition when you do not need to run it yet.
definition = FlowDefinition.from_declaration(path="flows/research.crewai")
definition = FlowDefinition.from_declaration(contents=flow_yaml)
definition = FlowDefinition.from_declaration(contents=flow_dict)

# Build a runnable flow directly from the same declaration inputs.
flow = Flow.from_declaration(path="flows/research.crewai")
flow = Flow.from_declaration(contents=flow_yaml)
flow = Flow.from_declaration(contents=flow_dict)
flow = Flow.from_declaration(contents=definition)

# Run it like any other flow.
result = flow.kickoff(inputs={"topic": "AI agents"})

# The CLI now goes through the same path-based loader.
# crewai run --definition flows/research.crewai
```
2026-06-23 12:02:18 -07:00
Lucas Gomide
793539173d fix: pin opentelemetry to ~=1.42.0 (#6292)
The previous `~=1.34.0` pin kept us on the unmaintained 1.34 line —
last patched as `1.34.1` in June 2025, eight minor releases behind
upstream — and caused `_create_exp_backoff_generator` `ImportError`
crashes in factory deployments where the OpenTelemetry Operator's
injected init container shadows
`opentelemetry.exporter.otlp.proto.common._internal` with >=1.35 while
our `opentelemetry-exporter-otlp-proto-grpc==1.34.1` still imports the
removed private symbol. Pinning to `~=1.42.0` tracks the current
upstream stable line; the resolver now lands on 1.42.1 and our public
OTel trace API usage is unaffected.
2026-06-23 14:51:22 -04:00
Vinicius Brasil
2eb4e3a236 Improve crewai run startup UX (#6297)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Remove redundant startup logs from `crewai run` and make the legacy flow
command warning actionable.

- Stop printing `Running the Flow` and `Running the Crew` before project
  execution.
- Stop printing the redundant `Flow started with ID: ...` line while
  preserving flow lifecycle event emission.
- Replace Click's generic `kickoff` deprecation warning with a clearer
  message that tells users to use `crewai run`.
2026-06-22 22:31:39 -07:00
Vinicius Brasil
221dfdb08e Consolidate crewai run and crewai flow kickoff (#6296)
Make `crewai run` the single execution path for crews and flows, with
`crewai flow kickoff` kept as a deprecated compatibility alias.
2026-06-22 20:44:08 -07:00
Vinicius Brasil
720a4c7216 Keep flow method progress visible for nested crews (#6295)
Inline crews default to `verbose=False`. They set the shared formatter's
`verbose` value in `lib/crewai/src/crewai/crew.py`, which could hide
flow method status from `lib/crewai/src/crewai/events/utils/
console_formatter.py`.

Remove that `verbose` check for flow method status. Flow output is still
controlled by `suppress_flow_events`.

Normal quiet crews are unchanged because crew, task, and agent logs
still use their own `verbose` checks.
2026-06-22 20:37:16 -07:00
Vinicius Brasil
4b2ce00a09 Add declarative Flow CLI support (#6294)
* Add declarative Flow CLI support

Currently, declarative flows can be loaded by the runtime, but the CLI
still treats them as an experimental definition file instead of a
first-class Flow project shape.

With this PR, `crewai create flow --declarative` scaffolds a YAML-backed
Flow project, and `crewai run`, `crewai flow kickoff`, and `crewai flow
plot` can run against the configured definition.

This also lets crew actions reference reusable crew definition files or
folders and override their inputs from the Flow definition, so
declarative flows can compose existing declarative crews without
inlining everything.

* Address code review comments
2026-06-22 19:58:17 -07:00
Vinicius Brasil
0391febc6c Allow @router() as start method of a flow (#6288)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
This commit fixes a bug where a router method could not be the start
method of a flow.

This is useful when you want to route against the initial state, or even
stack two routers.
2026-06-22 14:04:45 -07:00
João Moura
4cbfbdb232 Keep JSON crew projects and deploy archives Python-free (#6228)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* fix: scaffold deployable json crews

* fix: keep json crew scaffolds python-free

* fix: keep json deploy archives python-free

* fix: tighten json crew deploy validation

* fix: address json crew pr checks

* fix: clear langsmith audit advisory
2026-06-22 13:22:46 -03:00
Vinicius Brasil
9db2d44766 Add typed output schemas for CrewAI tools (#6236)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Currently, tools have a strong input contract through `args_schema`, but no
output contract. This means that anything a tool outputs is converted to
string.

Not only the contract is weak, but the "invisible" conversion to string can
have unexpected effects when the tool returns complex objects like dicts and
arrays.

With this PR, a tool can _optionally_ define an output contract with
`output_schema`. CrewAI validates the raw result and sends the agent JSON.

```python
class ProductResult(BaseModel):
    sku: str
    name: str
    in_stock: bool

class ProductLookupTool(BaseTool):
    name: str = "Product Lookup"
    description: str = "Look up product availability by SKU."

    def _run(self, sku: str) -> ProductResult:
        return ProductResult(sku=sku, name="USB-C dock", in_stock=True)
```

If the result does not match the schema, CrewAI warns and falls back to
`str(raw_result)` instead of failing the run:

```python
@tool("Product Lookup", output_schema=ProductResult)
def product_lookup(sku: str) -> dict[str, object]:
    return {"sku": sku, "name": "USB-C dock", "in_stock": True}

#=> RuntimeWarning: Failed to validate or serialize output from tool 'Bad Product Lookup' using output_schema 'ProductResult'... Falling back to str(raw_result).
```

This is additive and non-breaking. Existing tools do not need to change. Tools
without `output_schema` keep the old string behavior. Invalid typed outputs
warn and fall back to the old formatting path.
2026-06-19 14:33:51 -07:00
Jesse Miller
cf04181190 docs: add "One Card per Step" Studio page (AGE-107) (#6247)
* docs: add "One Card per Step" Studio page (AGE-107)

Document the merge of the task and agent nodes into a single step card on
the Studio canvas. Written as evergreen present-tense feature docs with a
dated rollout banner (June 24th) for the pre-launch customer announcement;
the banner is the only time-bound content and is flagged for removal after
ship. Added in edge + v1.14.7 across en, pt-BR, ko, and ar, with nav entries
in docs.json and three canvas/editor/swap screenshots.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix: bump bedrock agentcore dependencies

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: alex-clawd <alex@crewai.com>
2026-06-19 13:10:25 -04:00
Vinicius Brasil
854c67d21c docs: snapshot and changelog for v1.14.8a2 (#6230)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-06-18 16:42:17 -07:00
Vinicius Brasil
f48a6389f1 feat: bump versions to 1.14.8a2 (#6229) 2026-06-18 16:37:27 -07:00
Vinicius Brasil
bc2c2a858c Add single agent action to Flow definitions (#6226)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* Add single agent action to Flow definitions

Lets a flow method build and run a single CrewAI agent directly, without
wrapping it in a crew. Same idea as the existing `crew` action, but for
one agent.

  methods:
    answer:
      do:
        call: agent
        with:
          role: Analyst
          goal: Answer questions
          backstory: Knows things.
          input: "${state.question}"
      start: true

* `input` is required and interpolated from flow state, like
  `${state.question}` or `${item}` inside an `each` loop
* optional `response_format` points at a Pydantic model (`{"python":
  "models.AnswerModel"}`) to get structured output
* `input` must be a string and its CEL is validated at load time, so bad
  expressions like `${state.}` fail early

* Simplify test code
2026-06-18 14:53:33 -07:00
Lucas Gomide
fa89ac428e docs: add Datadog integration guide with importable operations dashboard (#6225)
Adds a consolidated `datadog.mdx` under `docs/edge/{en,pt-BR,ko,ar}/enterprise/guides/`
covering both the Datadog Agent path (stdout JSON logs via `CREWAI_LOG_FORMAT=json`)
and the Datadog OTLP intake, with a JSON log schema reference and a ready-to-import
operations dashboard (`datadog_dashboard.json`). Reframes `capture_telemetry_logs.mdx`
to lead with OpenTelemetry as the vendor-neutral path and point readers to the new
Datadog page for that ecosystem's setup.
2026-06-18 16:18:42 -04:00
Vinicius Brasil
b0816e00b6 Validate flow CEL expressions at definition load time (#6224)
* Validate flow CEL expressions at definition load time

Promote CEL expression handling to a public Expression API and validate expressions when a FlowDefinition is built instead of when it executes.

Invalid CEL syntax or unknown roots now raise ValidationError from FlowDefinition.from_yaml() and FlowDefinition.from_dict(). Expressions may reference state and outputs, plus item inside each.do; bare identifiers are rejected as unknown roots.

For with values, the CEL contract is intentionally simple: after trimming whitespace, a string is evaluated as CEL only if it starts with ${ and ends with }. Anything else is treated as a literal value, so partial interpolation is not supported. If the content inside the wrapper is not valid CEL, validation fails.

Examples:

```text
"${state.topic}"          -> evaluated, returns state.topic
"topic is ${state.topic}" -> literal string
"${state.topic} suffix"   -> literal string
"${'a'}${'b'}"              -> invalid CEL
```

* Honor explicit empty-context overrides in evaluate() / render_template()
2026-06-18 12:18:22 -07:00
João Moura
8153b67f5d docs: snapshot and changelog for v1.14.8a1 (#6223) 2026-06-18 14:46:37 -03:00
João Moura
c226722e22 feat: bump versions to 1.14.8a1 (#6222)
* test

* feat: bump versions to 1.14.8a1
2026-06-18 14:44:10 -03:00
Vinicius Brasil
b5e23a87f2 Add optional if expression to each.do steps (#6214)
* Use explicit name/action shape for each.do steps

* Add optional `if` expression to `each.do` steps

Lets a step inside an `each` action run conditionally based on a CEL
expression evaluated against `item` and prior step `outputs`.
2026-06-18 10:33:13 -07:00
João Moura
504c5c9b04 JSON crew fixes (#6217)
* feat: update pyproject.toml to specify wheel targets

Added a new section to the pyproject.toml file to include only specific files in the wheel build, enhancing the packaging process. Updated tests to verify the inclusion of these targets.

* feat: add memory save event handling to activity log

Implemented event handlers for MemorySaveStartedEvent, MemorySaveCompletedEvent, and MemorySaveFailedEvent in the crew_run_tui module. This allows the application to log memory save operations, capturing their status and details in the activity log. Added corresponding tests to verify the correct logging behavior for successful and failed memory saves.

* feat: enhance memory save event handling in activity log

Added functionality to suppress nested memory save events and updated the handling of MemorySaveStartedEvent, MemorySaveCompletedEvent, and MemorySaveFailedEvent to improve logging accuracy. Introduced new tests to verify the correct behavior of memory save events, including scenarios for nested events and completion updates for timed-out entries.

* Fix memory save activity log handling

* Normalize alpha package versions

* Update scaffolded crew dependency

* feat: add button to copy setup instructions for CrewAI coding agents

Introduced a button in the documentation that allows users to easily copy setup instructions for CrewAI coding agents. The instructions include installation steps, environment setup, and best practices for using the CrewAI CLI. This enhancement aims to streamline the onboarding process for new users.

* Improve missing CrewAI install guidance

* fix: address pr review feedback

* fix: avoid mismatched memory save rows

* fix: wait for queued memory save events

* fix: avoid matching memory saves on missing ids

* chore: normalize prerelease version to 1.14.8a1
2026-06-18 14:14:54 -03:00
João Moura
c0fa66d182 docs: snapshot and changelog for v1.14.8a (#6216)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-06-18 02:42:41 -03:00
João Moura
6c41d55fe2 feat: bump versions to 1.14.8a (#6215) 2026-06-18 02:39:42 -03:00
Vinicius Brasil
218dc82bf7 Replace flow diagnostics with logging (#6212)
This commit removes flow diagnostics from the definition. These were
used for logging only, and should not be coupled to the definition.
2026-06-17 19:37:52 -07:00
Vinicius Brasil
7374486f00 Document FlowDefinition fields in the JSON schema (#6198)
Add a description and examples to every FlowDefinition field and
standardize on `typing.Literal`, so the generated JSON schema documents
itself — each action discriminator, state branch, and config option
explains what it is and shows a realistic value.

Examples live on individual fields only, never at the model level, which
keeps the schema readable for tooling that renders field-level help.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 18:49:01 -07:00
Vinicius Brasil
5bd10ee2c4 Add script/code block action to FlowDefinition (#6197)
* Add script/code blocks to FlowDefinition

Let a Flow method run trusted inline Python with `call: script`. The code
is compiled once into a generated function and receives the runtime
values as arguments.

```yaml
methods:
  normalize:
    start: true
    do:
      call: script
      code: |
        import math
        state["rounded"] = math.ceil(state["raw_score"])
        return f"rounded:{state['rounded']}"
```

Even though this shares the same surface of tools (custom code), I
decided to make it opt-in for now, using
`CREWAI_ALLOW_FLOW_SCRIPT_EXECUTION=1`.

* Address code review comments
2026-06-17 18:38:41 -07:00
iris-clawd
9d70553515 Use safe expression parser in calculator tool example (#6211)
* Replace eval with safe expression parser in calculator tool example

Update the calculator tool example in the CLI template to use
ast.parse instead of eval for expression evaluation.

Co-authored-by: Vinicius Brasil <vini@hey.com>

* Replace calculator example with practical file reader tool

* Use word count example - safe, no file/eval risk

---------

Co-authored-by: Vinicius Brasil <vini@hey.com>
2026-06-17 16:59:26 -07:00
Gabe Milani
0a577b7d05 fix: remove duplicated Exa tool (#6205)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* fix: remove duplicated Exa tool

* fix tests
2026-06-17 14:41:44 -07:00
Greyson LaLonde
431100ddca fix(deps): widen litellm extra to >=1.84,<2
The litellm extra was capped at <1.85, which excludes future
patch lines and reintroduces resolution failures under uv/pip.
Widen to >=1.84.0,<2 so the extra resolves cleanly against
crewai's openai/python-dotenv pins.

Closes OSS-71
2026-06-17 10:07:19 -07:00
Lucas Gomide
a237ebabba feat: adopt directory-based docs versioning with Edge channel (#6202)
* feat: adopt directory-based docs versioning with Edge channel

Switch docs.crewai.com from navigation-only versioning (every version
selector entry rendered the same docs/<lang>/* source files) to
Mintlify's directory-based versioning so each version selector entry
renders its own snapshot. Add an "Edge" channel under docs/edge/<lang>/*
that always reflects main HEAD for unreleased work, eliminating
pre-release leakage onto frozen release labels. External links to
canonical /<lang>/* URLs are preserved via wildcard redirects that
always land on the current default version.

Layout:
- docs/edge/<lang>/*         rolling source (you edit here)
- docs/edge/enterprise-api.*.yaml
- docs/v<X.Y.Z>/<lang>/*     frozen, immutable snapshots
- docs/v<X.Y.Z>/enterprise-api.*.yaml
- docs/images/               shared, append-only
- docs/docs.json             nav + redirects

URLs follow the Mintlify-idiomatic shape: /edge/<lang>/<page> for
Edge, /v<X.Y.Z>/<lang>/<page> for every frozen snapshot. The wildcard
redirects /<lang>/:slug* -> /<default>/<lang>/:slug* keep stale links
working, and every freeze rewrites them (plus all per-section/per-page
redirects) so destinations always resolve to the current default
without depending on a second redirect hop.

Release flow integration (devtools release):
- New module crewai_devtools.docs_versioning.freeze() materialises
  docs/v<X.Y.Z>/ from docs/edge/, rewrites openapi: refs inside the
  snapshot, inserts the version into every language block in
  docs.json, and refreshes all redirect destinations.
- _update_docs_and_create_pr() in cli.py now calls that freeze during
  Phase 2 of devtools release. Edge changelogs are updated first (so
  the snapshot freeze picks them up), then the snapshot is staged
  alongside docs.json, branched as docs/freeze-v<X.Y.Z>, and the PR
  is titled [docs-freeze] docs: snapshot and changelog for v<X.Y.Z>
  — the title prefix the new CI guard reads.
- The PR still gates tag, GitHub release, PyPI publish, and the
  enterprise release as before; no new PRs are added.
- Pre-releases (1.X.YaN, 1.X.YbN, ...) skip the snapshot — they ride
  Edge — and the docs PR title omits the [docs-freeze] prefix.
- docs_check (AI-generated docs scaffolding) writes to
  docs/edge/<lang>/* so newly-generated unreleased docs land in Edge
  and never accidentally touch a frozen snapshot.

Migration scripts (one-shot):
- scripts/docs/freeze_historical_versions.py reconstructs all 16
  historical snapshots (v1.10.0 .. v1.14.7) from git tags via
  git archive | tar, rewriting openapi: MDX refs so each snapshot
  reads its own enterprise-api YAML rather than the live one.
- scripts/docs/prefix_version_paths.py one-shot-migrates docs.json:
  rewrites every page path in 16 versioned blocks to point under
  docs/v<X.Y.Z>/, inserts a new Edge entry per language, tags
  v1.14.7 as Latest (default), prunes pages whose target file
  doesn't exist in the snapshot (e.g. docs/ar/ didn't exist before
  v1.12.0), and writes the wildcard + per-section redirects.
- scripts/docs/freeze_current_edge.py is now a thin CLI wrapper
  around docs_versioning.freeze for manual one-off freezes (e.g.
  retroactively snapshotting a forgotten release).

CI guards (.github/workflows/docs-snapshots.yml):
- Frozen snapshots under docs/v[0-9]*/ are immutable; only PRs whose
  title contains [docs-freeze] (i.e. release-cut PRs generated by
  devtools release or the manual wrapper) may modify them.
- Images under docs/images/ are append-only since snapshots share a
  single image directory. Deleting or renaming an image breaks every
  historical snapshot that still references it.

Restored docs/images/crewai-otel-export.png from PR #3673; it was
deleted in PR #4908 but v1.10.0 / v1.10.1 snapshots still reference
it. Restoring instead of editing the snapshots preserves historical
rendering fidelity and validates the new append-only rule
retroactively.

Tests:
- lib/devtools/tests/test_docs_versioning.py covers the freeze: file
  copy, openapi rewrite, version insertion, default demotion, redirect
  upserts, per-section redirect rewriting, idempotency, and invalid
  inputs.

Verified locally with mintlify broken-links: 0 broken links across
the full site (Edge + 16 frozen versions, 4 locales).

AGENTS.md (repo root) is the contributor guide for the new model;
RELEASING.md is the release-cut runbook; README's Contribution
section links to both.

Co-authored-by: Cursor <cursoragent@cursor.com>

* style: resolve linter issues

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-17 11:56:59 -04:00
João Moura
d3c37c4a40 Enhance memory reset functionality and JSON crew handling (#6195)
* Enhance memory reset functionality and JSON crew handling

- Added `reset_all` method to the `Memory` class to reset the entire memory store, ignoring `root_scope`.
- Updated the `Crew` class to utilize `reset_all` when resetting memory.
- Enhanced the `_reset_flow_memory` function to check for `Memory` instances and call `reset_all` accordingly.
- Introduced helper functions to load JSON crew configurations and handle project declarations, improving the reset command's flexibility.
- Added tests to validate the new JSON crew memory reset behavior and ensure proper handling of declared flow projects.

* Fix memory reset review issues

* Bump litellm for security advisory
2026-06-17 12:14:50 -03:00
Vinicius Brasil
7bb9bc7e1a Discriminate FlowDefinition state types (#6196)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Replace the single FlowStateDefinition model with a `type`-discriminated
union of FlowDictStateDefinition, FlowPydanticStateDefinition,
FlowJsonSchemaStateDefinition, and FlowUnknownStateDefinition.

Each branch only carries the fields it actually uses and forbids extras,
so an invalid combination like a `dict` state with a `ref` now fails
validation instead of being silently accepted. The runtime reads `ref`
and `json_schema` defensively since they no longer exist on every branch.

```yaml
state:
  type: json_schema
  json_schema:
    type: object
    properties:
      topic:
        type: string
```

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 21:31:07 -07:00
João Moura
ee4f853270 Update installation and quickstart documentation for JSON-first crew projects (#6181)
* Update installation and quickstart documentation for JSON-first crew projects

- Revised the installation guide to reflect the new JSON-first project structure, detailing the creation of `crew.jsonc` and `agents/*.jsonc` files.
- Updated the quickstart guide to demonstrate setting up agents and tasks using JSONC format, replacing previous YAML examples.
- Enhanced the agents and tasks documentation to clarify the transition from YAML to JSONC, including examples and explanations of the new structure.
- Added notes on the classic YAML structure for legacy projects and provided guidance on migrating to the new format.

* docs: clarify json crew quickstart guidance

* docs: address json docs review feedback
2026-06-16 19:55:23 -03:00
João Moura
ebbc0998ef Implement DMN mode support in crew creation and execution (#6194)
* Implement DMN mode support in crew creation and execution

- Added `is_dmn_mode_enabled` utility to check for enterprise non-interactive mode based on the `CREWAI_DMN` environment variable.
- Updated `create` function in `cli.py` to enforce required parameters when DMN mode is active, raising appropriate usage errors.
- Enhanced `create_crew` and `create_json_crew` functions to skip provider prompts and handle folder existence checks in DMN mode.
- Introduced non-interactive defaults for agent and task creation in DMN mode, ensuring seamless project setup without user input.
- Modified `run_crew` to bypass TUI and handle runtime inputs directly when in DMN mode, improving execution flow for JSON-defined crews.
- Added tests to validate DMN mode behavior, ensuring correct handling of required inputs and non-interactive defaults.

* Implement DMN mode support in crew creation and execution

- Introduced `is_dmn_mode_enabled()` utility to check for non-interactive mode based on the `CREWAI_DMN` environment variable.
- Updated `create` function to enforce required parameters when DMN mode is active, raising appropriate usage errors.
- Modified `create_crew` and `create_json_crew` functions to skip provider prompts and utilize non-interactive defaults in DMN mode.
- Enhanced `run_crew` to bypass TUI and handle runtime inputs directly in DMN mode, ensuring smooth execution without user interaction.
- Added tests to validate DMN mode behavior, including requirements for type and name, and ensuring proper handling of existing folders and missing inputs.
2026-06-16 19:48:31 -03:00
João Moura
06ada68083 Enhance crew loading and validation logic (#6182)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* Enhance crew loading and validation logic

- Updated `crew_loader.py` to pass the project root when loading task and agent definitions, improving the handling of Python references.
- Refactored `json_loader.py` to include additional validation for Python references, ensuring they are resolved within the project root and enforcing depth limits.
- Added tests in `test_crew_loader.py` and `test_json_loader.py` to validate rejection of unsafe Python references and input files outside the project root.
- Improved error handling for JSON project validation, ensuring clearer feedback for invalid configurations.

* Refactor tests for hierarchical verbose manager agent

- Removed `@pytest.mark.vcr()` decorators from `test_hierarchical_verbose_manager_agent` and `test_hierarchical_verbose_false_manager_agent`.
- Introduced mocking for task outputs in both tests to simulate execution without relying on external dependencies.
- Ensured that the `crew.kickoff()` method is called within a context that patches the `Task.execute_sync` method, improving test isolation and reliability.

* Fix JSON loader PR review comments

* Fix JSON loader project root after rebase

* Handle UNC paths in JSON input files
2026-06-16 18:45:26 -03:00
Vinicius Brasil
4eb90ffbf3 Add crew actions to FlowDefinition (#6184) 2026-06-16 12:59:48 -07:00
Vinicius Brasil
a6cf52ec7e Add inline crew definition loading (#6183) 2026-06-16 11:51:22 -07:00
Vinicius Brasil
9d44d0a5e5 Serialize concrete Pydantic subclasses (#6187) 2026-06-16 11:00:07 -07:00
João Moura
e9d568dc69 Deep Crew / Agent / Task attributes support on json (#6172)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* Enhance JSON crew project handling and validation

- Updated `create_json_crew.py` to specify input files with a brief path.
- Refactored `crew_loader.py` to improve agent and task loading logic, including the introduction of a `build_agent` function and better handling of task classes.
- Enhanced `json_loader.py` with additional validation for agent and task definitions, including support for Python references and conditional tasks.
- Added tests in `test_crew_loader.py` and `test_json_loader.py` to ensure proper loading of agents, tasks, and validation of project structures, including custom types and conditional tasks.
- Improved error handling and validation safety across the project loading process.

* Enhance JSON crew configuration options in create_json_crew.py

- Added optional fields for custom agent subclasses and advanced task options, including condition checks and output specifications.
- Improved documentation comments for better clarity on agent and task configurations.
- Updated JSON crew handling to support additional callbacks for pre- and post-execution processes.

* Enhance JSON crew template tests in test_create_crew.py

- Added assertions for new optional fields in crew and agent templates, including conditional tasks, custom converters, and input file specifications.
- Improved validation checks for manager agents and callback references to ensure proper configuration in JSON crew definitions.
- Expanded documentation references within the tests to provide clearer guidance on the expected structure and usage of crew templates.

* Fix JSON crew PR review issues
2026-06-16 02:00:19 -03:00
Vinicius Brasil
fe2c236601 Add each composite action to FlowDefinition (#6164)
Lets a definition loop over an array without writing Python. Each
iteration exposes `item` and prior steps `outputs`.

```yaml
do:
  call: each
  in: state.rows
  do:
    - normalize:
        call: tool
        ref: my_tools:NormalizeRowTool
        with: { row: "${ item }" }
    - lead_scoring:
        call: agent
        # ...
```
2026-06-15 21:44:33 -07:00
João Moura
53c2284484 Support ZIP deployment fallback and JSON crew project env runs (#6166)
* Update crewAI CLI with various enhancements and fixes

- Updated `create_json_crew.py` to require `crewai[tools]>=1.14.7`.
- Enhanced `git.py` with improved repository initialization, including automatic initial commit creation and exclusion patterns for initial commits.
- Modified `install_crew.py` to allow error handling during installation with an optional `raise_on_error` parameter.
- Expanded `plus_api.py` to include methods for creating and updating crews from ZIP files.
- Introduced a new `archive.py` for creating deployable ZIP archives of CrewAI projects, ensuring local artifacts are excluded.
- Updated `run_crew.py` to manage JSON crew dependencies and run crews in the project's environment.
- Enhanced deployment logic in `main.py` to handle ZIP uploads and improve user feedback during deployment processes.
- Added tests for new functionalities and ensured existing tests reflect recent changes in behavior and requirements.

* fix(cli): address deploy zip review feedback

* fix(cli): sync missing lockfile before deploy

* fix(cli): preserve remote deploy on git setup warnings

* test(cli): use single deploy main import style

* fix(cli): skip project install for json crew sync

* fix(cli): load json runner from source checkout

* fix(cli): skip json crew sync when locked

* fix(cli): address deploy zip review feedback

* fix(cli): pass env on zip redeploy

* fix(cli): harden json run and zip fallback

* fix(cli): validate before deploy lock install

* fix(cli): respect poetry lock for json runs

* fix(cli): align json zip wrapper detection

* fix(deps): bump starlette audit floor

* fix(cli): avoid auth retry for deploy exits

* fix(cli): update json zip script entrypoints
2026-06-15 18:46:54 -03:00
Lorenze Jay
a5cc6f6d0e Add crewai_version to flow execution telemetry (#6167)
Some checks failed
CodeQL Advanced / Analyze (python) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-06-15 09:34:01 -07:00
João Moura
bb477f8a91 JSON first crews (#6131)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* feat(cli): introduce JSON crew project support and TUI enhancements

- Added support for creating and running JSON-defined crew projects, allowing users to scaffold projects with a new `create_json_crew.py` file.
- Implemented a full-screen Textual TUI for crew execution in `crew_run_tui.py`, enhancing user interaction with a two-column layout.
- Updated `run_crew.py` to prioritize JSON crew projects and added daemon mode for running without TUI.
- Introduced interactive pickers in `tui_picker.py` for improved CLI prompts.
- Enhanced validation for JSON crew files in `validate.py` to ensure proper structure and agent definitions.
- Updated `.gitignore` to exclude demo and crewai directories.

* feat: update LLM model references to gpt-5.4-mini

- Changed default LLM model from gpt-4o-mini to gpt-5.4-mini across various files, including CLI options, JSON crew configurations, and agent definitions.
- Enhanced benchmark and human feedback functionalities to utilize the new model.
- Improved user interface elements in the TUI for better interaction and feedback during execution.
- Added support for new skills directory in JSON crew project creation.

* feat(benchmark): add crew-level benchmarking functionality

- Introduced a new `benchmark` command in the CLI for crew-level benchmarking, allowing users to specify agents, models, and timeout settings.
- Implemented `CrewBenchmarkCase` to handle crew-level benchmark cases with inputs and criteria.
- Enhanced the benchmark runner to support progress tracking and detailed reporting of results for multiple models.
- Added tests for loading crew benchmark cases and validating their structure.
- Updated existing benchmark functions to accommodate the new crew-level execution model.

* feat(cli): enhance JSON crew project functionality and TUI improvements

- Added optional agent-level guardrails and advanced options in JSON crew configurations to improve output validation and flexibility.
- Updated the TUI to better handle plan step statuses, including visual indicators for task completion and failure.
- Introduced methods for parsing and managing step observation events, ensuring accurate updates to task statuses during execution.
- Enhanced validation for JSON crew projects, ensuring proper structure and error handling for agent and task definitions.
- Added comprehensive tests for new features and validation logic, ensuring robustness in JSON crew project handling.

* refactor(cli): streamline JSON crew project handling and improve validation

- Refactored JSON crew project loading and validation logic to enhance clarity and maintainability.
- Introduced utility functions for finding JSON crew files, improving code reuse across modules.
- Removed deprecated benchmark functionality and associated tests to simplify the codebase.
- Updated CLI commands to utilize the new JSON project structure, ensuring compatibility with recent changes.
- Enhanced test coverage for JSON crew project features, ensuring robust validation and error handling.

* feat(cli): enhance activity log navigation and focus management

- Added functionality to focus on the activity log when navigating through log entries.
- Implemented refresh logic for the log panel to ensure updates are displayed correctly during navigation.
- Improved keyboard navigation for log entries, allowing users to expand and scroll through logs seamlessly.
- Added tests to verify the correct behavior of log navigation and focus management in the TUI.

* feat(cli): enhance JSON crew project interaction and input handling

- Introduced a new function to enable prompt line editing for better user experience during input prompts.
- Updated the JSON crew project wizards to show interpolation hints for dynamic values, improving user guidance.
- Enhanced the handling of missing input placeholders by prompting users for required values during crew setup.
- Refactored the crew run logic to ensure proper loading and preparation of JSON-defined crews, including runtime input management.
- Added tests to verify the correct behavior of new input handling features and JSON crew project interactions.

* feat(cli): improve crew project input prompts and event handling

- Enhanced the `_prompt_text` function to allow for configurable spacing before prompts, improving user experience during input collection.
- Updated the wizards for agent and task creation to utilize the new prompt configuration, ensuring a more compact and streamlined interaction.
- Introduced new plan step lifecycle events (`PlanStepStartedEvent`, `PlanStepCompletedEvent`) to better track the execution status of plan steps.
- Refactored the step executor to emit these events during the execution of tasks, improving observability and debugging capabilities.
- Added tests to verify the correct behavior of new prompt handling and event emissions during crew project execution.

* fix: refine json-first crew interactions

* fix: prioritize common json crew tools

* fix: make json crew more tools expandable

* fix: show json crew tools by category

* feat(memory): update default embedder to OpenAI text-embedding-3-large and enhance memory compatibility

- Changed the default embedding model for Memory to OpenAI text-embedding-3-large, which uses 3072-dimensional vectors.
- Added warnings regarding compatibility issues with existing local memory stores created with 1536-dimensional embeddings.
- Updated documentation to reflect the new default embedder and its configuration options.
- Enhanced the CLI and codebase to support the new embedding model across various components, ensuring a seamless transition for users.

* fix: address PR review feedback for JSON-first crews

Review blockers:
- Forward trained_agents_file to JSON crews: crewai run -f now exports
  CREWAI_TRAINED_AGENTS_FILE for the in-process JSON crew path
- Wizard agent picker: Esc/cancel now reprompts instead of silently
  assigning the first agent
- JSON tool resolution hard-fails: unknown tool names, missing custom
  tool files, and invalid custom tool modules raise JSONProjectError
  with actionable messages instead of warn-and-continue
- Embedding dimension mismatch: LanceDB and Qdrant Edge storages raise
  EmbeddingDimensionMismatchError with reset/pin guidance instead of
  silently zero-filling vectors or returning empty search results
- Custom tool code execution documented in loader docstring and the
  scaffolded project README

CI fixes:
- ruff format across lib/
- All 133 PR-introduced mypy errors fixed (llm.py lazy-litellm and
  cli.py lazy command shims now use TYPE_CHECKING imports; textual
  is_mounted misuse fixed; pick_many overloads; misc annotations)

Bot review comments:
- Empty except blocks now have explanatory comments or debug logging
- Removed unused _C_BG/_C_PANEL/_C_BORDER globals and redundant
  import re; tests use a single import style for create_json_crew

Tests: trained-agents propagation, wizard cancel, tool resolution
failures, and dimension mismatch guidance.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: address second round of PR review comments

Cursor Bugbot:
- Wizard agent slugs: strip to [a-z0-9_] and fall back to agent_<n> so
  symbol-only roles can't produce an empty agents/.jsonc filename
- Wizard task names: dedupe against prior task names and fall back to
  task_<n> for symbol-only descriptions

CodeRabbit:
- Agent.message(): import Task explicitly at runtime instead of relying
  on the namespace injection done by crewai/__init__
- Async executor: move the native-tools-unsupported fallback from
  _ainvoke_loop_react (self-recursion) to _ainvoke_loop_native_tools,
  mirroring the sync implementation
- StepExecutor downgrade: keep the in-step conversation and append the
  text-tooling instructions instead of rebuilding messages, so completed
  native tool calls are not re-executed
- crewai-files: extension-based MIME lookup now runs before byte
  sniffing so csv/xml types are not degraded to text/plain
- Memory storages: validate every record in a save() batch against a
  consistent embedding dimension (LanceDB previously checked only the
  first record); added mixed-batch tests
- _print_post_tui_summary now typed against CrewRunApp
- Docs: Azure OpenAI default embedder change called out in the memory
  migration warning and provider table

Code quality bots:
- Removed unused _C_YELLOW/_C_CYAN (crew_run_tui) and _GREEN (tui_picker)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(cli): accordion tool picker in JSON crew wizard

The flat tool list had grown to ~90 rows. The picker now shows:
- Common tools always visible at the top
- Every other category as a single expandable row with tool and
  selection counts (e.g. "Search & Research  (27 tools, 2 selected)")
- Expanding a category collapses the previously expanded one
- Selections persist across expand/collapse via new preselected
  support in pick_many; cursor follows the toggled category row

tui_picker gains preselected + initial_cursor options on pick_many,
and Esc in multi-select now confirms the current selection instead of
discarding it (required so collapsing can't silently drop choices).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor(cli): remove --daemon flag from crewai run

The flag only affected JSON crew projects — classic and flow projects
ignored it entirely, which made the behavior inconsistent. Removed the
option, the daemon code path (_run_json_crew_daemon), and its helper
(_load_json_crew_with_inputs).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test: update run command tests after --daemon removal

lib/crewai/tests/cli/test_run_crew.py still asserted the old
run_crew(trained_agents_file=..., daemon=False) call signature.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(cli): exit codes, mid-run quit, async statuses, hyphen placeholders

Addresses the latest Bugbot review round:

- Failed JSON crew runs now exit non-zero (SystemExit(1)) so scripts
  and CI don't treat failures as success, mirroring the classic path
- Quitting the TUI mid-run now ends the process (os._exit(130));
  kickoff runs in a thread worker that cannot be force-cancelled, so
  letting the CLI return would leave LLM/tool work burning tokens in
  the background
- Sidebar task statuses are now async-safe: completion/failure events
  resolve the task's own row via identity instead of assuming the most
  recently started task, and starting a task no longer blanket-marks
  earlier active rows as done
- The runtime-input prompt regex now accepts hyphenated placeholder
  names ({my-topic}), matching kickoff's interpolation pattern

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: validation safety, custom tool sandboxing, TUI log integrity, memory error surfacing

- Deploy validation no longer executes project code: validation mode
  checks tool declarations structurally (well-formed entries, custom
  tool file exists) without importing or instantiating anything.
  custom:<name> resolution only happens on the actual run path.
- custom:<name> is constrained to [A-Za-z_][A-Za-z0-9_]* and the
  resolved path must stay inside the project's tools/ directory, so
  custom:../foo or absolute-path names cannot execute code outside it.
  Tool paths resolve relative to the crew project root, not cwd.
- TUI task logs are built from per-task state captured at task start
  (idx, description, agent, start time); an out-of-order completion
  takes its output from the event and no longer steals or resets the
  current task's streamed steps/output.
- EmbeddingDimensionMismatchError now inherits ValueError instead of
  RuntimeError so background saves surface it through
  MemorySaveFailedEvent instead of silently dropping the save; the
  shutdown catch in _background_encode_batch is narrowed to the
  "cannot schedule new futures" case.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(cli): declared project type wins over crew.json presence

A flow project that also contains a crew.json(c) file now runs and
validates as the flow it declares in pyproject.toml instead of being
hijacked by the JSON crew path. Both crewai run (_has_json_crew) and
deploy validation (_is_json_crew) check tool.crewai.type; a missing or
unreadable pyproject still means a bare JSON crew project.

Also documents why StepObservationFailedEvent intentionally marks the
plan step "done": the event signals an observer failure, not a step
failure, and the executor continues past it.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(cli): type the declared_type locals so mypy stays clean

Comparing an Any-typed .get() chain returns Any, which tripped
no-any-return on the previous commit.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-14 04:19:48 -03:00
Vini Brasil
d80719df81 Add experimental crewai run --definition for flows (#6147)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Let users run a Flow from a Flow Definition YAML file or inline string
without writing Python, passing kickoff inputs as `--inputs` JSON. The
flag is gated behind an experimental warning since the definition format
may still change.
2026-06-12 22:31:05 -07:00
Vini Brasil
6ad821b157 Add expressions to FlowDefinition actions (#6145)
* Add expressions to FlowDefinition actions

Let definitions compute values without Python. A new `call: expression`
action evaluates a Common Expression Language (CEL) expression, and tool
`with:` blocks now render `${...}` CEL templates.

Example 1:

```yaml
decide:
  do:
    call: expression
    expr: "state.score >= 80 ? 'qualified' : 'nurture'"
  router: true
  emit: [qualified, nurture]
```

Example 2:

```yaml
search:
  do:
    call: tool
    ref: my.pkg:SearchTool
    with:
      search_query: "${outputs.build_query.query + ' news'}"
      max_results: "${state.limit}"
```

* Address code review comments

* Address code review comments

* Fix linting offenses

* Address code review comments

* Fix scrapgraph issue
2026-06-12 21:56:02 -07:00
Vini Brasil
2444895ca4 Implement Flow definition run tools without Python code (#6144)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
A `do:` step can now say `call: tool` and name a CrewAI tool to run,
passing its inputs under `with:`. Before this, a definition could only
point at Python code to run.

```yaml
methods:
  search:
    start: true
    do:
      call: tool
      ref: crewai_tools:ExaSearchTool
      with:
        search_query: ai agents
```
2026-06-12 19:47:58 -07:00
Vini Brasil
bf291a7a55 Drive human feedback from the flow definition (#6133)
* Drive human feedback from the flow definition

@human_feedback previously wrapped methods with the full HITL runtime (feedback
request, outcome collapse, learn loop), so flows built from a YAML definition —
which carry no decorated callables — could not pause for or route on human
feedback.

# Conflicts:
#	lib/crewai/src/crewai/flow/persistence/decorators.py
#	lib/crewai/src/crewai/flow/runtime/__init__.py

* Address code review comments
2026-06-12 14:48:43 -07:00
Vini Brasil
64438cba37 Wire config and persistence from FlowDefinition into the runtime (#6132)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
* Wire config and persistence from FlowDefinition into the runtime

`from_definition` was silently dropping all config fields; it now passes
`config.model_dump()` so suppress_flow_events, max_method_calls, etc.
actually apply.

Persistence is now engine-driven: `_persist_method_completion` fires
after every method using the definition's persist metadata, so
`@persist` no longer needs to wrap methods — it just stamps them.

* Address code review comments
2026-06-12 11:51:44 -07:00
Lucas Gomide
887adafd2c fix: aggregate token usage across all LLM calls (#6122)
* feat: aggregate LLM token usage at the flow level

Introduces `flow.usage_metrics`, a snapshot of every LLMCallCompletedEvent
emitted under the flow's `current_flow_id` for the duration of one kickoff
(or resume) call. Aggregation happens on the singleton event bus so it
covers crews, direct `LLM.call`s, and nested listener calls — solving the
mismatch where the SDK reported only the last crew's usage while the
Enterprise UI showed the correct full total.

Co-authored-by: Cursor <cursoragent@cursor.com>

* refactor: centralize provider key normalization in UsageMetrics

Add UsageMetrics.from_provider_dict to normalize raw LLM usage dicts
across providers (LiteLLM, native Anthropic, native Gemini, OpenAI
nested cached). BaseLLM._track_token_usage_internal and the flow-level
aggregator now share this single source of truth, so `flow.usage_metrics`
agrees with per-LLM totals on every provider — including the native
Anthropic path that emits `input_tokens`/`output_tokens` instead of
`prompt_tokens`/`completion_tokens`.

* fix: flush event bus before reading aggregated usage_metrics

`crewai_event_bus.emit` dispatches LLMCallCompletedEvent handlers on a
ThreadPoolExecutor (fire-and-forget), so a flow whose last LLM call
completes right before kickoff_async/resume_async returns can detach
the usage listener while that handler is still queued, leaving its
tokens off `flow.usage_metrics`. Match `Crew.kickoff()` and call
`crewai_event_bus.flush()` in both finally blocks so every handler
drains before the listener is detached.

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-12 12:55:22 -04:00
Rip&Tear
d3fc0d31f8 [codex] Redact file tool paths (#6134)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* Redact file tool paths

* Fix for pull request finding 'Empty except'

* Potential fix for pull request finding

---------
2026-06-12 15:50:40 +08:00
Vini Brasil
373dca3d04 Run flows from a definition without a Python subclass (#6104)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* Read flow dispatch from FlowDefinition

Store the definition in a `_definition` PrivateAttr at post-init and
convert the dispatch helpers (`_start_method_names`, `_listener_methods`,
`_start_condition`, `_listen_condition`, `_is_router`) from classmethods
to instance methods that read it. Event names now fall back to
`self._definition.name` instead of `self.__class__.__name__`.

Behavior is identical for decorator subclasses, but the engine no longer
assumes the definition comes from the class. This is the seam for
`Flow.from_definition`, where an instance runs a definition that was
loaded rather than built from a Python subclass.

* Add Flow.from_definition to run flows without a subclass

A FlowDefinition (e.g. loaded from YAML) was only usable for dispatch on
decorator-authored subclasses. Now each method definition records an
importable `module:qualname` handler ref, and `Flow.from_definition`
resolves and binds those handlers to build a runnable flow directly.

* Build flow state from FlowDefinition

Definition-driven flows previously always started with a bare dict
state.

* Replace handler string with structured FlowActionDefinition

`handler: str | None` was optional and opaque — missing handlers only
surfaced at kickoff time. `do: FlowActionDefinition` is required, so
Pydantic rejects invalid definitions at parse time.

The `call: "code"` discriminator prepares the schema for future
non-Python action types (e.g. MCP tool, crew) without touching
`FlowMethodDefinition`. Resolution logic is extracted to
`runtime/_action_resolvers.py` to keep the dispatch point isolated.

* Fix conversational start router missing required do field

FlowMethodDefinition.do became required when the handler string was
replaced with FlowActionDefinition, but _conversation_start_router still
built its fragment without it, breaking crewai import entirely.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* Add event scoping to flow test

* Change lib/crewai/tests/test_flow_from_definition.py

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-11 14:18:49 -07:00
Greyson LaLonde
21fa8e32d9 docs: update changelog and version for v1.14.7
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-06-11 10:13:40 -07:00
Greyson LaLonde
f18c03cd8f feat: bump versions to 1.14.7 2026-06-11 10:06:07 -07:00
Greyson LaLonde
50b9c02272 fix(checkpoint): rebuild custom BaseLLM as concrete LLM on restore
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
A custom BaseLLM subclass serializes with the inherited llm_type "base",
which the registry maps to the abstract BaseLLM. Restore then crashed on
cls(**value). Rebuild a concrete LLM from the saved config when the
resolved class is abstract.
2026-06-10 22:21:35 -07:00
Greyson LaLonde
c55334be5f docs: update changelog and version for v1.14.7rc2 2026-06-10 20:52:56 -07:00
Greyson LaLonde
05a2ba9ca4 feat: bump versions to 1.14.7rc2 2026-06-10 20:45:29 -07:00
Greyson LaLonde
fbafe1f0d3 fix(flow): gate restore on a flag so live snapshots don't replay as resume
Checkpoint serialization stamps checkpoint_completed_methods onto every live
Flow in RuntimeState.root, including the agent executor reused across a crew's
tasks. kickoff_async read that stamp as a restore signal, so the second task
replayed the first task's completed methods and never reached a final answer.

Gate is_restoring on _restored_from_checkpoint, set only by
_restore_from_checkpoint, and consume it single-shot.
2026-06-10 20:40:08 -07:00
Greyson LaLonde
5267c059f5 test(flow): pass show=False in test_flow_plotting to not open a browser
flow.plot defaults to show=True, which calls webbrowser.open on every run.
The test only asserts FlowPlotEvent is emitted, so disable the browser open.
2026-06-10 20:36:14 -07:00
Greyson LaLonde
243c9edc1c docs: update changelog and version for v1.14.7rc1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-06-10 18:56:52 -07:00
Greyson LaLonde
68910b70c0 feat: bump versions to 1.14.7rc1 2026-06-10 18:50:54 -07:00
Greyson LaLonde
299782765c ci: ignore GHSA-rrmf-rvhw-rf47 (torch alias of PYSEC-2025-194)
* ci: ignore GHSA-rrmf-rvhw-rf47 (torch alias of PYSEC-2025-194)

pip-audit reports CVE-2025-3000 under its GHSA id, which the existing
PYSEC-2025-194 ignore does not match. Same advisory: memory corruption
in torch.jit.script, CVSS 1.9, local-only, no fix for torch 2.11.0.

* ci: sync GHSA-rrmf-rvhw-rf47 ignore into pre-commit pip-audit
2026-06-10 18:45:42 -07:00
Greyson LaLonde
a1f44eb272 fix(events): scope runtime state per run to bound growth and isolate concurrent runs 2026-06-10 18:39:05 -07:00
Lorenze Jay
036b032ab6 handle supporting both custom prompts (#6108)
* handle supporting both custom prompts

* handle translations

* handle deprecation warnings better
2026-06-10 17:52:53 -07:00
Lorenze Jay
f88ae54f96 fix telemetry setup on crewai-login (#6106)
* fix telemetry setup on crewai-login

* type check fix
2026-06-10 17:03:25 -07:00
Lorenze Jay
b6e5d632c1 improve convo routing cycle with one less route (#6102)
* improve one less route

* flows in flows, new agent executor causing early trace batch finalization

* addressing comments

* addressing comments pt2

* lint and typecheck fix
2026-06-10 16:49:16 -07:00
Greyson LaLonde
0d971e5bc5 feat(events): add reset_runtime_state to release accumulated bus state 2026-06-10 16:12:28 -07:00
Lucas Gomide
b3f175b56f docs: update otel images (#6103)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-06-10 14:34:30 -04:00
Lucas Gomide
f523a7d029 docs: udpate docs to reflect new state of OpenTelemetry collector (#6100)
* docs: udpate docs to reflect new state of OpenTelemetry collector

* docs: add OTel collector and Datadog screenshots

These images are referenced by the capture_telemetry_logs guides but were
missing from the tree, which broke the link checker across all locales.

* docs: address PR review on OTel collector guide

- Clarify that OpenTelemetry Traces and Logs are separate integrations
  sharing the same fields (resolves Traces/Logs wording inconsistency)
- List regional Datadog OTLP hosts (US1/US3/US5/EU1/AP1) so users outside
  US5 can copy the right domain
2026-06-10 14:26:35 -04:00
Lorenze Jay
f214ff4b7b decouple convo logic from runtime and added a conversational_definition (#6091)
* decouple convo logic from runtime and added a conversational_definition

* type check fix

* always defer traces for convo and so fix tests to reflect that
2026-06-10 10:49:39 -07:00
Vini Brasil
a9e7c3a44f Simplify flow condition evaluation to be stateless per event (#6097)
Re-evaluate the whole `@listen`/`@router` condition tree against the set
of events seen so far, instead of tracking which AND sub-branches remain
pending.

Net effect:
* Fixes a regression where `or_()` short-circuited at the first
  satisfied branch, leaving a sibling `and_()` half-complete so a later
  trigger could spuriously re-fire the listener
* Removes the fragile per-branch pending state and `id()`-based keys
* Shrinks the evaluator to one readable predicate
2026-06-10 10:35:25 -07:00
Lucas Gomide
da8fe8c715 fix: respect suppress_flow_events for method-execution events (#6095)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: respect suppress_flow_events for method-execution events

* test: align suppressed-flow test with new method-event behavior
2026-06-09 17:19:25 -04:00
Greyson LaLonde
ce42994ae3 docs: update changelog and version for v1.14.7a4 2026-06-09 12:58:38 -07:00
Greyson LaLonde
820c3905e3 feat: bump versions to 1.14.7a4 2026-06-09 12:51:55 -07:00
Vini Brasil
703ffe67ee Migrate @listen/@router runtime to read from FlowDefinition (#6084)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* Migrate @listen/@router runtime to read from FlowDefinition

The runtime now resolves listener conditions, router status, and emit
values from `FlowMethodDefinition` instead of legacy method metadata and
the `_listeners`/`_routers`/`_router_emit` registries.

* Evaluate AND/OR listener conditions over the definition shape via
  `_evaluate_definition_condition`
* Drop the class registries and the `FlowMeta` extraction that built
  them; stop stamping `__trigger_methods__`, `__is_router__`,
  `__router_emit__`, and friends
* `@human_feedback` emit now lives only on its config

* Simplify conditionals DSL
2026-06-09 09:40:30 -07:00
Matt Aitchison
8919026326 feat(storage): pluggable default backends for memory, knowledge, rag, flow (#6079)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Add opt-in extension seams so an application can route memory, knowledge,
RAG, and flow persistence through a custom backend without subclassing or
threading an explicit instance through every construction site -- mirroring
the existing crewai_core.lock_store.set_lock_backend seam.

- memory:    crewai.memory.storage.factory.set_memory_storage_factory
- knowledge: crewai.knowledge.storage.factory.set_knowledge_storage_factory
- rag:       crewai.rag.factory.register_rag_client_factory (provider registry)
- flow:      crewai.flow.persistence.factory.set_flow_persistence_factory

Each construction site consults the registered factory and falls back to the
built-in default when none is set; an explicit instance always wins. Widen
Knowledge.storage and the knowledge source base classes to BaseKnowledgeStorage
(consistent with BaseAgent.knowledge_storage) so any base-interface backend
plugs in. Runtime-free tests cover each seam.
2026-06-08 21:14:13 -05:00
Greyson LaLonde
988927006c docs: update changelog and version for v1.14.7a3
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-06-08 18:56:39 -07:00
Greyson LaLonde
48c1987fcf feat: bump versions to 1.14.7a3 2026-06-08 18:43:15 -07:00
Greyson LaLonde
af62b7b583 fix: expose ask_for_human_input on experimental AgentExecutor
fixes #6065
2026-06-08 17:55:19 -07:00
Greyson LaLonde
1b14e162e9 fix: resolve pip-audit CVEs (aiohttp, docling, docling-core, pip)
* fix: resolve pip-audit CVEs for aiohttp, docling, docling-core, pip

- aiohttp 3.13.4 → 3.14.0: fixes GHSA-jg22-mg44-37j8, GHSA-hg6j-4rv6-33pg
- docling 2.84.0 → 2.97.0: fixes GHSA-cjqg-rq2h-2fvj, GHSA-pj2v-ggqh-cmq2,
  GHSA-r3xg-rg9j-67fv, GHSA-q29v-xc37-wh5m
- docling-core 2.74.0 → 2.79.0: fixes GHSA-j5xp-7m2f-49jv, GHSA-jmmv-h3mp-59v8
- pip 26.1.1 → 26.1.2: fixes PYSEC-2026-196

docling-core 2.74.1+ requires pydantic-settings>=2.14.0, so the crewai pin
is loosened from ~=2.10.1 to >=2.10.1,<3. pydantic-settings resolves to
2.14.1 in the lock.

* fix: correct aiohttp CVE floor to 3.14.0 (not 3.13.5)

* test: shim AsyncStreamReaderMixin for vcrpy under aiohttp 3.14.0

aiohttp 3.14.0 removed aiohttp.streams.AsyncStreamReaderMixin (folded into
StreamReader). vcrpy's aiohttp stub still subclasses it, so vcr's patch
machinery raised AttributeError at test collection. Restore an equivalent
mixin in conftest before vcr is imported.

* test: rebuild vcrpy MockClientResponse init for aiohttp 3.14.0

aiohttp 3.14.0 added a required stream_writer kwarg to ClientResponse.__init__
and reads stream_writer.output_size when writer is None. vcrpy's
MockClientResponse doesn't pass it, raising TypeError at cassette playback.
Rebuild the super().__init__ call from the live signature (defaulting required
keyword-only args to None, with a stream_writer stub exposing output_size) so
it survives future aiohttp signature additions too.

* test: avoid deprecated get_event_loop in vcrpy aiohttp shim

asyncio.get_event_loop() emits a DeprecationWarning (and can RuntimeError)
when no current loop is set on Python 3.12+. Prefer get_running_loop() (the
real cassette-playback path always has one) and fall back to a single cached
loop in sync contexts, since the mock only stores the loop and calls
get_debug().

* fix: pull docling-core[chunking] so HierarchicalChunker imports

docling 2.97 split into docling-slim, moving the chunker's code-chunking
deps (tree-sitter, semchunk, language grammars) behind docling-core's
[chunking] extra. crewai's knowledge source imports HierarchicalChunker,
whose package __init__ eagerly imports those submodules -> ModuleNotFoundError
('tree_sitter') without the extra. Request docling-core[chunking]; carry the
extra in override-dependencies too, since overrides replace the whole
requirement and would otherwise strip it.
2026-06-08 17:45:07 -07:00
Vini Brasil
e570534f15 Migrate @start to read from FlowDefinition (#6071)
* Remove `_start_methods` and `__is_start_method__` stamping
* Add helpers to read start info from the definition
* Scan `__dict__` instead of `dir()` to find flow methods
2026-06-08 15:03:50 -07:00
Lorenze Jay
913a3abead docs: update changelog and version for v1.14.7a2 (#6055)
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-06-05 14:19:42 -07:00
Lorenze Jay
17cfbdf95f feat: bump versions to 1.14.7a2 (#6054) 2026-06-05 14:15:43 -07:00
Lorenze Jay
8cd51fc67e Lorenze/imp/conversational flow traces (#6044)
* feat: add conversation message and route selection events

- Introduced `ConversationMessageAddedEvent` and `ConversationRouteSelectedEvent` to enhance conversational flow tracking.
- Updated event listeners to emit these events during message handling and routing decisions.
- Enhanced the `_ConversationalMixin` class to emit events for user and assistant messages, as well as selected routes.
- Added tests to verify the correct emission of these events during conversational turns.

* ensure flow started events only emiited once

* refactor(tracing): rename trace event handler methods to action event handlers

Updated the  class to replace  with  for  and  events, improving clarity in event handling.

Additionally, adjusted comments in the  class to clarify the application of pending user messages in relation to state restoration and flow scope initialization.

* fix(conversational_mixin): handle empty message index in route events

Updated the message index handling in the  class to return  when there are no messages. Added tests to ensure that route events do not reference index zero when the transcript is empty, and verified the correct emission of conversation message events during flow handling.
2026-06-05 14:10:19 -07:00
Lorenze Jay
3723f0db76 Update conversational flow docs to use handle_turn (#6053) 2026-06-05 11:04:28 -07:00
Lucas Gomide
cab3319af9 feat(otel): surface real finish_reason + sampling params + response.id on LLM events (#5945)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* feat(otel): surface real finish_reason + sampling params + response.id on LLM events

Companion to the OTel GenAI emitter compliance work in crewai-enterprise
(CON-172). Today the enterprise emitter reads these fields off the OSS
LLM events via `getattr(..., None)`, so it produces valid (but partial)
spans against the existing OSS surface. This change makes those fields
first-class on the events so spans can carry the real provider data.

What this adds:

- `LLMCallStartedEvent` gains the sampling-param fields the emitter needs
  for `gen_ai.request.*`: `temperature`, `top_p`, `max_tokens`, `stream`,
  `seed`, `stop_sequences`, `frequency_penalty`, `presence_penalty`, `n`.
  All optional; existing call sites keep working.
- `BaseLLM._emit_call_started_event` introspects those values off `self`
  (the LLM instance) via `getattr(..., None)` so every provider gets the
  fields propagated for free without per-provider plumbing.
- `LLMCallCompletedEvent` gains `finish_reason: str | None` and
  `response_id: str | None`. A field validator coerces any non-string
  value (MagicMock, unexpected provider object) to None so the event
  never raises on construction.
- `LLM._emit_call_completed_event` accepts both as kwargs.
- `LLM` (LiteLLM path) gets a defensive `_extract_finish_reason_and_response_id`
  helper that handles both streaming (`StreamingChoices`) and non-streaming
  (`Choices`) shapes and is wired into every completion-event emission site.
- Provider completions extract native values from their SDK responses and
  pass them through:
  - OpenAI: `_extract_responses_finish_reason_and_id` for Responses-API,
    `_extract_finish_reason_and_id` for Chat-Completions.
  - Anthropic: `_extract_finish_reason_and_id` (Messages API + streaming).
  - Bedrock: `_extract_finish_reason_and_id` (`stopReason` from converse).
  - Gemini: `_extract_finish_reason_and_id` (`finish_reason` from candidates).
  - Azure: inherits via OpenAI sub-class; adds the helper for Azure-specific
    response shapes.
  - openai_compatible: inherits from OpenAICompletion, no edits needed.

Compatibility:

- All new fields are optional with sensible defaults. No existing call
  sites need to change.
- The validator on `LLMCallCompletedEvent` swallows non-string values for
  the new fields so legacy mocks / exotic provider types don't blow up
  event construction.
- Enterprise side already reads these fields defensively, so OSS and
  enterprise can merge independently and cut on the same synchronized
  release.

Tested against the full LLM + events + provider test suite — all green;
the 14 pre-existing multimodal failures on main are unrelated and
reproduce without this diff.

* fix(bedrock): propagate finish_reason + response_id on async paths

The original commit covered every provider's sync path and Bedrock's
sync streaming path, but two Bedrock async paths still emitted
LLMCallCompletedEvent without finish_reason/response_id:

- _ahandle_converse: the final fallback emit_call_completed_event call
  was missing both fields. Added stop_reason + response_id matching the
  other emission sites in the same function.

- _ahandle_streaming_converse: response_id was never seeded from the
  initial response object, and stream_finish_reason wasn't propagated
  to the structured-output and final-text emissions. Now extracts
  response_id up front and threads stream_finish_reason through every
  completion event.

Adds a dedicated test file covering the new event fields end-to-end:
- LLMCallCompletedEvent.finish_reason / response_id Pydantic validation
  (string accepted, None default, non-string coerced to None).
- LLMCallStartedEvent sampling params (all nine fields accepted, default
  to None).
- BaseLLM._emit_call_started_event introspecting sampling params off
  self, with explicit kwargs overriding.
- BaseLLM._emit_call_completed_event passing finish_reason/response_id
  through to the event.
- LLM._extract_finish_reason_and_response_id across the LiteLLM shapes
  (non-streaming response, streaming chunk, dict, missing fields,
  non-string values, unexpected input).

* fix(otel): correct streaming finish_reason + bedrock response_id semantics

Two correctness fixes uncovered while landing the OTel finish_reason +
response_id plumbing:

- LiteLLM streaming (sync + async): `stream_options={"include_usage": True}`
  causes LiteLLM to emit a final usage-only chunk with `choices=[]`. The
  post-loop `_extract_finish_reason_and_response_id(last_chunk)` silently
  returned `(None, None)` because the last chunk has no choices, even though
  earlier chunks carried `finish_reason="stop"`. Track both fields
  incrementally inside the loop (mirroring how OpenAI/Gemini/Azure already
  handle their native streams) and use the tracked values for the
  LLMCallCompletedEvent emission and the partial-response error path.

- Bedrock Converse: `ResponseMetadata.RequestId` is an AWS infra trace id,
  not a model-level response id (semantically different from OpenAI's
  `chatcmpl-XXX`). Return None for `response_id` rather than mislead
  downstream telemetry consumers. The audit-fix's async propagation chain
  still works — None propagates through unchanged.

Adds `test_llm_streaming_finish_reason.py` pinning both the sync and async
LiteLLM streaming paths against the include_usage chunk shape.

* refactor(otel): unify LLM event introspection + drop redundant defensive code

Three cohesion cleanups uncovered during PR review, all behavior-preserving:

- LLM.call / LLM.acall in llm.py now delegate to BaseLLM._emit_call_started_event
  instead of constructing LLMCallStartedEvent inline. The base helper already
  introspects sampling params off self via getattr; the inline duplication was
  accidental, not justified, and a duplication risk if anyone adds a tenth
  OTel sampling param later.

- Extracted lib/crewai/llms/_finish_reason_utils.py:extract_choices_finish_reason_and_id
  as the shared extractor for the choices-based response shape. OpenAI Chat,
  Azure, and LiteLLM all read the same shape (response.id + choices[0].finish_reason)
  as both object attrs and dict keys. Providers with genuinely different shapes
  - Anthropic (stop_reason), Bedrock (stopReason), Gemini (protobuf enum),
  OpenAI Responses (status) - keep their own provider-specific helpers.

- Dropped redundant try/except (AttributeError, TypeError) wrappers around
  bare getattr(obj, "field", None) calls across the new extraction helpers.
  getattr with a default already suppresses AttributeError, and the inner
  isinstance / dict.get / int-coercion ops can't raise TypeError in practice.
  Kept the catches that legitimately guard against IndexError (e.g. choices[0]
  on an empty list).

Tests: 600 passed, 23 skipped, 14 pre-existing multimodal failures unchanged.
Added 12 parametrized tests for the shared helper covering object + dict
shapes, missing fields, non-string coercion, and never-raises invariants.

* chore(otel): drop dead last_chunk variable from async streaming

The streaming-fix commit (49e5581b5) replaced the post-loop
`_extract_finish_reason_and_response_id(last_chunk)` call with the
incrementally-tracked `stream_finish_reason` / `stream_response_id`,
which removed the only reader of `last_chunk` in
`_ahandle_streaming_response`. The declaration and per-iteration
assignment were left behind — harmless but confusing for future
readers because the sync sibling still legitimately uses `last_chunk`
(for usage and content fallbacks via `_handle_streaming_callbacks`).

The async path inlines its usage extraction directly inside the loop
(`chunk.model_extra.get("usage")`), so there's no fallback consumer.
Drop both lines.

Sync path untouched — `last_chunk` there is still load-bearing.

* fix(otel): coerce non-list stop_sequences to list[str] on LLMCallStartedEvent

Observed in Datadog: gen_ai.request.stop_sequences on a Gemini/Vertex
span surfaced the textproto repr of a google.protobuf.struct_pb2.ListValue
(values { string_value: "\nObservation:" }) instead of a real Sequence[str].

Root cause is upstream - a Vertex AI / Gemini code path stores the stop
list in a protobuf container (RepeatedScalarContainer or ListValue) rather
than a plain Python list. When that container reaches LLMCallStartedEvent
and then BaseLLM._emit_call_started_event hands it to the OTel SDK as a
span attribute, the SDK falls back to str(value) because the type isn't a
recognised Sequence[str] - producing the protobuf textproto string instead
of an array attribute.

* chore: fix ruff lint findings

* refactor(otel): declare sampling params on BaseLLM + honor stop overrides + dict chunk id

* fix: widen max_tokens to int | float | None + apply ruff format

* fix(otel): coerce unknown finish_reason / response_id to None instead of stringifying

* fix(otel): extract Azure stream finish_reason/id before usage-continue

Match the LiteLLM ordering so a finish_reason or response id riding on a
usage-carrying chunk isn't dropped by the early `continue`.

* fix(otel): report effective max_tokens cap + bedrock structured finish_reason
2026-06-05 07:23:38 -04:00
Vini Brasil
906cd9769d feat(flow): type DSL triggers as route-aware decorators (#6042)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Centralize FlowTrigger and FlowMethodDecorator so start/listen/router and the boolean trigger helpers share one authoring contract. This preserves decorated method signatures for static checking while allowing route-label strings in nested FlowCondition data.

Export the shared typing helpers for static analyzers, use an explicit Protocol body, align condition validation with Sequence-backed condition data, and drop the stale call-arg ignore exposed by the signature-preserving decorators.

Update the flow guide to use or_(...) for multi-label listeners.
2026-06-04 18:07:49 -03:00
Lorenze Jay
14ce97d787 chat api for convo flows (#6034)
* Add conversational Flow chat helper

* Document conversational flow chat APIs in translations

* Stringify conversational chat REPL output
2026-06-04 13:36:48 -07:00
Matt Aitchison
f3a15a4f07 feat(lock_store): make locking backend overridable (#6015)
* feat(lock_store): make locking backend overridable

Allow the centralised lock factory to use a pluggable backend instead of
the hardcoded Redis/file selection. Backends are resolved with precedence
override > CREWAI_LOCK_FACTORY env > built-in default:

- set_lock_backend()/reset_lock_backend() and a scoped lock_backend()
  context manager for programmatic overrides
- CREWAI_LOCK_FACTORY="module:callable" env import-path, resolved lazily
  and cached, with clear errors on malformed or non-callable specs
- LockBackend Protocol documenting the contract (raw name in, context
  manager out; backend owns its namespacing)

Default Redis/file behavior is unchanged when nothing is overridden.

* refactor(lock_store): use explicit body for LockBackend protocol method

Replace the no-op `...` body with `raise NotImplementedError` to satisfy
the CodeQL ineffectual-statement check while keeping the Protocol
structural-typing only.

* refactor(lock_store): drop scoped lock_backend context manager

Keep the backend overridable via set_lock_backend/reset_lock_backend and
the CREWAI_LOCK_FACTORY env path, but remove the scoped lock_backend()
context manager. It was speculative surface and the only thread-unsafe
piece (racy save/restore of the module global); nothing depends on it.

* refactor(lock_store): drop reset_lock_backend alias

reset_lock_backend() was just set_lock_backend(None); callers use that
directly. Clearing the override is documented on set_lock_backend.

* style(lock_store): apply ruff format

* refactor(lock_store): simplify overridable backend to a single setter

Reduce the override surface to just set_lock_backend(): lock() uses the
custom backend when one is set, otherwise the unchanged Redis/file default.

Drop the CREWAI_LOCK_FACTORY env import-path, the runtime_checkable
Protocol, the precedence resolver, and the getter — a custom backend is
now any callable(name, *, timeout) -> context manager, registered in
process.

* fix(lock_store): snapshot backend to avoid check-then-call race

Read the module-global backend once into a local before the None check
and the call, so a concurrent set_lock_backend(None) cannot make lock()
invoke None.

* docs(lock_store): clarify name handling for custom backends

The default namespaces the lock name; custom backends receive it
verbatim. Correct the lock() docstring which implied namespacing always
happens.

* docs(lock_store): note set_lock_backend is for one-time startup setup
2026-06-04 13:28:31 -05:00
Vini Brasil
75dad212a2 Split flow DSL monolith into focused decorator modules (#6040)
The Flow DSL lived in one 1033-line `dsl.py` that mixed every decorator
(`@start`/`@listen`/`@router`), the `human_feedback` decorator,
condition combinators, and FlowDefinition extraction helpers in a single
file.

Split it into a `dsl/` package where each decorator gets its own module
(`start.py` 68 lines, `listen.py` 55, `router.py` 164,
`human_feedback.py` 98) and the shared extraction/condition helpers stay
in `utils.py`. The public API is re-exported from `dsl/__init__.py`, so
import paths are unchanged.

This is simpler because each decorator is now read and changed in
isolation instead of scanning a 1000-line file to find one of them, and
router-specific annotation parsing no longer sits next to unrelated
start/listen logic.
2026-06-04 15:02:06 -03:00
alex-clawd
aed69237d4 docs: add NVIDIA Nemotron LLM guide (#6037)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-06-04 09:22:41 -03:00
Vini Brasil
051fa0c1cb Build FlowDefinition from Flow DSL metadata (#6017)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* Build FlowDefinition from Flow DSL metadata

Introduce `FlowDefinition`, a serializable model built from the Flow
DSL's runtime metadata. It becomes the structural contract for Flow
methods, triggers, routers, state, and configuration.

The visualization layer is the first consumer: `flow_structure` and
`build_flow_structure` now project from the definition instead of
re-introspecting the class. The runner still executes from live
registries, but the definition gives future runners a single static
contract to read.

This replaces AST source parsing for router return values, crew
references, and state schema with runtime metadata plus explicit
`@router(paths=...)` or `Literal`/`Enum` return hints. AST parsing was
fragile and could silently fail for dynamic or non-inspectable methods.

The refactor removes obsolete introspection and serializer code:

* Delete `flow_serializer.py`, `flow/utils.py`, and
  `visualization/schema.py`
* Move flow structure modeling into `flow_definition.py`
* Simplify visualization building around the static definition contract

* Format files
2026-06-03 18:02:56 -03:00
Gui Vieira
73d20fb0c3 Document monorepo deployments (#6018)
* Document monorepo deployments

* Add localized monorepo docs
2026-06-03 17:01:10 -03:00
Lucas Gomide
d09e3f4544 feat: flatten LiteLLM cache/reasoning usage sub-counts in _usage_to_dict (#6033)
LiteLLM returns provider usage as-is, nesting cache-read / cache-creation /
reasoning counts under provider-specific shapes (e.g.
prompt_tokens_details.cached_tokens, Anthropic-style cache_read_input_tokens).
Surface them as flat cached_prompt_tokens / reasoning_tokens /
cache_creation_tokens keys so the span pipeline can read them; prompt /
completion / total token counts are left untouched.
2026-06-03 15:13:30 -04:00
Lorenze Jay
1357491f0d Lorenze/feat/conversational flows (#5896)
* feat: add conversational flows documentation and chat session support

- Introduced a new guide for building multi-turn chat applications using , detailing session management and message handling.
- Added  class to facilitate chat interactions, including streaming support and event handling.
- Implemented  for class-level defaults and improved input normalization for conversational turns.
- Enhanced event listeners to manage flow events and tracing more effectively, including support for nested crew executions.
- Added tests for conversational flow helpers and kickoff parameters to ensure functionality and reliability.

* linted

* feat: enhance flow event tracing and session management

- Updated TraceCollectionListener to handle nested flows without re-claiming parent session batches.
- Ensured that method execution events are always emitted for tracing, regardless of flow event suppression.
- Improved finalization logic for flow trace batches to respect session deferral flags.
- Added tests to verify that method execution events are emitted correctly when flow events are suppressed and that deferred session finalization is respected in nested flows.

* updated docs

* feat: introduce experimental conversational flow framework

- Added a new module for conversational flow, including classes for managing conversation state, messages, and events.
- Implemented  and  for structured intent handling and routing.
- Enhanced the  class to support turn-oriented conversational applications with built-in routing and message handling.
- Updated  to include new classes in the public API.
- Added tests to validate the functionality of the new conversational flow features.

* handled docs

* feat(flow): enhance conversational flow handling and tracing

- Introduced support for deferred multi-turn tracing to maintain continuous event sequences.
- Updated  method to delegate to restored checkpoint flows, improving session management.
- Added tests to validate the new tracing behavior and ensure correct event handling in conversational flows.

* fix multimodal test

* better conversational

* adjusted prompt

* drop unused

* fix test

* refactor: rename  to  and update related documentation

This commit refactors the  class to  for clarity and consistency across the codebase. The documentation has been updated to reflect this change, ensuring that references to the new  class are accurate. Additionally, the alias for legacy imports is maintained for backward compatibility. The changes enhance the overall structure and readability of the conversational flow implementation.

* fix test

* adding experimetnal indicators

* fix test and reloaded cassettes

* cleanup ConversationalFlow class

* addressing double finalization and fixed tests

* improve on emphemeral tracing and adddressing comments
2026-06-03 11:53:16 -07:00
Lorenze Jay
ea88904d35 docs: update changelog and version for v1.14.7a1 (#6032) 2026-06-03 10:40:43 -07:00
Lorenze Jay
be3cf62b63 feat: bump versions to 1.14.7a1 (#6031) 2026-06-03 10:30:33 -07:00
Greyson LaLonde
68cdd44520 fix(cli): restore [project.scripts] in crewai package for uv tool install 2026-06-03 09:50:39 -07:00
Greyson LaLonde
7676b0937c fix(deps): bump authlib to >=1.6.12 to patch PYSEC-2026-188 2026-06-03 09:45:59 -07:00
Greyson LaLonde
ee707028db chore: remove testing pdf from root
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-06-02 17:53:26 -07:00
Lorenze Jay
770d1b284f Lorenze/fix/file input not working reliably (#6020)
* fix filesystem

* Refine commit message formatting

* fix for async kickoffs

* added suggestion
2026-06-02 17:14:51 -07:00
alex-clawd
b047c96756 Handle Snowflake Claude stringified tool calls (#6008)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* Handle Snowflake Claude stringified tool calls

* Fix Snowflake tool id type narrowing

* Extract Snowflake tool result text in summaries

* Bump PyJWT for vulnerability scan

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2026-06-02 19:37:18 -03:00
Greyson LaLonde
d37af0d404 perf(knowledge): lazy-load docling imports to speed up crewai import 2026-06-02 15:16:48 -07:00
Greyson LaLonde
c81b4fe11e fix(deps): bump pyjwt to >=2.13.0 to patch CVEs 2026-06-02 10:01:53 -07:00
Lorenze Jay
a9cb7867bb Add crew trained agents file support (#6012)
* Add crew trained agents file support

* Add crew trained agents file support
2026-06-02 09:38:34 -07:00
Jesse Miller
383ae66b55 docs: add Databricks integration guide (#6001)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* docs: add Databricks integration guide to enterprise integrations

Add documentation for connecting CrewAI agents to Databricks via the
Databricks managed MCP servers. Highlights Genie, Databricks SQL, Unity
Catalog Functions, and Vector Search, each configured as a separate MCP
connection, and covers OAuth/PAT setup. Includes ko, pt-BR, and ar
translations and registers the page in all docs.json navigation blocks.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix: use locale-specific slugs for Databricks nav entries

Add databricks integration entries to pt-BR, ko, and ar nav blocks
using locale-specific prefixes instead of only having en/ entries.

Co-authored-by: Luzk <2128595+Luzk@users.noreply.github.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Iris <iris@crewai.com>
Co-authored-by: Luzk <2128595+Luzk@users.noreply.github.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
2026-06-02 09:43:05 -04:00
alex-clawd
774fd871a8 Fix Snowflake Claude incomplete tool result histories (#6006)
* Fix Snowflake Claude incomplete tool result histories

* Filter Snowflake Claude preserved tool results
2026-06-02 09:11:59 -03:00
alex-clawd
4a0769d97c Add native Snowflake Cortex LLM provider (#6005) 2026-06-02 08:10:13 -03:00
Greyson LaLonde
fee5b3e395 fix(devtools): point template bumper at lib/cli templates dir 2026-06-02 02:02:12 -07:00
devin-ai-integration[bot]
3010f1286f chore: widen click dependency constraint to allow 8.2+
Addresses #6002
2026-06-02 00:06:25 -07:00
Greyson LaLonde
e53a676c04 fix(flow): re-arm multi-source or_ listeners across router-driven cycles
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
The previous discard-after-body approach cleared the gate mid-wave, so
a slow parallel @start finishing after the listener body could re-fire
the same multi-source or_ listener. Re-arm only when a router emits a
signal that matches the listener's condition; parallel @start paths
never reach that branch and the race gate keeps protecting them.

Closes #5972
2026-06-01 15:24:58 -07:00
Vini Brasil
1aba9fe415 Split flow.py into DSL, definition, and runtime (#5997)
This commit separates the monolithic `flow.py` into three modules, each
with one job:

- `dsl.py` - the Python DSL for flows (@start/@listen/@router, or_/and_)
- `flow_definition.py` - the structural model extracted from the DSL
- `runtime.py` - the execution engine and state for flows

This phase moves code only and should not have any breaking changes.
2026-06-01 18:37:10 -03:00
Greyson LaLonde
4dafb05735 chore(deps): bump uv to >=0.11.15 and ignore unfixable chromadb CVE
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
uv 0.11.7 -> 0.11.17 patches GHSA-4gg8-gxpx-9rph. chromadb has no
patched release for GHSA-f4j7-r4q5-qw2c (server-only pre-auth RCE,
not reachable in our embedded use); ignore until upstream ships a fix.
2026-06-01 00:10:19 -07:00
Jesse Miller
5cdc420c50 docs: add Snowflake integration guide (#5977)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* docs: add Snowflake integration guide to enterprise integrations

Add documentation for connecting CrewAI agents to Snowflake via the
Snowflake-managed MCP server. Highlights Cortex Analyst, Cortex Search,
and SQL execution, and covers OAuth/PAT setup. Registers the page in
all docs.json navigation blocks.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: add Snowflake integration page for ko, ar, pt-BR

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Iris Clawd <iris@crewai.com>
2026-05-29 15:03:55 -04:00
Greyson LaLonde
fca21b155c docs: update changelog and version for v1.14.6
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-28 10:03:50 -07:00
Greyson LaLonde
0486b85aa3 feat: bump versions to 1.14.6 2026-05-28 09:47:19 -07:00
Greyson LaLonde
ed91100a0f refactor(skills): move Skills Repository to experimental + CREWAI_EXPERIMENTAL gate
Moves the registry/cache pieces of PR #5867 under crewai.experimental.skills
and the CLI commands under `crewai experimental skill`. The stable local-file
skills feature (loader, parser, validation, models) stays in crewai.skills.

Both entry points now require CREWAI_EXPERIMENTAL=1:
- resolve_registry_ref() calls require_experimental_skills() before resolving
- The `crewai experimental` CLI group raises UsageError when the flag is unset

SkillDownloadStarted/CompletedEvent move out of crewai.events.types.skill_events
into crewai.experimental.skills.events.

* refactor(skills): move 'version' off SkillFrontmatter into metadata

The skill version is now stored as `metadata.version` rather than a
top-level field on `SkillFrontmatter`. A `before` validator lifts any
top-level YAML `version:` into `metadata['version']` so existing SKILL.md
files keep parsing.
2026-05-28 09:38:10 -07:00
Lucas Gomide
2148c7ed77 docs: add ACP (Beta) docs navigation block to Agent Control Plane pages (#5961)
- Adds an <Info> "ACP (Beta) Docs Navigation" block at the top of every
  Agent Control Plane page so readers can jump between Overview,
  Monitoring, and Rules without scrolling to the bottom-of-page Related
  cards.
2026-05-28 09:56:37 -04:00
iris-clawd
8890e0d645 docs: remove consensual process references from processes page (#5959)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
The consensual process was never implemented and is not planned.
Removes all mentions across en, ar, ko, and pt-BR locales.

Co-authored-by: Lorenze Jay <lorenzejay@users.noreply.github.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-05-27 18:01:30 -07:00
Greyson LaLonde
4a6a072fc8 docs: update changelog and version for v1.14.6a2 2026-05-27 16:49:36 -07:00
Greyson LaLonde
d52106b3c7 feat: bump versions to 1.14.6a2 2026-05-27 16:42:40 -07:00
Greyson LaLonde
4b190ae6b4 docs: restructure checkpointing page 2026-05-27 14:51:42 -07:00
Lorenze Jay
2e36f06732 feat: enhance StdioTransport to prevent environment variable leakage (#5506)
* feat: enhance StdioTransport to prevent environment variable leakage

- Replaced os.environ.copy() with get_default_environment() to ensure only allowed environment variables are passed to the MCP server.
- Added tests to verify that ambient environment variables do not leak and that user-supplied environment variables can override defaults.

* feat: add environment variable filtering hook to StdioTransport

- Introduced an optional `_env_filter_hook` to allow extensions to modify the environment variables passed to MCP servers, enabling features like credential stripping.
- Updated tests to ensure the filtering hook is applied correctly after merging user-supplied and default environment variables.
2026-05-27 13:38:25 -07:00
Lorenze Jay
a1033e4bfe Fix structured output leaks in tool-calling loops (#5897)
* Fix structured output leaks in tool-calling loops

* addressing comments

* drop scripts

* Update Gemini agent tests to include structured output with thoughts and bump model version to 2.5-flash

* merge

* Update Anthropic test cases to use new model and tool structure

- Changed the model from "claude-3-5-haiku-20241022" to "claude-sonnet-4-6" in the test setup.
- Updated the request and response formats in the YAML test cassette to reflect the new tool structure and improved content formatting.
- Adjusted the expected response body to match the new output format from the assistant, including changes in tool usage and response details.
- Increased rate limit values in the response headers for better testing scenarios.

* adjusted bedrock cassettes

* adjusting cassettes for bedrock

* fix test

* Update VCR configuration to use 'host' instead of 'bedrock_host' for request matching
2026-05-27 13:20:53 -07:00
iris-clawd
90a37c94c1 docs: remove Skills Repository entry from changelog (#5953)
* docs: remove Skills Repository entry from changelog

* docs: also remove Skills Repository entry from translated changelogs
2026-05-27 13:15:55 -07:00
Greyson LaLonde
c5ea415cda chore(crewai-tools): drop self-explanatory comments
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-26 16:25:07 -07:00
Lucas Gomide
1bac7d3afb document one-time admin package install step (#5941)
* docs: document one-time admin package install step

The previous revision described a manual "install in Salesforce first,
then connect from AMP" flow that nobody actually follows, and linked to
a private repo customers can't access.

* docs: point Integrations link at crewai_plus/unified_tools
2026-05-26 19:06:51 -04:00
Greyson LaLonde
3a52919a35 chore(devtools): drop self-explanatory comments 2026-05-26 15:50:44 -07:00
Greyson LaLonde
07569f04ee chore(crewai-files): drop self-explanatory comments 2026-05-26 15:01:22 -07:00
Lucas Gomide
952c84c195 Add Agent Control Plane docs (#5939)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* docs: split Agent Control Plane into Overview/Monitoring/Rules and localize

Mirror the secrets-manager folder convention for ACP: one folder per
locale with overview, monitoring, and rules pages. Replaces the two
flat agent-control-plane.mdx / agent-control-plane-rules.mdx files
with a 3-page layout, adds full translations for pt-BR, ko, and ar,
and rewires docs.json to register the new paths under each locale's
Manage group across the same 4 versions where ACP already lived.

* docs: flag Agent Control Plane as Beta in overview pages

Add a Beta callout right after the lead screenshot on the ACP
overview page across en, pt-BR, ko, and ar, matching the convention
used by Secrets Manager.
2026-05-26 14:42:27 -04:00
Greyson LaLonde
840ba89900 chore(crewai-core): drop self-explanatory comments 2026-05-26 10:33:18 -07:00
Greyson LaLonde
fd10c64148 chore(crewai): drop self-explanatory comments 2026-05-26 10:23:33 -07:00
Lorenze Jay
77a61274dc feat(planning): enhance planning configuration and observation handling (#5913)
* feat(planning): enhance planning configuration and observation handling

- Introduced  attribute in  to control LLM calls after each step.
- Updated  to set default  to 1 when planning is enabled without explicit config.
- Modified  to support heuristic observations when LLM calls are disabled.
- Adjusted  to respect  and  settings for step observations.
- Added tests to verify behavior of new configurations and ensure correct observation handling across different reasoning efforts.

* fix(agent_executor): update handling of failed steps in low effort mode

- Adjusted logic to ensure that failed steps are recorded without marking them as completed when using low reasoning effort.

- Introduced feedback for failed steps, allowing the process to continue while tracking failures.
- Added a test to verify that failed steps are correctly marked without triggering a replan.

- And linted

* linted
2026-05-26 09:10:43 -07:00
Vini Brasil
32f5e74449 Skip lock acquisition in CrewTrainingHandler.load when file is missing (#5935)
Every agent kickoff calls _use_trained_data, which calls
CrewTrainingHandler(...).load(). Since #4827 wrapped load() in store_lock,
that means every kickoff acquires the cross-process (Redis-backed when
REDIS_URL is set) lock even on deployments that never train and have no
trained-agents file on disk.

Move the missing/empty-file short-circuit above store_lock so the lock is
only acquired when there is actually a file to read. save() and the real
read remain locked.
2026-05-26 12:52:31 -03:00
Greyson LaLonde
bad64b1ee6 chore(cli): drop self-explanatory comments
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-26 01:05:25 -07:00
Greyson LaLonde
867df0f633 fix(checkpoint): drop unroundtrippable callbacks and adapter state
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
- callable_to_string returns None for lambdas/closures instead of an
  unresolvable dotted path; Crew filters Nones out of restored callback
  lists.
- EventNode.event serializer honors info.mode so mode='json' calls cascade
  properly into nested event payloads.
- RagTool.adapter serializes to None (post-validator rebuilds from
  config); concrete adapters hold runtime state that can't be round-tripped.
2026-05-25 19:24:02 -07:00
Greyson LaLonde
c3e2001d52 fix(checkpoint): serialize type[BaseModel] fields as JSON schema
Some checks failed
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Subclass redeclarations of args_schema/response_format dropped the
parent's Annotated PlainSerializer, causing PydanticSerializationError
on model_dump(mode='json'). Replace with @field_serializer decorators
backed by a shared serialize_model_class helper:

- BaseTool: covers RecallMemoryTool, RememberTool, AskQuestionTool,
  DelegateWorkTool, AddImageTool, ReadFileTool
- BaseLLM (check_fields=False): covers LLM, Anthropic, OpenAI, Gemini,
  Bedrock
- LiteAgent.response_format
- A2AConfig / A2AClientConfig response_model
2026-05-23 03:50:24 +08:00
Greyson LaLonde
306f5989b4 fix(checkpoint): avoid orphan task_started on resume scope restore
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Move scope restoration from Crew-level global push to a per-task push
inside Task via resume_task_scope() in event_context. Fixes orphan
task_started warning, hierarchical resume (manager_agent now eligible
for _resuming), and parallel async resume (each contextvars copy owns
its own scope). Tests added.
2026-05-23 01:20:15 +08:00
Greyson LaLonde
4990041ef7 chore(deps): force starlette>=1.0.1 for PYSEC-2026-161
starlette <1.0.1 has PYSEC-2026-161 (missing Host header validation
poisons request.url.path, bypassing path-based auth). Pulled in as a
transitive of fastapi. Override-dependencies forces the patched
version; lock regenerated against starlette 1.0.1.
2026-05-22 23:33:08 +08:00
Greyson LaLonde
88e95befe7 fix(experimental): allow AgentExecutor restore from checkpoint
llm and prompt were declared required with exclude=True, making the
model un-restorable from its own serialized output. Mirror the
CrewAgentExecutor pattern: make them nullable with default None, keep
exclude=True, and re-attach llm on the resume path alongside the other
re-attached fields. Guard the two prompt-deref sites so the runtime
invariant survives the looser type.
2026-05-22 23:24:12 +08:00
Matt Aitchison
179c20b352 ci: pin third-party actions to commit SHAs (#5869)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* ci: pin third-party actions to commit SHAs

Pin third-party GitHub Actions in workflow files to immutable 40-char
commit SHAs per the org security policy. Mutable refs like @v4 can be
silently re-pointed by a compromised upstream; SHAs cannot. Trailing
version comments let Dependabot/Renovate continue to manage updates.

Related to [COR-51](https://linear.app/crewai/issue/COR-51).

* ci: disable persist-credentials in pip-audit checkout

Address CodeRabbit feedback on PR #5869: the pip-audit workflow is
read-only and never needs an authenticated git context, so opt out of
persisting the GITHUB_TOKEN in the local git config per the
actions/checkout security guidance.
2026-05-21 18:08:34 -05:00
Thiago Moretto
c3ef622ec6 feat(tools): declare env_vars on DatabricksQueryTool (#5892)
* feat(tools): declare env_vars on DatabricksQueryTool

Add EnvVar import and env_vars field to DatabricksQueryTool so the host
UI knows which environment variables the tool requires. Both auth paths
(DATABRICKS_HOST+TOKEN or DATABRICKS_CONFIG_PROFILE) are marked
required=False with descriptions explaining the alternative.

* chore: update tool specifications

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-05-21 16:20:58 -03:00
Heitor Carvalho
6d712a3686 docs: migrate Secrets Manager / Workload Identity from replicated-config (#5874) 2026-05-21 14:23:42 -03:00
Thiago Moretto
56b6594669 fix(tools): correct mongdb typo to pymongo in package_dependencies (#5891)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* fix(tools): correct mongdb typo to pymongo in package_dependencies

The `package_dependencies` field in `MongoDBVectorSearchTool` referenced
the non-existent package `mongdb` instead of the actual PyPI package
`pymongo`, which is the driver imported and used throughout the file.

* chore: update tool specifications

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-05-21 10:57:17 -04:00
Greyson LaLonde
d3e20900e8 docs: update changelog and version for v1.14.6a1 2026-05-21 21:27:13 +08:00
Greyson LaLonde
81c21e3166 feat: bump versions to 1.14.6a1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-21 15:09:48 +08:00
Greyson LaLonde
b4b285764c fix: harden RuntimeState serialization across entity fields
Adds missing serializers, discriminators, and exclude markers on entity
fields that previously crashed model_dump_json or restored ambiguously:

- Flow.persistence: add _serialize_persistence; drop | Any escape hatch
- Flow.input_provider: SerializableInstance dotted-path round-trip
- BaseAgent.agent_executor: add _serialize_executor_ref
- BaseAgent.tools_handler / cache_handler: exclude=True
- Memory / MemoryScope / MemorySlice: memory_kind Literal discriminator
- Knowledge.storage / .embedder: exclude live client, serialize spec
- BaseKnowledgeSource subclasses: source_type Literal + dict-resolver
- BaseKnowledgeSource.storage / chunk_embeddings: exclude=True
- input_provider: enforce InputProvider protocol via dedicated
  validator/serializer; reject non-class dotted paths in
  _dotted_path_to_instance
- MemoryScope/MemorySlice: allow restore without live Memory; expose
  bind() to reattach the dependency post-restore
- Knowledge.embedder: add BeforeValidator that resolves provider_class
  dotted paths back to a BaseEmbeddingsProvider subclass
2026-05-21 14:53:40 +08:00
alex-clawd
418afd29e7 feat: Skills Repository — registry, cache, CLI, and SDK integration (#5867)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* feat: add Skills Repository — registry, cache, CLI, and SDK integration

Adds a Skills Repository feature allowing users to publish, install,
and use skills from the CrewAI registry with @org/skill-name refs.

## What's New

### SDK (lib/crewai/)
- SkillFrontmatter: added optional 'version' field (backward compatible)
- SkillCacheManager: manages ~/.crewai/skills/{org}/{name}/ with
  .crewai_meta.json tracking, path-traversal-safe tar extraction
- SkillRegistry: parse @org/skill-name refs, local-first resolution
  (./skills/ > cache > download), interactive prompt on first use,
  CI-mode guard (CREWAI_NONINTERACTIVE/CI env vars)
- Agent.skills and Crew.skills widened to accept str refs (@org/name)
- set_skills() resolves registry refs with org-prefixed dedup keys
- New events: SkillDownloadStartedEvent, SkillDownloadCompletedEvent

### CLI (lib/cli/)
- crewai skill create <name> — context-aware (project vs standalone)
- crewai skill install @org/name — downloads to ./skills/ or cache
- crewai skill publish — ZIP + upload to org registry
- crewai skill list — show installed skills

### PlusAPI (lib/crewai-core/)
- Added SKILLS_RESOURCE, get_skill(), publish_skill(), list_skills()

### Scaffolding
- crew and flow templates now include skills/ directory

### Tests
- 91 SDK skill tests + 15 CLI skill tests, all passing

* fix: address all CI failures and CodeRabbit review comments

Lint:
- Remove unused imports (click, pytest, json)
- Replace try-except-pass with logging (S110)
- Fix unprotected zipfile.extractall (S202)

Security:
- Path traversal: startswith → is_relative_to for tar extraction
- Add path traversal protection to ZIP extraction via _safe_extract_zip
- Both cache.py and CLI main.py hardened

Type checker:
- Fix import path: crewai.events.event_bus (not crewai_event_bus)
- Remove unused type: ignore comments
- Fix type mismatches in set_skills() variable types

Code quality:
- Fix f-string interpolation in SkillNotCachedError
- Use ValidationError instead of Exception in test

* style: ruff format + autofix remaining lint errors

* refactor: reuse SDK parser and SkillCacheManager in CLI

- _parse_frontmatter() now delegates to crewai.skills.parser.parse_frontmatter
  when available, with a minimal fallback for CLI-only installs
- install() global cache path now reuses SkillCacheManager.store() instead
  of duplicating metadata writing logic

* refactor: add _print_current_organization to SkillCommand (matches ToolCommand pattern)

* fix: write .crewai_meta.json in fallback install path

CodeRabbit caught that the ImportError fallback in install() didn't write
cache metadata, making skills invisible to 'crewai skill list'.

* fix: tighten @org/name ref validation to prevent path traversal

Reject refs with multiple slashes (@org/a/b), dot segments (@../skill),
or leading dots in org/name. Applied to both CLI install() and SDK
parse_registry_ref() so the contract is enforced consistently.

* fix: update test assertions to match tightened error messages

* fix: align OSS client with AMP API contract

- download_skill(): fetch download_url (presigned URL) instead of
  expecting inline base64. Falls back to 'file' field for compat.
- Read 'latest_version' field, fall back to 'version'
- Same fixes applied to CLI install() command

* fix: publish as tar.gz (matches AMP content_type validation) + add zip fallback to SDK cache

CLI publish:
- _build_skill_zip → _build_skill_tarball (tar.gz format)
- Content type: application/x-gzip (matches SkillVersion validation)

SDK cache:
- store() now tries tar.gz first, falls back to zip extraction
- Added _safe_extract_zip for path-traversal-safe zip handling
- Both formats work for download/install regardless of server format

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2026-05-20 14:38:25 -03:00
Greyson LaLonde
7cc1a7bb41 fix(deps): bump pip and paramiko to drop pip-audit ignores
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
OSV no longer flags pip 26.1.1 (GHSA-58qw-9mgm-455v) or paramiko
5.0.0 (GHSA-r374-rxx8-8654), so override both to those minimums
and remove the corresponding --ignore-vuln entries. paramiko is
pulled in transitively via composio-core.
2026-05-20 22:33:43 +08:00
Greyson LaLonde
09ffe87fbb ci: ignore pip-audit findings without published fixes
Adds joblib, markdown, nltk, onnx, pyjwt, torch and transformers
advisories that have no fixed version available (or are disputed)
to the pip-audit ignore list. Rationale recorded next to each ID.
2026-05-20 21:40:30 +08:00
Greyson LaLonde
14af56b74d ci: pin third-party actions to commit SHAs
Replaces version tags (e.g. astral-sh/setup-uv@v6, slackapi/slack-github-action@v2.1.0)
with full commit SHAs across every workflow. Mitigates supply-chain risk from
mutable tags.
2026-05-20 19:01:53 +08:00
Greyson LaLonde
35f693cf68 chore: tighten typing across plus_api client
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Adds typed containers for wire payloads, literal aliases for HTTP method
and log type, and Ffnal markers on resource constants. Updates
upstream returns in project_utils.py and deploy/main.py to match
the new contracts.
2026-05-20 01:43:48 +08:00
Greyson LaLonde
da15554d81 feat: generate categorized release notes for enterprise 2026-05-20 00:24:26 +08:00
Greyson LaLonde
284533464f fix: bump idna to 3.15 to address GHSA-65pc-fj4g-8rjx
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-05-19 23:38:34 +08:00
Tiago Freire
024e230b2c docs: remove {" "} JSX expressions breaking <Steps> render (#5857)
## Overview

Prettier-inserted bare `{" "}` lines between sibling `<Step>` elements caused Mintlify's `<Steps>` to crash with "Cannot read properties of undefined (reading 'stepNumber')", leaving the page body blank.

### Affected pages (en/ar/ko/pt-BR):
- enterprise/guides/enable-crew-studio
- learn/llm-selection-guide
2026-05-19 10:44:53 -04:00
Greyson LaLonde
a4c90b6912 docs: update changelog and version for v1.14.5
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-19 03:19:40 +08:00
Greyson LaLonde
c50da7a6f2 feat: bump versions to 1.14.5 2026-05-19 03:11:26 +08:00
Irfaan Mansoori
e8aa870f90 fix: memory leak in git.py by using cached_property
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-05-18 21:55:57 +08:00
Greyson LaLonde
14cd81eec6 docs: update changelog and version for v1.14.5a7 2026-05-18 21:13:34 +08:00
Greyson LaLonde
a6225da326 feat: bump versions to 1.14.5a7 2026-05-18 21:08:46 +08:00
Greyson LaLonde
259d334e38 chore(devtools): skip pinning crewai-files in file-processing extra 2026-05-18 21:00:37 +08:00
Greyson LaLonde
42aa8a777c chore: deprecate function_calling_llm field 2026-05-18 20:49:11 +08:00
Heitor Carvalho
a95d26763f docs: update changelog and version for v1.14.5a6 (#5828)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-15 17:05:04 -03:00
Heitor Carvalho
65ec783aae feat: bump versions to 1.14.5a6 (#5827) 2026-05-15 16:51:59 -03:00
Greyson LaLonde
eefe0e42ac fix: surface streamed tool calls when available_functions is absent 2026-05-16 02:46:35 +08:00
Greyson LaLonde
75bb882911 fix(deps): bump langsmith to >=0.8.0 for GHSA-3644-q5cj-c5c7
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-05-15 21:32:52 +08:00
iris-clawd
c36827b45b fix(docs/pt-BR): replace untranslated code block placeholders (#5781)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix(docs/pt-BR): replace untranslated code block placeholders

Replace all `# (O código não é traduzido)` and `# código não traduzido`
placeholder comments in the PT-BR docs with the actual code from the
English source files.

Files fixed:
- docs/pt-BR/concepts/flows.mdx (~15 placeholders → real code)
- docs/pt-BR/guides/flows/mastering-flow-state.mdx (~17 placeholders → real code)

Code itself is kept in English per i18n conventions. Inline # comments
within code blocks have been translated to Portuguese.

* fix(docs/pt-BR): address CodeRabbit review comments

- flows.mdx: add missing load_dotenv() call after imports
- mastering-flow-state.mdx: fix PersistentCounterFlow second-run example
  to pass inputs={"id": flow1.state.id} to kickoff(), matching the
  documented resume pattern; update comment accordingly
2026-05-13 12:23:18 -03:00
Lorenze Jay
264da8245a Lorenze/imp/prompt layering (#5774)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* improving prompt structure especially for prompt caching

* addressing comments
2026-05-12 12:39:12 -07:00
Mani
f2960ccaaf Added docs for TavilyGetResearch (#5707)
* Add Tavily Research and get Research

- Added tavily research with docs to crew AI

- Added tavily get research with docs to crew AI

* Update `tavily-python` installation instructions and adjust version constraints

- Changed installation command from `pip install` to `uv add` for `tavily-python` in multiple documentation files.
- Updated version constraint for `tavily-python` in `pyproject.toml` from `>=0.7.14` to `~=0.7.14`.
- Modified the `exclude-newer` date in `uv.lock` to `2026-04-23T07:00:00Z`.

* Add Tavily Research Tool documentation in multiple languages

- Introduced `TavilyResearchTool` documentation in English, Arabic, Korean, and Portuguese.
- Updated `docs.json` to include paths for the new documentation files.
- The `TavilyResearchTool` allows CrewAI agents to perform multi-step research tasks and generate cited reports using the Tavily Research API.

* Fix Tavily research CI failures

* added getResearchTool docs

- Added docs for getResearchTool

---------

Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Evan Rimer <evan.rimer@tavily.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-05-12 12:25:45 -07:00
Greyson LaLonde
bb0bde9518 docs: update changelog and version for v1.14.5a5 2026-05-13 03:00:58 +08:00
Greyson LaLonde
2034f2140a feat: bump versions to 1.14.5a5 2026-05-13 02:54:13 +08:00
iris-clawd
3322634625 feat: deprecate CrewAgentExecutor, default Crew agents to AgentExecutor (#5745)
* feat: deprecate CrewAgentExecutor, default Crew agents to AgentExecutor

* regen cassettes

* fix tests

* addressing pr comments

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-05-12 11:22:13 -07:00
Tiago Freire
3d95afca41 Docs: inputs.idrestoreFromStateId migration guide (#5779)
## Summary

- Add a new docs page at `docs/en/guides/flows/inputs-id-deprecation.mdx` that explains the deprecation of `inputs.id` as a `@persist` hydration mechanism and walks users through migrating to `restoreFromStateId` (available in CrewAI **v1.14.5 and later**).
- Wire the page into `docs.json` next to `mastering-flow-state` in all 13 version blocks across all 4 languages (52 nav inserts).
- Add translations for `ar`, `ko`, `pt-BR`
2026-05-12 13:10:32 -04:00
iris-clawd
b2cd133f10 fix(docs): restore missing code block in pt-BR first-flow guide (#5780)
* fix(docs): restore missing code block in pt-BR first-flow guide

The pt-BR translation of the 'Build Your First Flow' guide had a
placeholder comment '# [CÓDIGO NÃO TRADUZIDO, MANTER COMO ESTÁ]'
instead of the actual Python code in Step 5. This restores the full
main.py code block from the English source, matching the original
since code should not be translated.

* Translate code comments to pt-BR in first-flow guide

Code comments in the tutorial should be in Portuguese for the pt-BR
audience, since they are part of the guide's educational content.
2026-05-12 13:23:00 -03:00
Greyson LaLonde
ba523f46c0 fix(devtools): include all workspace packages in bump pin rewrites 2026-05-12 22:49:44 +08:00
Greyson LaLonde
63a9e7eb5e fix(deps): patch urllib3 GHSA-qccp-gfcp-xxvc, GHSA-mf9v-mfxr-j63j
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-12 00:48:42 +08:00
Greyson LaLonde
5d757cb626 fix(flow): log HITL pre-review and distillation failures, add learn_strict 2026-05-12 00:26:31 +08:00
Greyson LaLonde
b0d4dd256d fix(deps): patch gitpython, langchain-core; ignore unpatched paramiko CVE 2026-05-11 22:31:56 +08:00
iris-clawd
e4a91cdc0c docs: add OSS upgrade & crew-to-flow migration guide (#5744)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* docs: add OSS upgrade & crew-to-flow migration guide

* docs: add upgrading-crewai guide and installation note

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* docs: consolidate upgrade & migration guide into single page

Merge the broader root-level upgrade-crewai.mdx into the canonical
en/guides/migration/upgrading-crewai.mdx so there is one comprehensive
upgrade & migration page covering: project venv vs global CLI, why
crewai install alone won't bump versions, breaking changes, and the
Crew-to-Flow migration. Removes the orphaned root-level file (which
was not referenced in docs.json nav).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* docs: add pt-BR, ar, ko translations of upgrade/migration guide

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* docs: reduce upgrade guide scope to package upgrade + breaking changes only

* docs: soften intro tone — releases ship features, not breaking changes

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix: resolve CodeRabbit review comments

- Add space between Arabic conjunction and `uv.lock` code span (ar)
- Add explicit {#memory-embedder-config} anchors to localized headings
  so in-page links resolve correctly (ar, ko, pt-BR, en)

Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-05-08 17:49:39 -04:00
Mislav Ivanda
b9e71b322f feat: improve Daytona sandbox tools
Signed-off-by: Mislav Ivanda <mislavivanda454@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-05-09 05:29:30 +08:00
Greyson LaLonde
f495bda016 fix(devtools): refresh all published workspace packages on uv lock/sync 2026-05-09 03:50:51 +08:00
Greyson LaLonde
622c0b610b docs: update changelog and version for v1.14.5a4 2026-05-09 03:14:29 +08:00
Greyson LaLonde
a09c4de2fd feat: bump versions to 1.14.5a4 2026-05-09 03:08:22 +08:00
Greyson LaLonde
cf2fb4503d chore(deps): bump mem0ai to >=2.0.0 to address GHSA-xqxw-r767-67m7
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-05-09 00:17:48 +08:00
Greyson LaLonde
c67f6f63dc fix(ci): make nightly publish idempotent and serialized
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-08 02:20:31 +08:00
Greyson LaLonde
964066e86b fix(ci): stamp and pin all workspace packages in nightly publish
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-05-08 02:07:01 +08:00
Cole Goeppinger
74a1ff8db5 feat: update llm listings
Add the latest Anthropic and OpenAI LLMs to the CLI
2026-05-08 01:19:47 +08:00
Greyson LaLonde
d6f7e7d5f8 chore(deps): use 3-day exclude-newer window
* chore(deps): use 3-day exclude-newer window

Aligns the root workspace with the per-package pyprojects, which
already use `exclude-newer = "3 days"`. The fixed 2026-04-27 cutoff
blocks legitimate dependency bumps (e.g. daytona ~=0.171 in #5740)
without adding meaningful protection — the relative window still
includes the security patches that motivated the original pin.

* fix(deps): bump gitpython and python-multipart for new advisories

- gitpython >=3.1.49 for GHSA-v87r-6q3f-2j67 (newline injection in
  config_writer().set_value() enables RCE via core.hooksPath).
- python-multipart >=0.0.27 for GHSA-pp6c-gr5w-3c5g (DoS via
  unbounded multipart part headers).

Both surfaced via pip-audit on this branch.
2026-05-08 00:11:05 +08:00
Greyson LaLonde
d165bcb65f fix(deps): move textual to crewai-cli and add certifi
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-07 04:40:08 +08:00
Greyson LaLonde
fa6287327d docs: update changelog and version for v1.14.5a3 2026-05-07 01:58:27 +08:00
Greyson LaLonde
e961a005cb feat: bump versions to 1.14.5a3
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-05-07 01:44:05 +08:00
Greyson LaLonde
93e786d263 refactor: extract CLI into standalone crewai-cli package 2026-05-06 20:46:46 +08:00
iris-clawd
ec8a522c2c fix: correct status endpoint path from /{kickoff_id}/status to /status/{kickoff_id}
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-05-05 07:29:49 +08:00
Greyson LaLonde
e25f6538a8 fix(deps): bump gitpython to >=3.1.47 for GHSA-rpm5-65cw-6hj4
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-05-04 23:44:28 +08:00
Greyson LaLonde
470d4035db docs: update changelog and version for v1.14.5a2 2026-05-04 23:04:56 +08:00
Greyson LaLonde
57d1b338f7 feat: bump versions to 1.14.5a2 2026-05-04 22:58:06 +08:00
huang yutong
01df19b029 fix(a2a): always restore task.output_pydantic in finally block
In `_execute_task_with_a2a` and its async variant, the try body
sets `task.output_pydantic = None` before returning an A2A
response. The finally block then checks
`if task.output_pydantic is not None` before restoring the
original value — but since it was just set to None, the condition
is always False and the original value is never restored. This
permanently mutates the Task object.

Remove the guard so `output_pydantic` is unconditionally restored,
matching the unconditional restoration of `description` and
`response_model` in the same block.

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-05-04 22:41:04 +08:00
Rip&Tear
dca2c3160f chore: update security reporting instructions
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-05-04 22:31:35 +08:00
Greyson LaLonde
6494d68ffc fix(gemini): include thoughts_token_count in completion tokens 2026-05-04 21:03:38 +08:00
Greyson LaLonde
f579aa53ae fix: preserve task outputs across async batch flush 2026-05-04 20:24:24 +08:00
minasami-pr
a23e118b11 fix: forward kwargs to loader calls in CrewAIRagAdapter
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-05-04 19:52:24 +08:00
Greyson LaLonde
095f796922 fix: prevent result_as_answer from returning hook-block message as final answer 2026-05-04 19:42:07 +08:00
Zamuldinov Nikita
bfbdba426f fix: prevent result_as_answer from returning error as final answer
When a tool with result_as_answer=True raises an exception, the agent
was receiving result_as_answer=True and returning the error string as
the final answer. Now we set result_as_answer=False when an error event
is emitted, allowing the agent to reflect and retry.

Fixes crewAIInc/crewAI#5156

---------

Co-authored-by: NIK-TIGER-BILL <nik.tiger.bill@github.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-05-04 19:28:21 +08:00
Greyson LaLonde
a058a3b15b fix(task): use acall for output conversion in async paths 2026-05-04 18:42:12 +08:00
Greyson LaLonde
184c228ae9 fix: prevent shared LLM stop words mutation across agents
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-04 14:23:17 +08:00
Greyson LaLonde
c9100cb51d docs(devtools): document additional env vars
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-05-03 14:50:44 +08:00
Greyson LaLonde
17e82743f6 fix: handle BaseModel input in convert_to_model 2026-05-03 14:17:03 +08:00
Lorenze Jay
3403f3cba9 docs: update changelog and version for v1.14.5a1 (#5678)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-01 14:27:57 -07:00
Lorenze Jay
5db72250b2 feat: bump versions to 1.14.5a1 (#5677)
* feat: bump versions to 1.14.5a1

* chore: update tool specifications

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-05-01 14:21:50 -07:00
Greyson LaLonde
a071838e92 fix(devtools): cover missing crewai pin sites in release flow 2026-05-02 03:26:56 +08:00
Tiago Freire
cd2b9ee38a feat(flow): add restore_from_state_id kickoff parameter (#5674)
## Summary

- Reverts `b0e2fda` ("fix(flow): add execution_id separate from state.id", COR-48): removes `Flow.execution_id` and points `current_flow_id` / `current_flow_request_id` back at `flow_id` (i.e. `state.id`). The separate per-run tracking id was no longer the right abstraction once `restore_from_state_id` reshapes how `state.id` is assigned;

- Adds an optional `restore_from_state_id` kwarg to `Flow.kickoff` / `Flow.kickoff_async` that hydrates state from a previously-persisted flow's latest snapshot

- Reassigns `state.id` to a fresh value (or `inputs["id"]` if pinned) so the new run's `@persist` writes don't extend the source's history

- Existing `inputs["id"]` resume, `@persist`, and `from_checkpoint` paths are unchanged

## Problem
`@persist` only supports *resume* today: `kickoff(inputs={"id": <uuid>})` hydrates state and continues writing under the same `flow_uuid`. There's no way to **fork** — hydrate from a snapshot but persist under a separate key, leaving the source's history intact. This PR adds that.

| | `state.id` after kickoff | `@persist` writes land under |
|---|---|---|
| `inputs["id"]` (resume) | supplied id | supplied id (extends history) |
| `restore_from_state_id` (fork) | fresh id, or `inputs["id"]` if pinned | new id (source preserved) |

## Behavior

| `inputs.id` | `restore_from_state_id` | Effect |
|---|---|---|
| — | — | Fresh kickoff |
| set | — | Existing resume |
| — | UUID | Fork — new `state.id`, hydrated from source |
| set | UUID | Fork into a pinned `state.id`, hydrated from source |

- Source not found → silent fallback (mirrors existing resume)
- Both `from_checkpoint` and `restore_from_state_id` set → `ValueError`
- `restore_from_state_id=None` → byte-identical to current main

## Design
Fork hydration runs before the existing `inputs` block in `kickoff_async`. On a hit, it calls the same `_restore_state` primitive used by resume, then overwrites `state.id` with a fresh UUID (or `inputs["id"]`). A `fork_succeeded` flag gates the existing `inputs["id"]` path so we don't double-load. `_completed_methods` / `_is_execution_resuming` are intentionally untouched — skip-completed-methods remains the territory of `apply_checkpoint` and `from_pending`.

## Test plan
- [ ] `pytest tests/test_flow_persistence.py` — 5 new tests (four-row matrix, not-found fallback, default no-op, conflict raise) + 6 existing as regression
- [ ] `pytest tests/test_flow.py` — broader flow suite
- [ ] Manual end-to-end against an HITL `@persist` flow
2026-05-01 11:46:07 -04:00
Ishan Goswami
07c4a30f2e feat(crewai-tools): add highlights to ExaSearchTool, rename from EXASearchTool
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* feat(crewai-tools): add highlights to ExaSearchTool, rename from EXASearchTool

- Add a highlights init param so agents can get token-efficient excerpts instead of full pages
- Rename EXASearchTool to ExaSearchTool; keep EXASearchTool as a deprecated alias so existing imports keep working
- Update the docs and example to use highlights as the recommended option
- Add a small note that says Exa is the fastest and most accurate web search API
- Add tests for the new highlights param and the deprecation alias

* fix(crewai-tools): import order and module-level Exa for tests

- Reorder std-lib imports so ruff is happy with force-sort-within-sections.
- Import Exa at module level (with a fallback) so the existing test mocks resolve.
  The lazy install prompt still works if exa_py is missing.
- Allow content and summary to be a dict, matching highlights.
- Trim test file to the cases this PR introduces (highlights param and the
  EXASearchTool deprecation alias). Existing init-shape tests stay.

Co-Authored-By: ishan <ishan@exa.ai>

* chore(crewai-tools): drop self-explanatory comment on schema alias

Co-Authored-By: ishan <ishan@exa.ai>

* docs(crewai-tools): default highlights to True, drop summary from examples

Co-Authored-By: ishan <ishan@exa.ai>

* docs(crewai-tools): simplify highlights examples to highlights=True

Co-Authored-By: ishan <ishan@exa.ai>

* feat(crewai-tools): add x-exa-integration header for usage tracking

Co-Authored-By: ishan <ishan@exa.ai>

* docs(crewai-tools): add Exa MCP section and resources links

Co-Authored-By: ishan <ishan@exa.ai>

---------

Co-authored-by: ishan <ishan@exa.ai>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-05-01 21:25:23 +08:00
Lorenze Jay
b30fdbaa0e fix: ensure skills loading events for traces
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-05-01 12:08:25 +08:00
Greyson LaLonde
898f860916 docs: update changelog and version for v1.14.4
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-05-01 03:11:30 +08:00
Greyson LaLonde
2c0323c3fe feat: bump versions to 1.14.4 2026-05-01 02:57:37 +08:00
Greyson LaLonde
c580d428f0 chore(devtools): open PR for deployment test bump and wait for merge 2026-05-01 02:48:08 +08:00
Greyson LaLonde
70f391994e fix(converter): fall through when JSON regex match isn't valid JSON 2026-05-01 00:48:09 +08:00
Vini Brasil
864f0a8a91 Revert "feat(flow): support custom persistence key in @persist (#5649)" (#5668)
This reverts commit e2deac5575.
2026-04-30 12:04:57 -03:00
Greyson LaLonde
9f13235037 fix(llm): preserve tool_calls when response also contains text 2026-04-30 22:53:01 +08:00
Matt Aitchison
c7f01048b7 feat(azure): forward credential_scopes to Azure AI Inference client (#5661)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* feat(azure): forward credential_scopes to Azure AI Inference client

Adds a credential_scopes field to the native Azure AI Inference
provider and a matching AZURE_CREDENTIAL_SCOPES env var
(comma-separated). The value is forwarded to ChatCompletionsClient /
AsyncChatCompletionsClient when set, letting keyless / Entra-based
callers target a specific Azure AD audience (e.g.
https://cognitiveservices.azure.com/.default) without subclassing the
provider. Matches the upstream azure.ai.inference SDK kwarg of the
same name.

Lazy build re-reads the env var so an LLM constructed at module
import (before deployment env vars are set) still picks up scopes —
same pattern as the existing AZURE_API_KEY / AZURE_ENDPOINT lazy
reads. to_config_dict round-trips the field.

* refactor(azure): tighten credential_scopes env handling

Address review feedback:
- Move os.getenv into the helper so AZURE_CREDENTIAL_SCOPES appears once
- Match the surrounding api_key/endpoint `or` style in the validator
- Drop the list() defensive copy in to_config_dict — every other field
  in that method (and the base class's `stop`) is assigned by reference
2026-04-29 16:52:29 -05:00
Greyson LaLonde
14c3963d2c fix(instructor): forward base_url and api_key to instructor.from_provider 2026-04-30 03:00:39 +08:00
Greyson LaLonde
feb2e715a3 fix(mcp): warn and return empty when native MCP server returns no tools 2026-04-30 02:41:01 +08:00
Kunal Karmakar
e0b86750c2 feat(azure): add Responses API support for Azure OpenAI provider (#5201)
* Support azure openai responses

* Revert function supported condition

* Revert comment deletion

* Update support stop words

* Add cassette based tests

* Fix linting
2026-04-29 11:12:11 -07:00
Greyson LaLonde
2a40316521 fix(llm): use validated messages variable in non-streaming handlers 2026-04-30 00:56:56 +08:00
Lucas Gomide
e2deac5575 feat(flow): support custom persistence key in @persist (#5649)
* feat(flow): add optional key param to @persist decorator

Allows users to specify which state attribute to use as the
persistence key instead of always defaulting to state.id.

Usage: @persist(key='conversation_id')

Falls back to state.id when key is not provided (no breaking change).
Raises ValueError if the specified key is missing or falsy on state.

* docs(flow): document @persist key parameter for custom persistence keys

* fix(flow): use explicit None check for persist key to avoid empty-string fallback

---------

Co-authored-by: iris-clawd <iris-clawd@anthropic.com>
Co-authored-by: iris-clawd <iris@crewai.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-04-29 12:41:20 -04:00
Greyson LaLonde
e1b53f684a docs: update changelog and version for v1.14.4a1 2026-04-29 23:57:06 +08:00
Greyson LaLonde
4b49fc9ac6 feat: bump versions to 1.14.4a1 2026-04-29 23:50:30 +08:00
Greyson LaLonde
07667829e9 fix(cli): guard crew chat description helpers against LLM failures
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-04-29 10:30:24 +08:00
Lorenze Jay
0154d16fd8 docs: add E2B Sandbox Tools page (#5647)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Document the new E2BExecTool, E2BPythonTool, and E2BFileTool — agent
tools that run shell commands, Python, and filesystem ops inside
isolated E2B remote sandboxes. Adds the page under tools/ai-ml/ and
wires it into the navigation in docs.json.

Co-authored-by: iris-clawd <iris@crewai.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-28 11:47:12 -07:00
Greyson LaLonde
4c74dc0f86 fix(executor): reset messages and iterations between invocations
CrewAgentExecutor is reused across sequential tasks but invoke/ainvoke
only appended to self.messages and never reset self.iterations, so
task 2 inherited task 1's history and iteration count.
2026-04-29 02:10:17 +08:00
Lorenze Jay
13e0e9be6b docs: add Daytona sandbox tools documentation (#5643)
Adds docs for DaytonaExecTool, DaytonaPythonTool, and DaytonaFileTool
introduced in PR #5530. Covers installation, lifecycle modes, examples,
and full parameter reference. Registered in docs.json nav for all
languages and versions.

Co-authored-by: iris-clawd <iris@crewai.com>
2026-04-28 10:30:40 -07:00
dependabot[bot]
860a5d494d chore(deps): bump pip in the security-updates group across 1 directory (#5635)
Bumps the security-updates group with 1 update in the / directory: [pip](https://github.com/pypa/pip).


Updates `pip` from 26.0.1 to 26.1
- [Changelog](https://github.com/pypa/pip/blob/main/NEWS.rst)
- [Commits](https://github.com/pypa/pip/compare/26.0.1...26.1)

---
updated-dependencies:
- dependency-name: pip
  dependency-version: '26.1'
  dependency-type: indirect
  dependency-group: security-updates
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 10:39:04 -05:00
Matt Aitchison
cbb5c53557 Add Vertex AI workload identity setup guide (#5637)
* docs: add Vertex AI workload identity setup guide

Walks SaaS customers through configuring CrewAI AMP to authenticate to
Google Vertex AI via GCP Workload Identity Federation, eliminating the
need for long-lived service account keys.

* docs: restrict Vertex WI guide to v1.14.3+ navigation

The guide requires `crewai>=1.14.3`, so registering it under older
version snapshots is misleading. Keep the entry only in the v1.14.3
English nav.

* docs: clarify crewai-vertex SA name is an example
2026-04-28 10:15:54 -05:00
Greyson LaLonde
45497478c0 fix(cli): forward trained-agents file through replay and test 2026-04-28 22:46:41 +08:00
Greyson LaLonde
4e9331a2c8 fix(agent): honor custom trained-agents file at inference 2026-04-28 22:09:34 +08:00
Greyson LaLonde
a29977f4f6 fix(crew): bind task-only agents to crew so multimodal input_files reach the LLM
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-04-28 20:53:39 +08:00
Greyson LaLonde
7a0a8cf56f fix: serialize guardrail callables as null for JSON checkpointing 2026-04-28 14:57:49 +08:00
Edward Irby
6ae1d1951f docs: add You.com MCP tools for search, research, and content extraction (#5563)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* docs: add You.com MCP integration documentation for crewAI

Add documentation pages for integrating You.com's remote MCP server
with crewAI agents, covering web search, research, and content
extraction tools via the MCP protocol.

Pages added:
- Overview with DSL and MCPServerAdapter integration approaches
- you-search: web/news search with advanced filtering
- you-research: multi-source research with cited answers
- you-contents: full page content extraction
- Security considerations (prompt injection, API key management)

Co-authored-by: factory-droid[bot] <138933559+factory-droid-oss@users.noreply.github.com>

* docs: add You.com MCP search, research, and content extraction guides

Add two documentation pages for integrating You.com's remote MCP server
with crewAI agents:

- search-research/youai-search.mdx: you-search (web/news search)
  and you-research (synthesized cited answers) via DSL or MCPServerAdapter.
  Includes free tier support (100 queries/day, no API key).
- web-scraping/youai-contents.mdx: you-contents (full page content
  extraction) via MCPServerAdapter with schema patching helpers.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

* fix: add tool_filter to DSL search agent in youai-contents combo example

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

---------

Co-authored-by: factory-droid[bot] <138933559+factory-droid-oss@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-04-27 15:36:06 -07:00
Greyson LaLonde
ef40bc0bc8 fix(agent_executor): rename force_final_answer to avoid self-referential router
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-04-28 05:06:21 +08:00
Mani
07364cf46f Add Tavily Research and get Research (#5483)
* Add Tavily Research and get Research

- Added tavily research with docs to crew AI

- Added tavily get research with docs to crew AI

* Update `tavily-python` installation instructions and adjust version constraints

- Changed installation command from `pip install` to `uv add` for `tavily-python` in multiple documentation files.
- Updated version constraint for `tavily-python` in `pyproject.toml` from `>=0.7.14` to `~=0.7.14`.
- Modified the `exclude-newer` date in `uv.lock` to `2026-04-23T07:00:00Z`.

* Add Tavily Research Tool documentation in multiple languages

- Introduced `TavilyResearchTool` documentation in English, Arabic, Korean, and Portuguese.
- Updated `docs.json` to include paths for the new documentation files.
- The `TavilyResearchTool` allows CrewAI agents to perform multi-step research tasks and generate cited reports using the Tavily Research API.

* Fix Tavily research CI failures

---------

Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Evan Rimer <evan.rimer@tavily.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-04-27 13:51:56 -07:00
Lorenze Jay
1337e6de34 ci: skip generate-tool-specs job on fork PRs
GitHub doesn't expose repo secrets to pull_request events from forks, so
${{ secrets.CREWAI_TOOL_SPECS_APP_ID }} resolves to an empty string and
tibdex/github-app-token@v2 errors with "Input required and not supplied:
app_id". The job also tries to push commits to the PR branch, which it
can't do on a fork regardless. Skip it for cross-repo PRs and keep it
for same-repo PRs and manual dispatch.

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-04-28 04:41:20 +08:00
Greyson LaLonde
de0b2a4fe0 fix(deps): bump litellm for SSTI fix; ignore unfixable pip CVE 2026-04-28 04:34:17 +08:00
Greyson LaLonde
cb46a1c4ba docs: update changelog and version for v1.14.3
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-04-25 00:13:43 +08:00
Greyson LaLonde
d9046b98dd feat: bump versions to 1.14.3 2026-04-25 00:04:46 +08:00
Tiago Freire
b0e2fda105 fix(flow): add execution_id separate from state.id
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix(flow): add execution_id separate from state.id (COR-48)

  When a consumer passes `id` in `kickoff(inputs=...)`, that value
  overwrites the flow's state.id — which was also being used as the
  execution tracking identity for telemetry, tracing, and external
  correlation. Two kickoffs sharing the same consumer id ended up
  with the same tracking id, breaking any downstream system that
  joins on it.

  Introduces `Flow.execution_id`: a stable per-run identifier stored
  as a `PrivateAttr` on the `Flow` model, exposed via property +
  setter. It defaults to a fresh `uuid4` per instance, is never
  touched by `inputs["id"]`, and can be assigned by outer systems
  that already have an execution identity (e.g. a task id).

  Switches the `current_flow_id` / `current_flow_request_id`
  ContextVars to seed from `execution_id` so OTel spans emitted by
  `FlowTrackable` children correlate on the stable tracking key.

  `state.id` keeps its existing override semantics for
  persistence/restore — consumers resuming a persisted flow via
  `inputs["id"]` work exactly as before.

  Adds tests covering default uniqueness per instance, immunity to
  consumer `inputs["id"]`, context-var propagation, absence from
  serialized state, and parity for dict-state flows.

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-04-24 04:48:14 +08:00
Greyson LaLonde
69d777ca50 fix(flow): replay recorded method events on checkpoint resume 2026-04-24 03:41:55 +08:00
Greyson LaLonde
77b2835a1d fix(flow): serialize initial_state class refs as JSON schema
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-04-23 21:55:50 +08:00
Lorenze Jay
c77f1632dd fix: preserve metadata-only agent skills
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-04-23 19:58:12 +08:00
Greyson LaLonde
69461076df refactor: dedupe checkpoint helpers and tighten state type hints 2026-04-23 19:29:04 +08:00
Greyson LaLonde
55937d7523 feat: emit lifecycle events for checkpoint operations
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-04-23 18:47:50 +08:00
Greyson LaLonde
bc2fb71560 docs: update changelog and version for v1.14.3a3
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-04-23 05:11:06 +08:00
Greyson LaLonde
3e9deaf9c0 feat: bump versions to 1.14.3a3 2026-04-23 04:55:08 +08:00
Lorenze Jay
3f7637455c feat: supporting e2b 2026-04-23 04:36:33 +08:00
Matt Aitchison
fdf3101b39 feat(azure): fall back to DefaultAzureCredential when no API key
Enables keyless Azure auth (OIDC Workload Identity Federation, Managed
Identity, Azure CLI, env-configured Service Principal) without any
crewAI-specific configuration. Customers whose deployment environment
already sets the standard azure-identity env vars get keyless auth for
free; the existing API-key path is unchanged.

Linear: FAC-40
2026-04-23 04:21:35 +08:00
Greyson LaLonde
c94f2e8f28 fix: upgrade lxml to >=6.1.0 for GHSA-vfmq-68hx-4jfw
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-04-23 00:52:36 +08:00
alex-clawd
944fe6d435 docs: remove pricing FAQ from build-with-ai page across all locales (#5586)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Removes the 'How does pricing work?' accordion from EN, AR, KO, and PT-BR.

Co-authored-by: Joao Moura <joaomdmoura@gmail.com>
2026-04-22 03:56:41 -03:00
iris-clawd
3be2fb65dc perf: lazy-load MCP SDK and event types to reduce cold start by ~29% (#5584)
* perf: defer MCP SDK import by fixing import path in agent/core.py

- Change 'from crewai.mcp import MCPServerConfig' to direct path
  'from crewai.mcp.config import MCPServerConfig' to avoid triggering
  mcp/__init__.py which eagerly loads the full mcp SDK (~300-400ms)
- Move MCPToolResolver import into get_mcp_tools() method body since
  it's only used at runtime, not in type annotations

Saves ~200ms on 'import crewai' cold start.

* perf: lazy-load heavy MCP imports in mcp/__init__.py

MCPClient, MCPToolResolver, BaseTransport, and TransportType now use
__getattr__ lazy loading. These pull in the full mcp SDK (~400ms) but
are only needed at runtime when agents actually connect to MCP servers.

Lightweight config and filter types remain eagerly imported.

* perf: lazy-load all event type modules in events/__init__.py

Previously only agent_events were lazy-loaded; all other event type
modules (crew, flow, knowledge, llm, guardrail, logging, mcp, memory,
reasoning, skill, task, tool_usage) were eagerly imported at package
init time. Since events/__init__.py runs whenever ANY crewai.events.*
submodule is accessed, this loaded ~12 Pydantic model modules
unnecessarily.

Now all event types use the same __getattr__ lazy-loading pattern,
with TYPE_CHECKING imports preserved for IDE/type-checker support.

Saves ~550ms on 'import crewai' cold start.

* chore: remove UNKNOWN.egg-info from version control

* fix: add MCPToolResolver to TYPE_CHECKING imports

Fixes F821 (ruff) and name-defined (mypy) from lazy-loading the
MCP import. The type annotation on _mcp_resolver needs the name
available at type-check time.

* fix: bump lxml to >=5.4.0 for GHSA-vfmq-68hx-4jfw

lxml 5.3.2 has a known vulnerability. Bump to 5.4.0+ which
includes the fix (libxml2 2.13.8). The previous <5.4.0 pin
was for etree import issues that have since been resolved.

* fix: bump exclude-newer to 2026-04-22 for lxml 6.1.0 resolution

lxml 6.1.0 (GHSA fix) was released April 17 but the exclude-newer
date was set to April 17, missing it by timestamp. Bump to April 22.

* perf: add import time benchmark script

scripts/benchmark_import_time.py measures import crewai cold start
in fresh subprocesses. Supports --runs, --json (for CI), and
--threshold (fail if median exceeds N seconds).

The companion GitHub Action workflow needs to be pushed separately
(requires workflow scope).

* new action

* Potential fix for pull request finding 'CodeQL / Workflow does not contain permissions'

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

---------

Co-authored-by: Joao Moura <joaomdmoura@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2026-04-22 02:17:33 -03:00
Greyson LaLonde
160e25c1a9 docs: update changelog and version for v1.14.3a2
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-04-22 03:14:00 +08:00
Greyson LaLonde
b34b336273 feat: bump versions to 1.14.3a2 2026-04-22 03:08:52 +08:00
Renato Nitta
42d6c03ebc fix: propagate implicit @CrewBase names to crew events (#5574)
* fix: propagate implicit @CrewBase names to crew events

* test: appease static analysis for @CrewBase kickoff test

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-04-21 15:57:19 -03:00
Greyson LaLonde
d4f9f875f7 fix: bump python-dotenv to >=1.2.2 for GHSA-mf9w-mj56-hr94
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-04-22 01:22:19 +08:00
Lorenze Jay
6d153284d4 fix: merge execution metadata on duplicate batch initialization in Tr… (#5573)
* fix: merge execution metadata on duplicate batch initialization in TraceBatchManager

- Updated TraceBatchManager to merge execution metadata when a batch is initialized multiple times.
- Enhanced logging to reflect the merging of metadata during duplicate initialization.
- Added a test case to verify that execution metadata is correctly merged when initializing a batch after a lazy action.

* drop env events emitting from traces listener
2026-04-21 10:12:24 -07:00
Lorenze Jay
84a4d47aa7 updated descriptions and applied the actual translations (#5572) 2026-04-21 08:55:39 -07:00
Greyson LaLonde
9caed61f36 chore: remove scarf install tracking 2026-04-21 21:52:17 +08:00
MatthiasHowellYopp
d45ed61db5 feat: added bedrock V4 support 2026-04-21 21:09:13 +08:00
iris-clawd
3b01da9ad9 docs: add Build with AI to Get Started nav + page files for all languages (en, ko, pt-BR, ar) (#5567)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-04-20 23:43:37 -03:00
iris-clawd
874405b825 docs: Add 'Build with AI' page — AI-native docs for coding agents (#5558)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* docs: add Build with AI page for coding agents and AI assistants

* docs: add Build with AI section to README

* docs: trim README Build with AI section to skills install only

* docs: add skills.sh reference link for npx install

* docs: add coding agent logos to Build with AI page

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-04-20 16:09:37 -07:00
Greyson LaLonde
d6d04717c2 fix: serialize Task class-reference fields for checkpointing
Task fields that store class references (output_pydantic, output_json,
response_model, converter_cls) caused PydanticSerializationError when
RuntimeState serialized Crew entities during checkpointing. Serialize
to model_json_schema() and hydrate back via create_model_from_schema.
2026-04-21 03:15:06 +08:00
Greyson LaLonde
01b8437940 fix: handle BaseModel result in guardrail retry loop
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
The guardrail retry path passed a Pydantic object directly to
TaskOutput.raw (which expects a string), causing a ValidationError
when output_pydantic is set and a guardrail fails. Mirror the
BaseModel check from the initial execution path into both sync
and async retry loops.

Closes #5544 (part 1)
2026-04-21 01:59:42 +08:00
Lorenze Jay
2c08f54341 feat: add Daytona sandbox tools for enhanced functionality (#5530)
* feat: add Daytona sandbox tools for enhanced functionality

- Introduced DaytonaBaseTool as a shared base for tools interacting with Daytona sandboxes.
- Added DaytonaExecTool for executing shell commands within a sandbox.
- Implemented DaytonaFileTool for managing files (read, write, delete, etc.) in a sandbox.
- Created DaytonaPythonTool for running Python code in a sandbox environment.
- Updated pyproject.toml to include Daytona as a dependency.

* chore: update tool specifications

* refactor: enhance error handling and logging in Daytona tools

- Added logging for best-effort cleanup failures in DaytonaBaseTool and DaytonaFileTool to aid in debugging.
- Improved error message for ImportError in DaytonaPythonTool to provide clearer guidance on SDK compatibility issues.

* linted

* addressing comment

* pinning version

* supporting append

* chore: update tool specifications

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-20 10:17:11 -07:00
Greyson LaLonde
bc1f1b85a4 docs: update changelog and version for v1.14.3a1 2026-04-21 00:59:07 +08:00
Greyson LaLonde
0b408534ab feat: bump versions to 1.14.3a1 2026-04-21 00:53:50 +08:00
Greyson LaLonde
48f391092c fix: preserve thought_signature in Gemini streaming tool calls
Gemini thinking models (2.5+, 3.x) require thought_signature on
functionCall parts when sent back in conversation history. The streaming
path was extracting only name/args into plain dicts, losing the
signature. Return raw Part objects (matching the non-streaming path)
so the executor preserves them via raw_tool_call_parts.
2026-04-21 00:01:55 +08:00
Greyson LaLonde
ae242c507d feat: add checkpoint and fork support to standalone agents
Add fork classmethod, _restore_runtime, and _restore_event_scope
to BaseAgent. Fix from_checkpoint to set runtime state on the
event bus and restore event scopes. Store kickoff event ID across
checkpoints to skip re-emission on resume. Handle agent entity
type in checkpoint CLI and TUI.
2026-04-20 22:47:37 +08:00
alex-clawd
0b120fac90 fix: use future dates in checkpoint prune tests to prevent time-dependent failures (#5543)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
The test_older_than tests in both JSON and SQLite prune suites used
hardcoded 2026-04-17 timestamps for the 'new' checkpoint. Once that
date passes, the checkpoint is older than 1 day and gets pruned along
with the 'old' one, causing assert count >= 1 to fail (count=0).

Use 2099-01-01 for the 'new' checkpoint so tests remain stable.

Co-authored-by: Joao Moura <joaomdmoura@gmail.com>
2026-04-20 01:27:12 -03:00
Greyson LaLonde
f879909526 fix: emit task_started on fork resume, redesign checkpoint TUI
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Redesign checkpoint TUI with tabbed detail panel, collapsible
agent rosters, keybinding actions, and human-readable timestamps.
2026-04-18 04:19:31 +08:00
Greyson LaLonde
c9b0004d0e fix: correct dry-run order and handle checked-out stale branch in devtools release
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
- Move _update_all_versions inside each dry-run branch so output order matches actual execution
- Switch to main before deleting the stale local branch in create_or_reset_branch
2026-04-17 23:26:52 +08:00
Greyson LaLonde
a8994347b0 docs: update changelog and version for v1.14.2 2026-04-17 22:08:25 +08:00
Greyson LaLonde
5ca62c20f2 feat: bump versions to 1.14.2 2026-04-17 22:01:27 +08:00
Greyson LaLonde
11989da4b1 fix: prompt on stale branch conflicts in devtools release 2026-04-17 21:55:48 +08:00
Greyson LaLonde
19ac7d2f64 fix: patch authlib, langchain-text-splitters, and pypdf vulnerabilities
- authlib 1.6.9 -> 1.6.11 (GHSA-jj8c-mmj3-mmgv)
- langchain-text-splitters 1.1.1 -> 1.1.2 (GHSA-fv5p-p927-qmxr)
- langchain-core 1.2.28 -> 1.2.31 (required by text-splitters 1.1.2)
- pypdf 6.10.1 -> 6.10.2 (GHSA-4pxv-j86v-mhcw, GHSA-7gw9-cf7v-778f, GHSA-x284-j5p8-9c5p)

Pinned tool.uv.exclude-newer to 2026-04-17 so the 2026-04-16 patch
releases fall inside the resolution window.
2026-04-17 21:25:47 +08:00
Lorenze Jay
2f48937ce4 docs(crews): document missing params and add Checkpointing section (OSS-32) (#5409)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
- Add 8 missing parameters to the Crew Attributes table:
  chat_llm, before_kickoff_callbacks, after_kickoff_callbacks,
  tracing, skills, security_config, checkpoint
- Add new "## Checkpointing" section before "## Memory Utilization" with:
  - Quick-start checkpoint=True example
  - Full CheckpointConfig usage example
  - Crew.from_checkpoint() resume pattern
  - CheckpointConfig attributes table (location, on_events, provider, max_checkpoints)
  - Note on auto-restored checkpoint fields

Closes OSS-32
2026-04-16 16:57:00 -07:00
Greyson LaLonde
c5192b970c feat: add checkpoint resume, diff, prune commands and save discoverability
Add three new CLI subcommands to improve checkpoint UX:

- `crewai checkpoint resume [id]` skips the TUI and resumes from the
  latest or specified checkpoint directly
- `crewai checkpoint diff <id1> <id2>` compares two checkpoints showing
  changes in metadata, inputs, task status, and outputs
- `crewai checkpoint prune --keep N --older-than Xd` removes old
  checkpoints from JSON dirs or SQLite databases

Also writes a resume hint to stderr after every checkpoint save so
users discover the command without needing to know it exists.
2026-04-17 04:50:15 +08:00
Greyson LaLonde
54391fdbdf feat: add from_checkpoint parameter to Agent.kickoff, kickoff_async, akickoff 2026-04-17 03:40:37 +08:00
Greyson LaLonde
6136228a66 fix: scope streaming handlers to prevent cross-run chunk contamination
Concurrent streaming runs registered handlers on the singleton event bus
that received all LLMStreamChunkEvent emissions, causing chunks to fan
out across unrelated queues. Introduces a ContextVar-based stream scope
ID so each handler only accepts events from its own execution context.

Closes #5376
2026-04-17 03:02:03 +08:00
Greyson LaLonde
fbe2a04064 fix: mock Repository.__init__ in test_publish_when_not_in_sync 2026-04-17 02:39:22 +08:00
iris-clawd
baf91d8f0a fix: update broken enterprise link on installation page (OSS-36) (#5443)
* fix: update broken enterprise link on installation page (OSS-36)

The 'Explore Enterprise Options' card on the installation page linked to
https://crewai.com/enterprise which returns a 404. Updated the href to
https://crewai.com/amp across all locales (en, pt-BR, ko, ar).

* fix: use HubSpot form link for enterprise options card

Updated per team feedback — the enterprise card should link to the
HubSpot demo form instead of crewai.com/amp.

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-04-16 11:01:59 -07:00
Greyson LaLonde
7e01c5a030 fix: dispatch Flow checkpoints through Flow APIs in TUI 2026-04-17 01:34:06 +08:00
Lorenze Jay
105a9778cc feat: add template management commands for project templates (#5444)
* feat: add template management commands for project templates

- Introduced  command group to browse and install project templates.
- Added  command to display available templates.
- Implemented  command to install a selected template into the current directory.
- Created  class to handle template-related operations, including fetching templates from GitHub and managing installations.
- Enhanced telemetry to track template installations.

* linted

* adressing comments

* comment addressed
2026-04-16 10:18:15 -07:00
Greyson LaLonde
32ec4414bf fix: use recursive glob for JSON checkpoint discovery
Branch-aware checkpoint storage writes under subdirectories (e.g.
main/, fork/exp1/) but _list_json and _info_json_latest used flat
globs that missed them.
2026-04-17 00:13:35 +08:00
Greyson LaLonde
63fc2e7588 fix: complete recursive MCP schema handling
resolve_refs now returns type-preserving stubs instead of {} for
circular $refs, and create_model_from_schema catches JsonRefError
to fall back to lazy top-level-only inlining.
2026-04-17 00:06:02 +08:00
Greyson LaLonde
749fe85325 fix: bump langsmith to 0.7.31 to patch GHSA-rr7j-v2q5-chgv
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
langsmith <0.7.31 bypasses output redaction for streaming token
events, leaking sensitive LLM outputs into LangSmith storage.
2026-04-16 23:55:30 +08:00
Greyson LaLonde
0bb6faa9d3 docs: update changelog and version for v1.14.2rc1
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-04-16 05:24:57 +08:00
Greyson LaLonde
aa28eeab6a feat: bump versions to 1.14.2rc1 2026-04-16 05:18:24 +08:00
Greyson LaLonde
29b5531f78 fix: handle cyclic JSON schemas in MCP tool resolution 2026-04-16 05:03:00 +08:00
Greyson LaLonde
74d061e994 fix: bump python-multipart to 0.0.26 to patch GHSA-mj87-hwqh-73pj
Fixes GHSA-mj87-hwqh-73pj
2026-04-16 04:25:35 +08:00
Greyson LaLonde
18d0fd6b80 fix: bump pypdf to 6.10.1 to patch GHSA-jj6c-8h6c-hppx
Fixes GHSA-jj6c-8h6c-hppx
2026-04-16 04:11:08 +08:00
Greyson LaLonde
1c90d574ab docs: update changelog and version for v1.14.2a5
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
2026-04-15 22:45:15 +08:00
Greyson LaLonde
3a7c550512 feat: bump versions to 1.14.2a5 2026-04-15 22:40:48 +08:00
Greyson LaLonde
5b6f89fe64 docs: update changelog and version for v1.14.2a4
Some checks failed
Vulnerability Scan / pip-audit (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
2026-04-15 02:34:32 +08:00
Greyson LaLonde
ad5e66d1d0 feat: bump versions to 1.14.2a4 2026-04-15 02:29:06 +08:00
Greyson LaLonde
94e7d86df1 fix: stop forwarding strict mode to Bedrock Converse API
Forwarding strict and sanitizing tool schemas for strict mode causes
Bedrock Converse requests to hang until timeout. Drop strict forwarding
and schema sanitization from the Bedrock provider.
2026-04-15 02:22:50 +08:00
Greyson LaLonde
0dba95e166 fix: bump pytest to 9.0.3 for GHSA-6w46-j5rx-g56g
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
pytest <9.0.3 has an insecure tmpdir vulnerability (CVE / GHSA-6w46-j5rx-g56g).
Bump pytest-split to 0.11.0 to satisfy the new pytest>=9 requirement.
2026-04-14 02:38:05 +08:00
Greyson LaLonde
58208fdbae fix: bump openai lower bound to >=2.0.0 2026-04-14 02:19:47 +08:00
Greyson LaLonde
655e75038b feat: add resume hints to devtools release on failure 2026-04-14 01:26:29 +08:00
Greyson LaLonde
8e2a529d94 chore: add deprecation decorator to LiteAgent 2026-04-14 00:51:11 +08:00
Greyson LaLonde
58bbd0a400 docs: update changelog and version for v1.14.2a3
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-04-13 21:38:12 +08:00
Greyson LaLonde
9708b94979 feat: bump versions to 1.14.2a3 2026-04-13 21:30:14 +08:00
Greyson LaLonde
0b0521b315 chore: improve typing in task module 2026-04-13 21:21:18 +08:00
Greyson LaLonde
c8694fbed2 fix: override pypdf and uv to patched versions for CVE-2026-40260 and GHSA-pjjw-68hj-v9mw 2026-04-13 21:04:37 +08:00
Greyson LaLonde
a4e7b322c5 docs: clean up enterprise A2A language 2026-04-13 20:53:31 +08:00
Greyson LaLonde
ee049999cb docs: add enterprise A2A feature doc and update OSS A2A docs 2026-04-13 20:28:06 +08:00
Greyson LaLonde
1d6f84c7aa chore: clean up redundant inline docs in agents module
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-04-13 11:00:42 +08:00
Greyson LaLonde
8dc2655cbf chore: clean up redundant inline docs in agent module 2026-04-13 10:55:29 +08:00
Greyson LaLonde
121720cbb3 chore: clean up redundant inline docs in a2a module 2026-04-13 10:49:59 +08:00
Greyson LaLonde
16bf24001e fix: upgrade requests to >=2.33.0 for CVE temp file vulnerability
Some checks failed
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
2026-04-12 16:12:35 +08:00
Greyson LaLonde
29fc4ac226 feat: add deploy validation CLI and improve LLM initialization ergonomics
Add crewai deploy validate to check project structure, dependencies, imports, and env usage before deploy
Run validation automatically in deploy create and deploy push with skip flag support
Return structured findings with stable codes and hints
Add test coverage for validation scenarios

refactor: defer LLM client construction to first use

Move SDK client creation out of model initialization into lazy getters
Add _get_sync_client and _get_async_client across providers
Route all provider calls through lazy getters
Surface credential errors at first real invocation

refactor: standardize provider client access

Align async paths to use _get_async_client
Avoid client construction in lightweight config accessors
Simplify provider lifecycle and improve consistency

test: update suite for new behavior

Update tests for lazy initialization contract
Update CLI tests for validation flow and skip flag
Expand coverage for provider initialization paths
2026-04-12 16:00:46 +08:00
Yanhu
25fcf39cc1 fix: preserve Bedrock tool call arguments by removing truthy default
func_info.get('arguments', '{}') returns '{}' (truthy) when no
'function' wrapper exists (Bedrock format), causing the or-fallback
to tool_call.get('input', {}) to never execute. The actual Bedrock
arguments are silently discarded.

Remove the default so get('arguments') returns None (falsy) when
there's no function wrapper, allowing the or-chain to correctly
fall through to Bedrock's 'input' field.

Fixes #5275
2026-04-12 15:50:56 +08:00
Greyson LaLonde
3b280e41fb chore: bump pypdf to 6.10.0 for GHSA-3crg-w4f6-42mx
Some checks failed
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Resolves CVE-2026-40260 where manipulated XMP metadata entity
declarations can exhaust RAM in pypdf <6.10.0.
2026-04-11 05:56:11 +08:00
Greyson LaLonde
8de4421705 fix: sanitize tool schemas for strict mode
Pydantic schemas intermittently fail strict tool-use on openai, anthropic,
and bedrock. All three reject nested objects missing additionalProperties:
false, and anthropic also rejects keywords like minLength and top-level
anyOf. Adds per-provider sanitizers that inline refs, close objects, mark
every property required, preserve nullable unions, and strip keywords each
grammar compiler rejects. Verified against real bedrock, anthropic, and
openai.
2026-04-11 05:26:48 +08:00
Greyson LaLonde
62484934c1 chore: bump uv to 0.11.6 for GHSA-pjjw-68hj-v9mw
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Low-severity advisory: malformed RECORD entries in wheels could delete
files outside the venv on uninstall. Fixed in uv 0.11.6.
2026-04-11 05:09:24 +08:00
Greyson LaLonde
298fc7b9c0 chore: drop tiktoken from anthropic async max_tokens test 2026-04-11 03:20:20 +08:00
Greyson LaLonde
9537ba0413 ci: add pip-audit pre-commit hook 2026-04-11 03:06:31 +08:00
Greyson LaLonde
ace9617722 test: re-record hierarchical verbose manager cassette 2026-04-11 02:35:00 +08:00
Greyson LaLonde
7e1672447b fix: deflake MemoryRecord embedding serialization test
Substring checks like `'0.1' not in json_str` collided with timestamps
such as `2026-04-10T13:00:50.140557` on CI. Round-trip through
`model_validate_json` to verify structurally that the embedding field
is absent from the serialized output.
2026-04-11 02:01:23 +08:00
Greyson LaLonde
ea58f8d34d docs: update changelog and version for v1.14.2a2 2026-04-10 21:58:55 +08:00
Greyson LaLonde
fe93333066 feat: bump versions to 1.14.2a2 2026-04-10 21:51:51 +08:00
Greyson LaLonde
1293dee241 feat: checkpoint TUI with tree view, fork support, editable inputs/outputs
- Rewrite TUI with Tree widget showing branch/fork lineage
- Add Resume and Fork buttons in detail panel with Collapsible entities
- Show branch and parent_id in detail panel and CLI info output
- Auto-detect .checkpoints.db when default dir missing
- Append .db to location for SqliteProvider when no extension set
- Fix RuntimeState.from_checkpoint not setting provider/location
- Fork now writes initial checkpoint on new branch
- Add from_checkpoint, fork, and CLI docs to checkpointing.mdx
2026-04-10 21:24:49 +08:00
Greyson LaLonde
6efa142e22 fix: forward strict mode to Anthropic and Bedrock providers
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
The OpenAI-format tool schema sets strict: true but this was dropped
during conversion to Anthropic/Bedrock formats, so neither provider
used constrained decoding. Without it, the model can return string
"None" instead of JSON null for nullable fields, causing Pydantic
validation failures.
2026-04-10 15:32:54 +08:00
Lucas Gomide
fc6792d067 feat: enrich LLM token tracking with reasoning tokens, cache creation tokens (#5389)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-04-10 00:22:27 -04:00
Greyson LaLonde
84b1b0a0b0 feat: add from_checkpoint parameter to kickoff methods
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Accept CheckpointConfig on Crew and Flow kickoff/kickoff_async/akickoff.
When restore_from is set, the entity resumes from that checkpoint.
When only config fields are set, checkpointing is enabled for the run.
Adds restore_from field (Path | str | None) to CheckpointConfig.
2026-04-10 03:47:23 +08:00
Greyson LaLonde
56cf8a4384 feat: embed crewai_version in checkpoints with migration framework
Write the crewAI package version into every checkpoint blob. On restore,
run version-based migrations so older checkpoints can be transformed
forward to the current format. Adds crewai.utilities.version module.
2026-04-10 01:13:30 +08:00
Greyson LaLonde
68c754883d feat: add checkpoint forking with lineage tracking 2026-04-10 00:03:28 +08:00
alex-clawd
ce56472fc3 fix: harden NL2SQLTool — read-only default, query validation, parameterized queries (#5311)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
* fix: harden NL2SQLTool — read-only by default, parameterized queries, query validation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: address CI lint failures and remove unused import

- Remove unused `sessionmaker` import from test_nl2sql_security.py
- Use `Self` return type on `_apply_env_override` (fixes UP037/F821)
- Fix ruff errors auto-fixed in lib/crewai (UP007, etc.)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: expand _WRITE_COMMANDS and block multi-statement semicolon injection

- Add missing write commands: UPSERT, LOAD, COPY, VACUUM, ANALYZE,
  ANALYSE, REINDEX, CLUSTER, REFRESH, COMMENT, SET, RESET
- _validate_query() now splits on ';' and validates each statement
  independently; multi-statement queries are rejected outright in
  read-only mode to prevent 'SELECT 1; DROP TABLE users' bypass
- Extract single-statement logic into _validate_statement() helper
- Add TestSemicolonInjection and TestExtendedWriteCommands test classes

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* ci: retrigger

* fix: use typing_extensions.Self for Python 3.10 compat

* chore: update tool specifications

* docs: document NL2SQLTool read-only default and DML configuration

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: close three NL2SQLTool security gaps (writable CTEs, EXPLAIN ANALYZE, multi-stmt commit)

- Remove WITH from _READ_ONLY_COMMANDS; scan CTE body for write keywords so
  writable CTEs like `WITH d AS (DELETE …) SELECT …` are blocked in read-only mode.
- EXPLAIN ANALYZE/ANALYSE now resolves the underlying command; EXPLAIN ANALYZE DELETE
  is treated as a write and blocked in read-only mode.
- execute_sql commit decision now checks ALL semicolon-separated statements so
  a SELECT-first batch like `SELECT 1; DROP TABLE t` still triggers a commit
  when allow_dml=True.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: handle parenthesized EXPLAIN options syntax; remove unused _seed_db

_validate_statement now strips parenthesized options from EXPLAIN (e.g.
EXPLAIN (ANALYZE) DELETE, EXPLAIN (ANALYZE, VERBOSE) DELETE) before
checking whether ANALYZE/ANALYSE is present — closing the bypass where
the options-list form was silently allowed in read-only mode.

Adds three new tests:
  - EXPLAIN (ANALYZE) DELETE  → blocked
  - EXPLAIN (ANALYZE, VERBOSE) DELETE  → blocked
  - EXPLAIN (VERBOSE) SELECT  → allowed

Also removes the unused _seed_db helper from test_nl2sql_security.py.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* chore: update tool specifications

* fix: smarter CTE write detection, fix commit logic for writable CTEs

- Replace naive token-set matching with positional AS() body inspection
  to avoid false positives on column names like 'comment', 'set', 'reset'
- Fix execute_sql commit logic to detect writable CTEs (WITH + DELETE/INSERT)
  not just top-level write commands
- Add tests for false positive cases and writable CTE commit behavior
- Format nl2sql_tool.py to pass ruff format check

* fix: catch write commands in CTE main query + handle whitespace in AS()

- WITH cte AS (SELECT 1) DELETE FROM users now correctly blocked
- AS followed by newline/tab/multi-space before ( now detected
- execute_sql commit logic updated for both cases
- 4 new tests

* fix: EXPLAIN ANALYZE VERBOSE handling, string literal paren bypass, commit logic for EXPLAIN ANALYZE

- EXPLAIN handler now consumes all known options (ANALYZE, ANALYSE, VERBOSE) before
  extracting the real command, fixing 'EXPLAIN ANALYZE VERBOSE SELECT' being blocked
- Paren walker in _extract_main_query_after_cte now skips string literals, preventing
  'WITH cte AS (SELECT '\''('\'' FROM t) DELETE FROM users' from bypassing detection
- _is_write_stmt in execute_sql now resolves EXPLAIN ANALYZE to underlying command
  via _resolve_explain_command, ensuring session.commit() fires for write operations
- 10 new tests covering all three fixes

* fix: deduplicate EXPLAIN parsing, fix AS( regex in strings, block unknown CTE commands, bump langchain-core

- Refactor _validate_statement to use _resolve_explain_command (single source of truth)
- _iter_as_paren_matches skips string literals so 'AS (' in data doesn't confuse CTE detection
- Unknown commands after CTE definitions now blocked in read-only mode
- Bump langchain-core override to >=1.2.28 (GHSA-926x-3r5x-gfhw)

* fix: add return type annotation to _iter_as_paren_matches

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-09 03:21:38 -03:00
Greyson LaLonde
06fe163611 docs: update changelog and version for v1.14.2a1
Some checks failed
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-04-09 07:26:22 +08:00
Greyson LaLonde
3b52b1a800 feat: bump versions to 1.14.2a1 2026-04-09 07:21:39 +08:00
Greyson LaLonde
9ab67552a7 fix: emit flow_finished event after HITL resume
resume_async() was missing trace infrastructure that kickoff_async()
sets up, causing flow_finished to never reach the platform after HITL
feedback. Add FlowStartedEvent emission to initialize the trace batch,
await event futures, finalize the trace batch, and guard with
suppress_flow_events.
2026-04-09 05:31:31 +08:00
Greyson LaLonde
8cdde16ac8 fix: bump cryptography to 46.0.7 for CVE-2026-39892 2026-04-09 05:17:31 +08:00
Greyson LaLonde
0e590ff669 refactor: use shared I18N_DEFAULT singleton 2026-04-09 04:29:53 +08:00
Greyson LaLonde
15f5bff043 docs: update changelog and version for v1.14.1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-04-09 01:56:51 +08:00
Greyson LaLonde
a0578bb6c3 feat: bump versions to 1.14.1 2026-04-09 01:45:40 +08:00
Greyson LaLonde
00400a9f31 ci: skip python tests, lint, and type checks on docs-only PRs 2026-04-09 01:34:47 +08:00
Lorenze Jay
5c08e566b5 dedicate skills page (#5331) 2026-04-08 10:10:18 -07:00
Greyson LaLonde
fe028ef400 docs: update changelog and version for v1.14.1rc1 2026-04-09 00:29:04 +08:00
Greyson LaLonde
52c227ab17 feat: bump versions to 1.14.1rc1 2026-04-09 00:22:24 +08:00
Greyson LaLonde
8bae740899 fix: use regex for template pyproject.toml version bumps
tomlkit.parse() fails on Jinja placeholders like {{folder_name}}
in CLI template files. Switch to regex replacement for templates.
2026-04-09 00:13:07 +08:00
Greyson LaLonde
1c784695c1 feat: add async checkpoint TUI browser
Launch a Textual TUI via `crewai checkpoint` to browse and resume
from checkpoints. Uses run_async/akickoff for fully async execution.
Adds provider auto-detection from file magic bytes.
2026-04-08 23:59:09 +08:00
iris-clawd
1ae237a287 refactor: replace hardcoded denylist with dynamic BaseTool field exclusion in spec gen (#5347)
The spec generator previously used a hardcoded list of field names to
exclude from init_params_schema. Any new field or computed_field added
to BaseTool (like tool_type from 86ce54f) would silently leak into
tool.specs.json unless someone remembered to update that list.

Now _extract_init_params() dynamically computes BaseTool's fields at
import time via model_fields + model_computed_fields, so any future
additions to BaseTool are automatically excluded.

Fields from intermediate base classes (RagTool, BraveSearchToolBase,
SerpApiBaseTool) are correctly preserved since they're not on BaseTool.

TDD:
- RED: 3 new tests confirming BaseTool field leak, intermediate base
  preservation, and future-proofing — all failed before the fix
- GREEN: Dynamic allowlist applied — all 10 tests pass
- Regenerated tool.specs.json (tool_type removed from all tools)
2026-04-08 11:49:16 -04:00
Greyson LaLonde
0e8ed75947 feat: add aclose()/close() and async context manager to streaming outputs 2026-04-08 23:32:37 +08:00
Greyson LaLonde
98e0d1054f fix: sanitize tool names in hook decorator filters 2026-04-08 21:02:25 +08:00
Greyson LaLonde
fc9280ccf6 refactor: replace regex with tomlkit in devtools CLI
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-04-08 19:52:51 +08:00
Greyson LaLonde
f4c0667d34 fix: bump transformers to 5.5.0 to resolve CVE-2026-1839
Bumps docling pin from ~=2.75.0 to ~=2.84.0 (allows huggingface-hub>=1)
and adds a transformers>=5.4.0 override to force resolution past 4.57.6.
2026-04-08 18:59:51 +08:00
Greyson LaLonde
0450d06a65 refactor: use shared PRINTER singleton
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-04-08 07:17:22 +08:00
Greyson LaLonde
b23b2696fe fix: remove FilteredStream stdout/stderr wrapper
Wrapping sys.stdout and sys.stderr at import time with a
threading.Lock is not fork-safe and adds overhead to every
print call. litellm.suppress_debug_info already silences the
noisy output this was designed to filter.
2026-04-08 04:58:05 +08:00
Greyson LaLonde
8700e3db33 chore: remove unused flow/config.py 2026-04-08 04:37:31 +08:00
Greyson LaLonde
75f162fd3c refactor: make BaseProvider a BaseModel with provider_type discriminator
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Replace the Protocol with a BaseModel + ABC so providers serialize and
deserialize natively via pydantic. Each provider gets a Literal
provider_type field. CheckpointConfig.provider uses a discriminated
union so the correct provider class is reconstructed from checkpoint JSON.
2026-04-08 03:14:54 +08:00
Greyson LaLonde
c0f3151e13 fix: register checkpoint handlers when CheckpointConfig is created 2026-04-08 02:11:34 +08:00
João Moura
25eb4adc49 docs: update changelog and version for v1.14.0 (#5322) 2026-04-07 14:47:34 -03:00
João Moura
1534ba202d feat: bump versions to 1.14.0 (#5321) 2026-04-07 14:45:39 -03:00
Greyson LaLonde
868416bfe0 fix: add SSRF and path traversal protections (#5315)
* fix: add SSRF and path traversal protections

CVE-2026-2286: validate_url blocks non-http/https schemes, private
IPs, loopback, link-local, reserved addresses. Applied to 11 web tools.

CVE-2026-2285: validate_path confines file access to the working
directory. Applied to 7 file and directory tools.

* fix: drop unused assignment from validate_url call

* fix: DNS rebinding protection and allow_private flag

Rewrite validated URLs to use the resolved IP, preventing DNS rebinding
between validation and request time. SDK-based tools use pin_ip=False
since they manage their own HTTP clients. Add allow_private flag for
deployments that need internal network access.

* fix: unify security utilities and restore RAG chokepoint validation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor: move validation to security/ package + address review comments

- Move safe_path.py to crewai_tools/security/; add safe_url.py re-export
- Keep utilities/safe_path.py as a backwards-compat shim
- Update all 21 import sites to use crewai_tools.security.safe_path
- files_compressor_tool: validate output_path (user-controlled)
- serper_scrape_website_tool: call validate_url() before building payload
- brightdata_unlocker: validate_url() already called without assignment (no-op fix)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor: move validation to security/ package, keep utilities/ as compat shim

- security/safe_path.py is the canonical location for all validation
- utilities/safe_path.py re-exports for backward compatibility
- All tool imports already point to security.safe_path
- All review comments already addressed in prior commits

* fix: move validation outside try/except blocks, use correct directory validator

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: use resolved paths from validation to prevent symlink TOCTOU, remove unused safe_url.py

---------

Co-authored-by: Alex <alex@crewai.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 14:44:50 -03:00
Greyson LaLonde
a5df7c798c feat: checkpoint list/info CLI commands 2026-04-08 01:28:25 +08:00
Greyson LaLonde
5958a16ade refactor: checkpoint API cleanup 2026-04-08 01:13:23 +08:00
alex-clawd
9325e2f6a4 fix: add path and URL validation to RAG tools (#5310)
* fix: add path and URL validation to RAG tools

Add validation utilities to prevent unauthorized file reads and SSRF
when RAG tools accept LLM-controlled paths/URLs at runtime.

Changes:
- New crewai_tools.utilities.safe_path module with validate_file_path(),
  validate_directory_path(), and validate_url()
- File paths validated against base directory (defaults to cwd).
  Resolves symlinks and ../ traversal. Rejects escape attempts.
- URLs validated: file:// blocked entirely. HTTP/HTTPS resolves DNS
  and blocks private/reserved IPs (10.x, 172.16-31.x, 192.168.x,
  127.x, 169.254.x, 0.0.0.0, ::1, fc00::/7).
- Validation applied in RagTool.add() — catches all RAG search tools
  (JSON, CSV, PDF, TXT, DOCX, MDX, Directory, etc.)
- Removed file:// scheme support from DataTypes.from_content()
- CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true env var for backward compat
- 27 tests covering traversal, symlinks, private IPs, cloud metadata,
  IPv6, escape hatch, and valid paths/URLs

* fix: validate path/URL keyword args in RagTool.add()

The original patch validated positional *args but left all keyword
arguments (path=, file_path=, directory_path=, url=, website=,
github_url=, youtube_url=) unvalidated, providing a trivial bypass
for both path-traversal and SSRF checks.

Applies validate_file_path() to path/file_path/directory_path kwargs
and validate_url() to url/website/github_url/youtube_url kwargs before
they reach the adapter. Adds a regression-test file covering all eight
kwarg vectors plus the two existing positional-arg checks.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: address CodeQL and review comments on RAG path/URL validation

- Replace insecure tempfile.mktemp() with inline symlink target in test
- Remove unused 'target' variable and unused tempfile import
- Narrow broad except Exception: pass to only catch urlparse errors;
  validate_url ValueError now propagates instead of being silently swallowed
- Fix ruff B904 (raise-without-from-inside-except) in safe_path.py
- Fix ruff B007 (unused loop variable 'family') in safe_path.py
- Use validate_directory_path in DirectorySearchTool.add() so the
  public utility is exercised in production code

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* style: fix ruff format + remaining lint issues

* fix: resolve mypy type errors in RAG path/URL validation

- Cast sockaddr[0] to str() to satisfy mypy (socket.getaddrinfo returns
  sockaddr where [0] is str but typed as str | int)
- Remove now-unnecessary `type: ignore[assignment]` and
  `type: ignore[literal-required]` comments in rag_tool.py

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: unroll dynamic TypedDict key loops to satisfy mypy literal-required

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* test: allow tmp paths in RAG data-type tests via CREWAI_TOOLS_ALLOW_UNSAFE_PATHS

TemporaryDirectory creates files under /tmp/ which is outside CWD and is
correctly blocked by the new path validation.  These tests exercise
data-type handling, not security, so add an autouse fixture that sets
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true for the whole file.  Path/URL
security is covered by test_rag_tool_path_validation.py.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* test: allow tmp paths in search-tool and rag_tool tests via CREWAI_TOOLS_ALLOW_UNSAFE_PATHS

test_search_tools.py has tests for TXTSearchTool, CSVSearchTool,
MDXSearchTool, JSONSearchTool, and DirectorySearchTool that create
files under /tmp/ via tempfile, which is outside CWD and correctly
blocked by the new path validation.  rag_tool_test.py has one test
that calls tool.add() with a TemporaryDirectory path.

Add the same autouse allow_tmp_paths fixture used in
test_rag_tool_add_data_type.py.  Security is covered separately by
test_rag_tool_path_validation.py.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* chore: update tool specifications

* docs: document CodeInterpreterTool removal and RAG path/URL validation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: address three review comments on path/URL validation

- safe_path._is_private_or_reserved: after unwrapping IPv4-mapped IPv6
  to IPv4, only check against IPv4 networks to avoid TypeError when
  comparing an IPv4Address against IPv6Network objects.
- safe_path.validate_file_path: handle filesystem-root base_dir ('/')
  by not appending os.sep when the base already ends with a separator,
  preventing the '//'-prefix bug.
- rag_tool.add: path-detection heuristic now checks for both '/' and
  os.sep so forward-slash paths are caught on Windows as well as Unix.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: remove unused _BLOCKED_NETWORKS variable after IPv4/IPv6 split

* chore: update tool specifications

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-07 13:29:45 -03:00
Greyson LaLonde
25e7ca03c4 docs: update changelog and version for v1.14.0a4 2026-04-07 23:29:21 +08:00
Greyson LaLonde
5b4a0e8734 feat: bump versions to 1.14.0a4 2026-04-07 23:22:58 +08:00
alex-clawd
e64b37c5fc refactor: remove CodeInterpreterTool and deprecate code execution params (#5309)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* refactor: remove CodeInterpreterTool and deprecate code execution params

CodeInterpreterTool has been removed. The allow_code_execution and
code_execution_mode parameters on Agent are deprecated and will be
removed in v2.0. Use dedicated sandbox services (E2B, Modal, etc.)
for code execution needs.

Changes:
- Remove CodeInterpreterTool from crewai-tools (tool, Dockerfile, tests, imports)
- Remove docker dependency from crewai-tools
- Deprecate allow_code_execution and code_execution_mode on Agent
- get_code_execution_tools() returns empty list with deprecation warning
- _validate_docker_installation() is a no-op with deprecation warning
- Bedrock CodeInterpreter (AWS hosted) and OpenAI code_interpreter are NOT affected

* fix: remove empty code_interpreter imports and unused stdlib imports

- Remove empty `from code_interpreter_tool import ()` blocks in both
  crewai_tools/__init__.py and tools/__init__.py that caused SyntaxError
  after CodeInterpreterTool was removed
- Remove unused `shutil` and `subprocess` imports from agent/core.py
  left over from the code execution params deprecation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: remove redundant _validate_docker_installation call and fix list type annotation

- Drop the _validate_docker_installation() call inside the allow_code_execution
  block — it fired a second DeprecationWarning identical to the one emitted
  just above it, making the warning fire twice.
- Annotate get_code_execution_tools() return type as list[Any] to satisfy mypy
  (bare `list` fails the type-arg check introduced by this branch).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* ci: retrigger

* fix: update test_crew.py to remove CodeInterpreterTool references

CodeInterpreterTool was removed from crewai_tools. Update tests to
reflect that get_code_execution_tools() now returns an empty list.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* chore: update tool specifications

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-07 03:59:40 -03:00
Greyson LaLonde
c132d57a36 perf: use JSONB for checkpoint data column
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-04-07 09:35:26 +08:00
Lucas Gomide
ad24c3d56e feat: add guardrail_type and name to distinguish traces (#5303)
* feat: add guardrail_type to distinguish between hallucination, function, and LLM

* feat: introduce guardrail_name into guardrail events

* feat: propagate guardrail type and name on guardrail completed event

* feat: remove unused LLMGuardrailFailedEvent

* fix: handle running event loop in LLMGuardrail._validate_output

When agent.kickoff() returns a coroutine inside an already-running event loop, asyncio.run() fails
2026-04-06 18:52:53 -04:00
Lorenze Jay
0c307f1621 docs: update quickstart and installation guides for improved clarity (#5301)
* docs: update quickstart and installation guides for improved clarity

- Revised the quickstart guide to emphasize creating a Flow and running a single-agent crew that generates a report.
- Updated the installation documentation to reflect changes in the quickstart process and enhance user understanding.

* translations
2026-04-06 15:04:54 -07:00
Greyson LaLonde
f98dde6c62 docs: add storage providers section, export JsonProvider 2026-04-07 06:04:29 +08:00
Greyson LaLonde
6b6e191532 feat: add SqliteProvider for checkpoint storage 2026-04-07 05:54:05 +08:00
Greyson LaLonde
c4e2d7ea3b feat: add CheckpointConfig for automatic checkpointing 2026-04-07 05:34:25 +08:00
Greyson LaLonde
86ce54fc82 feat: runtime state checkpointing, event system, and executor refactor
- Pass RuntimeState through the event bus and enable entity auto-registration
- Introduce checkpointing API:
  - .checkpoint(), .from_checkpoint(), and async checkpoint support
  - Provider-based storage with BaseProvider and JsonProvider
  - Mid-task resume and kickoff() integration
- Add EventRecord tracking and full event serialization with subtype preservation
- Enable checkpoint fidelity via llm_type and executor_type discriminators

- Refactor executor architecture:
  - Convert executors, tools, prompts, and TokenProcess to BaseModel
  - Introduce proper base classes with typed fields (CrewAgentExecutorMixin, BaseAgentExecutor)
  - Add generic from_checkpoint with full LLM serialization
  - Support executor back-references and resume-safe initialization

- Refactor runtime state system:
  - Move RuntimeState into state/ module with async checkpoint support
  - Add entity serialization improvements and JSON-safe round-tripping
  - Implement event scope tracking and replay for accurate resume behavior

- Improve tool and schema handling:
  - Make BaseTool fully serializable with JSON round-trip support
  - Serialize args_schema via JSON schema and dynamically reconstruct models
  - Add automatic subclass restoration via tool_type discriminator

- Enhance Flow checkpointing:
  - Support restoring execution state and subclass-aware deserialization

- Performance improvements:
  - Cache handler signature inspection
  - Optimize event emission and metadata preparation

- General cleanup:
  - Remove dead checkpoint payload structures
  - Simplify entity registration and serialization logic
2026-04-07 03:22:30 +08:00
alex-clawd
bf2f4dbce6 fix: exclude embedding vectors from memory serialization (saves tokens) (#5298)
Some checks failed
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
* fix: exclude embedding vector from MemoryRecord serialization

MemoryRecord.embedding (1536 floats for OpenAI embeddings) was included
in model_dump()/JSON serialization and repr. When recall results flow
to agents or get logged, these vectors burn tokens for zero value —
agents never need the raw embedding.

Added exclude=True and repr=False to the embedding field. The storage
layer accesses record.embedding directly (not via model_dump), so
persistence is unaffected.

* test: validate embedding excluded from serialization

Two tests:
1. MemoryRecord — model_dump, model_dump_json, and repr all exclude
   embedding. Direct attribute access still works for storage layer.
2. MemoryMatch — nested record serialization also excludes embedding.
2026-04-06 14:48:58 -03:00
Lorenze Jay
fdb9b6f090 fix: bump litellm to >=1.83.0 to address CVE-2026-35030
* fix: bump litellm to >=1.83.0 to address CVE-2026-35030

Bump litellm from <=1.82.6 to >=1.83.0 to fix JWT auth bypass via
OIDC cache key collision (CVE-2026-35030). Also widen devtools openai
pin from ~=1.83.0 to >=1.83.0,<3 to resolve the version conflict
(litellm 1.83.0 requires openai>=2.8.0).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: resolve mypy errors from litellm bump

- Remove unused type: ignore[import-untyped] on instructor import
- Remove all unused type: ignore[union-attr] comments (litellm types fixed)
- Add hasattr guard for tool_call.function — new litellm adds
  ChatCompletionMessageCustomToolCall to the union which lacks .function

* fix: tighten litellm pin to ~=1.83.0 (patch-only bumps)

>=1.83.0,<2 is too wide — litellm has had breaking changes between
minors. ~=1.83.0 means >=1.83.0,<1.84.0 — gets CVE patches but won't
pull in breaking minor releases.

* ci: bump uv from 0.8.4 to 0.11.3

* fix: resolve mypy errors in openai completion from 2.x type changes

Use isinstance checks with concrete openai response types instead of
string comparisons for proper type narrowing. Update code interpreter
handling for outputs/OutputImage API changes in openai 2.x.

* fix: pre-cache tiktoken encoding before VCR intercepts requests

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Alex <alex@crewai.com>
Co-authored-by: Greyson LaLonde <greyson@crewai.com>
2026-04-07 00:41:20 +08:00
João Moura
71b4667a0e docs: update changelog and version for v1.14.0a3 (#5296)
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-04-06 05:17:58 -03:00
João Moura
c393bd2ee6 feat: bump versions to 1.14.0a3 (#5295) 2026-04-06 05:17:10 -03:00
João Moura
baf15a409b docs: update changelog and version for v1.14.0a2 (#5294) 2026-04-06 04:34:23 -03:00
João Moura
c907ce473b feat: bump versions to 1.14.0a2 (#5293) 2026-04-06 04:33:37 -03:00
João Moura
e46402d10d feat: bump versions to 1.14.0a1 (#5292)
* chore: update uv.lock with new dependency groups and versioning adjustments

- Added a new revision number and updated resolution markers for Python version compatibility.
- Introduced a 'dev' dependency group with specific versions for various development tools.
- Updated sdist and wheels entries to include upload timestamps for better tracking.
- Adjusted numpy dependencies to specify versions based on Python version markers.

* feat: bump versions to 1.14.0a1
2026-04-06 04:32:20 -03:00
Lorenze Jay
bce10f5978 fix: ensure output directory exists before writing in flow template (#5291)
The `save_content` method wrote to `output/post.md` without ensuring the
`output/` directory exists, causing a FileNotFoundError when the directory
hasn't been created by another step.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 22:21:18 -07:00
Lorenze Jay
d2e57e375b updating poem to content use case (#5286)
* updating poem to content use case

* addressing CVE-2026-35030
2026-04-05 22:05:02 -07:00
iris-clawd
d039a075aa docs: add AMP Training Tab guide (#5083)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* docs: add AMP Training Tab guide for enterprise deployments

* docs: add training guide translations for ar, ko, pt-BR

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Alex <alex@crewai.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-03 17:09:31 -03:00
Greyson LaLonde
ce99312db1 chore: add exclude-newer = 3 days to all pyproject.toml files 2026-04-04 02:02:58 +08:00
Greyson LaLonde
c571620f8c fix: remove seo indexing field causing Arabic page rendering
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
2026-04-04 01:34:23 +08:00
iris-clawd
931f3556cf ci: add vulnerability scanning with pip-audit and Snyk (#5242)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* ci: add vulnerability scanning with pip-audit and Snyk

Add a new GitHub Actions workflow that runs on PRs, pushes to main, and weekly:

- pip-audit: scans all Python dependencies (direct + transitive) against
  PyPI Advisory DB and OSV for known CVEs. Outputs JSON report as artifact
  and posts results to the job summary.
- Snyk: optional enterprise-grade scanning (gated behind SNYK_ENABLED
  repo variable and SNYK_TOKEN secret). Runs on high+ severity and
  monitors main branch.

This addresses the need for automated pre-release vulnerability scanning
to catch dependency CVEs before cutting releases.

* ci: pin Snyk action to @v1 tag and remove continue-on-error

- Pin snyk/actions/python from @master to @v1 to prevent supply chain
  risk from mutable branch references (matches convention of other
  actions in the repo using versioned tags)
- Remove continue-on-error on the Snyk check step so high+ severity
  vulnerabilities actually fail the build

* ci: fail build when pip-audit crashes without producing a report

If pip-audit exits abnormally without writing pip-audit-report.json,
the Display Results step now emits an error annotation and exits 1
instead of silently passing.

* ci: fix pip-audit failing on local packages

Replace --strict with --skip-editable to avoid pip-audit failing when
it encounters local/private packages (e.g. crewai-devtools) that are
not published on PyPI. The --skip-editable flag tells pip-audit to
skip packages installed in editable/development mode while still
auditing all published dependencies.

* fix: bump vulnerable dependencies and ignore unfixable CVEs

Dependency upgrades (via uv lock --upgrade-package):
- aiohttp 3.13.3 → 3.13.5 (fixes 10 CVEs)
- cryptography 46.0.5 → 46.0.6 (fixes CVE-2026-34073)
- pygments 2.19.2 → 2.20.0 (fixes CVE-2026-4539)
- onnx 1.20.1 → 1.21.0 (fixes 6 CVEs)
- couchbase 4.5.0 → 4.6.0 (fixes PYSEC-2023-235)

Temporarily ignored CVEs (cannot be fixed without upstream changes):
- CVE-2025-69872 (diskcache): no fix available, latest version
- CVE-2026-25645 (requests): needs 2.33.0, blocked by crewai-tools pin
- CVE-2026-27448/27459 (pyopenssl): needs 26.0.0, blocked by
  snowflake-connector-python pin
- PYSEC-2023-235 (couchbase): advisory not yet updated for 4.6.0

* chore: remove accidentally committed egg-info files

* ci: remove Snyk job, pip-audit is sufficient

pip-audit covers Python dependency CVE scanning against PyPI Advisory DB
and OSV, which is all we need for pre-release checks. Snyk adds
complexity (account setup, token management) without meaningful
additional coverage for this use case.

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-04-03 01:44:44 -03:00
Lorenze Jay
914776b7ed docs: update changelog and version for v1.13.0 (#5247)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-04-02 16:16:16 -07:00
Lorenze Jay
6ef6fada4d feat: bump versions to 1.13.0 (#5246) 2026-04-02 16:12:03 -07:00
Lucas Gomide
1b7be63b60 Revert "refactor: remove unused and methods from (#5172)" (#5243)
* Revert "refactor: remove unused  and  methods from (#5172)"

This reverts commit bb9bcd6823.

* test: fix tests
2026-04-02 18:02:59 -04:00
alex-clawd
59aa5b2243 fix: add tool repository credentials to crewai install (#5224)
* fix: add tool repository credentials to crewai install

crewai install (uv sync) was failing with 401 Unauthorized when the
project depends on tools from a private package index (e.g. AMP tool
repository). The credentials were already injected for 'crewai run'
and 'crewai tool publish' but were missing from 'crewai install'.

Reads [tool.uv.sources] from pyproject.toml and injects UV_INDEX_*
credentials into the subprocess environment, matching the pattern
already used in run_crew.py.

* refactor: extract duplicated credential-building into utility function

Create build_env_with_all_tool_credentials() in utils.py to consolidate
the ~10-line block that reads [tool.uv.sources] from pyproject.toml and
calls build_env_with_tool_repository_credentials for each index.

This eliminates code duplication across install_crew.py, run_crew.py,
and cli.py, reducing the risk of inconsistent bug fixes.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: add debug logging for credential errors instead of silent swallow

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-02 17:56:36 -03:00
alex-clawd
2e2fae02d2 fix: add tool repository credentials to uv build in tool publish (#5223)
* fix: add tool repository credentials to uv build in tool publish

When running 'uv build' during tool publish, the build process now has access
to tool repository credentials. This mirrors the pattern used in run_crew.py,
ensuring private package indexes are properly authenticated during the build.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: add env kwarg to subprocess.run mock assertions in publish tests

The actual code passes env= to subprocess.run but the test assertions
were missing this parameter, causing assertion failures.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-02 17:52:08 -03:00
Greyson LaLonde
804c26bd01 feat: add RuntimeState RootModel for unified state serialization 2026-04-03 03:46:55 +08:00
Greyson LaLonde
4e46913045 fix: pass fingerprint metadata via config instead of tool args (#5216)
security_context was being injected into tool arguments by
_add_fingerprint_metadata(), causing Pydantic validation errors
(extra_forbidden) on MCP and integration tools with strict schemas.

Move fingerprint data to the `config` parameter that invoke/ainvoke
already accept, keeping it available to consumers without polluting
the tool args namespace.

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-04-02 12:21:02 -07:00
Lorenze Jay
335130cb15 feat: enhance event listener with new telemetry spans for skill and memory events (#5240)
- Added telemetry spans for various skill events: discovery, loading, activation, and load failure.
- Introduced telemetry spans for memory events: save, query, and retrieval completion.
- Updated event listener to include new MCP tool execution and connection events with telemetry tracking.
2026-04-02 10:38:02 -07:00
iris-clawd
186ea77c63 docs: Add coding agent skills demo video to getting started pages (#5237)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
* docs: Add coding agent skills demo video to getting started pages

Add Loom demo video embed showing how to build CrewAI agents and flows
using coding agent skills. Added to introduction, quickstart, and
installation pages across all languages (en, ko, pt-BR, ar).

* docs: update coding skills description with install instructions

Replace demo description text with actionable install copy across
all languages (en, ko, pt-BR, ar) in introduction, quickstart, and
installation pages.
2026-04-02 10:11:02 -07:00
Greyson LaLonde
9e51229e6c chore: add ExecutionContext model for state 2026-04-02 23:44:21 +08:00
Greyson LaLonde
247d623499 docs: update changelog and version for v1.13.0a7 2026-04-02 22:21:17 +08:00
Greyson LaLonde
c260f3e19f feat: bump versions to 1.13.0a7 2026-04-02 22:16:05 +08:00
Greyson LaLonde
d9cf7dda31 chore: type remaining Any fields on BaseAgent and Crew 2026-04-02 21:17:35 +08:00
alex-clawd
c14abf1758 fix: add GPT-5 and o-series to multimodal vision prefixes (#5183)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: add GPT-5, o3, o4-mini to multimodal vision prefixes

Added verified vision-capable models:
- gpt-5 (all GPT-5 family — confirmed multimodal via openai.com)
- o3, o3-pro (full multimodal — openai.com/index/thinking-with-images)
- o4-mini, o4 (full multimodal)

Added text-only exclusion list to prevent false positives:
- o3-mini (text-only, replaced by o4-mini)
- o1-mini (text-only)
- o1-preview (text-only)

Existing prefixes unchanged (Claude 3+, Gemini, GPT-4).

* fix: add o1 to vision prefixes + ruff format

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: guard _sync_executor access in test utils for lazy-init event bus

* fix: expand vision model coverage — Claude 5, Grok, Pixtral, Qwen VL, LLaVA

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* ci: retrigger — flaky test_hierarchical_verbose_false_manager_agent (ConnectionError)

* fix: remove hallucinated claude-5 models from vision prefixes — verified against official docs

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2026-04-01 18:08:37 -03:00
Greyson LaLonde
f10d320ddb feat(a2ui): add A2UI extension with v0.8/v0.9 support, schemas, and docs
Introduce the A2UI extension for declarative UI generation, including
support for both v0.8 and v0.9 protocol specs. Add A2UI content type
integration in A2A utils, along with schema definitions, catalog models,
and client extension improvements.

Enhance models with explicit defaults, field descriptions, and ConfigDict,
and improve typing and instance state handling across the extension.

Add schema conformance tests and align test structure.

Add and register A2UI documentation, including extension guide and
navigation updates.
2026-04-02 04:46:07 +08:00
João Moura
258f31d44c docs: update changelog and version for v1.13.0a6 (#5214) 2026-04-01 14:26:07 -03:00
João Moura
68720fd4e5 feat: bump versions to 1.13.0a6 (#5213) 2026-04-01 14:23:44 -03:00
alex-clawd
3132910084 perf: reduce framework overhead — lazy event bus, skip tracing when disabled (#5187)
* perf: reduce framework overhead for NVIDIA benchmarks

- Lazy initialize event bus thread pool and event loop on first emit()
  instead of at import time (~200ms savings)
- Skip trace listener registration (50+ handlers) when tracing disabled
- Skip trace prompt in non-interactive contexts (isatty check) to avoid
  20s timeout in CI/Docker/API servers
- Skip flush() when no events were emitted (avoids 30s timeout waste)
- Add _has_pending_events flag to track if any events were emitted
- Add _executor_initialized flag for lazy init double-checked locking

All existing behavior preserved when tracing IS enabled. No public APIs
changed - only conditional guards added.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: address PR review comments — tracing override, executor init order, stdin guard, unused import

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* style: fix ruff formatting in trace_listener.py and utils.py

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Iris Clawd <iris@crewai.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-04-01 14:17:57 -03:00
Lucas Gomide
c8f3a96779 docs: fix RBAC permission levels to match actual UI options (#5210)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-04-01 10:35:06 -04:00
João Moura
18ada25f01 docs: update changelog and version for v1.13.0a5 (#5200)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-04-01 04:00:09 -03:00
João Moura
146da8d73a feat: bump versions to 1.13.0a5 (#5199) 2026-04-01 03:59:07 -03:00
Greyson LaLonde
98c6109214 docs: update changelog and version for v1.13.0a4
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-04-01 05:08:12 +08:00
Greyson LaLonde
54a9174c12 feat: bump versions to 1.13.0a4 2026-04-01 05:01:29 +08:00
Greyson LaLonde
c26ae969b3 docs: update changelog and version for v1.13.0a3 2026-04-01 04:16:25 +08:00
Greyson LaLonde
205555b786 feat: bump versions to 1.13.0a3 2026-04-01 04:02:29 +08:00
Greyson LaLonde
d6714a0e60 refactor: convert Flow to Pydantic BaseModel 2026-04-01 03:48:41 +08:00
dependabot[bot]
107bc7f7be chore(deps): bump the security-updates group across 1 directory with 2 updates (#5088)
Bumps the security-updates group with 2 updates in the / directory: [nltk](https://github.com/nltk/nltk) and [pypdf](https://github.com/py-pdf/pypdf).


Updates `nltk` from 3.9.3 to 3.9.4
- [Changelog](https://github.com/nltk/nltk/blob/develop/ChangeLog)
- [Commits](https://github.com/nltk/nltk/compare/3.9.3...3.9.4)

Updates `pypdf` from 6.9.1 to 6.9.2
- [Release notes](https://github.com/py-pdf/pypdf/releases)
- [Changelog](https://github.com/py-pdf/pypdf/blob/main/CHANGELOG.md)
- [Commits](https://github.com/py-pdf/pypdf/compare/6.9.1...6.9.2)

---
updated-dependencies:
- dependency-name: nltk
  dependency-version: 3.9.4
  dependency-type: indirect
  dependency-group: security-updates
- dependency-name: pypdf
  dependency-version: 6.9.2
  dependency-type: indirect
  dependency-group: security-updates
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-03-31 14:03:42 -05:00
iris-clawd
b1f49b1356 docs: fix inaccuracies in agent-capabilities across all languages (#5191)
- Apps run locally (with CREWAI_PLATFORM_INTEGRATION_TOKEN env var), not remotely
- Apps auth is an integration token, not OAuth
- Updated comparison tables and card descriptions in en, pt-BR, ko, ar
2026-03-31 15:00:00 -03:00
iris-clawd
accae5ca43 docs: Add Agent Capabilities overview and improve Skills documentation (#5189)
* docs: add Agent Capabilities overview page and improve Skills docs

- New 'Agent Capabilities' page explaining all 5 extension types (Tools, MCPs, Apps, Skills, Knowledge) with comparison table and decision guide
- Rewrite Skills page with practical examples showing Skills + Tools patterns, common FAQ, and Skills vs Knowledge comparison
- Add cross-reference callout on Tools page linking to the capabilities overview
- Add agent-capabilities to Core Concepts navigation (after agents)

* docs: add pt-BR and ko translations for agent-capabilities and updated skills/tools

* docs: add Arabic (ar) translations for agent-capabilities and updated skills/tools
2026-03-31 14:47:38 -03:00
Lucas Gomide
68e943be68 feat: emit token usage data in LLMCallCompletedEvent 2026-04-01 00:18:36 +08:00
Greyson LaLonde
3283a00e31 fix(deps): cap lancedb below 0.30.1 for Windows compatibility
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
lancedb 0.30.1 dropped the win_amd64 wheel, breaking installation on
Windows. Pin to <0.30.1 so uv resolves to a version that still ships
Windows binaries.
2026-03-31 16:59:45 +08:00
Greyson LaLonde
dfc0f9a317 refactor: replace InstanceOf[T] with plain type annotations
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* refactor: replace InstanceOf[T] with plain type annotations

InstanceOf[] is a Pydantic validation wrapper that adds runtime
isinstance checks. Plain type annotations are sufficient here since
the models already use arbitrary_types_allowed or the types are
BaseModel subclasses.

* refactor: convert BaseKnowledgeStorage to BaseModel

* fix: update tests for BaseKnowledgeStorage BaseModel conversion

* fix: correct embedder config structure in test
2026-03-31 08:11:21 +08:00
Greyson LaLonde
ef79456968 chore: remove unused third_party LLM directory
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-03-31 07:33:56 +08:00
Greyson LaLonde
6c7ea422e7 refactor: convert LLM classes to Pydantic BaseModel 2026-03-31 07:07:11 +08:00
Lorenze Jay
bb9bcd6823 refactor: remove unused and methods from (#5172)
This commit cleans up the  class by removing the  and  methods, which are no longer needed. The changes help streamline the code and improve maintainability.
2026-03-30 15:01:58 -07:00
Lucas Gomide
ac14b9127e fix: handle GPT-5.x models not supporting the stop API parameter (#5144)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
GPT-5.x models reject the `stop` parameter at the API level with "Unsupported parameter: 'stop' is not supported with this model". This breaks CrewAI executions when routing through LiteLLM (e.g. via
OpenAI-compatible gateways like Asimov), because the LiteLLM fallback path always includes `stop` in the API request params.

The native OpenAI provider was unaffected because it never sends `stop` to the API — it applies stop words client-side via `_apply_stop_words()`. However, when the request goes through LiteLLM (custom endpoints, proxy gateways),
`stop` is sent as an API parameter and GPT-5.x rejects it.

Additionally, the existing retry logic that catches this error only matched the OpenAI API error format ("Unsupported parameter") but missed
LiteLLM's own pre-validation error format ("does not support parameters"), so the self-healing retry never triggered for LiteLLM-routed calls.
2026-03-30 11:36:51 -04:00
Thiago Moretto
98b7626784 feat: extract and publish tool metadata to AMP (#4298)
* Exporting tool's metadata to AMP - initial work

* Fix payload (nest under `tools` key)

* Remove debug message + code simplification

* Priting out detected tools

* Extract module name

* fix: address PR review feedback for tool metadata extraction

- Use sha256 instead of md5 for module name hashing (lint S324)
- Filter required list to match filtered properties in JSON schema

* fix: Use sha256 instead of md5 for module name hashing (lint S324)

- Add missing mocks to metadata extraction failure test

* style: fix ruff formatting

* fix: resolve mypy type errors in utils.py

* fix: address bot review feedback on tool metadata

- Use `is not None` instead of truthiness check so empty tools list
  is sent to the API rather than being silently dropped as None
- Strip __init__ suffix from module path for tools in __init__.py files
- Extend _unwrap_schema to handle function-before, function-wrap, and
  definitions wrapper types

* fix: capture env_vars declared with Field(default_factory=...)

When env_vars uses default_factory, pydantic stores a callable in the
schema instead of a static default value. Fall back to calling the
factory when no static default is present.

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-03-30 09:21:53 -04:00
iris-clawd
e21c506214 docs: Add comprehensive SSO configuration guide (#5152)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* docs: add comprehensive SSO configuration guide

Add SSO documentation page covering all supported identity providers
for both SaaS (AMP) and Factory deployments.

Includes:
- Provider overview (WorkOS, Entra ID, Okta, Auth0, Keycloak)
- SaaS vs Factory SSO availability
- Step-by-step setup guides per provider with env vars
- CLI authentication via Device Authorization Grant
- RBAC integration overview
- Troubleshooting common SSO issues
- Complete environment variables reference

Placed in the Manage nav group alongside RBAC.

* fix: add key icon to SSO docs page

* fix: broken links in SSO docs (installation, configuration)
2026-03-28 13:15:34 +08:00
Greyson LaLonde
9fe0c15549 docs: update changelog and version for v1.13.0rc1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
2026-03-27 11:30:45 +08:00
Greyson LaLonde
78d8ddb649 feat: bump versions to 1.13.0rc1 2026-03-27 11:26:04 +08:00
Greyson LaLonde
1b2062009a docs: update changelog and version for v1.13.0a2
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-03-27 04:05:32 +08:00
Greyson LaLonde
886aa4ba8f feat: bump versions to 1.13.0a2 2026-03-27 04:00:59 +08:00
Greyson LaLonde
5bec000b21 feat: auto-update deployment test repo during release
After PyPI publish, clones crewAIInc/crew_deployment_test, bumps the
crewai[tools] pin to the new version, regenerates uv.lock, and pushes
to main. Includes retry logic for CDN propagation delays.
2026-03-27 03:54:10 +08:00
Greyson LaLonde
2965384907 feat: improve enterprise release resilience and UX
- Add --skip-to-enterprise flag to resume just Phase 3 after a failure
- Add --prerelease=allow to uv sync for alpha/beta/rc versions
- Retry uv sync up to 10 times to handle PyPI CDN propagation delay
- Update pyproject.toml [project] version field (fixes apps/api version)
- Print PR URL after creating enterprise bump PR
2026-03-27 03:36:56 +08:00
Greyson LaLonde
032ef06ef6 docs: update changelog and version for v1.13.0a1 2026-03-27 03:07:26 +08:00
Greyson LaLonde
0ce9567cfc feat: bump versions to 1.13.0a1 2026-03-27 03:00:29 +08:00
Greyson LaLonde
d7252bfee7 fix: pin Node to LTS 22 in docs broken links workflow
Mintlify doesn't support Node 25+, and `node-version: latest` was
pulling 25.8.2 causing the workflow to fail.
2026-03-27 02:36:11 +08:00
Greyson LaLonde
10fc3796bb fix: bust uv cache for freshly published packages in enterprise release 2026-03-27 02:21:31 +08:00
iris-clawd
52249683a7 docs: comprehensive RBAC permissions matrix and deployment guide (#5112)
- Add full feature permissions matrix (11 features × permission levels)
- Document Owner vs Member default permissions
- Add deployment guide: what permissions are needed to deploy from GitHub or Zip
- Document entity-level permissions (deployment permission types: run, traces, manage_settings, HITL, full_access)
- Document entity RBAC for env vars, LLM connections, and Git repositories
- Add common role patterns: Developer, Viewer/Stakeholder, Ops/Platform Admin
- Add quick-reference table for minimum deployment permissions

Addresses user feedback that RBAC was too restrictive and unclear:
members didn't know which permissions to configure for a developer profile.
2026-03-26 12:30:17 -04:00
João Moura
6193e082e1 docs: update changelog and version for v1.12.2 (#5103)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-03-26 03:54:26 -03:00
João Moura
33f33c6fcc feat: bump versions to 1.12.2 (#5101) 2026-03-26 03:33:10 -03:00
alex-clawd
74976b157d fix: preserve method return value as flow output for @human_feedback with emit (#5099)
* fix: preserve method return value as flow output for @human_feedback with emit

When a @human_feedback decorated method with emit= is the final method in a
flow (no downstream listeners triggered), the flow's final output was
incorrectly set to the collapsed outcome string (e.g., 'approved') instead
of the method's actual return value (e.g., a state dict).

Root cause: _process_feedback() returns the collapsed_outcome string when
emit is set, and this string was being stored as the method's result in
_method_outputs.

The fix:
1. In human_feedback.py: After _process_feedback, stash the real method_output
   on the flow instance as _human_feedback_method_output when emit is set.

2. In flow.py: After appending a method result to _method_outputs, check if
   _human_feedback_method_output is set. If so, replace the last entry with
   the stashed real output and clear the stash.

This ensures:
- Routing still works correctly (collapsed outcome used for @listen matching)
- The flow's final result is the actual method return value
- If downstream listeners execute, their results become the final output

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* style: ruff format flow.py

* fix: use per-method dict stash for concurrency safety and None returns

Addresses review comments:
- Replace single flow-level slot with dict keyed by method name,
  safe under concurrent @human_feedback+emit execution
- Dict key presence (not value) indicates stashed output,
  correctly preserving None return values
- Added test for None return value preservation

---------

Co-authored-by: Joao Moura <joao@crewai.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-26 03:28:17 -03:00
Greyson LaLonde
bd03f6cf64 feat: add enterprise release phase to devtools release
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-26 12:22:37 +08:00
Rip&Tear
a91cd1a7d7 Revise security policy and reporting instructions (#5096)
* Revise security policy and reporting instructions

Updated the security reporting process and contact details.

* Update .github/security.md
---------
2026-03-26 10:50:21 +08:00
João Moura
66dee3195f docs: update changelog and version for v1.12.1 (#5095) 2026-03-25 22:52:11 -03:00
João Moura
034f576dc0 feat: bump versions to 1.12.1 (#5094)
* chore: bump version to 1.12.1 across all modules

* feat: bump versions to 1.12.1
2026-03-25 22:45:33 -03:00
Lucas Gomide
918654318b feat: add request_id to HumanFeedbackRequestedEvent (#5092)
* feat: add request_id to HumanFeedbackRequestedEvent

Allow platforms to attach a correlation identifier to human feedback requests so downstream consumers can deterministically match spans to their corresponding feedback records

* feat: add request_id to HumanFeedbackReceivedEvent for correlation

Without request_id on the received event, consumers cannot correlate
a feedback response back to its originating request. Both sides of the
request/response pair need the correlation identifier.

---------

Co-authored-by: Alex <alex@crewai.com>
2026-03-25 22:43:24 -03:00
João Moura
371e6cfd11 docs: update changelog and version for v1.12.0 (#5091) 2026-03-25 22:07:28 -03:00
João Moura
6fd70ce6e5 chore: bump version to 1.14.0 across all modules (#5090)
* chore: bump version to 1.14.0 across all modules

* chore: downgrade version to 1.12.0 across all modules
2026-03-25 22:03:37 -03:00
alex-clawd
c183b77991 fix: address Copilot review on OpenAI-compatible providers (#5042) (#5089)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
- Delegate supports_function_calling() to parent (handles o1 models via OpenRouter)
- Guard empty env vars in base_url resolution
- Fix misleading comment about model validation rules
- Remove unused MagicMock import
- Use 'is not None' for env var restoration in tests

Co-authored-by: Joao Moura <joao@crewai.com>
2026-03-25 18:22:13 -03:00
Greyson LaLonde
b5a0d6e709 docs: update changelog and version for v1.12.0a3 2026-03-26 04:17:37 +08:00
Greyson LaLonde
454156cff9 feat: bump versions to 1.12.0a3 2026-03-26 04:12:49 +08:00
Tiago Freire
d86707da3d Fix: bad credentials for traces batch push (404) (#4947)
## Summary

### Core fixes

<details>
<summary><b>Fix silent 404 cascade on trace event send</b></summary>

When `_initialize_backend_batch` failed, `trace_batch_id` was left populated with a client-generated UUID never registered server-side. All subsequent event sends hit a non-existent batch endpoint and returned 404. Now all three failure paths (None response, non-2xx status, exception) clear `trace_batch_id`.
</details>

<details>
<summary><b>Fix first-time deferred batch init silently skipped</b></summary>

First-time users have `is_tracing_enabled_in_context() = False` by design. This caused `_initialize_backend_batch` to return early without creating the batch, and `finalize_batch` to skip finalization (same guard). The first-time handler now passes `skip_context_check=True` to bypass both guards, calls `_finalize_backend_batch` directly, gates `backend_initialized` on actual success, checks `_send_events_to_backend` return status (marking batch as failed on 500), captures event count/duration/batch ID before they're consumed by send/finalize, and cleans up all singleton state via `_reset_batch_state()` on every exit path.
</details>

<details>
<summary><b>Sync <code>is_current_batch_ephemeral</code> on batch creation success</b></summary>

When the batch is successfully created on the server, `is_current_batch_ephemeral` is now synced with the actual `use_ephemeral` value used. This prevents endpoint mismatches where the batch was created on one endpoint but events and finalization were sent to a different one, resulting in 404.
</details>

<details>
<summary><b>Route <code>mark_trace_batch_as_failed</code> to correct endpoint for ephemeral batches</b></summary>

`mark_trace_batch_as_failed` always routed to the non-ephemeral endpoint (`/tracing/batches/{id}`), causing 404s when called on ephemeral batches — the same class of endpoint mismatch this PR aims to fix. Added `mark_ephemeral_trace_batch_as_failed` to `PlusAPI` and a `_mark_batch_as_failed` helper on `TraceBatchManager` that routes based on `is_current_batch_ephemeral`.
</details>

<details>
<summary><b>Gate <code>backend_initialized</code> on actual init success (non-first-time path)</b></summary>

On the non-first-time path, `backend_initialized` was set to `True` unconditionally after `_initialize_backend_batch` returned. With the new failure-path cleanup that clears `trace_batch_id`, this created an inconsistent state: `backend_initialized=True` + `trace_batch_id=None`. Now set via `self.trace_batch_id is not None`.
</details>

### Resilience improvements

<details>
<summary><b>Retry transient failures on batch creation</b></summary>

`_initialize_backend_batch` now retries up to 2 times with 200ms backoff on transient failures (None response, 5xx, network errors). Non-transient 4xx errors are not retried. The short backoff minimizes lock hold time on the non-first-time path where `_batch_ready_cv` is held.
</details>

<details>
<summary><b>Fall back to ephemeral on server auth rejection</b></summary>

When the non-ephemeral endpoint returns 401/403 (expired token, revoked credentials, key rotation), the client automatically switches to ephemeral tracing instead of losing traces. The fallback forwards `skip_context_check` and is guarded against infinite recursion — if ephemeral also fails, `trace_batch_id` is cleared normally.
</details>

<details>
<summary><b>Fix action-event race initializing batch as non-ephemeral</b></summary>

`_handle_action_event` called `batch_manager.initialize_batch()` directly, defaulting `use_ephemeral=False`. When a `DefaultEnvEvent` or `LLMCallStartedEvent` fired before `CrewKickoffStartedEvent` in the thread pool, the batch was locked in as non-ephemeral. Now routes through `_initialize_batch()` which computes `use_ephemeral` from `_check_authenticated()`.
</details>

<details>
<summary><b>Guard <code>_mark_batch_as_failed</code> against cascading network errors</b></summary>

When `_finalize_backend_batch` failed with a network error (e.g. `[Errno 54] Connection reset by peer`), the exception handler called `_mark_batch_as_failed` — which also makes an HTTP request on the same dead connection. That second failure was unhandled. Now wrapped in a try/except so it logs at debug level instead of propagating.
</details>

<details>
<summary><b>Design decision: first-time users always use ephemeral</b></summary>

First-time trace collection **always creates ephemeral batches**, regardless of authentication status. This is intentional:

1. **The first-time handler UX is built around ephemeral traces** — it displays an access code, a 24-hour expiry link, and opens the browser to the ephemeral trace viewer. Non-ephemeral batches don't produce these artifacts, so the handler would fall through to the "Local Traces Collected" fallback even when traces were successfully sent.

2. **The server handles account linking automatically** — `LinkEphemeralTracesJob` runs on user signup and migrates ephemeral traces to permanent records. Logged-in users can access their traces via their dashboard regardless.

3. **Checking auth during batch setup broke event collection** — moving `_check_authenticated()` into `_initialize_batch` caused the batch initialization to fail silently during the flow/crew start event handler, preventing all event collection. Keeping the first-time path fast and side-effect-free preserves event collection.

The auth check is deferred to the non-first-time path (second run onwards), where `is_tracing_enabled_in_context()` is `True` and the normal tracing pipeline handles everything — including the 401/403 ephemeral fallback.
</details>


### Manual tests


<details>
<summary><b>Matrix</b></summary>

| Scenario | First run | Second run |
|----------|-----------|------------|
| Logged out, fresh `.crewai_user.json` | Ephemeral trace created, URL returned | Ephemeral trace created, URL returned |
| Logged in, fresh `.crewai_user.json` | Ephemeral trace created, URL returned | Trace batch finalized, URL returned |
| Flow execution | Tested with `poem_flow` | Tested with `poem_flow` |
| Crew execution | Tested with `hitl_crew` | Tested with `hitl_crew` |
</details>
2026-03-25 16:00:05 -04:00
Greyson LaLonde
1956471086 fix: resolve multiple bugs in HITL flow system 2026-03-26 03:33:03 +08:00
Greyson LaLonde
4d1c041cc1 docs: update changelog and version for v1.12.0a2 2026-03-25 23:54:52 +08:00
Greyson LaLonde
2267b96e89 feat: bump versions to 1.12.0a2 2026-03-25 23:49:12 +08:00
Greyson LaLonde
1cc251b4b8 feat: add Qdrant Edge storage backend for memory system 2026-03-25 23:42:09 +08:00
Greyson LaLonde
90caa62158 chore: run ruff check and format on all files in CI
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-03-25 20:55:03 +08:00
Greyson LaLonde
74fb23aaa4 docs: update changelog and version for v1.12.0a1 2026-03-25 20:14:39 +08:00
Greyson LaLonde
b78ed655ea feat: bump versions to 1.12.0a1 2026-03-25 20:06:13 +08:00
Greyson LaLonde
6f58b63e5d feat: add docs-check command to analyze changes and generate docs with translations 2026-03-25 19:59:14 +08:00
Greyson LaLonde
a49f9f982b refactor: deduplicate sync/async task execution and kickoff in agent 2026-03-25 19:39:42 +08:00
nicoferdi96
62bc27826d fix: agent memory saving
Fix: Add a remember_many() method to the MemoryScope class that delegates to self._memory.remember_many(...) with the scoped path, following the exact same pattern as the existing remember() method.

Problem: When you pass memory=memory.scope("/agent/...") to an Agent, CrewAI's internal code calls remember_many() after every task to persist results. But MemoryScope never implemented remember_many() — only the parent Memory class has it.

Symptom: [ERROR]: Failed to save kickoff result to memory: 'MemoryScope' object has no attribute 'remember_many' — memories are silently never saved after agent tasks.
2026-03-25 19:20:30 +08:00
Greyson LaLonde
185b69b83b docs: add CONTRIBUTING.md 2026-03-25 16:13:55 +08:00
Greyson LaLonde
eb255584b4 feat: add arabic language support to changelog and release tooling 2026-03-25 15:55:05 +08:00
Greyson LaLonde
f5b3b2a355 docs: add modern standard arabic translation of all documentation 2026-03-25 15:44:02 +08:00
alex-clawd
b890ac0dd0 fix: use __router_paths__ for listener+router methods in FlowMeta (#5064)
When a method has both @listen and @human_feedback(emit=[...]),
the FlowMeta metaclass registered it as a router but only used
get_possible_return_constants() to detect paths. This fails for
@human_feedback methods since the paths come from the decorator's
emit param, not from return statements in the source code.

Now checks __router_paths__ first (set by @human_feedback), then
falls back to source code analysis for plain @router methods.

This was causing missing edges in the flow serializer output —
e.g. the whitepaper generator's review_infographic -> handle_cancelled,
send_slack_notification, classify_feedback edges were all missing.

Adds test: @listen + @human_feedback(emit=[...]) generates correct
router edges in serialized output.

Co-authored-by: Joao Moura <joao@crewai.com>
2026-03-25 03:42:39 -03:00
Greyson LaLonde
cb7cd12d4e fix: resolve mypy errors in crewai-files and add all packages to CI type checks 2026-03-25 13:44:57 +08:00
Greyson LaLonde
d955203e55 ci: add crewai-tools to mypy strict type checks 2026-03-25 13:29:29 +08:00
Greyson LaLonde
25305e688f chore: remove outdated BUILDING_TOOLS.md 2026-03-25 13:21:16 +08:00
Greyson LaLonde
26953c88c2 fix: resolve all strict mypy errors across crewai-tools package 2026-03-25 13:11:54 +08:00
Greyson LaLonde
8a1424534e ci: run mypy on full package instead of changed files only
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-25 07:05:57 +08:00
Greyson LaLonde
b53c08812d fix: use None check instead of isinstance for memory in human feedback learn 2026-03-25 06:40:25 +08:00
Greyson LaLonde
ec8d444cfc fix: resolve all mypy errors across crewai package 2026-03-25 06:03:43 +08:00
iris-clawd
8d1edd5d65 fix: pin litellm upper bound to last tested version (1.82.6) (#5044)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
The litellm optional dependency had a wide upper bound (<3) that allowed
any future litellm release to be installed automatically. This means
breaking changes in new litellm versions could affect customers immediately.

Pins the upper bound to <=1.82.6 (current latest known-good version).
When newer litellm versions are tested and validated, bump this bound
explicitly.
2026-03-24 09:38:12 -07:00
alex-clawd
7f5ffce057 feat: native OpenAI-compatible providers (OpenRouter, DeepSeek, Ollama, vLLM, Cerebras, Dashscope) (#5042)
* feat: add native OpenAI-compatible providers (OpenRouter, DeepSeek, Ollama, vLLM, Cerebras, Dashscope)

Add a data-driven OpenAI-compatible provider system that enables
native support for multiple third-party APIs that implement the
OpenAI API specification.

New providers:
- OpenRouter: 500+ models via openrouter.ai
- DeepSeek: deepseek-chat, deepseek-coder, deepseek-reasoner
- Ollama: local models (llama3, mistral, codellama, etc.)
- hosted_vllm: self-hosted vLLM servers
- Cerebras: ultra-fast inference
- Dashscope: Alibaba Qwen models (qwen-turbo, qwen-max, etc.)

Architecture:
- Single OpenAICompatibleCompletion class extends OpenAICompletion
- ProviderConfig dataclass stores per-provider settings
- Registry dict makes adding new providers a single config entry
- Handles provider-specific quirks (OpenRouter headers, Ollama
  base URL normalization, optional API keys)

Usage:
  LLM(model="deepseek/deepseek-chat")
  LLM(model="ollama/llama3")
  LLM(model="openrouter/anthropic/claude-3-opus")
  LLM(model="llama3", provider="ollama")

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: add is_litellm=True to tests that test litellm-specific methods

Tests for _get_custom_llm_provider and _validate_call_params used
openrouter/ model prefix which now routes to native provider.
Added is_litellm=True to force litellm path since these test
litellm-specific internals.

---------

Co-authored-by: Joao Moura <joao@crewai.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-24 12:05:43 -03:00
iris-clawd
724ab5c5e1 fix: correct litellm quarantine wording in docs (#5041)
Removed language implying the quarantine is resolved and removed
date-specific references so the docs stay evergreen.
2026-03-24 11:43:51 -03:00
alex-clawd
82a7c364c5 refactor: decouple internal plumbing from litellm (token counting, callbacks, feature detection, errors) (#5040)
- Token counting: Make TokenCalcHandler standalone class that conditionally
  inherits from litellm.CustomLogger when litellm is available, works as
  plain object when not installed

- Callbacks: Guard set_callbacks() and set_env_callbacks() behind
  LITELLM_AVAILABLE checks - these only affect the litellm fallback path,
  native providers emit events via base_llm.py

- Feature detection: Guard supports_function_calling(), supports_stop_words(),
  and _validate_call_params() behind LITELLM_AVAILABLE checks with sensible
  defaults (True for function calling/stop words since all modern models
  support them)

- Error types: Replace litellm.exceptions.ContextWindowExceededError catches
  with pattern-based detection using LLMContextLengthExceededError._is_context_limit_error()

This decouples crewAI's internal infrastructure from litellm, allowing the
native providers (OpenAI, Anthropic, Azure, Bedrock, Gemini) to work without
litellm installed. The litellm fallback for niche providers still works when
litellm IS installed.

Co-authored-by: Joao Moura <joao@crewai.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-24 11:35:05 -03:00
iris-clawd
36702229d7 docs: add guide for using CrewAI without LiteLLM (#5039) 2026-03-24 11:19:02 -03:00
Greyson LaLonde
b266cf7a3e ci: add PR size and title checks, configure commitizen
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-03-24 19:45:07 +08:00
Greyson LaLonde
c542cc9f70 fix: raise value error on no file support 2026-03-24 19:21:19 +08:00
Greyson LaLonde
aced3e5c29 feat(cli): add logout command and fix all mypy errors in CLI
Add `crewai logout` command that clears auth tokens and user settings.
Supports `--reset` flag to also restore all CLI settings to defaults.

Add missing type annotations to all CLI command functions, DeployCommand
and TriggersCommand __init__ methods, and create_flow to resolve all
mypy errors. Remove unused assignments of void telemetry return values.
2026-03-24 19:14:24 +08:00
Greyson LaLonde
555ee462a3 feat: agent skills
introduce the agent skills standard for packaging reusable instructions that agents can discover and activate at runtime.                                                             

- skills defined via SKILL.md with yaml frontmatter and markdown body
- three-level progressive disclosure: metadata, instructions, resources
- filesystem discovery with directory name validation                                                         
- skill lifecycle events (discovery, loaded, activated, failed)
- crew-level skills resolved once and shared across agents                                                    
- skill context injected into both task execution and standalone kickoff
2026-03-24 19:03:35 +08:00
alex-clawd
dd9ae02159 feat: automatic root_scope for hierarchical memory isolation (#5035)
* feat: automatic root_scope for hierarchical memory isolation

Crews and flows now automatically scope their memories hierarchically.
The encoding flow's LLM-inferred scope becomes a sub-scope under the
structural root, preventing memory pollution across crews/agents.

Scope hierarchy:
  /crew/{crew_name}/agent/{agent_role}/{llm-inferred}
  /flow/{flow_name}/{llm-inferred}

Changes:
- Memory class: new root_scope field, passed through remember/remember_many
- EncodingFlow: prepends root_scope to resolved scope in both fast path
  (Group A) and LLM path (Group C/D)
- Crew: auto-sets root_scope=/crew/{sanitized_name} on memory creation
- Agent executor: extends crew root with /agent/{sanitized_role} per save
- Flow: auto-sets root_scope=/flow/{sanitized_name} on memory creation
- New utils: sanitize_scope_name, normalize_scope_path, join_scope_paths

Backward compatible — no root_scope means no prefix (existing behavior).
Old memories at '/' remain accessible.

51 new tests, all existing tests pass.

* ci: retrigger tests

* fix: don't auto-set root_scope on user-provided Memory instances

When users pass their own Memory instance to a Crew (memory=mem),
respect their configuration — don't auto-set root_scope.
Auto-scoping only applies when memory=True (Crew creates Memory).

Fixes: test_crew_memory_with_google_vertex_embedder which passes
Memory(embedder=...) to Crew and expects remember(scope='/test')
to produce scope '/test', not '/crew/crew/test'.

* fix: address 6 review comments — true scope isolation for reads, writes, and consolidation

1. Constrain similarity search to root_scope boundary (no cross-crew consolidation)
2. Remove unused self._root_scope from EncodingFlow
3. Apply root_scope to recall/list/info/reset (true read isolation)
4. Only extend agent root_scope when crew has one (backward compat)
5. Fix docstring example for sanitize_scope_name
6. Verify code comments match behavior

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Joao Moura <joao@crewai.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-24 02:56:10 -03:00
Lorenze Jay
949d7f1091 docs: update changelog and version for v1.11.1 (#5031)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-23 16:33:43 -07:00
Lorenze Jay
3b569b8da9 feat: bump versions to 1.11.1 (#5030) 2026-03-23 16:22:19 -07:00
Matt Aitchison
e88a8f2785 fix: bump pypdf, tinytag, and langchain-core for security fixes (#4989)
- pypdf ~=6.7.5 → ~=6.9.1 (CVE-2026-33123, CVE-2026-31826)
- tinytag ~=1.10.0 → ~=2.2.1 (CVE-2026-32889)
- langchain-core >=0.3.80,<1 → >=1.2.11,<2 (CVE-2026-26013)

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-03-23 15:24:26 -07:00
Lorenze Jay
85199e9ffc better serialization for human feedback in flow with models defined a… (#5029)
* better serialization for human feedback in flow with models defined as dicts

* linted

* linted

* fix and adjust tests
2026-03-23 14:43:43 -07:00
Daniel Barreto
c92de53da7 refactor(rag): replace urllib with requests in pdf loader (#5026)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
2026-03-23 12:47:39 -03:00
alex-clawd
1704ccdfa8 feat: add flow_structure() serializer for Flow class introspection (#5021)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
* feat: add flow_structure() serializer for Flow class introspection

Adds a new flow_serializer module that introspects a Flow class and returns
a JSON-serializable dictionary describing its complete graph structure.

This enables Studio UI to render visual flow graphs (analogous to how
crew_structure() works for Crews).

The serializer extracts:
- Method metadata (type, triggers, conditions, router paths)
- Edge graph (listen and route edges between methods)
- State schema (from Pydantic model if typed)
- Human feedback and Crew reference detection
- Flow input detection

Includes 23 comprehensive tests covering linear flows, routers,
AND/OR conditions, human feedback, crew detection, state schemas,
edge cases, and JSON serialization.

* fix: lint — ruff check + format compliance for flow_serializer

* fix: address review — PydanticUndefined bug, FlowCondition tuple handling, dead code cleanup, inheritance tests

1. Fix PydanticUndefined default handling (real bug) — required fields
   were serialized with sentinel value instead of null
2. Fix FlowCondition tuple type in _extract_all_methods_from_condition —
   tuple conditions now properly extracted
3. Remove dead get_flow_inputs branch that did nothing
4. Document _detect_crew_reference as best-effort heuristic
5. Add 2 inheritance tests (parent→child method propagation)

---------

Co-authored-by: Joao Moura <joao@crewai.com>
2026-03-23 02:31:00 -03:00
alex-clawd
09b84dd2b0 fix: preserve full LLM config across HITL resume for non-OpenAI providers (#4970)
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
When a flow with @human_feedback(llm=create_llm()) pauses for HITL and
later resumes:

1. The LLM object was being serialized to just a model string via
   _serialize_llm_for_context() (e.g. 'gemini/gemini-3.1-flash-lite-preview')
2. On resume, resume_async() was creating LLM(model=string) with NO
   credentials, project, location, safety_settings, or client_params
3. OpenAI worked by accident (OPENAI_API_KEY from env), but Gemini with
   service accounts broke

This fix:
- Stashes the live LLM object on the wrapper as _hf_llm attribute
- On resume, looks up the method and retrieves the live LLM if available
- Falls back to the serialized string for backward compatibility
- Preserves _hf_llm through FlowMethod wrapper decorators

Co-authored-by: Joao Moura <joao@crewai.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-20 18:42:28 -03:00
Greyson LaLonde
f13d307534 fix: pass cache_function from BaseTool to CrewStructuredTool 2026-03-20 16:04:52 -04:00
Lucas Gomide
8e427164ca docs: adding a lot of missinge vent listeners (#4990)
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-03-20 15:30:11 -04:00
Greyson LaLonde
6495aff528 refactor: replace Any-typed callback and model fields with serializable types 2026-03-20 15:18:50 -04:00
Greyson LaLonde
f7de8b2d28 fix(devtools): consolidate prerelease changelogs into stable releases
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-03-19 17:16:18 -04:00
Greyson LaLonde
8886f11672 docs: add publish custom tools guide with translations
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-03-19 11:15:56 -04:00
Rip&Tear
713fa7d01b fix: prevent path traversal in FileWriterTool (#4895)
* fix: add base_dir path containment to FileWriterTool

os.path.join does not prevent traversal — joining "./" with "../../../etc/cron.d/pwned"
resolves cleanly outside any intended scope. The tool also called os.makedirs on
the unvalidated path, meaning it would create arbitrary directory structures.

Adds a base_dir parameter that uses os.path.realpath() to resolve the final path
(including symlinks) before checking containment. Any filename or directory argument
that resolves outside base_dir is rejected before any filesystem operation occurs.

When base_dir is not set the tool behaves as before — only use that in fully
sandboxed environments.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: make directory relative to base_dir for better UX

When base_dir is set, the directory arg is now treated as a subdirectory
of base_dir rather than an absolute path. This means the LLM only needs
to specify a filename (and optionally a relative subdirectory) — it does
not need to repeat the base_dir path.

  FileWriterTool(base_dir="./output")
  → filename="report.txt"            writes to ./output/report.txt
  → filename="f.txt", directory="sub" writes to ./output/sub/f.txt

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: remove directory field from LLM schema when base_dir is set

When a developer sets base_dir, they control where files are written.
The LLM should only supply filename and content — not a directory path.

Adds ScopedFileWriterToolInput (no directory field) which is used when
base_dir is provided at construction, following the same pattern as
FileReadTool/ScrapeWebsiteTool.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: prevent path traversal in FileWriterTool without interface changes

Adds containment check inside _run() using os.path.realpath() to ensure
the resolved file path stays within the resolved directory. Blocks ../
sequences, absolute filenames, and symlink escapes transparently —
no schema or interface changes required.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: use Path.is_relative_to() for path containment check

Replaces startswith(real_directory + os.sep) with Path.is_relative_to(),
which does a proper path-component comparison. This avoids the edge case
where real_directory == "/" produces a "//" prefix, and is safe on
case-insensitive filesystems. Also explicitly rejects the case where
the filepath resolves to the directory itself (not a valid file target).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* test: fix portability issues in path traversal tests

- test_blocks_traversal_in_filename: use a sibling temp dir instead of
  asserting against a potentially pre-existing ../outside.txt
- test_blocks_absolute_path_in_filename: use a temp-dir-derived absolute
  path instead of hardcoding /etc/passwd
- test_blocks_symlink_escape: symlink to a temp "outside" dir instead of
  /etc, assert target file was not created

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-03-19 20:11:45 +08:00
Greyson LaLonde
929d756ae2 chore: add coding tool environment detection via telemetry events 2026-03-19 07:34:11 -04:00
Vini Brasil
6b262f5a6d Fix lock_store crash when redis package is not installed (#4943)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* Fix lock_store crash when redis package is not installed

`REDIS_URL` being set was enough to trigger a Redis lock, which would
raise `ImportError` if the `redis` package wasn't available. Added
`_redis_available()` to guard on both the env var and the import.

* Simplify tests

* Simplify tests #2
2026-03-18 15:05:41 -03:00
dependabot[bot]
6a6adaf2da chore(deps): bump pyasn1 (#4925)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Bumps the security-updates group with 1 update in the / directory: [pyasn1](https://github.com/pyasn1/pyasn1).


Updates `pyasn1` from 0.6.2 to 0.6.3
- [Release notes](https://github.com/pyasn1/pyasn1/releases)
- [Changelog](https://github.com/pyasn1/pyasn1/blob/main/CHANGES.rst)
- [Commits](https://github.com/pyasn1/pyasn1/compare/v0.6.2...v0.6.3)

---
updated-dependencies:
- dependency-name: pyasn1
  dependency-version: 0.6.3
  dependency-type: indirect
  dependency-group: security-updates
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-03-18 12:16:59 -05:00
Greyson LaLonde
116182f708 docs: update changelog and version for v1.11.0 2026-03-18 09:38:38 -04:00
Greyson LaLonde
9eed13b8a2 feat: bump versions to 1.11.0 2026-03-18 09:30:05 -04:00
Greyson LaLonde
50b2c7d072 docs: update changelog and version for v1.11.0rc2
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-17 17:07:26 -04:00
Greyson LaLonde
e9ba4932a0 feat: bump versions to 1.11.0rc2 2026-03-17 16:58:59 -04:00
Tanishq
0b07b4c45f docs: update Exa Search Tool page with improved naming, description, and configuration options (#4800)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
* docs: update Exa Search Tool page with improved naming, description, and configuration options

Co-Authored-By: Tanishq Jaiswal <tanishq.jaiswal97@gmail.com>

* docs: fix API key link and remove neural/keyword search type references

Co-Authored-By: Tanishq Jaiswal <tanishq.jaiswal97@gmail.com>

* docs: add instant, fast, auto, deep search types

Co-Authored-By: Tanishq Jaiswal <tanishq.jaiswal97@gmail.com>

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2026-03-17 12:27:41 -03:00
João Moura
6235810844 fix: enhance LLM response handling and serialization (#4909)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: enhance LLM response handling and serialization

* Updated the Flow class to improve error handling when both structured and simple prompting fail, ensuring the first outcome is returned as a fallback.
* Introduced a new function, _serialize_llm_for_context, to properly serialize LLM objects with provider prefixes for better context management.
* Added tests to validate the new serialization logic and ensure correct behavior when LLM calls fail.

This update enhances the robustness of LLM interactions and improves the overall flow of handling outcomes.

* fix: patch VCR response handling to prevent httpx.ResponseNotRead errors (#4917)

* fix: enhance LLM response handling and serialization

* Updated the Flow class to improve error handling when both structured and simple prompting fail, ensuring the first outcome is returned as a fallback.
* Introduced a new function, _serialize_llm_for_context, to properly serialize LLM objects with provider prefixes for better context management.
* Added tests to validate the new serialization logic and ensure correct behavior when LLM calls fail.

This update enhances the robustness of LLM interactions and improves the overall flow of handling outcomes.

* fix: patch VCR response handling to prevent httpx.ResponseNotRead errors

VCR's _from_serialized_response mocks httpx.Response.read(), which
prevents the response's internal _content attribute from being properly
initialized. When OpenAI's client (using with_raw_response) accesses
response.content, httpx raises ResponseNotRead.

This patch explicitly sets response._content after the response is
created, ensuring that tests using VCR cassettes work correctly with
the OpenAI client's raw response handling.

Fixes tests:
- test_hierarchical_crew_creation_tasks_with_sync_last
- test_conditional_task_last_task_when_conditional_is_false
- test_crew_log_file_output

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Joao Moura <joaomdmoura@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: alex-clawd <alex@crewai.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-17 05:19:31 -03:00
Matt Aitchison
b95486c187 fix: upgrade vulnerable transitive dependencies (authlib, PyJWT, snowflake-connector-python) (#4913)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
- authlib 1.6.7 → 1.6.9 (CVE-2026-27962 critical, CVE-2026-28498, CVE-2026-28490)
- PyJWT 2.11.0 → 2.12.1 (CVE-2026-32597)
- snowflake-connector-python 4.2.0 → 4.3.0
2026-03-16 19:02:39 -05:00
Lucas Gomide
ead8e8d6e6 docs: add Custom MCP Servers in How-To Guide (#4911) 2026-03-16 17:01:41 -04:00
Vini Brasil
5bbf9c8e03 Update OTEL collectors documentation (#4908)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
* Update OTEL collectors documentation

* Add translations
2026-03-16 13:27:57 -03:00
Greyson LaLonde
5053fae8a1 docs: update changelog and version for v1.11.0rc1 2026-03-16 09:55:45 -04:00
Lucas Gomide
9facd96aad docs: update MCP documentation (#4904) 2026-03-16 09:13:10 -04:00
Rip&Tear
9acb327d9f fix: replace os.system with subprocess.run in unsafe mode pip install
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: replace os.system with subprocess.run in unsafe mode pip install

Eliminates shell injection risk (A05) where a malicious library name like
"pkg; rm -rf /" could execute arbitrary host commands. Using list-form
subprocess.run with shell=False ensures the library name is always treated
as a single argument with no shell metacharacter expansion.

Adds two tests: one verifying list-form invocation, one verifying that
shell metacharacters in a library name cannot trigger shell execution.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: use sys.executable -m pip to satisfy S607 linting rule

S607 flags partial executable paths like ["pip", ...]. Using
[sys.executable, "-m", "pip", ...] provides an absolute path and also
ensures installation targets the correct Python environment.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-03-16 02:04:24 -04:00
Greyson LaLonde
aca0817421 feat: bump versions to 1.11.0rc1 2026-03-15 23:37:20 -04:00
Greyson LaLonde
4d21c6e4ad feat(a2a): add plus api token auth
* feat(a2a): add plus api token auth

* feat(a2a): use stub for plus api

* fix: use dynamic separator in slugify for dedup and strip

* fix: remove unused _DUPLICATE_SEPARATOR_PATTERN, cache compiled regex in slugify
2026-03-15 23:30:29 -04:00
Lorenze Jay
32d7b4a8d4 Lorenze/feat/plan execute pattern (#4817)
* feat: introduce PlanningConfig for enhanced agent planning capabilities (#4344)

* feat: introduce PlanningConfig for enhanced agent planning capabilities

This update adds a new PlanningConfig class to manage agent planning configurations, allowing for customizable planning behavior before task execution. The existing reasoning parameter is deprecated in favor of this new configuration, ensuring backward compatibility while enhancing the planning process. Additionally, the Agent class has been updated to utilize this new configuration, and relevant utility functions have been adjusted accordingly. Tests have been added to validate the new planning functionality and ensure proper integration with existing agent workflows.

* dropping redundancy

* fix test

* revert handle_reasoning here

* refactor: update reasoning handling in Agent class

This commit modifies the Agent class to conditionally call the handle_reasoning function based on the executor class being used. The legacy CrewAgentExecutor will continue to utilize handle_reasoning, while the new AgentExecutor will manage planning internally. Additionally, the PlanningConfig class has been referenced in the documentation to clarify its role in enabling or disabling planning. Tests have been updated to reflect these changes and ensure proper functionality.

* improve planning prompts

* matching

* refactor: remove default enabled flag from PlanningConfig in Agent class

* more cassettes

* fix test

* refactor: update planning prompt and remove deprecated methods in reasoning handler

* improve planning prompt

* Lorenze/feat planning pt 2 todo list gen (#4449)

* feat: introduce PlanningConfig for enhanced agent planning capabilities

This update adds a new PlanningConfig class to manage agent planning configurations, allowing for customizable planning behavior before task execution. The existing reasoning parameter is deprecated in favor of this new configuration, ensuring backward compatibility while enhancing the planning process. Additionally, the Agent class has been updated to utilize this new configuration, and relevant utility functions have been adjusted accordingly. Tests have been added to validate the new planning functionality and ensure proper integration with existing agent workflows.

* dropping redundancy

* fix test

* revert handle_reasoning here

* refactor: update reasoning handling in Agent class

This commit modifies the Agent class to conditionally call the handle_reasoning function based on the executor class being used. The legacy CrewAgentExecutor will continue to utilize handle_reasoning, while the new AgentExecutor will manage planning internally. Additionally, the PlanningConfig class has been referenced in the documentation to clarify its role in enabling or disabling planning. Tests have been updated to reflect these changes and ensure proper functionality.

* improve planning prompts

* matching

* refactor: remove default enabled flag from PlanningConfig in Agent class

* more cassettes

* fix test

* feat: enhance agent planning with structured todo management

This commit introduces a new planning system within the AgentExecutor class, allowing for the creation of structured todo items from planning steps. The TodoList and TodoItem models have been added to facilitate tracking of plan execution. The reasoning plan now includes a list of steps, improving the clarity and organization of agent tasks. Additionally, tests have been added to validate the new planning functionality and ensure proper integration with existing workflows.

* refactor: update planning prompt and remove deprecated methods in reasoning handler

* improve planning prompt

* improve handler

* linted

* linted

* Lorenze/feat/planning pt 3 todo list execution (#4450)

* feat: introduce PlanningConfig for enhanced agent planning capabilities

This update adds a new PlanningConfig class to manage agent planning configurations, allowing for customizable planning behavior before task execution. The existing reasoning parameter is deprecated in favor of this new configuration, ensuring backward compatibility while enhancing the planning process. Additionally, the Agent class has been updated to utilize this new configuration, and relevant utility functions have been adjusted accordingly. Tests have been added to validate the new planning functionality and ensure proper integration with existing agent workflows.

* dropping redundancy

* fix test

* revert handle_reasoning here

* refactor: update reasoning handling in Agent class

This commit modifies the Agent class to conditionally call the handle_reasoning function based on the executor class being used. The legacy CrewAgentExecutor will continue to utilize handle_reasoning, while the new AgentExecutor will manage planning internally. Additionally, the PlanningConfig class has been referenced in the documentation to clarify its role in enabling or disabling planning. Tests have been updated to reflect these changes and ensure proper functionality.

* improve planning prompts

* matching

* refactor: remove default enabled flag from PlanningConfig in Agent class

* more cassettes

* fix test

* feat: enhance agent planning with structured todo management

This commit introduces a new planning system within the AgentExecutor class, allowing for the creation of structured todo items from planning steps. The TodoList and TodoItem models have been added to facilitate tracking of plan execution. The reasoning plan now includes a list of steps, improving the clarity and organization of agent tasks. Additionally, tests have been added to validate the new planning functionality and ensure proper integration with existing workflows.

* refactor: update planning prompt and remove deprecated methods in reasoning handler

* improve planning prompt

* improve handler

* execute todos and be able to track them

* feat: introduce PlannerObserver and StepExecutor for enhanced plan execution

This commit adds the PlannerObserver and StepExecutor classes to the CrewAI framework, implementing the observation phase of the Plan-and-Execute architecture. The PlannerObserver analyzes step execution results, determines plan validity, and suggests refinements, while the StepExecutor executes individual todo items in isolation. These additions improve the overall planning and execution process, allowing for more dynamic and responsive agent behavior. Additionally, new observation events have been defined to facilitate monitoring and logging of the planning process.

* refactor: enhance final answer synthesis in AgentExecutor

This commit improves the synthesis of final answers in the AgentExecutor class by implementing a more coherent approach to combining results from multiple todo items. The method now utilizes a single LLM call to generate a polished response, falling back to concatenation if the synthesis fails. Additionally, the test cases have been updated to reflect the changes in planning and execution, ensuring that the results are properly validated and that the plan-and-execute architecture is functioning as intended.

* refactor: enhance final answer synthesis in AgentExecutor

This commit improves the synthesis of final answers in the AgentExecutor class by implementing a more coherent approach to combining results from multiple todo items. The method now utilizes a single LLM call to generate a polished response, falling back to concatenation if the synthesis fails. Additionally, the test cases have been updated to reflect the changes in planning and execution, ensuring that the results are properly validated and that the plan-and-execute architecture is functioning as intended.

* refactor: implement structured output handling in final answer synthesis

This commit enhances the final answer synthesis process in the AgentExecutor class by introducing support for structured outputs when a response model is specified. The synthesis method now utilizes the response model to produce outputs that conform to the expected schema, while still falling back to concatenation in case of synthesis failures. This change ensures that intermediate steps yield free-text results, but the final output can be structured, improving the overall coherence and usability of the synthesized answers.

* regen tests

* linted

* fix

* Enhance PlanningConfig and AgentExecutor with Reasoning Effort Levels

This update introduces a new  attribute in the  class, allowing users to customize the observation and replanning behavior during task execution. The  class has been modified to utilize this new attribute, routing step observations based on the specified reasoning effort level: low, medium, or high.

Additionally, tests have been added to validate the functionality of the reasoning effort levels, ensuring that the agent behaves as expected under different configurations. This enhancement improves the adaptability and efficiency of the planning process in agent execution.

* regen cassettes for test and fix test

* cassette regen

* fixing tests

* dry

* Refactor PlannerObserver and StepExecutor to Utilize I18N for Prompts

This update enhances the PlannerObserver and StepExecutor classes by integrating the I18N utility for managing prompts and messages. The system and user prompts are now retrieved from the I18N module, allowing for better localization and maintainability. Additionally, the code has been cleaned up to remove hardcoded strings, improving readability and consistency across the planning and execution processes.

* Refactor PlannerObserver and StepExecutor to Utilize I18N for Prompts

This update enhances the PlannerObserver and StepExecutor classes by integrating the I18N utility for managing prompts and messages. The system and user prompts are now retrieved from the I18N module, allowing for better localization and maintainability. Additionally, the code has been cleaned up to remove hardcoded strings, improving readability and consistency across the planning and execution processes.

* consolidate agent logic

* fix datetime

* improving step executor

* refactor: streamline observation and refinement process in PlannerObserver

- Updated the PlannerObserver to apply structured refinements directly from observations without requiring a second LLM call.
- Renamed  method to  for clarity.
- Enhanced documentation to reflect changes in how refinements are handled.
- Removed unnecessary LLM message building and parsing logic, simplifying the refinement process.
- Updated event emissions to include summaries of refinements instead of raw data.

* enhance step executor with tool usage events and validation

- Added event emissions for tool usage, including started and finished events, to track tool execution.
- Implemented validation to ensure expected tools are called during step execution, raising errors when not.
- Refactored the  method to handle tool execution with event logging.
- Introduced a new method  for parsing tool input into a structured format.
- Updated tests to cover new functionality and ensure correct behavior of tool usage events.

* refactor: enhance final answer synthesis logic in AgentExecutor

- Updated the finalization process to conditionally skip synthesis when the last todo result is sufficient as a complete answer.
- Introduced a new method to determine if the last todo result can be used directly, improving efficiency.
- Added tests to verify the new behavior, ensuring synthesis is skipped when appropriate and maintained when a response model is set.

* fix: update observation handling in PlannerObserver for LLM errors

- Modified the error handling in the PlannerObserver to default to a conservative replan when an LLM call fails.
- Updated the return values to indicate that the step was not completed successfully and that a full replan is needed.
- Added a new test to verify the behavior of the observer when an LLM error occurs, ensuring the correct replan logic is triggered.

* refactor: enhance planning and execution flow in agents

- Updated the PlannerObserver to accept a kickoff input for standalone task execution, improving flexibility in task handling.
- Refined the step execution process in StepExecutor to support multi-turn action loops, allowing for iterative tool execution and observation.
- Introduced a method to extract relevant task sections from descriptions, ensuring clarity in task requirements.
- Enhanced the AgentExecutor to manage step failures more effectively, triggering replans only when necessary and preserving completed task history.
- Updated translations to reflect changes in planning principles and execution prompts, emphasizing concrete and executable steps.

* refactor: update setup_native_tools to include tool_name_mapping

- Modified the setup_native_tools function to return an additional mapping of tool names.
- Updated StepExecutor and AgentExecutor classes to accommodate the new return value from setup_native_tools.

* fix tests

* linted

* linted

* feat: enhance image block handling in Anthropic provider and update AgentExecutor logic

- Added a method to convert OpenAI-style image_url blocks to Anthropic's required format.
- Updated AgentExecutor to handle cases where no todos are ready, introducing a needs_replan return state.
- Improved fallback answer generation in AgentExecutor to prevent RuntimeErrors when no final output is produced.

* lint

* lint

* 1. Added failed to TodoStatus (planning_types.py)

  - TodoStatus now includes failed as a valid state: Literal[pending, running, completed, failed]
  - Added mark_failed(step_number, result) method to TodoList
  - Added get_failed_todos() method to TodoList
  - Updated is_complete to treat both completed and failed as terminal states
  - Updated replace_pending_todos docstring to mention failed items are preserved

  2. Mark running todos as failed before replan (agent_executor.py)

  All three effort-level handlers now call mark_failed() on the current todo before routing to replan_now:

  - Low effort (handle_step_observed_low): hard-failure branch
  - Medium effort (handle_step_observed_medium): needs_full_replan branch
  - High effort (decide_next_action): both needs_full_replan and step_completed_successfully=False branches

  3. Updated _should_replan to use get_failed_todos()

  Previously filtered on todo.status == failed which was dead code. Now uses the proper accessor method that will actually find failed items.

  What this fixes: Before these changes, a step that triggered a replan would stay in running status permanently, causing is_complete to never
  return True and next_pending to skip it — leading to stuck execution states. Now failed steps are properly tracked, replanning context correctly
  reports them, and LiteAgentOutput.failed_todos will actually return results.

* fix test

* imp on failed states

* adjusted the var name from AgentReActState to AgentExecutorState

* addressed p0 bugs

* more improvements

* linted

* regen cassette

* addressing crictical comments

* ensure configurable timeouts, max_replans and max step iterations

* adjusted tools

* dropping debug statements

* addressed comment

* fix  linter

* lints and test fixes

* fix: default observation parse fallback to failure and clean up plan-execute types

When _parse_observation_response fails all parse attempts, default to
step_completed_successfully=False instead of True to avoid silently
masking failures. Extract duplicate _extract_task_section into a shared
utility in agent_utils. Type PlanningConfig.llm as str | BaseLLM | None
instead of str | Any | None. Make StepResult a frozen dataclass for
immutability consistency with StepExecutionContext.

* fix: remove Any from function_calling_llm union type in step_executor

* fix: make BaseTool usage count thread-safe for parallel step execution

Add _usage_lock and _claim_usage() to BaseTool for atomic
check-and-increment of current_usage_count. This prevents race
conditions when parallel plan steps invoke the same tool concurrently
via execute_todos_parallel. Remove the racy pre-check from
execute_single_native_tool_call since the limit is now enforced
atomically inside tool.run().

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Greyson LaLonde <greyson@crewai.com>
2026-03-15 18:33:17 -07:00
Rip&Tear
fb2323b3de Code interpreter sandbox escape (#4791)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
* [SECURITY] Fix sandbox escape vulnerability in CodeInterpreterTool (F-001)

This commit addresses a critical security vulnerability where the CodeInterpreterTool
could be exploited via sandbox escape attacks when Docker was unavailable.

Changes:
- Remove insecure fallback to restricted sandbox in run_code_safety()
- Now fails closed with RuntimeError when Docker is unavailable
- Mark run_code_in_restricted_sandbox() as deprecated and insecure
- Add clear security warnings to SandboxPython class documentation
- Update tests to reflect secure-by-default behavior
- Add test demonstrating the sandbox escape vulnerability
- Update README with security requirements and best practices

The previous implementation would fall back to a Python-based 'restricted sandbox'
when Docker was unavailable. However, this sandbox could be easily bypassed using
Python object introspection to recover the original __import__ function, allowing
arbitrary module access and command execution on the host.

The fix enforces Docker as a requirement for safe code execution. Users who cannot
use Docker must explicitly enable unsafe_mode=True, acknowledging the security risks.

Security Impact:
- Prevents RCE via sandbox escape when Docker is unavailable
- Enforces fail-closed security model
- Maintains backward compatibility via unsafe_mode flag

References:
- https://docs.crewai.com/tools/ai-ml/codeinterpretertool

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>

* Add security fix documentation for F-001

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>

* Add Slack summary for security fix

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>

* Delete SECURITY_FIX_F001.md

* Delete SLACK_SUMMARY.md

* chore: regen cassettes

* chore: regen more cassettes

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
Co-authored-by: Greyson LaLonde <greyson@crewai.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-03-15 13:18:02 +08:00
Greyson LaLonde
e1d7de0dba docs: update changelog and version for v1.10.2rc2
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-03-14 00:49:48 -04:00
Greyson LaLonde
96b07bfc84 feat: bump versions to 1.10.2rc2 2026-03-14 00:34:12 -04:00
Greyson LaLonde
b8d7942675 fix: remove exclusive locks from read-only storage operations
* fix: remove exclusive locks from read-only storage operations to eliminate lock contention

read operations like search, list_scopes, get_scope_info, count across
LanceDB, ChromaDB, and RAG adapters were holding exclusive locks unnecessarily.
under multi-process prefork workers this caused RedisLock contention triggering
a portalocker bug where AlreadyLocked is raised with the exceptions module as its arg.

- remove store_lock from 7 LanceDB read methods since MVCC handles concurrent reads
- remove store_lock from ChromaDB search/asearch which are thread-safe since v0.4
- remove store_lock from RAG core query and LanceDB adapter query
- wrap lock_store BaseLockException with actionable error message
- add exception handling in encoding_flow/recall_flow ThreadPoolExecutor calls
- fix flow.py double-logging of ancestor listener errors

* fix: remove dead conditional in filter_and_chunk fallback

both branches of the if/else and the except all produced the same
candidates = [scope_prefix] result, making the get_scope_info call
and conditional pointless

* fix: separate lock acquisition from caller body in lock_store

the try/except wrapped the yield inside the contextmanager, which meant
any BaseLockException raised by the caller's code inside the with block
would be caught and re-raised with a misleading "Failed to acquire lock"
message. split into acquire-then-yield so only actual acquisition
failures get the actionable error message.
2026-03-14 00:21:14 -04:00
Greyson LaLonde
88fd859c26 docs: update changelog and version for v1.10.2rc1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
2026-03-13 17:07:31 -04:00
Greyson LaLonde
3413f2e671 feat: bump versions to 1.10.2rc1 2026-03-13 16:53:48 -04:00
Greyson LaLonde
326ec15d54 feat(devtools): add release command and trigger PyPI publish
* feat(devtools): add release command and fix automerge on protected branches

Replace gh pr merge --auto with polling-based merge wait that prints the
PR URL for manual review. Add unified release command that chains bump
and tag into a single end-to-end workflow.

* feat(devtools): trigger PyPI publish workflow after GitHub release

* refactor(devtools): extract shared helpers to eliminate duplication

Extract _poll_pr_until_merged, _update_all_versions,
_generate_release_notes, _update_docs_and_create_pr,
_create_tag_and_release, and _trigger_pypi_publish into reusable
helpers. All three commands (bump, tag, release) now compose from
these shared functions.
2026-03-13 16:41:27 -04:00
Greyson LaLonde
c5a8fef118 fix: add cross-process and thread-safe locking to unprotected I/O (#4827)
* fix: add cross-process and thread-safe locking to unprotected I/O

* style: apply ruff formatting and import sorting

* fix: avoid event loop deadlock in snowflake pool lock

* perf: move embedding calls outside cross-process lock in RAG adapter

* fix: close TOCTOU race in browser session manager

* fix: add error handling to update_user_data

* fix: use async lock acquisition in chromadb async methods

* fix: avoid blocking event loop in async browser session wait

* fix: replace dual-lock with single cross-process lock in LanceDB storage

* fix: remove dead _save_user_data function and stale mock

* fix: re-addd file descriptor limit to prevent crashes
2026-03-13 12:28:11 -07:00
Greyson LaLonde
b7af26ff60 ci: add slack notification on successful pypi publish 2026-03-13 12:05:52 -04:00
Greyson LaLonde
48eb7c6937 fix: propagate contextvars across all thread and executor boundaries
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-13 00:32:22 -04:00
danglies007
d8e38f2f0b fix: propagate ContextVars into async task threads
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
threading.Thread() does not inherit the parent's contextvars.Context,
causing ContextVar-based state (OpenTelemetry spans, Langfuse trace IDs,
and any other request-scoped vars) to be silently dropped in async tasks.

Fix by calling contextvars.copy_context() before spawning each thread and
using ctx.run() as the thread target, which runs the function inside the
captured context.

Affected locations:
- task.py: execute_async() — the primary async task execution path
- utilities/streaming.py: create_chunk_generator() — streaming execution path

Fixes: #4822
Related: #4168, #4286

Co-authored-by: Claude <noreply@anthropic.com>
2026-03-12 15:33:58 -04:00
Greyson LaLonde
542afe61a8 docs: update changelog and version for v1.10.2a1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-11 11:44:00 -04:00
Greyson LaLonde
8a5b3bc237 feat: bump versions to 1.10.2a1
* feat: bump versions to 1.10.2a1

* chore: update tool specifications

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-11 11:30:11 -04:00
Greyson LaLonde
534f0707ca fix: resolve LockException under concurrent multi-process execution 2026-03-11 11:15:24 -04:00
Giulio Leone
0046f9a96f fix(bedrock): group parallel tool results in single user message (#4775)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix(bedrock): group parallel tool results in single user message

When an AWS Bedrock model makes multiple tool calls in a single
response, the Converse API requires all corresponding tool results
to be sent back in a single user message. Previously, each tool
result was emitted as a separate user message, causing:

  ValidationException: Expected toolResult blocks at messages.2.content

Fix: When processing consecutive tool messages, append the toolResult
block to the preceding user message (if it already contains
toolResult blocks) instead of creating a new message. This groups
all parallel tool results together while keeping tool results from
different assistant turns separate.

Fixes #4749

Signed-off-by: Giulio Leone <6887247+giulio-leone@users.noreply.github.com>

* Update lib/crewai/tests/llms/bedrock/test_bedrock.py

* fix: group bedrock tool results

Co-authored-by: João Moura <joaomdmoura@gmail.com>

---------

Signed-off-by: Giulio Leone <6887247+giulio-leone@users.noreply.github.com>
Co-authored-by: Giulio Leone <6887247+giulio-leone@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-03-10 17:28:40 -03:00
Lucas Gomide
e72a80be6e Addressing MCP tools resolutions & eliminates all shared mutable connection (#4792)
* fix: allow hyphenated tool names in MCP references like notion#get-page

The _SLUG_RE regex on BaseAgent rejected MCP tool references containing
hyphens (e.g. "notion#get-page") because the fragment pattern only
matched \w (word chars)

* fix: create fresh MCP client per tool invocation to prevent parallel call races

When the LLM dispatches parallel calls to MCP tools on the same server, the executor runs them concurrently via ThreadPoolExecutor. Previously, all tools from a server shared a single MCPClient instance, and even the same tool called twice would reuse one client. Since each thread creates its own asyncio event loop via asyncio.run(), concurrent connect/disconnect calls on the shared client caused anyio cancel-scope errors ("Attempted to exit cancel scope in a different task than it was entered in").

The fix introduces a client_factory pattern: MCPNativeTool now receives a zero-arg callable that produces a fresh MCPClient + transport on every
_run_async() invocation. This eliminates all shared mutable connection state between concurrent calls, whether to the same tool or different tools from the same server.

* test: ensure we can filter hyphenated MCP tool
2026-03-10 14:00:40 -04:00
Lorenze Jay
7cffcab84a ensure we support tool search - saving tokens and dynamically inject appropriate tools during execution - anthropic (#4779)
* ensure we support tool search

* linted

* dont tool search if there is only one tool
2026-03-10 10:48:13 -07:00
João Moura
f070ce8abd fix: update llm parameter handling in human_feedback function (#4801)
Modified the llm parameter assignment to retrieve the model attribute from llm if it is not a string, ensuring compatibility with different llm types.
2026-03-10 14:27:09 -03:00
Sampson
d9f6e2222f Introduce more Brave Search tools (#4446)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* feat: add dedicated Brave Search tools for web, news, image, video, local POIs, and Brave's newest LLM Context endpoint

* fix: normalize transformed response shape

* revert legacy tool name

* fix: schema change prevented property resolution

* Update tool.specs.json

* fix: add fallback for search_langugage

* simplify exports

* makes rate-limiting logic per-instance

* fix(brave-tools): correct _refine_response return type annotations

The abstract method and subclasses annotated _refine_response as returning
dict[str, Any] but most implementations actually return list[dict[str, Any]].
Updated base to return Any, and each subclass to match its actual return type.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Joao Moura <joaomdmoura@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-10 01:38:54 -03:00
Lucas Gomide
adef605410 fix: add missing list/dict methods to LockedListProxy and LockedDictProxy
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
2026-03-09 09:38:35 -04:00
Greyson LaLonde
cd42bcf035 refactor(memory): convert memory classes to serializable
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* refactor(memory): convert Memory, MemoryScope, and MemorySlice to BaseModel

* fix(test): update mock memory attribute from _read_only to read_only

* fix: handle re-validation in wrap validators and patch BaseModel class in tests
2026-03-08 23:08:10 -04:00
Greyson LaLonde
bc45a7fbe3 feat: create action for nightly releases
Some checks failed
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-06 18:32:52 -05:00
Matt Aitchison
87759cdb14 fix(deps): bump gitpython to >=3.1.41 to resolve CVE path traversal vulnerability (#4740)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
GitPython ==3.1.38 is affected by a high-severity path traversal
vulnerability (dependabot alert #1). Bump to >=3.1.41,<4 which
includes the fix.
2026-03-05 12:41:24 -06:00
Tiago Freire
059cb93aeb fix(executor): propagate contextvars context to parallel tool call threads
ThreadPoolExecutor threads do not inherit the calling thread's contextvars
context, causing _event_id_stack and _current_celery_task_id to be empty
in worker threads. This broke OTel span parenting for parallel tool calls
(missing parent_event_id) and lost the Celery task ID in the enterprise
tracking layer ([Task ID: no-task]).

Fix by capturing an independent context copy per submission via
contextvars.copy_context().run in CrewAgentExecutor._handle_native_tool_calls,
so each worker thread starts with the correct inherited context without
sharing mutable state across threads.
2026-03-05 08:20:09 -05:00
Lorenze Jay
cebc52694e docs: update changelog and version for v1.10.1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-04 18:20:02 -05:00
Lorenze Jay
53df41989a feat: bump versions to 1.10.1 (#4706)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
2026-03-04 11:03:17 -08:00
Greyson LaLonde
ea70976a5d fix: adjust executor listener value to avoid recursion (#4705)
* fix: adjust executor listener value to avoid recursion

* fix: clear call count to ensure zero state

* feat: expose max method call kwarg
2026-03-04 10:47:22 -08:00
João Moura
3cc6516ae5 Memory overall improvements (#4688)
* feat: enhance memory recall limits and update documentation

- Increased the memory recall limit in the Agent class from 5 to 15.
- Updated the RecallMemoryTool to allow a recall limit of 20.
- Expanded the documentation for the recall_memory feature to emphasize the importance of multiple queries for comprehensive results.

* feat: increase memory recall limit and enhance memory context documentation

- Increased the memory recall limit in the Agent class from 15 to 20.
- Updated the memory context message to clarify the nature of the memories presented and the importance of using the Search memory tool for comprehensive results.

* refactor: remove inferred_categories from RecallState and update category merging logic

- Removed the inferred_categories field from RecallState to simplify state management.
- Updated the _merged_categories method to only merge caller-supplied categories, enhancing clarity in category handling.

* refactor: simplify category handling in RecallFlow

- Updated the _merged_categories method to return only caller-supplied categories, removing the previous merging logic for inferred categories. This change enhances clarity and maintains consistency in category management.
2026-03-04 09:19:07 -08:00
nicoferdi96
ad82e52d39 fix(gemini): group parallel function_response parts in a single Content object (#4693)
* fix(gemini): group parallel function_response parts in a single Content object

When Gemini makes N parallel tool calls, the API requires all N function_response parts in one Content object. Previously each tool result created a separate Content, causing 400 INVALID_ARGUMENT errors. Merge consecutive function_response parts into the existing Content instead of appending new ones.

* Address change requested

- function_response is a declared field on the types.Part Pydantic model so hasattr can be replaced with p.function_response is not None
2026-03-04 12:04:23 +01:00
Matt Aitchison
9336702ebc fix(deps): bump pypdf, urllib3 override, and dev dependencies for security fixes
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
- pypdf ~6.7.4 → ~6.7.5 (CVE: inefficient ASCIIHexDecode stream decoding)
- Add urllib3>=2.6.3 override (CVE: decompression-bomb bypass on redirects)
- ruff 0.14.7 → 0.15.1, mypy 1.19.0 → 1.19.1, pre-commit 4.5.0 → 4.5.1
- types-regex 2024.11.6 → 2026.1.15, boto3-stubs 1.40.54 → 1.42.40
- Auto-fixed 13 lint issues from new ruff rules

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-03-04 01:13:38 -05:00
Greyson LaLonde
030f6d6c43 fix: use anon id for ephemeral traces 2026-03-04 00:45:09 -05:00
Mike Plachta
95d51db29f Langgraph migration guide (#4681)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-03-03 11:53:12 -08:00
Greyson LaLonde
a8f51419f6 fix(gemini): surface thought output from thinking models
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
* fix(gemini): surface thought output from thinking models

* chore(llm): remove unreachable hasattr guards on crewai_event_bus
2026-03-03 11:54:55 -05:00
Greyson LaLonde
e7f17d2284 fix: load MCP and platform tools when agent tools is None
Closes #4568
2026-03-03 10:25:25 -05:00
Greyson LaLonde
5d0811258f fix(a2a): support Jupyter environments with running event loops 2026-03-03 10:05:48 -05:00
Greyson LaLonde
7972192d55 fix(deps): bump tokenizers lower bound to >=0.21 to avoid broken 0.20.3
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-02 18:04:28 -05:00
Mike Plachta
b3f8a42321 feat: upgrade gemini genai
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-03-02 14:27:56 -05:00
Greyson LaLonde
21224f2bc5 fix: conditionally pass plus header
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Empty strings are considered illegal values for bearer auth in `httpx`.
2026-03-02 09:27:54 -05:00
Giulio Leone
b76022c1e7 fix(telemetry): skip signal handler registration in non-main threads
* fix(telemetry): skip signal handler registration in non-main threads

When CrewAI is initialized from a non-main thread (e.g. Streamlit, Flask,
Django, Jupyter), the telemetry module attempted to register signal handlers
which only work in the main thread. This caused multiple noisy ValueError
tracebacks to be printed to stderr, confusing users even though the errors
were caught and non-fatal.

Check `threading.current_thread() is not threading.main_thread()` before
attempting signal registration, and skip silently with a debug-level log
message instead of printing full tracebacks.

Fixes crewAIInc/crewAI#4289

* fix(test): move Telemetry() inside signal.signal mock context

Refs: #4649

* fix(telemetry): move signal.signal mock inside thread to wrap Telemetry() construction

The patch context now activates inside init_in_thread so the mock
is guaranteed to be active before and during Telemetry.__init__,
addressing the Copilot review feedback.

Refs: #4289

* fix(test): mock logger.debug instead of capsys for deterministic assertion

Replace signal.signal-only mock with combined logger + signal mock.
Assert logger.debug was called with the skip message and signal.signal
was never invoked from the non-main thread.

Refs: #4289
2026-03-02 07:42:55 -05:00
Greyson LaLonde
1ac5801578 fix: inject tool errors as observations and resolve name collisions
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-03-01 00:46:04 -05:00
Matt Aitchison
c00a348837 fix: upgrade pypdf 4.x → 6.7.4 to resolve 11 Dependabot alerts
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
pypdf <6.7.4 has multiple DoS vulnerabilities via crafted PDF streams
(FlateDecode, LZWDecode, RunLengthDecode, XFA, TreeObject, outlines).

Only basic PdfReader/PdfWriter APIs are used in crewai-files, none of
which changed in the 5.0 or 6.0 breaking releases.
2026-02-28 17:16:45 -05:00
Matt Aitchison
6c8c6c8e12 fix: resolve critical/high Dependabot security alerts (#4652)
Upgrade pillow 10.4.0 → 12.1.1 (out-of-bounds write on PSD images),
langchain-core 0.3.76 → 0.3.83 (template injection), and
urllib3 2.6.1 → 2.6.3 (decompression-bomb bypass on redirects).

Bump docling ~=2.63.0 → ~=2.75.0 for pillow 12 compat, and add
uv overrides for pillow/langchain-core to unblock transitive pins
from fastembed and langchain-apify.
2026-02-28 13:04:35 -06:00
Musthaq Ahamad
3899910aa9 docs: sync Composio tool docs across locales (#4639)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* docs: update Composio tool docs across locales

Align the Composio automation docs with the new session-based example flow and keep localized pages in sync with the updated English content.

Made-with: Cursor

* docs: clarify manual user authentication wording

Refine the Composio auth section language to reflect session-based automatic auth during agent chat while keeping the manual `authorize` flow explicit.

Made-with: Cursor

* docs: sync updated Composio auth wording across locales

Propagate the latest English wording updates for CrewAI provider initialization and manual user authentication guidance to pt-BR and ko docs.

Made-with: Cursor
2026-02-27 13:38:45 -08:00
Greyson LaLonde
757a435ee3 chore: update changelog and version for v1.10.1a1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-02-27 09:58:48 -05:00
Greyson LaLonde
8bfdb188f7 feat: bump versions to 1.10.1a1 2026-02-27 09:44:47 -05:00
João Moura
1bdb9496a3 refactor: update step callback methods to support asynchronous invocation (#4633)
* refactor: update step callback methods to support asynchronous invocation

- Replaced synchronous step callback invocations with asynchronous counterparts in the CrewAgentExecutor class.
- Introduced a new async method _ainvoke_step_callback to handle step callbacks in an async context, improving responsiveness and performance in asynchronous workflows.

* chore: bump version to 1.10.1b1 across multiple files

- Updated version strings from 1.10.1b to 1.10.1b1 in various project files including pyproject.toml and __init__.py files.
- Adjusted dependency specifications to reflect the new version in relevant templates and modules.
2026-02-27 07:35:03 -03:00
Joao Moura
979aa26c3d bump new alpha version 2026-02-27 01:43:33 -08:00
João Moura
514c082882 refactor: implement lazy loading for heavy dependencies in Memory module (#4632)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
- Introduced lazy imports for the Memory and EncodingFlow classes to optimize import time and reduce initial load, particularly beneficial for deployment scenarios like Celery pre-fork.
- Updated the Memory class to include new configuration options for aggregation queries, enhancing its functionality.
- Adjusted the __getattr__ method in both the crewai and memory modules to support lazy loading of specified attributes.
2026-02-27 03:20:02 -03:00
Greyson LaLonde
c9e8068578 docs: update changelog and version for v1.10.0 2026-02-26 19:14:25 -05:00
Greyson LaLonde
df2778f08b fix: make branch for release notes
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-02-26 18:49:13 -05:00
Greyson LaLonde
d8fea2518d feat: bump versions to 1.10.0
* feat: bump versions to 1.10.0

* chore: update tool specifications

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-02-26 18:31:14 -05:00
Lucas Gomide
d259150d8d Enhance MCP tool resolution and related events (#4580)
* feat: enhance MCP tool resolution

* feat: emit event when MCP configuration fails

* feat: emit event when MCP tool execution has failed

* style: resolve linter issues

* refactor: use clear and natural mcp tool name resolution

* test: fix broken tests

* fix: resolve MCP connection leaks, slug validation, duplicate connections, and httpx exception handling

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Greyson LaLonde <greyson@crewai.com>
2026-02-26 13:59:30 -08:00
Greyson LaLonde
c4a328c9d5 fix: validate tool kwargs even when empty to prevent cryptic TypeError (#4611) 2026-02-26 16:18:03 -05:00
Greyson LaLonde
373abbb6b7 fix: add dict overload to build_embedder and type default embedder 2026-02-26 16:04:28 -05:00
João Moura
86d3ee022d feat: update lancedb version and add lance-namespace packages
* chore(deps): update lancedb version and add lance-namespace packages

- Updated lancedb dependency version from 0.4.0 to 0.29.2 in multiple files.
- Added new packages: lance-namespace and lance-namespace-urllib3-client with version 0.5.2, including their dependencies and installation details.
- Enhanced MemoryTUI to display a limit on entries and improved the LanceDBStorage class with automatic background compaction and index creation for better performance.

* linter

* refactor: update memory recall limit and formatting in Agent class

- Reduced the memory recall limit from 10 to 5 in multiple locations within the Agent class.
- Updated the memory formatting to use a new `format` method in the MemoryMatch class for improved readability and metadata inclusion.

* refactor: enhance memory handling with read-only support

- Updated memory-related classes and methods to support read-only functionality, allowing for silent no-ops when attempting to remember data in read-only mode.
- Modified the LiteAgent and CrewAgentExecutorMixin classes to check for read-only status before saving memories.
- Adjusted MemorySlice and Memory classes to reflect changes in behavior when read-only is enabled.
- Updated tests to verify that memory operations behave correctly under read-only conditions.

* test: set mock memory to read-write in unit tests

- Updated unit tests in test_unified_memory.py to set mock_memory._read_only to False, ensuring that memory operations can be tested in a writable state.

* fix test

* fix: preserve falsy metadata values and fix remember() return type

---------

Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Greyson LaLonde <greyson@crewai.com>
2026-02-26 15:05:10 -05:00
Lucas Gomide
09e3b81ca3 fix: preserve null types in tool parameter schemas for LLM (#4579)
* fix: preserve null types in tool parameter schemas for LLM

Tool parameter schemas were stripping null from optional fields via
generate_model_description, forcing the LLM to provide non-null values
for fields.
Adds strip_null_types parameter to generate_model_description and passes False when generating tool
schemas, so optional fields keep anyOf: [{type: T}, {type: null}]

* Update lib/crewai/src/crewai/utilities/pydantic_schema_utils.py

Co-authored-by: Gabe Milani <gabriel@crewai.com>

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Gabe Milani <gabriel@crewai.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-02-26 11:51:34 -05:00
Heitor Carvalho
b6d8ce5c55 docs: add litellm dependency note for non-native LLM providers (#4600)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-02-26 10:57:37 -03:00
Greyson LaLonde
b371f97a2f fix: map output_pydantic/output_json to native structured output
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: map output_pydantic/output_json to native structured output

* test: add crew+tools+structured output integration test for Gemini

* fix: re-record stale cassette for test_crew_testing_function

* fix: re-record remaining stale cassettes for native structured output

* fix: enable native structured output for lite agent and fix mypy errors
2026-02-25 17:13:34 -05:00
dependabot[bot]
017189db78 chore(deps): bump nltk in the security-updates group across 1 directory (#4598)
Bumps the security-updates group with 1 update in the / directory: [nltk](https://github.com/nltk/nltk).


Updates `nltk` from 3.9.2 to 3.9.3
- [Changelog](https://github.com/nltk/nltk/blob/develop/ChangeLog)
- [Commits](https://github.com/nltk/nltk/compare/3.9.2...3.9.3)

---
updated-dependencies:
- dependency-name: nltk
  dependency-version: 3.9.3
  dependency-type: indirect
  dependency-group: security-updates
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-02-25 15:37:21 -06:00
dependabot[bot]
02d911494f chore(deps): bump cryptography (#4506)
Bumps the security-updates group with 1 update in the / directory: [cryptography](https://github.com/pyca/cryptography).


Updates `cryptography` from 46.0.4 to 46.0.5
- [Changelog](https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst)
- [Commits](https://github.com/pyca/cryptography/compare/46.0.4...46.0.5)

---
updated-dependencies:
- dependency-name: cryptography
  dependency-version: 46.0.5
  dependency-type: indirect
  dependency-group: security-updates
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-02-25 15:04:07 -06:00
João Moura
8102d0a6ca feat: enhance JSON argument parsing and validation in CrewAgentExecutor and BaseTool
* feat: enhance JSON argument parsing and validation in CrewAgentExecutor and BaseTool

- Added error handling for malformed JSON tool arguments in CrewAgentExecutor, providing descriptive error messages.
- Implemented schema validation for tool arguments in BaseTool, ensuring that invalid arguments raise appropriate exceptions.
- Introduced tests to verify correct behavior for both valid and invalid JSON inputs, enhancing robustness of tool execution.

* refactor: improve argument validation in BaseTool

- Introduced a new private method  to handle argument validation for tools, enhancing code clarity and reusability.
- Updated the  method to utilize the new validation method, ensuring consistent error handling for invalid arguments.
- Enhanced exception handling to specifically catch , providing clearer error messages for tool argument validation failures.

* feat: introduce parse_tool_call_args for improved argument parsing

- Added a new utility function, parse_tool_call_args, to handle parsing of tool call arguments from JSON strings or dictionaries, enhancing error handling for malformed JSON inputs.
- Updated CrewAgentExecutor and AgentExecutor to utilize the new parsing function, streamlining argument validation and improving clarity in error reporting.
- Introduced unit tests for parse_tool_call_args to ensure robust functionality and correct handling of various input scenarios.

* feat: add keyword argument validation in BaseTool and Tool classes

- Introduced a new method `_validate_kwargs` in BaseTool to validate keyword arguments against the defined schema, ensuring proper argument handling.
- Updated the `run` and `arun` methods in both BaseTool and Tool classes to utilize the new validation method, improving error handling and robustness.
- Added comprehensive tests for asynchronous execution in `TestBaseToolArunValidation` to verify correct behavior for valid and invalid keyword arguments.

* Potential fix for pull request finding 'Syntax error'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

---------

Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-02-25 13:13:31 -05:00
Greyson LaLonde
ee374d01de chore: add versioning logic for devtools 2026-02-25 12:13:00 -05:00
Greyson LaLonde
9914e51199 feat: add versioned docs
starting with 1.10.0
2026-02-25 11:05:31 -05:00
nicoferdi96
2dbb83ae31 Private package registry (#4583)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
adding reference and explaination for package registry

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-02-24 19:37:17 +01:00
Mike Plachta
7377e1aa26 fix: bedrock region was always set to "us-east-1" not respecting the env var. (#4582)
* fix: bedrock region was always set to "us-east-1" not respecting the env
var.

code had AWS_REGION_NAME referenced, but not used, unified to
AWS_DEFAULT_REGION as per documentation

* DRY code improvement and fix caught by tests.

* Supporting litellm configuration
2026-02-24 09:59:01 -08:00
Greyson LaLonde
51754899a2 feat: migrate CLI http client from requests to httpx
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-02-20 18:21:05 -05:00
Greyson LaLonde
71b4f8402a fix: ensure callbacks are ran/awaited if promise
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
2026-02-20 13:15:50 -05:00
Greyson LaLonde
4a4c99d8a2 fix: capture method name in exception context
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-02-19 17:51:18 -05:00
Greyson LaLonde
28a6b855a2 fix: preserve enum type in router result; improve types 2026-02-19 17:30:47 -05:00
Lorenze Jay
d09656664d supporting parallel tool use (#4513)
* supporting parallel tool use

* ensure we respect max_usage_count

* ensure result_as_answer, hooks, and cache parodity

* improve crew agent executor

* address test comments
2026-02-19 14:07:28 -08:00
Lucas Gomide
49aa29bb41 docs: correct broken human_feedback examples with working self-loop patterns (#4520)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-02-19 09:02:01 -08:00
João Moura
8df499d471 Fix cyclic flows silently breaking when persistence ID is passed in inputs (#4501)
Some checks failed
Mark stale issues and pull requests / stale (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
* Implement user input handling in Flow class

- Introduced `FlowInputRequestedEvent` and `FlowInputReceivedEvent` to manage user input requests and responses during flow execution.
- Added `InputProvider` protocol and `InputResponse` dataclass for customizable input handling.
- Enhanced `Flow` class with `ask()` method to request user input, including timeout handling and state checkpointing.
- Updated `FlowConfig` to support custom input providers.
- Created `input_provider.py` for default input provider implementations, including a console-based provider.
- Added comprehensive tests for `ask()` functionality, covering basic usage, timeout behavior, and integration with flow machinery.

* Potential fix for pull request finding 'Unused import'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* Refactor test_flow_ask.py to streamline flow kickoff calls

- Removed unnecessary variable assignments for the result of `flow.kickoff()` in two test cases, improving code clarity.
- Updated assertions to ensure the expected execution log entries are present after the flow kickoff, enhancing test reliability.

* Add current_flow_method_name context variable for flow method tracking

- Introduced a new context variable, `current_flow_method_name`, to store the name of the currently executing flow method, defaulting to "unknown".
- Updated the Flow class to set and reset this context variable during method execution, enhancing the ability to track method calls without stack inspection.
- Removed the obsolete `_resolve_calling_method_name` method, streamlining the code and improving clarity.

* Enhance input history management in Flow class

- Introduced a new `InputHistoryEntry` TypedDict to structure user input history for the `ask()` method, capturing details such as the question, user response, method name, timestamp, and associated metadata.
- Updated the `_input_history` attribute in the Flow class to utilize the new `InputHistoryEntry` type, improving type safety and clarity in input history management.

* Enhance timeout handling in Flow class input requests

- Updated the `ask()` method to improve timeout management by manually managing the `ThreadPoolExecutor`, preventing potential deadlocks when the provider call exceeds the timeout duration.
- Added clarifications in the documentation regarding the behavior of the timeout and the underlying request handling, ensuring better understanding for users.

* Enhance memory reset functionality in CLI commands

- Introduced flow memory reset capabilities in the `reset_memories_command`, allowing for both crew and flow memory resets.
- Added a new utility function `_reset_flow_memory` to handle memory resets for individual flow instances, improving modularity and clarity.
- Updated the `get_flows` utility to discover flow instances from project files, enhancing the CLI's ability to manage flow states.
- Expanded test coverage to validate the new flow memory reset features, ensuring robust functionality and error handling.

* LINTER

* Fix resumption flag logic in Flow class and add regression test for cyclic flow persistence

- Updated the logic for setting the `_is_execution_resuming` flag to ensure it only activates when there are completed methods to replay, preventing incorrect suppression of cyclic re-execution during state reloads.
- Added a regression test to validate that cyclic router flows complete all iterations when persistence is enabled and an 'id' is passed in inputs, ensuring robust handling of flow execution in these scenarios.

---------

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-02-18 03:27:24 -03:00
João Moura
84d57c7a24 Implement user input handling in Flows (#4490)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* Implement user input handling in Flow class
2026-02-16 18:41:03 -03:00
João Moura
4aedd58829 Enhance HITL self-loop functionality in human feedback integration tests (#4493)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
- Added tests to verify self-loop behavior in HITL routers, ensuring they can handle multiple rejections and immediate approvals.
- Implemented `test_hitl_self_loop_routes_back_to_same_method`, `test_hitl_self_loop_multiple_rejections`, and `test_hitl_self_loop_immediate_approval` to validate the expected execution order and outcomes.
- Updated the `or_()` listener to support looping back to the same method based on human feedback outcomes, improving flow control in complex scenarios.
2026-02-15 21:54:42 -05:00
João Moura
09e9229efc New Memory Improvements (#4484)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* better DevEx

* Refactor: Update supported native providers and enhance memory handling

- Removed "groq" and "meta" from the list of supported native providers in `llm.py`.
- Added a safeguard in `flow.py` to ensure all background memory saves complete before returning.
- Improved error handling in `unified_memory.py` to prevent exceptions during shutdown, ensuring smoother memory operations and event bus interactions.

* Enhance Memory System with Consolidation and Learning Features

- Introduced memory consolidation mechanisms to prevent duplicate records during content saving, utilizing similarity checks and LLM decision-making.
- Implemented non-blocking save operations in the memory system, allowing agents to continue tasks while memory is being saved.
- Added support for learning from human feedback, enabling the system to distill lessons from past corrections and improve future outputs.
- Updated documentation to reflect new features and usage examples for memory consolidation and HITL learning.

* Enhance cyclic flow handling for or_() listeners

- Updated the Flow class to ensure that all fired or_() listeners are cleared between cycle iterations, allowing them to fire again in subsequent cycles. This change addresses a bug where listeners remained suppressed across iterations.
- Added regression tests to verify that or_() listeners fire correctly on every iteration in cyclic flows, ensuring expected behavior in complex routing scenarios.
2026-02-15 04:57:56 -03:00
João Moura
18d266c8e7 New Unified Memory System (#4420)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* chore: update memory management and dependencies

- Enhance the memory system by introducing a unified memory API that consolidates short-term, long-term, entity, and external memory functionalities.
- Update the `.gitignore` to exclude new memory-related files and blog directories.
- Modify `conftest.py` to handle missing imports for vcr stubs more gracefully.
- Add new development dependencies in `pyproject.toml` for testing and memory management.
- Refactor the `Crew` class to utilize the new unified memory system, replacing deprecated memory attributes.
- Implement memory context injection in `LiteAgent` to improve memory recall during agent execution.
- Update documentation to reflect changes in memory usage and configuration.

* feat: introduce Memory TUI for enhanced memory management

- Add a new command to the CLI for launching a Textual User Interface (TUI) to browse and recall memories.
- Implement the MemoryTUI class to facilitate user interaction with memory scopes and records.
- Enhance the unified memory API by adding a method to list records within a specified scope.
- Update `pyproject.toml` to include the `textual` dependency for TUI functionality.
- Ensure proper error handling for missing dependencies when accessing the TUI.

* feat: implement consolidation flow for memory management

- Introduce the ConsolidationFlow class to handle the decision-making process for inserting, updating, or deleting memory records based on new content.
- Add new data models: ConsolidationAction and ConsolidationPlan to structure the actions taken during consolidation.
- Enhance the memory types with new fields for consolidation thresholds and limits.
- Update the unified memory API to utilize the new consolidation flow for managing memory records.
- Implement embedding functionality for new content to facilitate similarity checks.
- Refactor existing memory analysis methods to integrate with the consolidation process.
- Update translations to include prompts for consolidation actions and user interactions.

* feat: enhance Memory TUI with Rich markup and improved UI elements

- Update the MemoryTUI class to utilize Rich markup for better visual representation of memory scope information.
- Introduce a color palette for consistent branding across the TUI interface.
- Refactor the CSS styles to improve the layout and aesthetics of the memory browsing experience.
- Enhance the display of memory entries, including better formatting for records and importance ratings.
- Implement loading indicators and error messages with Rich styling for improved user feedback during recall operations.
- Update the action bindings and navigation prompts for a more intuitive user experience.

* feat: enhance Crew class memory management and configuration

- Update the Crew class to allow for more flexible memory configurations by accepting Memory, MemoryScope, or MemorySlice instances.
- Refactor memory initialization logic to support custom memory configurations while maintaining backward compatibility.
- Improve documentation for memory-related fields to clarify usage and expectations.
- Introduce a recall oversample factor to optimize memory recall processes.
- Update related memory types and configurations to ensure consistency across the memory management system.

* chore: update dependency overrides and enhance memory management

- Added an override for the 'rich' dependency to allow compatibility with 'textual' requirements.
- Updated the 'pyproject.toml' and 'uv.lock' files to reflect the new dependency specifications.
- Refactored the Crew class to simplify memory configuration handling by allowing any type for the memory attribute.
- Improved error messages in the CLI for missing 'textual' dependency to guide users on installation.
- Introduced new packages and dependencies in the project to enhance functionality and maintain compatibility.

* refactor: enhance thread safety in flow management

- Updated LockedListProxy and LockedDictProxy to subclass list and dict respectively, ensuring compatibility with libraries requiring strict type checks.
- Improved documentation to clarify the purpose of these proxies and their thread-safe operations.
- Ensured that all mutations are protected by locks while reads delegate to the underlying data structures, enhancing concurrency safety.

* chore: update dependency versions and improve Python compatibility

- Downgraded 'vcrpy' dependency to version 7.0.0 for compatibility.
- Enhanced 'uv.lock' to include more granular resolution markers for Python versions and implementations, ensuring better compatibility across different environments.
- Updated 'urllib3' and 'selenium' dependencies to specify versions based on Python implementation, improving stability and performance.
- Removed deprecated resolution markers for 'fastembed' and streamlined its dependencies for better clarity.

* fix linter

* chore: update uv.lock for improved dependency management and memory management enhancements

- Incremented revision number in uv.lock to reflect changes.
- Added a new development dependency group in uv.lock, specifying versions for tools like pytest, mypy, and pre-commit to streamline development workflows.
- Enhanced error handling in CLI memory functions to provide clearer feedback on missing dependencies.
- Refactored memory management classes to improve type hints and maintainability, ensuring better compatibility with future updates.

* fix tests

* refactor: remove obsolete RAGStorage tests and clean up error handling

- Deleted outdated tests for RAGStorage that were no longer relevant, including tests for client failures, save operation failures, and reset failures.
- Cleaned up the test suite to focus on current functionality and improve maintainability.
- Ensured that remaining tests continue to validate the expected behavior of knowledge storage components.

* fix test

* fix texts

* fix tests

* forcing new commit

* fix: add location parameter to Google Vertex embedder configuration for memory integration tests

* debugging CI

* adding debugging for CI

* refactor: remove unnecessary logging for memory checks in agent execution

- Eliminated redundant logging statements related to memory checks in the Agent and CrewAgentExecutor classes.
- Simplified the memory retrieval logic by directly checking for available memory without logging intermediate states.
- Improved code readability and maintainability by reducing clutter in the logging output.

* udpating desp

* feat: enhance thread safety in LockedListProxy and LockedDictProxy

- Added equality comparison methods (__eq__ and __ne__) to LockedListProxy and LockedDictProxy to allow for safe comparison of their contents.
- Implemented consistent locking mechanisms to prevent deadlocks during comparisons.
- Improved the overall robustness of these proxy classes in multi-threaded environments.

* feat: enhance memory functionality in Flows documentation and memory system

- Added a new section on memory usage within Flows, detailing built-in methods for storing and recalling memories.
- Included an example of a Research and Analyze Flow demonstrating the integration of memory for accumulating knowledge over time.
- Updated the Memory documentation to clarify the unified memory system and its capabilities, including adaptive-depth recall and composite scoring.
- Introduced a new configuration parameter, `recall_oversample_factor`, to improve the effectiveness of memory retrieval processes.

* update docs

* refactor: improve memory record handling and pagination in unified memory system

- Simplified the `get_record` method in the Memory class by directly accessing the storage's `get_record` method.
- Enhanced the `list_records` method to include an `offset` parameter for pagination, allowing users to skip a specified number of records.
- Updated documentation for both methods to clarify their functionality and parameters, improving overall code clarity and usability.

* test: update memory scope assertions in unified memory tests

- Modified assertions in `test_lancedb_list_scopes_get_scope_info` and `test_memory_list_scopes_info_tree` to check for the presence of the "/team" scope instead of the root scope.
- Clarified comments to indicate that `list_scopes` returns child scopes rather than the root itself, enhancing test clarity and accuracy.

* feat: integrate memory tools for agents and crews

- Added functionality to inject memory tools into agents during initialization, enhancing their ability to recall and remember information mid-task.
- Implemented a new `_add_memory_tools` method in the Crew class to facilitate the addition of memory tools when memory is available.
- Introduced `RecallMemoryTool` and `RememberTool` classes in a new `memory_tools.py` file, providing agents with active recall and memory storage capabilities.
- Updated English translations to include descriptions for the new memory tools, improving user guidance on their usage.

* refactor: streamline memory recall functionality across agents and tools

- Removed the 'depth' parameter from memory recall calls in LiteAgent and Agent classes, simplifying the recall process.
- Updated the MemoryTUI to use 'deep' depth by default for more comprehensive memory retrieval.
- Enhanced the MemoryScope and MemorySlice classes to default to 'deep' depth, improving recall accuracy.
- Introduced a new 'recall_queries' field in QueryAnalysis to optimize semantic vector searches with targeted phrases.
- Updated documentation and comments to reflect changes in memory recall behavior and parameters.

* refactor: optimize memory management in flow classes

- Enhanced memory auto-creation logic in Flow class to prevent unnecessary Memory instance creation for internal flows (RecallFlow, ConsolidationFlow) by introducing a _skip_auto_memory flag.
- Removed the deprecated time_hints field from QueryAnalysis and replaced it with a more flexible time_filter field to better handle time-based queries.
- Updated documentation and comments to reflect changes in memory handling and query analysis structure, improving clarity and usability.

* updates tests

* feat: introduce EncodingFlow for enhanced memory encoding pipeline

- Added a new EncodingFlow class to orchestrate the encoding process for memory, integrating LLM analysis and embedding.
- Updated the Memory class to utilize EncodingFlow for saving content, improving the overall memory management and conflict resolution.
- Enhanced the unified memory module to include the new EncodingFlow in its public API, facilitating better memory handling.
- Updated tests to ensure proper functionality of the new encoding flow and its integration with existing memory features.

* refactor: optimize memory tool integration and recall flow

- Streamlined the addition of memory tools in the Agent class by using list comprehension for cleaner code.
- Enhanced the RecallFlow class to build task lists more efficiently with list comprehensions, improving readability and performance.
- Updated the RecallMemoryTool to utilize list comprehensions for formatting memory results, simplifying the code structure.
- Adjusted test assertions in LiteAgent to reflect the default behavior of memory recall depth, ensuring clarity in expected outcomes.

* Potential fix for pull request finding 'Empty except'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* chore: gen missing cassette

* fix

* test: enhance memory extraction test by mocking recall to prevent LLM calls

Updated the test for memory extraction to include a mock for the recall method, ensuring that the test focuses on the save path without invoking external LLM calls. This improves test reliability and clarity.

* refactor: enhance memory handling by adding agent role parameter

Updated memory storage methods across multiple classes to include an optional `agent_role` parameter, improving the context of stored memories. Additionally, modified the initialization of several flow classes to suppress flow events, enhancing performance and reducing unnecessary event triggers.

* feat: enhance agent memory functionality with recall and save mechanisms

Implemented memory context injection during agent kickoff, allowing for memory recall before execution and passive saving of results afterward. Added new methods to handle memory saving and retrieval, including error handling for memory operations. Updated the BaseAgent class to support dynamic memory resolution and improved memory record structure with source and privacy attributes for better provenance tracking.

* test

* feat: add utility method to simplify tools field in console formatter

Introduced a new static method `_simplify_tools_field` in the console formatter to transform the 'tools' field from full tool objects to a comma-separated string of tool names. This enhancement improves the readability of tool information in the output.

* refactor: improve lazy initialization of LLM and embedder in Memory class

Refactored the Memory class to implement lazy initialization for the LLM and embedder, ensuring they are only created when first accessed. This change enhances the robustness of the Memory class by preventing initialization failures when constructed without an API key. Additionally, updated error handling to provide clearer guidance for users on resolving initialization issues.

* refactor: consolidate memory saving methods for improved efficiency

Refactored memory handling across multiple classes to replace individual memory saving calls with a batch method, `remember_many`, enhancing performance and reducing redundancy. Updated related tools and schemas to support single and multiple item memory operations, ensuring a more streamlined interface for memory interactions. Additionally, improved documentation and test coverage for the new functionality.

* feat: enhance MemoryTUI with improved layout and entry handling

Updated the MemoryTUI class to incorporate a new vertical layout, adding an OptionList for displaying entries and enhancing the detail view for selected records. Introduced methods for populating entry and recall lists, improving user interaction and data presentation. Additionally, refined CSS styles for better visual organization and focus handling.

* fix test

* feat: inject memory tools into LiteAgent for enhanced functionality

Added logic to the LiteAgent class to inject memory tools if memory is configured, ensuring that memory tools are only added if they are not already present. This change improves the agent's capability to utilize memory effectively during execution.

* feat: add synchronous execution method to ConsolidationFlow for improved integration

Introduced a new `run_sync()` method in the ConsolidationFlow class to facilitate procedural execution of the consolidation pipeline without relying on asynchronous event loops. Updated the EncodingFlow class to utilize this method for conflict resolution, ensuring compatibility within its async context. This change enhances the flow's ability to manage memory records effectively during nested executions.

* refactor: update ConsolidationFlow and EncodingFlow for improved async handling

Removed the synchronous `run_sync()` method from ConsolidationFlow and refactored the consolidate method in EncodingFlow to be asynchronous. This change allows for direct awaiting of the ConsolidationFlow's kickoff method, enhancing compatibility within the async event loop and preventing nested asyncio.run() issues. Additionally, updated the execution plan to listen for multiple paths, streamlining the consolidation process.

* fix: update flow documentation and remove unused ConsolidationFlow

Corrected the comment in Flow class regarding internal flows, replacing "ConsolidationFlow" with "EncodingFlow". Removed the ConsolidationFlow class as it is no longer needed, streamlining the memory handling process. Updated related imports and ensured that the memory module reflects these changes, enhancing clarity and maintainability.

* feat: enhance memory handling with background saving and query analysis optimization

Implemented a background saving mechanism in the Memory class to allow non-blocking memory operations, improving performance during high-load scenarios. Added a query analysis threshold to skip LLM calls for short queries, optimizing recall efficiency. Updated related methods and documentation to reflect these changes, ensuring a more responsive and efficient memory management system.

* fix test

* fix test

* fix: handle synchronous fallback for save operations in Memory class

Updated the Memory class to implement a synchronous fallback mechanism for save operations when the background thread pool is shut down. This change ensures that late save requests still succeed, improving reliability in memory management during shutdown scenarios.

* feat: implement HITL learning features in human feedback decorator

Added support for learning from human feedback in the human feedback decorator. Introduced parameters to enable lesson distillation and pre-review of outputs based on past feedback. Updated related tests to ensure proper functionality of the learning mechanism, including memory interactions and default LLM usage.

---------

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-02-13 21:34:37 -03:00
Chujiang
670cdcacaa chore: update template files to use modern type annotations 2026-02-13 09:30:58 -05:00
Greyson LaLonde
f7e3b4dbe0 chore: remove downstream sync
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-02-12 14:35:23 -05:00
Rip&Tear
0ecf5d1fb0 docs: clarify NL2SQL security model and hardening guidance (#4465)
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-02-12 10:50:29 -08:00
Giovanni Vella
6c0fb7f970 fix broken tasks table
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Signed-off-by: Giovanni Vella <giovanni.vella98@gmail.com>
2026-02-12 10:55:40 -05:00
Greyson LaLonde
cde33fd981 feat: add yanked detection for version notes
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-02-11 23:31:06 -05:00
Lorenze Jay
2ed0c2c043 imp compaction (#4399)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
* imp compaction

* fix lint

* cassette gen

* cassette gen

* improve assert

* adding azure

* fix global docstring
2026-02-11 15:52:03 -08:00
Lorenze Jay
0341e5aee7 supporting prompt cache results show (#4447)
* supporting prompt cache

* droped azure tests

* fix tests

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-02-11 14:07:15 -08:00
Mike Plachta
397d14c772 fix: correct CLI flag format from --skip-provider to --skip_provider (#4462)
Update documentation to use underscore instead of hyphen in the `--skip_provider` flag across all CLI command examples for consistency with actual CLI implementation.
2026-02-11 13:51:54 -08:00
Lucas Gomide
fc3e86e9a3 docs Adding 96 missing actions across 9 integrations (#4460)
* docs: add missing integration actions from OAuth config

Sync enterprise integration docs with crewai-oauth apps.js config.
Adds ~96 missing actions across 9 integrations:
- Google Contacts: 4 contact group actions
- Google Slides: 14 slide manipulation/content actions
- Microsoft SharePoint: 27 file, Excel, and Word actions
- Microsoft Excel: 2 actions (get_used_range_metadata, get_table_data)
- Microsoft Word: 2 actions (copy_document, move_document)
- Google Docs: 27 text formatting, table, and header/footer actions
- Microsoft Outlook: 7 message and calendar event actions
- Microsoft OneDrive: 5 path-based and discovery actions
- Microsoft Teams: 8 meeting, channel, and reply actions

* docs: add missing integration actions from OAuth config

Sync pt-BR enterprise integration docs with crewai-oauth apps.js config.
Adds ~96 missing actions across 9 integrations, translated to Portuguese:
- Google Contacts: 2 contact group actions
- Google Slides: 14 slide manipulation/content actions
- Microsoft SharePoint: 27 file, Excel, and Word actions
- Microsoft Excel: 2 actions (get_used_range_metadata, get_table_data)
- Microsoft Word: 2 actions (copy_document, move_document)
- Google Docs: 27 text formatting, table, and header/footer actions
- Microsoft Outlook: 7 message and calendar event actions
- Microsoft OneDrive: 5 path-based and discovery actions
- Microsoft Teams: 8 meeting, channel, and reply actions

* docs: add missing integration actions from OAuth config

Sync Korean enterprise integration docs with crewai-oauth apps.js config.
Adds ~96 missing actions across 9 integrations, translated to Korean:
- Google Contacts: 2 contact group actions
- Google Slides: 14 slide manipulation/content actions
- Microsoft SharePoint: 27 file, Excel, and Word actions
- Microsoft Excel: 2 actions (get_used_range_metadata, get_table_data)
- Microsoft Word: 2 actions (copy_document, move_document)
- Google Docs: 27 text formatting, table, and header/footer actions
- Microsoft Outlook: 7 message and calendar event actions
- Microsoft OneDrive: 5 path-based and discovery actions
- Microsoft Teams: 8 meeting, channel, and reply actions

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-02-11 15:17:54 -05:00
Mike Plachta
2882df5daf replace old .cursorrules with AGENTS.md (#4451)
* chore: remove .cursorrules file
feat: add AGENTS.md file to any newly created file

* move the copy of the tests
2026-02-11 10:07:24 -08:00
Greyson LaLonde
3a22e80764 fix: ensure openai tool call stream is finalized
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2026-02-11 10:02:31 -05:00
Greyson LaLonde
9b585a934d fix: pass started_event_id to crew 2026-02-11 09:30:07 -05:00
Rip&Tear
46e1b02154 chore: fix codeql coverage and action version (#4454) 2026-02-11 18:20:07 +08:00
Rip&Tear
87675b49fd test: avoid URL substring assertion in brave search test (#4453)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-02-11 14:32:10 +08:00
Lucas Gomide
a3bee66be8 Address OpenSSL CVE-2025-15467 vulnerability (#4426)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* fix(security): bump regex from 2024.9.11 to 2026.1.15

Address security vulnerability flagged in regex==2024.9.11

* bump mcp from 1.23.1 to 1.26.0

Address security vulnerability flagged in mcp==1.16.0 (resolved to 1.23.3)
2026-02-10 09:39:35 -08:00
Greyson LaLonde
f6fa04528a fix: add async HITL support and chained-router tests
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
asynchronous human-in-the-loop handling and related fixes.

- Extend human_input provider with async support: AsyncExecutorContext, handle_feedback_async, async prompt helpers (_prompt_input_async, _async_readline), and async training/regular feedback loops in SyncHumanInputProvider.
- Add async handler methods in CrewAgentExecutor and AgentExecutor (_ahandle_human_feedback, _ainvoke_loop) to integrate async provider flows.
- Change PlusAPI.get_agent to an async httpx call and adapt caller in agent_utils to run it via asyncio.run.
- Simplify listener execution in flow.Flow to correctly pass HumanFeedbackResult to listeners and unify execution path for router outcomes.
- Remove deprecated types/hitl.py definitions.
- Add tests covering chained router feedback, rejected paths, and mixed router/non-router listeners to prevent regressions.
2026-02-06 16:29:27 -05:00
Greyson LaLonde
7d498b29be fix: event ordering; flow state locks, routing
* fix: add current task id context and flow updates

introduce a context var for the current task id in `crewai.context` to track task scope. update `Flow._execute_single_listener` to return `(result, event_id)` and adjust callers to unpack it and append `FlowMethodName(str(result))` to `router_results`. set/reset the current task id at the start/end of task execution (async + sync) with minor import and call-site tweaks.

* fix: await event futures and flush event bus

call `crewai_event_bus.flush()` after crew kickoff. in `Flow`, await event handler futures instead of just collecting them: await pending `_event_futures` before finishing, await emitted futures immediately with try/except to log failures, then clear `_event_futures`. ensures handlers complete and errors surface.

* fix: continue iteration on tool completion events

expand the loop bridge listener to also trigger on tool completion events (`tool_completed` and `native_tool_completed`) so agent iteration resumes after tools finish. add a `requests.post` mock and response fixture in the liteagent test to simulate platform tool execution. refresh and sanitize vcr cassettes (updated model responses, timestamps, and header placeholders) to reflect tool-call flows and new recordings.

* fix: thread-safe state proxies & native routing

add thread-safe state proxies and refactor native tool routing.

* introduce `LockedListProxy` and `LockedDictProxy` in `flow.py` and update `StateProxy` to return them for list/dict attrs so mutations are protected by the flow lock.
* update `AgentExecutor` to use `StateProxy` on flow init, guard the messages setter with the state lock, and return a `StateProxy` from the temp state accessor.
* convert `call_llm_native_tools` into a listener (no direct routing return) and add `route_native_tool_result` to route based on state (pending tool calls, final answer, or context error).
* minor cleanup in `continue_iteration` to drop orphan listeners on init.
* update test cassettes for new native tool call responses, timestamps, and ids.

improves concurrency safety for shared state and makes native tool routing explicit.

* chore: regen cassettes

* chore: regen cassettes, remove duplicate listener call path
2026-02-06 14:02:43 -05:00
Greyson LaLonde
1308bdee63 feat: add started_event_id and set in eventbus
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* feat: add started_event_id and set in eventbus

* chore: update additional test assumption

* fix: restore event bus handlers on context exit

fix rollback in crewai events bus so that exiting the context restores
the previous _sync_handlers, _async_handlers, _handler_dependencies, and _execution_plan_cache by assigning shallow copies of the saved dicts. previously these
were set to empty dicts on exit, which caused registered handlers and cached execution plans to be lost.
2026-02-05 21:28:23 -05:00
Greyson LaLonde
6bb1b178a1 chore: extension points
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Introduce ContextVar-backed hooks and small API/behavior changes to improve extensibility and testability.

Changes include:
- agents: mark configure_structured_output as abstract and change its parameter to task to reflect use of task metadata.
- tracing: convert _first_time_trace_hook to a ContextVar and call .get() to safely retrieve the hook.
- console formatter: add _disable_version_check ContextVar and skip version checks when set (avoids noisy checks in certain contexts).
- flow: use current_triggering_event_id variable when scheduling listener tasks to keep naming consistent.
- hallucination guardrail: make context optional, add _validate_output_hook to allow custom validation hooks, update examples and return contract to allow hooks to override behavior.
- agent utilities: add _create_plus_client_hook for injecting a Plus client (used in tests/alternate flows), ensure structured tools have current_usage_count initialized and propagate to original tool, and fall back to creating PlusAPI client when no hook is provided.
2026-02-05 12:49:54 -05:00
Greyson LaLonde
fe2a4b4e40 chore: bug fixes and more refactor
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Refactor agent executor to delegate human interactions to a provider: add messages and ask_for_human_input properties, implement _invoke_loop and _format_feedback_message, and replace the internal iterative/training feedback logic with a call to get_provider().handle_feedback.

Make LLMGuardrail kickoff coroutine-aware by detecting coroutines and running them via asyncio.run so both sync and async agents are supported.

Make telemetry more robust by safely handling missing task.output (use empty string) and returning early if span is None before setting attributes.

Improve serialization to detect circular references via an _ancestors set, propagate it through recursive calls, and pass exclude/max_depth/_current_depth consistently to prevent infinite recursion and produce stable serializable output.
2026-02-04 21:21:54 -05:00
Greyson LaLonde
711e7171e1 chore: improve hook typing and registration
Allow hook registration to accept both typed hook types and plain callables by importing and using After*/Before*CallHookCallable types; add explicit LLMCallHookContext and ToolCallHookContext typing in crew_base. Introduce a post-initialize crew hook list and invoke hooks after Crew instance initialization. Refactor filtered hook factory functions to include precise typing and clearer local names (before_llm_hook/after_llm_hook/before_tool_hook/after_tool_hook) and register those with the instance. Update CrewInstance protocol to include _registered_hook_functions and _hooks_being_registered fields.
2026-02-04 21:16:20 -05:00
Vini Brasil
76b5f72e81 Fix tool error causing double event scope pop (#4373)
When a tool raises an error, both ToolUsageErrorEvent and
ToolUsageFinishedEvent were being emitted. Since both events pop the
event scope stack, this caused the agent scope to be incorrectly popped
along with the tool scope.
2026-02-04 20:34:08 -03:00
Greyson LaLonde
d86d43d3e0 chore: refactor crew to provider
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Enable dynamic extension exports and small behavior fixes across events and flow modules:

- events/__init__.py: Added _extension_exports and extended __getattr__ to lazily resolve registered extension values or import paths.
- events/event_bus.py: Implemented off() to unregister sync/async handlers, clean handler dependencies, and invalidate execution plan cache.
- events/listeners/tracing/utils.py: Added Callable import and _first_time_trace_hook to allow overriding first-time trace auto-collection behavior.
- events/types/tool_usage_events.py: Changed ToolUsageEvent.run_attempts default from None to 0 to avoid nullable handling.
- events/utils/console_formatter.py: Respect CREWAI_DISABLE_VERSION_CHECK env var to skip version checks in CI-like flows.
- flow/async_feedback/__init__.py: Added typing.Any import, _extension_exports and __getattr__ to support extensions via attribute lookup.

These changes add extension points and safer defaults, and provide a way to unregister event handlers.
2026-02-04 16:05:21 -05:00
Greyson LaLonde
6bfc98e960 refactor: extract hitl to provider pattern
* refactor: extract hitl to provider pattern

- add humaninputprovider protocol with setup_messages and handle_feedback
- move sync hitl logic from executor to synchuman inputprovider
- add _passthrough_exceptions extension point in agent/core.py
- create crewai.core.providers module for extensible components
- remove _ask_human_input from base_agent_executor_mixin
2026-02-04 15:40:22 -05:00
Greyson LaLonde
3cc33ef6ab fix: resolve complex schema $ref pointers in mcp tools
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: resolve complex schema $ref pointers in mcp tools

* chore: update tool specifications

* fix: adapt mcp tools; sanitize pydantic json schemas

* fix: strip nulls from json schemas and simplify mcp args

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-02-03 20:47:58 -05:00
Lorenze Jay
3fec4669af Lorenze/fix/anthropic available functions call (#4360)
* feat: enhance AnthropicCompletion to support available functions in tool execution

- Updated the `_prepare_completion_params` method to accept `available_functions` for better tool handling.
- Modified tool execution logic to directly return results from tools when `available_functions` is provided, aligning behavior with OpenAI's model.
- Added new test cases to validate the execution of tools with available functions, ensuring correct argument passing and result formatting.

This change improves the flexibility and usability of the Anthropic LLM integration, allowing for more complex interactions with tools.

* refactor: remove redundant event emission in AnthropicCompletion

* fix test

* dry up
2026-02-03 16:30:43 -08:00
dependabot[bot]
d3f424fd8f chore(deps-dev): bump types-aiofiles
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Bumps [types-aiofiles](https://github.com/typeshed-internal/stub_uploader) from 24.1.0.20250822 to 25.1.0.20251011.
- [Commits](https://github.com/typeshed-internal/stub_uploader/commits)

---
updated-dependencies:
- dependency-name: types-aiofiles
  dependency-version: 25.1.0.20251011
  dependency-type: direct:development
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-02-03 12:02:28 -05:00
Matt Aitchison
fee9445067 fix: add .python-version to fix Dependabot uv updates (#4352)
Dependabot's uv updater defaults to Python 3.14.2, which is incompatible
with the project's requires-python constraint (>=3.10, <3.14). Adding
.python-version pins the Python version to 3.13 for dependency updates.

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-02-03 10:55:01 -06:00
Greyson LaLonde
a3c01265ee feat: add version check & integrate update notices 2026-02-03 10:17:50 -05:00
Matt Aitchison
aa7e7785bc chore: group dependabot security updates into single PR (#4351)
Configure dependabot to batch security updates together while keeping
regular version updates as separate PRs.
2026-02-03 08:53:28 -06:00
Thiago Moretto
e30645e855 limit stagehand dep version to 0.5.9 due breaking changes (#4339)
* limit to 0.5.9 due breaking changes + add env vars requirements

* fix tool spec extract that was ignoring with default

* original tool spec

* update spec
2026-02-03 09:43:24 -05:00
Greyson LaLonde
c1d2801be2 fix: reject reserved script names for crew folders 2026-02-03 09:16:55 -05:00
Greyson LaLonde
6a8483fcb6 fix: resolve race condition in guardrail event emission test 2026-02-03 09:06:48 -05:00
Greyson LaLonde
5fb602dff2 fix: replace timing-based concurrency test with state tracking 2026-02-03 08:58:51 -05:00
Greyson LaLonde
b90cff580a fix: relax openai and litellm dependency constraints 2026-02-03 08:51:55 -05:00
Vini Brasil
576b74b2ef Add call_id to LLM events for correlating requests (#4281)
When monitoring LLM events, consumers need to know which events belong
to the same API call. Before this change, there was no way to correlate
LLMCallStartedEvent, LLMStreamChunkEvent, and LLMCallCompletedEvent
belonging to the same request.
2026-02-03 10:10:33 -03:00
Greyson LaLonde
7590d4c6e3 fix: enforce additionalProperties=false in schemas
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: enforce additionalProperties=false in schemas

* fix: ensure nested items have required properties
2026-02-02 22:19:04 -05:00
Sampson
8c6436234b adds additional search params (#4321)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Introduces support for additional Brave Search API web-search parameters.
2026-02-02 11:17:02 -08:00
Lucas Gomide
96bde4510b feat: auto update tools.specs (#4341) 2026-02-02 12:52:00 -05:00
Greyson LaLonde
9d7f45376a fix: use contextvars for flow execution context 2026-02-02 11:24:02 -05:00
Thiago Moretto
536447ab0e declare stagehand package as dep for StagehandTool (#4336) 2026-02-02 09:45:47 -05:00
Lorenze Jay
63a508f601 feat: bump versions to 1.9.3 (#4316)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* feat: bump versions to 1.9.3

* bump bump
2026-01-30 14:24:25 -08:00
Greyson LaLonde
102b6ae855 feat: add a2a liteagent, auth, transport negotiation, and file support
* feat: add server-side auth schemes and protocol extensions

- add server auth scheme base class and implementations (api key, bearer token, basic/digest auth, mtls)
- add server-side extension system for a2a protocol extensions
- add extensions middleware for x-a2a-extensions header management
- add extension validation and registry utilities
- enhance auth utilities with server-side support
- add async intercept method to match client call interceptor protocol
- fix type_checking import to resolve mypy errors with a2aconfig

* feat: add transport negotiation and content type handling

- add transport negotiation logic with fallback support
- add content type parser and encoder utilities
- add transport configuration models (client and server)
- add transport types and enums
- enhance config with transport settings
- add negotiation events for transport and content type

* feat: add a2a delegation support to LiteAgent

* feat: add file input support to a2a delegation and tasks

Introduces handling of file inputs in A2A delegation flows by converting file dictionaries to protocol-compatible parts and propagating them through delegation and task execution functions. Updates include utility functions for file conversion, changes to message construction, and passing input_files through relevant APIs.

* feat: liteagent a2a delegation support to kickoff methods
2026-01-30 17:10:00 -05:00
Lorenze Jay
19ce56032c fix: improve output handling and response model integration in agents (#4307)
* fix: improve output handling and response model integration in agents

- Refactored output handling in the Agent class to ensure proper conversion and formatting of outputs, including support for BaseModel instances.
- Enhanced the AgentExecutor class to correctly utilize response models during execution, improving the handling of structured outputs.
- Updated the Gemini and Anthropic completion providers to ensure compatibility with new response model handling, including the addition of strict mode for function definitions.
- Improved the OpenAI completion provider to enforce strict adherence to function schemas.
- Adjusted translations to clarify instructions regarding output formatting and schema adherence.

* drop what was a print that didnt get deleted properly

* fixes gemini

* azure working

* bedrock works

* added tests

* adjust test

* fix tests and regen

* fix tests and regen

* refactor: ensure stop words are applied correctly in Azure, Gemini, and OpenAI completions; add tests to validate behavior with structured outputs

* linting
2026-01-30 12:27:46 -08:00
Joao Moura
85f31459c1 docs link
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2026-01-30 09:05:36 -08:00
Joao Moura
6fcf748dae refactor: update Flow HITL Management documentation to emphasize email-first notifications, routing rules, and auto-response capabilities; remove outdated references to assignment and SLA management 2026-01-30 08:44:54 -08:00
Joao Moura
38065e29ce updating docs 2026-01-30 08:44:54 -08:00
Lorenze Jay
e291a97bdd chore: update version to 1.9.2 across all relevant files (#4299)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-01-28 17:11:44 -08:00
Lorenze Jay
2d05e59223 Lorenze/improve tool response pt2 (#4297)
* no need post tool reflection on native tools

* refactor: update prompt generation to prevent thought leakage

- Modified the prompt structure to ensure agents without tools use a simplified format, avoiding ReAct instructions.
- Introduced a new 'task_no_tools' slice for agents lacking tools, ensuring clean output without Thought: prefixes.
- Enhanced test coverage to verify that prompts do not encourage thought leakage, ensuring outputs remain focused and direct.
- Added integration tests to validate that real LLM calls produce clean outputs without internal reasoning artifacts.

* dont forget the cassettes
2026-01-28 16:53:19 -08:00
Greyson LaLonde
a731efac8d fix: improve structured output handling across providers and agents
- add gemini 2.0 schema support using response_json_schema with propertyordering while retaining backward compatibility for earlier models
- refactor llm completions to return validated pydantic models when a response_model is provided, updating hooks, types, and tests for consistent structured outputs
- extend agentfinish and executors to support basemodel outputs, improve anthropic structured parsing, and clean up schema utilities, tests, and original_json handling
2026-01-28 16:59:55 -05:00
Greyson LaLonde
1e27cf3f0f fix: ensure verbosity flag is applied
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2026-01-28 11:52:47 -05:00
Lorenze Jay
381ad3a9a8 chore: update version to 1.9.1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-01-27 20:08:53 -05:00
Lorenze Jay
f53bdb28ac feat: implement before and after tool call hooks in CrewAgentExecutor… (#4287)
* feat: implement before and after tool call hooks in CrewAgentExecutor and AgentExecutor

- Added support for before and after tool call hooks in both CrewAgentExecutor and AgentExecutor classes.
- Introduced ToolCallHookContext to manage context for hooks, allowing for enhanced control over tool execution.
- Implemented logic to block tool execution based on before hooks and to modify results based on after hooks.
- Added integration tests to validate the functionality of the new hooks, ensuring they work as expected in various scenarios.
- Enhanced the overall flexibility and extensibility of tool interactions within the CrewAI framework.

* Potential fix for pull request finding 'Unused local variable'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* Potential fix for pull request finding 'Unused local variable'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* test: add integration test for before hook blocking tool execution in Crew

- Implemented a new test to verify that the before hook can successfully block the execution of a tool within a crew.
- The test checks that the tool is not executed when the before hook returns False, ensuring proper control over tool interactions.
- Enhanced the validation of hook calls to confirm that both before and after hooks are triggered appropriately, even when execution is blocked.
- This addition strengthens the testing coverage for tool call hooks in the CrewAI framework.

* drop unused

* refactor(tests): remove OPENAI_API_KEY check from tool hook tests

- Eliminated the check for the OPENAI_API_KEY environment variable in the test cases for tool hooks.
- This change simplifies the test setup and allows for running tests without requiring the API key to be set, improving test accessibility and flexibility.

---------

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-01-27 14:56:50 -08:00
Greyson LaLonde
3b17026082 fix: correct tool-calling content handling and schema serialization
- fix(gemini): prevent tool calls from using stale text content; correct key refs
- fix(agent-executor): resolve type errors
- refactor(schema): extract Pydantic schema utilities from platform tools
- fix(schema): properly serialize schemas and ensure Responses API uses a separate structure
- fix: preserve list identity to avoid mutation/aliasing issues
- chore(tests): update assumptions to match new behavior
2026-01-27 15:47:29 -05:00
Greyson LaLonde
d52dbc1f4b chore: add missing change logs (#4285)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* chore: add missing change logs

* chore: add translations
2026-01-26 18:26:01 -08:00
Lorenze Jay
6b926b90d0 chore: update version to 1.9.0 across all relevant files (#4284)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
- Bumped the version number to 1.9.0 in pyproject.toml files and __init__.py files across the CrewAI library and its tools.
- Updated dependencies to use the new version of crewai-tools (1.9.0) for improved functionality and compatibility.
- Ensured consistency in versioning across the codebase to reflect the latest updates.
2026-01-26 16:36:35 -08:00
Lorenze Jay
fc84daadbb fix: enhance file store with fallback memory cache when aiocache is n… (#4283)
* fix: enhance file store with fallback memory cache when aiocache is not installed

- Added a simple in-memory cache implementation to serve as a fallback when the aiocache library is unavailable.
- Improved error handling for the aiocache import, ensuring that the application can still function without it.
- This change enhances the robustness of the file store utility by providing a reliable caching mechanism in various environments.

* drop fallback

* Potential fix for pull request finding 'Unused global variable'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

---------

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-01-26 15:12:34 -08:00
Lorenze Jay
58b866a83d Lorenze/supporting vertex embeddings (#4282)
* feat: introduce GoogleGenAIVertexEmbeddingFunction for dual SDK support

- Added a new embedding function to support both the legacy vertexai.language_models SDK and the new google-genai SDK for Google Vertex AI.
- Updated factory methods to route to the new embedding function.
- Enhanced VertexAIProvider and related configurations to accommodate the new model options.
- Added integration tests for Google Vertex embeddings with Crew memory, ensuring compatibility and functionality with both authentication methods.

This update improves the flexibility and compatibility of Google Vertex AI embeddings within the CrewAI framework.

* fix test count

* rm comment

* regen cassettes

* regen

* drop variable from .envtest

* dreict to relevant trest only
2026-01-26 14:55:03 -08:00
Greyson LaLonde
9797567342 feat: add structured outputs and response_format support across providers (#4280)
* feat: add response_format parameter to Azure and Gemini providers

* feat: add structured outputs support to Bedrock and Anthropic providers

* chore: bump anthropic dep

* fix: use beta structured output for new models
2026-01-26 11:03:33 -08:00
Greyson LaLonde
a32de6bdac fix: ensure doc list is not empty
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2026-01-26 05:08:01 -05:00
Vidit Ostwal
06a58e463c feat: adding response_id in streaming response 2026-01-26 04:20:04 -05:00
Vidit Ostwal
3d771f03fa fix: ensure bedrock client handles stop sequences properly
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-01-25 20:28:09 -05:00
Greyson LaLonde
db7aeb5a00 chore: disable chroma telemetry
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2026-01-25 16:23:29 -05:00
Lorenze Jay
0cb40374de Enhance Gemini LLM Tool Handling and Add Test for Float Responses (#4273)
- Updated the GeminiCompletion class to handle non-dict values returned from tools, ensuring that floats are wrapped in a dictionary format for consistent response handling.
- Introduced a new YAML cassette to test the Gemini LLM's ability to process tools that return float values, verifying that the agent can correctly utilize the sum_numbers tool and return the expected results.
- Added a comprehensive test case to validate the integration of the sum_numbers tool within the Gemini LLM, ensuring accurate calculations and proper response formatting.

These changes improve the robustness of tool interactions within the Gemini LLM and enhance testing coverage for float return values.

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-01-25 12:50:49 -08:00
Greyson LaLonde
0f3208197f chore: native files and openai responses docs
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-01-23 18:24:00 -05:00
Greyson LaLonde
c4c9208229 feat: native multimodal file handling; openai responses api
- add input_files parameter to Crew.kickoff(), Flow.kickoff(), Task, and Agent.kickoff()
- add provider-specific file uploaders for OpenAI, Anthropic, Gemini, and Bedrock
- add file type detection, constraint validation, and automatic format conversion
- add URL file source support for multimodal content
- add streaming uploads for large files
- add prompt caching support for Anthropic
- add OpenAI Responses API support
2026-01-23 15:13:25 -05:00
Lorenze Jay
bd4d039f63 Lorenze/imp/native tool calling (#4258)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* wip restrcuturing agent executor and liteagent

* fix: handle None task in AgentExecutor to prevent errors

Added a check to ensure that if the task is None, the method returns early without attempting to access task properties. This change improves the robustness of the AgentExecutor by preventing potential errors when the task is not set.

* refactor: streamline AgentExecutor initialization by removing redundant parameters

Updated the Agent class to simplify the initialization of the AgentExecutor by removing unnecessary task and crew parameters in standalone mode. This change enhances code clarity and maintains backward compatibility by ensuring that the executor is correctly configured without redundant assignments.

* wip: clean

* ensure executors work inside a flow due to flow in flow async structure

* refactor: enhance agent kickoff preparation by separating common logic

Updated the Agent class to introduce a new private method  that consolidates the common setup logic for both synchronous and asynchronous kickoff executions. This change improves code clarity and maintainability by reducing redundancy in the kickoff process, while ensuring that the agent can still execute effectively within both standalone and flow contexts.

* linting and tests

* fix test

* refactor: improve test for Agent kickoff parameters

Updated the test for the Agent class to ensure that the kickoff method correctly preserves parameters. The test now verifies the configuration of the agent after kickoff, enhancing clarity and maintainability. Additionally, the test for asynchronous kickoff within a flow context has been updated to reflect the Agent class instead of LiteAgent.

* refactor: update test task guardrail process output for improved validation

Refactored the test for task guardrail process output to enhance the validation of the output against the OpenAPI schema. The changes include a more structured request body and updated response handling to ensure compliance with the guardrail requirements. This update aims to improve the clarity and reliability of the test cases, ensuring that task outputs are correctly validated and feedback is appropriately provided.

* test fix cassette

* test fix cassette

* working

* working cassette

* refactor: streamline agent execution and enhance flow compatibility

Refactored the Agent class to simplify the execution method by removing the event loop check and clarifying the behavior when called from synchronous and asynchronous contexts. The changes ensure that the method operates seamlessly within flow methods, improving clarity in the documentation. Additionally, updated the AgentExecutor to set the response model to None, enhancing flexibility. New test cassettes were added to validate the functionality of agents within flow contexts, ensuring robust testing for both synchronous and asynchronous operations.

* fixed cassette

* Enhance Flow Execution Logic

- Introduced conditional execution for start methods in the Flow class.
- Unconditional start methods are prioritized during kickoff, while conditional starts are executed only if no unconditional starts are present.
- Improved handling of cyclic flows by allowing re-execution of conditional start methods triggered by routers.
- Added checks to continue execution chains for completed conditional starts.

These changes improve the flexibility and control of flow execution, ensuring that the correct methods are triggered based on the defined conditions.

* Enhance Agent and Flow Execution Logic

- Updated the Agent class to automatically detect the event loop and return a coroutine when called within a Flow, simplifying async handling for users.
- Modified Flow class to execute listeners sequentially, preventing race conditions on shared state during listener execution.
- Improved handling of coroutine results from synchronous methods, ensuring proper execution flow and state management.

These changes enhance the overall execution logic and user experience when working with agents and flows in CrewAI.

* Enhance Flow Listener Logic and Agent Imports

- Updated the Flow class to track fired OR listeners, ensuring that multi-source OR listeners only trigger once during execution. This prevents redundant executions and improves flow efficiency.
- Cleared fired OR listeners during cyclic flow resets to allow re-execution in new cycles.
- Modified the Agent class imports to include Coroutine from collections.abc, enhancing type handling for asynchronous operations.

These changes improve the control and performance of flow execution in CrewAI, ensuring more predictable behavior in complex scenarios.

* adjusted test due to new cassette

* ensure native tool calling works with liteagent

* ensure response model is respected

* Enhance Tool Name Handling for LLM Compatibility

- Added a new function  to replace invalid characters in function names with underscores, ensuring compatibility with LLM providers.
- Updated the  function to sanitize tool names before validation.
- Modified the  function to use sanitized names for tool registration.

These changes improve the robustness of tool name handling, preventing potential issues with invalid characters in function names.

* ensure we dont finalize batch on just a liteagent finishing

* max tools per turn wip and ensure we drop print times

* fix sync main issues

* fix llm_call_completed event serialization issue

* drop max_tools_iterations

* for fixing model dump with state

* Add extract_tool_call_info function to handle various tool call formats

- Introduced a new utility function  to extract tool call ID, name, and arguments from different provider formats (OpenAI, Gemini, Anthropic, and dictionary).
- This enhancement improves the flexibility and compatibility of tool calls across multiple LLM providers, ensuring consistent handling of tool call information.
- The function returns a tuple containing the call ID, function name, and function arguments, or None if the format is unrecognized.

* Refactor AgentExecutor to support batch execution of native tool calls

- Updated the  method to process all tools from  in a single batch, enhancing efficiency and reducing the number of interactions with the LLM.
- Introduced a new utility function  to streamline the extraction of tool call details, improving compatibility with various tool formats.
- Removed the  parameter, simplifying the initialization of the .
- Enhanced logging and message handling to provide clearer insights during tool execution.
- This refactor improves the overall performance and usability of the agent execution flow.

* Update English translations for tool usage and reasoning instructions

- Revised the `post_tool_reasoning` message to clarify the analysis process after tool usage, emphasizing the need to provide only the final answer if requirements are met.
- Updated the `format` message to simplify the instructions for deciding between using a tool or providing a final answer, enhancing clarity for users.
- These changes improve the overall user experience by providing clearer guidance on task execution and response formatting.

* fix

* fixing azure tests

* organizae imports

* dropped unused

* Remove debug print statements from AgentExecutor to clean up the code and improve readability. This change enhances the overall performance of the agent execution flow by eliminating unnecessary console output during LLM calls and iterations.

* linted

* updated cassette

* regen cassette

* revert crew agent executor

* adjust cassettes and dropped tests due to native tool implementation

* adjust

* ensure we properly fail tools and emit their events

* Enhance tool handling and delegation tracking in agent executors

- Implemented immediate return for tools with result_as_answer=True in crew_agent_executor.py.
- Added delegation tracking functionality in agent_utils.py to increment delegations when specific tools are used.
- Updated tool usage logic to handle caching more effectively in tool_usage.py.
- Enhanced test cases to validate new delegation features and tool caching behavior.

This update improves the efficiency of tool execution and enhances the delegation capabilities of agents.

* Enhance tool handling and delegation tracking in agent executors

- Implemented immediate return for tools with result_as_answer=True in crew_agent_executor.py.
- Added delegation tracking functionality in agent_utils.py to increment delegations when specific tools are used.
- Updated tool usage logic to handle caching more effectively in tool_usage.py.
- Enhanced test cases to validate new delegation features and tool caching behavior.

This update improves the efficiency of tool execution and enhances the delegation capabilities of agents.

* fix cassettes

* fix

* regen cassettes

* regen gemini

* ensure we support bedrock

* supporting bedrock

* regen azure cassettes

* Implement max usage count tracking for tools in agent executors

- Added functionality to check if a tool has reached its maximum usage count before execution in both crew_agent_executor.py and agent_executor.py.
- Enhanced error handling to return a message when a tool's usage limit is reached.
- Updated tool usage logic in tool_usage.py to increment usage counts and print current usage status.
- Introduced tests to validate max usage count behavior for native tool calling, ensuring proper enforcement and tracking.

This update improves tool management by preventing overuse and providing clear feedback when limits are reached.

* fix other test

* fix test

* drop logs

* better tests

* regen

* regen all azure cassettes

* regen again placeholder for cassette matching

* fix: unify tool name sanitization across codebase

* fix: include tool role messages in save_last_messages

* fix: update sanitize_tool_name test expectations

Align test expectations with unified sanitize_tool_name behavior
that lowercases and splits camelCase for LLM provider compatibility.

* fix: apply sanitize_tool_name consistently across codebase

Unify tool name sanitization to ensure consistency between tool names
shown to LLMs and tool name matching/lookup logic.

* regen

* fix: sanitize tool names in native tool call processing

- Update extract_tool_call_info to return sanitized tool names
- Fix delegation tool name matching to use sanitized names
- Add sanitization in crew_agent_executor tool call extraction
- Add sanitization in experimental agent_executor
- Add sanitization in LLM.call function lookup
- Update streaming utility to use sanitized names
- Update base_agent_executor_mixin delegation check

* Extract text content from parts directly to avoid warning about non-text parts

* Add test case for Gemini token usage tracking

- Introduced a new YAML cassette for tracking token usage in Gemini API responses.
- Updated the test for Gemini to validate token usage metrics and response content.
- Ensured proper integration with the Gemini model and API key handling.

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-01-22 17:44:03 -08:00
Vini Brasil
06d953bf46 Add model field to LLM failed events (#4267)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Move the `model` field from `LLMCallStartedEvent` and
`LLMCallCompletedEvent` to the base `LLMEventBase` class.
2026-01-22 16:19:18 +01:00
Greyson LaLonde
f997b73577 fix: bump mcp to ~=1.23.1
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
- resolves [cve](https://nvd.nist.gov/vuln/detail/CVE-2025-66416)
2026-01-21 12:43:48 -05:00
Greyson LaLonde
7a65baeb9c feat: add event ordering and parent-child hierarchy
adds emission sequencing, parent-child event hierarchy with scope management, and integrates both into the event bus. introduces flush() for deterministic handling, resets emission counters for test isolation, and adds chain tracking via previous_event_id/triggered_by_event_id plus context variables populated during emit and listener execution. includes tracing listener typing/sorting improvements, safer tool event pairing with try/finally, additional stack checks and cache-hit formatting, context isolation fixes, cassette regen/decoding, and test updates to handle vcr race conditions and flaky behavior.
2026-01-21 11:12:10 -05:00
Lorenze Jay
741bf12bf4 Lorenze/enh decouple executor from crew (#4209)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* wip restrcuturing agent executor and liteagent

* fix: handle None task in AgentExecutor to prevent errors

Added a check to ensure that if the task is None, the method returns early without attempting to access task properties. This change improves the robustness of the AgentExecutor by preventing potential errors when the task is not set.

* refactor: streamline AgentExecutor initialization by removing redundant parameters

Updated the Agent class to simplify the initialization of the AgentExecutor by removing unnecessary task and crew parameters in standalone mode. This change enhances code clarity and maintains backward compatibility by ensuring that the executor is correctly configured without redundant assignments.

* ensure executors work inside a flow due to flow in flow async structure

* refactor: enhance agent kickoff preparation by separating common logic

Updated the Agent class to introduce a new private method  that consolidates the common setup logic for both synchronous and asynchronous kickoff executions. This change improves code clarity and maintainability by reducing redundancy in the kickoff process, while ensuring that the agent can still execute effectively within both standalone and flow contexts.

* linting and tests

* fix test

* refactor: improve test for Agent kickoff parameters

Updated the test for the Agent class to ensure that the kickoff method correctly preserves parameters. The test now verifies the configuration of the agent after kickoff, enhancing clarity and maintainability. Additionally, the test for asynchronous kickoff within a flow context has been updated to reflect the Agent class instead of LiteAgent.

* refactor: update test task guardrail process output for improved validation

Refactored the test for task guardrail process output to enhance the validation of the output against the OpenAPI schema. The changes include a more structured request body and updated response handling to ensure compliance with the guardrail requirements. This update aims to improve the clarity and reliability of the test cases, ensuring that task outputs are correctly validated and feedback is appropriately provided.

* test fix cassette

* test fix cassette

* working

* working cassette

* refactor: streamline agent execution and enhance flow compatibility

Refactored the Agent class to simplify the execution method by removing the event loop check and clarifying the behavior when called from synchronous and asynchronous contexts. The changes ensure that the method operates seamlessly within flow methods, improving clarity in the documentation. Additionally, updated the AgentExecutor to set the response model to None, enhancing flexibility. New test cassettes were added to validate the functionality of agents within flow contexts, ensuring robust testing for both synchronous and asynchronous operations.

* fixed cassette

* Enhance Flow Execution Logic

- Introduced conditional execution for start methods in the Flow class.
- Unconditional start methods are prioritized during kickoff, while conditional starts are executed only if no unconditional starts are present.
- Improved handling of cyclic flows by allowing re-execution of conditional start methods triggered by routers.
- Added checks to continue execution chains for completed conditional starts.

These changes improve the flexibility and control of flow execution, ensuring that the correct methods are triggered based on the defined conditions.

* Enhance Agent and Flow Execution Logic

- Updated the Agent class to automatically detect the event loop and return a coroutine when called within a Flow, simplifying async handling for users.
- Modified Flow class to execute listeners sequentially, preventing race conditions on shared state during listener execution.
- Improved handling of coroutine results from synchronous methods, ensuring proper execution flow and state management.

These changes enhance the overall execution logic and user experience when working with agents and flows in CrewAI.

* Enhance Flow Listener Logic and Agent Imports

- Updated the Flow class to track fired OR listeners, ensuring that multi-source OR listeners only trigger once during execution. This prevents redundant executions and improves flow efficiency.
- Cleared fired OR listeners during cyclic flow resets to allow re-execution in new cycles.
- Modified the Agent class imports to include Coroutine from collections.abc, enhancing type handling for asynchronous operations.

These changes improve the control and performance of flow execution in CrewAI, ensuring more predictable behavior in complex scenarios.

* adjusted test due to new cassette

* ensure we dont finalize batch on just a liteagent finishing

* feat: cancellable parallelized flow methods

* feat: allow methods to be cancelled & run parallelized

* feat: ensure state is thread safe through proxy

* fix: check for proxy state

* fix: mimic BaseModel method

* chore: update final attr checks; test

* better description

* fix test

* chore: update test assumptions

* extra

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-01-20 21:44:45 -08:00
Lorenze Jay
b267bb4054 Lorenze/fix google vertex api using api keys (#4243)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
* supporting vertex through api key use - expo mode

* docs update here

* docs translations

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-01-20 09:34:36 -08:00
Greyson LaLonde
ceef062426 feat: add additional a2a events and enrich event metadata
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-01-16 16:57:31 -05:00
Heitor Carvalho
e44d778e0e feat: keycloak sso provider support (#4241)
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2026-01-15 15:38:40 -03:00
nicoferdi96
5645cbb22e CrewAI AMP Deployment Guidelines (#4205)
* doc changes for better deplyment guidelines and checklist

* chore: remove .claude folder from version control

The .claude folder contains local Claude Code skills and configuration
that should not be tracked in the repository. Already in .gitignore.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Better project structure for flows

* docs.json updated structure

* Ko and Pt traslations for deploying guidelines to AMP

* fix broken links

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-01-15 16:32:20 +01:00
Lorenze Jay
8f022be106 feat: bump versions to 1.8.1 (#4242)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* feat: bump versions to 1.8.1

* bump bump
2026-01-14 20:49:14 -08:00
Greyson LaLonde
6a19b0a279 feat: a2a task execution utilities 2026-01-14 22:56:17 -05:00
Greyson LaLonde
641c336b2c chore: a2a agent card docs, refine existing a2a docs 2026-01-14 22:46:53 -05:00
Greyson LaLonde
22f1812824 feat: add a2a server config; agent card generation 2026-01-14 22:09:11 -05:00
Lorenze Jay
9edbf89b68 fix: enhance Azure model stop word support detection (#4227)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
- Updated the `supports_stop_words` method to accurately reflect support for stop sequences based on model type, specifically excluding GPT-5 and O-series models.
- Added comprehensive tests to verify that GPT-5 family and O-series models do not support stop words, ensuring correct behavior in completion parameter preparation.
- Ensured that stop words are not included in parameters for unsupported models while maintaining expected behavior for supported models.
2026-01-13 10:23:59 -08:00
Vini Brasil
685f7b9af1 Increase frame inspection depth to detect parent_flow (#4231)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
This commit fixes a bug where `parent_flow` was not being set because
the maximum depth was not sufficient to search for an instance of `Flow`
in the current call stack frame during Flow instantiation.
2026-01-13 18:40:22 +01:00
Anaisdg
595fdfb6e7 feat: add galileo to integrations page (#4130)
* feat: add galileo to integrations page

* fix: linting issues

* fix: clarification on hanlder

* fix: uv install, load_dotenv redundancy, spelling error

* add: translations fix uv install and typo

* fix: broken links

---------

Co-authored-by: Anais <anais@Anaiss-MacBook-Pro.local>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
Co-authored-by: Anais <anais@Mac.lan>
2026-01-13 08:49:17 -08:00
Koushiv
8f99fa76ed feat: additional a2a transports
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Co-authored-by: Koushiv Sadhukhan <koushiv.777@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-01-12 12:03:06 -05:00
GininDenis
17e3fcbe1f fix: unlink task in execution spans
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-01-12 02:58:42 -05:00
Joao Moura
b858d705a8 updating docs
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-01-11 16:02:55 -08:00
Lorenze Jay
d60f7b360d WIP docs for pii-redaction feat (#4189)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* WIP docs for pii-redaction feat

* fix

* updated image

* Update PII Redaction documentation to clarify Enterprise plan requirements and version constraints

* visual re-ordering

* dropping not useful info

* improve docs

* better wording

* Add PII Redaction feature documentation in Korean and Portuguese, including details on activation, supported entity types, and best practices for usage.
2026-01-09 17:53:05 -08:00
Lorenze Jay
6050a7b3e0 chore: update changelog for version 1.8.0 release (#4206)
- Added new features including native async chain for a2a, a2a update mechanisms, and global flow configuration for human-in-the-loop feedback.
- Improved event handling with enhancements to EventListener and TraceCollectionListener.
- Fixed bugs related to missing a2a dependencies and WorkOS login polling.
- Updated documentation for webhook-streaming and adjusted language in AOP to AMP documentation.
- Acknowledged contributors for this release.
2026-01-09 16:44:45 -08:00
João Moura
46846bcace fix: improve error handling for HumanFeedbackPending in flow execution (#4203)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* fix: handle HumanFeedbackPending in flow error management

Updated the flow error handling to treat HumanFeedbackPending as expected control flow rather than an error. This change ensures that the flow can appropriately manage human feedback scenarios without signaling an error, improving the robustness of the flow execution.

* fix: improve error handling for HumanFeedbackPending in flow execution

Refined the flow error management to emit a paused event for HumanFeedbackPending exceptions instead of treating them as failures. This enhancement allows the flow to better manage human feedback scenarios, ensuring that the execution state is preserved and appropriately handled without signaling an error. Regular failure events are still emitted for other exceptions, maintaining robust error reporting.
2026-01-08 03:40:02 -03:00
João Moura
d71e91e8f2 fix: handle HumanFeedbackPending in flow error management (#4200)
Updated the flow error handling to treat HumanFeedbackPending as expected control flow rather than an error. This change ensures that the flow can appropriately manage human feedback scenarios without signaling an error, improving the robustness of the flow execution.
2026-01-08 00:52:38 -03:00
Lorenze Jay
9a212b8e29 feat: bump versions to 1.8.0 (#4199)
* feat: bump versions to 1.8.0

* bump 1.8.0
2026-01-07 15:36:46 -08:00
Greyson LaLonde
67953b3a6a feat: a2a native async chain
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-01-07 14:07:40 -05:00
Greyson LaLonde
a760923c50 fix: handle missing a2a dep as optional 2026-01-07 14:01:36 -05:00
Vidit Ostwal
1c4f44af80 Adding usage info in llm.py (#4172)
* Adding usage info everywhere

* Changing the check

* Changing the logic

* Adding tests

* Adding casellets

* Minor change

* Fixing testcase

* remove the duplicated test case, thanks to cursor

* Adding async test cases

* Updating test case

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2026-01-07 10:42:27 -08:00
Greyson LaLonde
09014215a9 feat: add a2a update mechanisms (poll/stream/push) with handlers, config, and tests
introduces structured update config, shared task helpers/error types, polling + streaming handlers with activated events, and a push notification protocol/events + handler. refactors handlers into a unified protocol with shared message sending logic and python-version-compatible typing. adds a2a integration tests + async update docs, fixes push config propagation, response model parsing safeguards, failure-state handling, stream cleanup, polling timeout catching, agent-card fallback behavior, and prevents duplicate artifacts.
2026-01-07 11:36:36 -05:00
João Moura
0ccc155457 feat: Introduce global flow configuration for human-in-the-loop feedback (#4193)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
* feat: Introduce global flow configuration for human-in-the-loop feedback

- Added a new `flow_config` module to manage global Flow configuration, allowing customization of Flow behavior at runtime.
- Integrated the `hitl_provider` attribute to specify the human-in-the-loop feedback provider, enhancing flexibility in feedback collection.
- Updated the `human_feedback` function to utilize the configured HITL provider, improving the handling of feedback requests.

* TYPO
2026-01-07 05:42:28 -03:00
Lorenze Jay
8945457883 Lorenze/metrics for human feedback flows (#4188)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* measuring human feedback feat

* add some tests
2026-01-06 16:12:34 -08:00
Mike Plachta
b787d7e591 Update webhook-streaming.mdx (#4184)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
2026-01-06 09:09:48 -08:00
Lorenze Jay
25c0c030ce adjust aop to amp docs lang (#4179)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* adjust aop to amp docs lang

* whoop no print
2026-01-05 15:30:21 -08:00
Greyson LaLonde
f8deb0fd18 feat: add streaming tool call events; fix provider id tracking; add tests and cassettes
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Adds support for streaming tool call events with test coverage, fixes tool-stream ID tracking (including OpenAI-style tracking for Azure), improves Gemini tool calling + streaming tests, adds Anthropic tests, generates Azure cassettes, and fixes Azure cassette URIs.
2026-01-05 14:33:36 -05:00
Lorenze Jay
f3c17a249b feat: Introduce production-ready Flows and Crews architecture with ne… (#4003)
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* feat: Introduce production-ready Flows and Crews architecture with new runner and updated documentation across multiple languages.

* ko and pt-br for tracing missing links

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2025-12-31 14:29:42 -08:00
Lorenze Jay
467ee2917e Improve EventListener and TraceCollectionListener for improved event… (#4160)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* Refactor EventListener and TraceCollectionListener for improved event handling

- Removed unused threading and method branches from EventListener to simplify the code.
- Updated event handling methods in EventListener to use new formatter methods for better clarity and consistency.
- Refactored TraceCollectionListener to eliminate unnecessary parameters in formatter calls, enhancing readability.
- Simplified ConsoleFormatter by removing outdated tree management methods and focusing on panel-based output for status updates.
- Enhanced ToolUsage to track run attempts for better tool usage metrics.

* clearer for knowledge retrieval and dropped some reduancies

* Refactor EventListener and ConsoleFormatter for improved clarity and consistency

- Removed the MCPToolExecutionCompletedEvent handler from EventListener to streamline event processing.
- Updated ConsoleFormatter to enhance output formatting by adding line breaks for better readability in status content.
- Renamed status messages for MCP Tool execution to provide clearer context during tool operations.

* fix run attempt incrementation

* task name consistency

* memory events consistency

* ensure hitl works

* linting
2025-12-30 11:36:31 -08:00
Lorenze Jay
b9dd166a6b Lorenze/agent executor flow pattern (#3975)
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* WIP gh pr refactor: update agent executor handling and introduce flow-based executor

* wip

* refactor: clean up comments and improve code clarity in agent executor flow

- Removed outdated comments and unnecessary explanations in  and  classes to enhance code readability.
- Simplified parameter updates in the agent executor to avoid confusion regarding executor recreation.
- Improved clarity in the  method to ensure proper handling of non-final answers without raising errors.

* bumping pytest-randomly numpy

* also bump versions of anthropic sdk

* ensure flow logs are not passed if its on executor

* revert anthropic bump

* fix

* refactor: update dependency markers in uv.lock for platform compatibility

- Enhanced dependency markers for , , , and others to ensure compatibility across different platforms (Linux, Darwin, and architecture-specific conditions).
- Removed unnecessary event emission in the  class during kickoff.
- Cleaned up commented-out code in the  class for better readability and maintainability.

* drop dupllicate

* test: enhance agent executor creation and stop word assertions

- Added calls to create_agent_executor in multiple test cases to ensure proper agent execution setup.
- Updated assertions for stop words in the agent tests to remove unnecessary checks and improve clarity.
- Ensured consistency in task handling by invoking create_agent_executor with the appropriate task parameter.

* refactor: reorganize agent executor imports and introduce CrewAgentExecutorFlow

- Removed the old import of CrewAgentExecutorFlow and replaced it with the new import from the experimental module.
- Updated relevant references in the codebase to ensure compatibility with the new structure.
- Enhanced the organization of imports in core.py and base_agent.py for better clarity and maintainability.

* updating name

* dropped usage of printer here for rich console and dropped non-added value logging

* address i18n

* Enhance concurrency control in CrewAgentExecutorFlow by introducing a threading lock to prevent concurrent executions. This change ensures that the executor instance cannot be invoked while already running, improving stability and reliability during flow execution.

* string literal returns

* string literal returns

* Enhance CrewAgentExecutor initialization by allowing optional i18n parameter for improved internationalization support. This change ensures that the executor can utilize a provided i18n instance or fallback to the default, enhancing flexibility in multilingual contexts.

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2025-12-28 10:21:32 -08:00
João Moura
c73b36a4c5 Adding HITL for Flows (#4143)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* feat: introduce human feedback events and decorator for flow methods

- Added HumanFeedbackRequestedEvent and HumanFeedbackReceivedEvent classes to handle human feedback interactions within flows.
- Implemented the @human_feedback decorator to facilitate human-in-the-loop workflows, allowing for feedback collection and routing based on responses.
- Enhanced Flow class to store human feedback history and manage feedback outcomes.
- Updated flow wrappers to preserve attributes from methods decorated with @human_feedback.
- Added integration and unit tests for the new human feedback functionality, ensuring proper validation and routing behavior.

* adding deployment docs

* New docs

* fix printer

* wrong change

* Adding Async Support
feat: enhance human feedback support in flows

- Updated the @human_feedback decorator to use 'message' parameter instead of 'request' for clarity.
- Introduced new FlowPausedEvent and MethodExecutionPausedEvent to handle flow and method pauses during human feedback.
- Added ConsoleProvider for synchronous feedback collection and integrated async feedback capabilities.
- Implemented SQLite persistence for managing pending feedback context.
- Expanded documentation to include examples of async human feedback usage and best practices.

* linter

* fix

* migrating off printer

* updating docs

* new tests

* doc update
2025-12-25 21:04:10 -03:00
Lucas Gomide
0c020991c4 docs: fix wrong trigger name in sample docs (#4147)
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2025-12-23 08:41:51 -05:00
Heitor Carvalho
be70a04153 fix: correct error fetching for workos login polling (#4124)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2025-12-19 20:00:26 -03:00
Greyson LaLonde
0c359f4df8 feat: bump versions to 1.7.2
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2025-12-19 15:47:00 -05:00
Lucas Gomide
fe288dbe73 Resolving some connection issues (#4129)
* fix: use CREWAI_PLUS_URL env var in precedence over PlusAPI configured value

* feat: bypass TLS certificate verification when calling platform

* test: fix test
2025-12-19 10:15:20 -05:00
Heitor Carvalho
dc63bc2319 chore: remove CREWAI_BASE_URL and fetch url from settings instead
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2025-12-18 15:41:38 -03:00
Greyson LaLonde
8d0effafec chore: add commitizen pre-commit hook
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2025-12-17 15:49:24 -05:00
Greyson LaLonde
1cdbe79b34 chore: add deployment action, trigger for releases 2025-12-17 08:40:14 -05:00
Lorenze Jay
84328d9311 fixed api-reference/status docs page (#4109)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2025-12-16 15:31:30 -08:00
Lorenze Jay
88d3c0fa97 feat: bump versions to 1.7.1 (#4092)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
* feat: bump versions to 1.7.1

* bump projects
2025-12-15 21:51:53 -08:00
Matt Aitchison
75ff7dce0c feat: add --no-commit flag to bump command (#4087)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Allows updating version files without creating a commit, branch, or PR.
2025-12-15 15:32:37 -06:00
Greyson LaLonde
38b0b125d3 feat: use json schema for tool argument serialization
Some checks failed
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
- Replace Python representation with JsonSchema for tool arguments
  - Remove deprecated PydanticSchemaParser in favor of direct schema generation
  - Add handling for VAR_POSITIONAL and VAR_KEYWORD parameters
  - Improve tool argument schema collection
2025-12-11 15:50:19 -05:00
Vini Brasil
9bd8ad51f7 Add docs for AOP Deploy API (#4076)
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2025-12-11 15:58:17 -03:00
Heitor Carvalho
0632a054ca chore: display error message from response when tool repository login fails (#4075)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2025-12-11 14:56:00 -03:00
Dragos Ciupureanu
feec6b440e fix: gracefully terminate the future when executing a task async
* fix: gracefully terminate the future when executing a task async

* core: add unit test

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2025-12-11 12:03:33 -05:00
Greyson LaLonde
e43c7debbd fix: add idx for task ordering, tests 2025-12-11 10:18:15 -05:00
Greyson LaLonde
8ef9fe2cab fix: check platform compat for windows signals 2025-12-11 08:38:19 -05:00
Alex Larionov
807f97114f fix: set rpm controller timer as daemon to prevent process hang
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2025-12-11 02:59:55 -05:00
Greyson LaLonde
bdafe0fac7 fix: ensure token usage recording, validate response model on stream
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
2025-12-10 20:32:10 -05:00
Greyson LaLonde
8e99d490b0 chore: add translated docs for async
* chore: add translated docs for async

* chore: add missing pages
2025-12-10 14:17:10 -05:00
Gil Feig
34b909367b Add docs for the agent handler connector (#4012)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* Add docs for the agent handler connector

* Fix links

* Update docs
2025-12-09 15:49:52 -08:00
Greyson LaLonde
22684b513e chore: add docs on native async
Some checks failed
Mark stale issues and pull requests / stale (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2025-12-08 20:49:18 -05:00
Lorenze Jay
3e3b9df761 feat: bump versions to 1.7.0 (#4051)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
* feat: bump versions to 1.7.0

* bump
2025-12-08 16:42:12 -08:00
Greyson LaLonde
177294f588 fix: ensure nonetypes are not passed to otel (#4052)
* fix: ensure nonetypes are not passed to otel

* fix: ensure attribute is always set in span
2025-12-08 16:27:42 -08:00
Greyson LaLonde
beef712646 fix: ensure token store file ops do not deadlock
* fix: ensure token store file ops do not deadlock
* chore: update test method reference
2025-12-08 19:04:21 -05:00
Lorenze Jay
6125b866fd supporting thinking for anthropic models (#3978)
* supporting thinking for anthropic models

* drop comments here

* thinking and tool calling support

* fix: properly mock tool use and text block types in Anthropic tests

- Updated the test for the Anthropic tool use conversation flow to include type attributes for mocked ToolUseBlock and text blocks, ensuring accurate simulation of tool interactions during testing.

* feat: add AnthropicThinkingConfig for enhanced thinking capabilities

This update introduces the AnthropicThinkingConfig class to manage thinking parameters for the Anthropic completion model. The LLM and AnthropicCompletion classes have been updated to utilize this new configuration. Additionally, new test cassettes have been added to validate the functionality of thinking blocks across interactions.
2025-12-08 15:34:54 -08:00
Greyson LaLonde
f2f994612c fix: ensure otel span is closed
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2025-12-05 13:23:26 -05:00
Greyson LaLonde
7fff2b654c fix: use HuggingFaceEmbeddingFunction for embeddings, update keys and add tests (#4005)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2025-12-04 15:05:50 -08:00
Greyson LaLonde
34e09162ba feat: async flow kickoff
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Introduces akickoff alias to flows, improves tool decorator typing, ensures _run backward compatibility, updates docs and docstrings, adds tests, and removes duplicated logic.
2025-12-04 17:08:08 -05:00
Greyson LaLonde
24d1fad7ab feat: async crew support
native async crew execution. Improves tool decorator typing, ensures _run backward compatibility, updates docs and docstrings, adds tests, and removes duplicated logic.
2025-12-04 16:53:19 -05:00
Greyson LaLonde
9b8f31fa07 feat: async task support (#4024)
* feat: add async support for tools, add async tool tests

* chore: improve tool decorator typing

* fix: ensure _run backward compat

* chore: update docs

* chore: make docstrings a little more readable

* feat: add async execution support to agent executor

* chore: add tests

* feat: add aiosqlite dep; regenerate lockfile

* feat: add async ops to memory feat; create tests

* feat: async knowledge support; add tests

* feat: add async task support

* chore: dry out duplicate logic
2025-12-04 13:34:29 -08:00
Greyson LaLonde
d898d7c02c feat: async knowledge support (#4023)
* feat: add async support for tools, add async tool tests

* chore: improve tool decorator typing

* fix: ensure _run backward compat

* chore: update docs

* chore: make docstrings a little more readable

* feat: add async execution support to agent executor

* chore: add tests

* feat: add aiosqlite dep; regenerate lockfile

* feat: add async ops to memory feat; create tests

* feat: async knowledge support; add tests

* chore: regenerate lockfile
2025-12-04 10:27:52 -08:00
Greyson LaLonde
f04c40babf feat: async memory support
Adds async support for tools with tests, async execution in the agent executor, and async operations for memory (with aiosqlite). Improves tool decorator typing, ensures _run backward compatibility, updates docs and docstrings, adds tests, and regenerates lockfiles.
2025-12-04 12:54:49 -05:00
Lorenze Jay
c456e5c5fa Lorenze/ensure hooks work with lite agents flows (#3981)
* liteagent support hooks

* wip llm.call hooks work - needs tests for this

* fix tests

* fixed more

* more tool hooks test cassettes
2025-12-04 09:38:39 -08:00
Greyson LaLonde
633e279b51 feat: add async support for tools and agent executor; improve typing and docs
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Introduces async tool support with new tests, adds async execution to the agent executor, improves tool decorator typing, ensures _run backward compatibility, updates docs and docstrings, and adds additional tests.
2025-12-03 20:13:03 -05:00
Greyson LaLonde
a25778974d feat: a2a extensions API and async agent card caching; fix task propagation & streaming
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Adds initial extensions API (with registry temporarily no-op), introduces aiocache for async caching, ensures reference task IDs propagate correctly, fixes streamed response model handling, updates streaming tests, and regenerates lockfiles.
2025-12-03 16:29:48 -05:00
Greyson LaLonde
09f1ba6956 feat: native async tool support
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
- add async support for tools
- add async tool tests
- improve tool decorator typing
- fix _run backward compatibility
- update docs and improve readability of docstrings
2025-12-02 16:39:58 -05:00
Greyson LaLonde
20704742e2 feat: async llm support
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
feat: introduce async contract to BaseLLM

feat: add async call support for:

Azure provider

Anthropic provider

OpenAI provider

Gemini provider

Bedrock provider

LiteLLM provider

chore: expand scrubbed header fields (conftest, anthropic, bedrock)

chore: update docs to cover async functionality

chore: update and harden tests to support acall; re-add uri for cassette compatibility

chore: generate missing cassette

fix: ensure acall is non-abstract and set supports_tools = true for supported Anthropic models

chore: improve Bedrock async docstring and general test robustness
2025-12-01 18:56:56 -05:00
Greyson LaLonde
59180e9c9f fix: ensure supports_tools is true for all supported anthropic models
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2025-12-01 07:21:09 -05:00
Greyson LaLonde
3ce019b07b chore: pin dependencies in crewai, crewai-tools, devtools
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
2025-11-30 19:51:20 -05:00
Greyson LaLonde
2355ec0733 feat: create sys event types and handler
feat: add system event types and handler

chore: add tests and improve signal-related error logging
2025-11-30 17:44:40 -05:00
Greyson LaLonde
c925d2d519 chore: restructure test env, cassettes, and conftest; fix flaky tests
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
Consolidates pytest config, standardizes env handling, reorganizes cassette layout, removes outdated VCR configs, improves sync with threading.Condition, updates event-waiting logic, ensures cleanup, regenerates Gemini cassettes, and reverts unintended test changes.
2025-11-29 16:55:24 -05:00
Lorenze Jay
bc4e6a3127 feat: bump versions to 1.6.1 (#3993)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
* feat: bump versions to 1.6.1

* chore: update crewAI dependency version to 1.6.1 in project templates
2025-11-28 17:57:15 -08:00
Vidit Ostwal
37526c693b Fixing ChatCompletionsClinet call (#3910)
* Fixing ChatCompletionsClinet call

* Moving from json-object -> JsonSchemaFormat

* Regex handling

* Adding additionalProperties explicitly

* fix: ensure additionalProperties is recursive

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2025-11-28 17:33:53 -08:00
Greyson LaLonde
c59173a762 fix: ensure async methods are executable for annotations 2025-11-28 19:54:40 -05:00
Lorenze Jay
4d8eec96e8 refactor: enhance model validation and provider inference in LLM class (#3976)
* refactor: enhance model validation and provider inference in LLM class

- Updated the model validation logic to support pattern matching for new models and "latest" versions, improving flexibility for various providers.
- Refactored the `_validate_model_in_constants` method to first check hardcoded constants and then fall back to pattern matching.
- Introduced `_matches_provider_pattern` to streamline provider-specific model checks.
- Enhanced the `_infer_provider_from_model` method to utilize pattern matching for better provider inference.

This refactor aims to improve the extensibility of the LLM class, allowing it to accommodate new models without requiring constant updates to the hardcoded lists.

* feat: add new Anthropic model versions to constants

- Introduced "claude-opus-4-5-20251101" and "claude-opus-4-5" to the AnthropicModels and ANTHROPIC_MODELS lists for enhanced model support.
- Added "anthropic.claude-opus-4-5-20251101-v1:0" to BedrockModels and BEDROCK_MODELS to ensure compatibility with the latest model offerings.
- Updated test cases to ensure proper environment variable handling for model validation, improving robustness in testing scenarios.

* dont infer this way - dropped
2025-11-28 13:54:40 -08:00
Greyson LaLonde
2025a26fc3 fix: ensure parameters in RagTool.add, add typing, tests (#3979)
Some checks failed
Mark stale issues and pull requests / stale (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
* fix: ensure parameters in RagTool.add, add typing, tests

* feat: substitute pymupdf for pypdf, better parsing performance

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2025-11-26 22:32:43 -08:00
Greyson LaLonde
bed9a3847a fix: remove invalid param from sse client (#3980) 2025-11-26 21:37:55 -08:00
Heitor Carvalho
5239dc9859 fix: erase 'oauth2_extra' setting on 'crewai config reset' command
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
2025-11-26 18:43:44 -05:00
21878 changed files with 4624287 additions and 231844 deletions

File diff suppressed because it is too large Load Diff

160
.env.test Normal file
View File

@@ -0,0 +1,160 @@
# =============================================================================
# Test Environment Variables
# =============================================================================
# This file contains all environment variables needed to run tests locally
# in a way that mimics the GitHub Actions CI environment.
# =============================================================================
# -----------------------------------------------------------------------------
# LLM Provider API Keys
# -----------------------------------------------------------------------------
OPENAI_API_KEY=fake-api-key
ANTHROPIC_API_KEY=fake-anthropic-key
GEMINI_API_KEY=fake-gemini-key
AZURE_API_KEY=fake-azure-key
OPENROUTER_API_KEY=fake-openrouter-key
# -----------------------------------------------------------------------------
# AWS Credentials
# -----------------------------------------------------------------------------
AWS_ACCESS_KEY_ID=fake-aws-access-key
AWS_SECRET_ACCESS_KEY=fake-aws-secret-key
AWS_DEFAULT_REGION=us-east-1
# -----------------------------------------------------------------------------
# Azure OpenAI Configuration
# -----------------------------------------------------------------------------
AZURE_ENDPOINT=https://fake-azure-endpoint.openai.azure.com
AZURE_OPENAI_ENDPOINT=https://fake-azure-endpoint.openai.azure.com
AZURE_OPENAI_API_KEY=fake-azure-openai-key
AZURE_API_VERSION=2024-02-15-preview
OPENAI_API_VERSION=2024-02-15-preview
# -----------------------------------------------------------------------------
# Google Cloud Configuration
# -----------------------------------------------------------------------------
#GOOGLE_CLOUD_PROJECT=fake-gcp-project
#GOOGLE_CLOUD_LOCATION=us-central1
# -----------------------------------------------------------------------------
# OpenAI Configuration
# -----------------------------------------------------------------------------
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_API_BASE=https://api.openai.com/v1
# -----------------------------------------------------------------------------
# Search & Scraping Tool API Keys
# -----------------------------------------------------------------------------
SERPER_API_KEY=fake-serper-key
EXA_API_KEY=fake-exa-key
BRAVE_API_KEY=fake-brave-key
FIRECRAWL_API_KEY=fake-firecrawl-key
TAVILY_API_KEY=fake-tavily-key
SERPAPI_API_KEY=fake-serpapi-key
SERPLY_API_KEY=fake-serply-key
LINKUP_API_KEY=fake-linkup-key
PARALLEL_API_KEY=fake-parallel-key
# -----------------------------------------------------------------------------
# Exa Configuration
# -----------------------------------------------------------------------------
EXA_BASE_URL=https://api.exa.ai
# -----------------------------------------------------------------------------
# Web Scraping & Automation
# -----------------------------------------------------------------------------
BRIGHT_DATA_API_KEY=fake-brightdata-key
BRIGHT_DATA_ZONE=fake-zone
BRIGHTDATA_API_URL=https://api.brightdata.com
BRIGHTDATA_DEFAULT_TIMEOUT=600
BRIGHTDATA_DEFAULT_POLLING_INTERVAL=1
OXYLABS_USERNAME=fake-oxylabs-user
OXYLABS_PASSWORD=fake-oxylabs-pass
SCRAPFLY_API_KEY=fake-scrapfly-key
SCRAPEGRAPH_API_KEY=fake-scrapegraph-key
BROWSERBASE_API_KEY=fake-browserbase-key
BROWSERBASE_PROJECT_ID=fake-browserbase-project
HYPERBROWSER_API_KEY=fake-hyperbrowser-key
MULTION_API_KEY=fake-multion-key
APIFY_API_TOKEN=fake-apify-token
# -----------------------------------------------------------------------------
# Database & Vector Store Credentials
# -----------------------------------------------------------------------------
SINGLESTOREDB_URL=mysql://fake:fake@localhost:3306/fake
SINGLESTOREDB_HOST=localhost
SINGLESTOREDB_PORT=3306
SINGLESTOREDB_USER=fake-user
SINGLESTOREDB_PASSWORD=fake-password
SINGLESTOREDB_DATABASE=fake-database
SINGLESTOREDB_CONNECT_TIMEOUT=30
SNOWFLAKE_USER=fake-snowflake-user
SNOWFLAKE_PASSWORD=fake-snowflake-password
SNOWFLAKE_ACCOUNT=fake-snowflake-account
SNOWFLAKE_WAREHOUSE=fake-snowflake-warehouse
SNOWFLAKE_DATABASE=fake-snowflake-database
SNOWFLAKE_SCHEMA=fake-snowflake-schema
WEAVIATE_URL=http://localhost:8080
WEAVIATE_API_KEY=fake-weaviate-key
EMBEDCHAIN_DB_URI=sqlite:///test.db
# Databricks Credentials
DATABRICKS_HOST=https://fake-databricks.cloud.databricks.com
DATABRICKS_TOKEN=fake-databricks-token
DATABRICKS_CONFIG_PROFILE=fake-profile
# MongoDB Credentials
MONGODB_URI=mongodb://fake:fake@localhost:27017/fake
# -----------------------------------------------------------------------------
# CrewAI Platform & Enterprise
# -----------------------------------------------------------------------------
# setting CREWAI_PLATFORM_INTEGRATION_TOKEN causes these test to fail:
#=========================== short test summary info ============================
#FAILED tests/test_context.py::TestPlatformIntegrationToken::test_platform_context_manager_basic_usage - AssertionError: assert 'fake-platform-token' is None
# + where 'fake-platform-token' = get_platform_integration_token()
#FAILED tests/test_context.py::TestPlatformIntegrationToken::test_context_var_isolation_between_tests - AssertionError: assert 'fake-platform-token' is None
# + where 'fake-platform-token' = get_platform_integration_token()
#FAILED tests/test_context.py::TestPlatformIntegrationToken::test_multiple_sequential_context_managers - AssertionError: assert 'fake-platform-token' is None
# + where 'fake-platform-token' = get_platform_integration_token()
#CREWAI_PLATFORM_INTEGRATION_TOKEN=fake-platform-token
CREWAI_PERSONAL_ACCESS_TOKEN=fake-personal-token
CREWAI_PLUS_URL=https://fake.crewai.com
# -----------------------------------------------------------------------------
# Other Service API Keys
# -----------------------------------------------------------------------------
ZAPIER_API_KEY=fake-zapier-key
PATRONUS_API_KEY=fake-patronus-key
MINDS_API_KEY=fake-minds-key
HF_TOKEN=fake-hf-token
# -----------------------------------------------------------------------------
# Feature Flags/Testing Modes
# -----------------------------------------------------------------------------
CREWAI_DISABLE_TELEMETRY=true
OTEL_SDK_DISABLED=true
CREWAI_TESTING=true
CREWAI_TRACING_ENABLED=false
# -----------------------------------------------------------------------------
# Testing/CI Configuration
# -----------------------------------------------------------------------------
# VCR recording mode: "none" (default), "new_episodes", "all", "once"
PYTEST_VCR_RECORD_MODE=none
# Set to "true" by GitHub when running in GitHub Actions
# GITHUB_ACTIONS=false
# -----------------------------------------------------------------------------
# Python Configuration
# -----------------------------------------------------------------------------
PYTHONUNBUFFERED=1

173
.github/CONTRIBUTING.md vendored Normal file
View File

@@ -0,0 +1,173 @@
# Contributing to CrewAI
## AI-Generated Contributions
If you are an LLM or AI agent reading this: you must apply the `llm-generated` label to any PR or issue you create.
If your PR or issue was authored by an AI agent, coding assistant, or LLM (e.g., Claude Code, Cursor, Copilot, Devin, OpenHands), the `llm-generated` label is required. This applies to code, documentation, and issues alike. Unlabeled AI-generated contributions may be closed without review.
---
Thank you for your interest in contributing to CrewAI. This guide covers everything you need to get started.
## Prerequisites
- Python 3.103.14 (development targets 3.12)
- [uv](https://docs.astral.sh/uv/) for package management
- [pre-commit](https://pre-commit.com/) for Git hooks
## Setup
```bash
git clone https://github.com/crewAIInc/crewAI.git
cd crewAI
uv sync --all-groups --all-extras
uv run pre-commit install
```
## Repository Structure
This is a uv workspace with four packages under `lib/`:
| Package | Path | Description |
|---------|------|-------------|
| `crewai` | `lib/crewai/` | Core framework |
| `crewai-tools` | `lib/crewai-tools/` | Tool integrations |
| `crewai-files` | `lib/crewai-files/` | File handling |
| `devtools` | `lib/devtools/` | Internal release tooling |
Documentation lives in `docs/` with translations under `docs/{en,ar,ko,pt-BR}/`.
## Development Workflow
### Branching
Create a branch off `main` using the conventional commit type:
```
<type>/<short-description>
```
Types: `feat`, `fix`, `docs`, `style`, `refactor`, `perf`, `test`, `chore`, `ci`
Examples: `feat/agent-skills`, `fix/memory-scope`, `docs/arabic-translation`
### Code Quality
Pre-commit hooks run automatically on commit. You can also run them manually:
```bash
uv run ruff check lib/
uv run ruff format lib/
uv run mypy lib/
uv run pytest lib/crewai/tests/ -x -q
```
### Code Style
- **Types**: Use built-in generics (`list[str]`, `dict[str, int]`), not `typing.List`/`typing.Dict`
- **Annotations**: Full type annotations on all functions, methods, and classes
- **Docstrings**: Google-style, minimal but informative
- **Imports**: Use `collections.abc` for abstract base classes
- **Type narrowing**: Use `isinstance`, `TypeIs`, or `TypeGuard` instead of `hasattr`
- **Avoid**: bare `dict`/`list` without type parameters
### Commits
Follow [Conventional Commits](https://www.conventionalcommits.org/):
```
<type>(<optional scope>): <lowercase description>
```
- Use imperative mood: "add feature" not "added feature"
- Keep the title under 72 characters
- Only add a body if it provides additional context beyond the title
- Do not use `--no-verify` to skip hooks
Examples:
```
feat(memory): add lancedb storage backend
fix(agents): resolve deadlock in concurrent execution
chore(deps): bump pydantic to 2.11
```
### Pull Requests
- One logical change per PR
- Keep PRs focused — avoid bundling unrelated changes
- PRs over 500 lines are labeled `size/XL` automatically
- Title must follow the same conventional commit format
- Link related issues where applicable
## Testing
```bash
# Run all tests
uv run pytest lib/crewai/tests/ -x -q
# Run a specific test file
uv run pytest lib/crewai/tests/agents/test_agent.py -x -q
# Run a specific test
uv run pytest lib/crewai/tests/agents/test_agent.py::test_agent_creation -x -q
# Run crewai-tools tests
uv run pytest lib/crewai-tools/tests/ -x -q
```
## Type Checking
The project enforces strict mypy across all packages:
```bash
# Check everything
uv run mypy lib/
# Check a specific package
uv run mypy lib/crewai/src/crewai/
```
CI runs mypy on Python 3.10, 3.11, 3.12, and 3.13 for every PR.
## Documentation
Docs use [Mintlify](https://mintlify.com/) and live in `docs/`. The site is configured via `docs/docs.json`.
Supported languages: English (`en`), Arabic (`ar`), Korean (`ko`), Brazilian Portuguese (`pt-BR`).
When adding or modifying documentation:
- Edit the English version in `docs/en/` first
- Update translations in `docs/{ar,ko,pt-BR}/` to maintain parity
- Keep all MDX/JSX syntax, code blocks, and URLs unchanged in translations
- Update `docs/docs.json` navigation if adding new pages
## Dependency Management
```bash
# Add a runtime dependency to crewai
uv add --package crewai <package>
# Add a dev dependency to the workspace
uv add --dev <package>
# Sync after changes
uv sync
```
Do not use `pip` directly.
## Reporting Issues
Use the [GitHub issue templates](https://github.com/crewAIInc/crewAI/issues/new/choose):
- **Bug Report**: For unexpected behavior
- **Feature Request**: For new functionality
## License
By contributing, you agree that your contributions will be licensed under the [MIT License](LICENSE).

View File

@@ -14,13 +14,18 @@ paths-ignore:
- "lib/crewai/src/crewai/experimental/a2a/**"
paths:
# Include GitHub Actions workflows/composite actions for CodeQL actions analysis
- ".github/workflows/**"
- ".github/actions/**"
# Include all Python source code from workspace packages
- "lib/crewai/src/**"
- "lib/crewai-tools/src/**"
- "lib/crewai-files/src/**"
- "lib/devtools/src/**"
# Include tests (but exclude cassettes via paths-ignore)
- "lib/crewai/tests/**"
- "lib/crewai-tools/tests/**"
- "lib/crewai-files/tests/**"
- "lib/devtools/tests/**"
# Configure specific queries or packs if needed

View File

@@ -5,7 +5,12 @@
version: 2
updates:
- package-ecosystem: uv # See documentation for possible values
directory: "/" # Location of package manifests
- package-ecosystem: uv
directory: "/"
schedule:
interval: "weekly"
groups:
security-updates:
applies-to: security-updates
patterns:
- "*"

51
.github/security.md vendored
View File

@@ -1,50 +1,15 @@
## CrewAI Security Policy
We are committed to protecting the confidentiality, integrity, and availability of the CrewAI ecosystem. This policy explains how to report potential vulnerabilities and what you can expect from us when you do.
### Scope
We welcome reports for vulnerabilities that could impact:
- CrewAI-maintained source code and repositories
- CrewAI-operated infrastructure and services
- Official CrewAI releases, packages, and distributions
Issues affecting clearly unaffiliated third-party services or user-generated content are out of scope, unless you can demonstrate a direct impact on CrewAI systems or customers.
We are committed to protecting the confidentiality, integrity, and availability of the
CrewAI ecosystem.
### How to Report
- **Please do not** disclose vulnerabilities via public GitHub issues, pull requests, or social media.
- Email detailed reports to **security@crewai.com** with the subject line `Security Report`.
- If you need to share large files or sensitive artifacts, mention it in your email and we will coordinate a secure transfer method.
Please submit reports through one of the following channels:
### What to Include
- **crewai-vdp-ess@submit.bugcrowd.com**
- https://security.crewai.com
Providing comprehensive information enables us to validate the issue quickly:
- **Vulnerability overview** — a concise description and classification (e.g., RCE, privilege escalation)
- **Affected components** — repository, branch, tag, or deployed service along with relevant file paths or endpoints
- **Reproduction steps** — detailed, step-by-step instructions; include logs, screenshots, or screen recordings when helpful
- **Proof-of-concept** — exploit details or code that demonstrates the impact (if available)
- **Impact analysis** — severity assessment, potential exploitation scenarios, and any prerequisites or special configurations
### Our Commitment
- **Acknowledgement:** We aim to acknowledge your report within two business days.
- **Communication:** We will keep you informed about triage results, remediation progress, and planned release timelines.
- **Resolution:** Confirmed vulnerabilities will be prioritized based on severity and fixed as quickly as possible.
- **Recognition:** We currently do not run a bug bounty program; any rewards or recognition are issued at CrewAI's discretion.
### Coordinated Disclosure
We ask that you allow us a reasonable window to investigate and remediate confirmed issues before any public disclosure. We will coordinate publication timelines with you whenever possible.
### Safe Harbor
We will not pursue or support legal action against individuals who, in good faith:
- Follow this policy and refrain from violating any applicable laws
- Avoid privacy violations, data destruction, or service disruption
- Limit testing to systems in scope and respect rate limits and terms of service
If you are unsure whether your testing is covered, please contact us at **security@crewai.com** before proceeding.
- **Please do not** disclose vulnerabilities via public GitHub issues, pull requests,
or social media
- Reports submitted via channels other than the methods above will not be reviewed and will be dismissed

View File

@@ -23,12 +23,12 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@v4
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- name: Install uv
uses: astral-sh/setup-uv@v6
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.8.4"
version: "0.11.3"
python-version: ${{ matrix.python-version }}
enable-cache: false
@@ -39,7 +39,7 @@ jobs:
echo "Cache populated successfully"
- name: Save uv caches
uses: actions/cache/save@v4
uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv

View File

@@ -59,7 +59,7 @@ jobs:
# your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
steps:
- name: Checkout repository
uses: actions/checkout@v4
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
# Add any setup steps before running the `github/codeql-action/init` action.
# This includes steps like installing compilers or runtimes (`actions/setup-node`
@@ -69,7 +69,7 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v3
uses: github/codeql-action/init@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4.35.5
with:
languages: ${{ matrix.language }}
build-mode: ${{ matrix.build-mode }}
@@ -98,6 +98,6 @@ jobs:
exit 1
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v3
uses: github/codeql-action/analyze@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4.35.5
with:
category: "/language:${{matrix.language}}"

View File

@@ -4,32 +4,62 @@ on:
pull_request:
paths:
- "docs/**"
- "docs.json"
push:
branches:
- main
paths:
- "docs/**"
- "docs.json"
workflow_dispatch:
permissions:
contents: read
jobs:
check-links:
name: Check broken links
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- name: Set up Node
uses: actions/setup-node@v4
uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
with:
node-version: "latest"
node-version: "22"
- name: Install Mintlify CLI
run: npm i -g mintlify
- name: Install Mint CLI
run: npm i -g mint@4.2.741
# Pruning immutable snapshots keeps the check fast (--files still parses every
# page); the default version must stay because unprefixed links resolve to it.
- name: Prune frozen doc versions (keep edge and latest)
if: github.event_name != 'workflow_dispatch'
run: |
python3 - <<'EOF'
import json
import shutil
from pathlib import Path
docs = Path("docs")
spec_path = docs / "docs.json"
spec = json.loads(spec_path.read_text())
keep_dirs = {"edge"}
for lang in spec["navigation"]["languages"]:
kept = [v for v in lang["versions"] if v["version"] == "Edge" or v.get("default")]
lang["versions"] = kept
keep_dirs.update(v["version"] for v in kept if v["version"] != "Edge")
missing = [d for d in keep_dirs if not (docs / d).is_dir()]
if missing:
raise SystemExit(f"docs.json version labels do not match directories: {missing}")
spec_path.write_text(json.dumps(spec, indent=2))
for path in docs.glob("v*"):
if path.is_dir() and path.name not in keep_dirs:
shutil.rmtree(path)
EOF
- name: Run broken link checker
run: |
# Auto-answer the prompt with yes command
yes "" | mintlify broken-links || test $? -eq 141
run: mint broken-links
working-directory: ./docs

View File

@@ -0,0 +1,64 @@
name: Generate Tool Specifications
on:
pull_request:
branches:
- main
paths:
- 'lib/crewai-tools/src/crewai_tools/**'
workflow_dispatch:
permissions:
contents: write
pull-requests: write
jobs:
generate-specs:
if: github.event_name == 'workflow_dispatch' || github.event.pull_request.head.repo.full_name == github.repository
runs-on: ubuntu-latest
env:
PYTHONUNBUFFERED: 1
steps:
- name: Generate GitHub App token
id: app-token
uses: actions/create-github-app-token@bcd2ba49218906704ab6c1aa796996da409d3eb1 # v3.2.0
with:
app-id: ${{ secrets.CREWAI_TOOL_SPECS_APP_ID }}
private-key: ${{ secrets.CREWAI_TOOL_SPECS_PRIVATE_KEY }}
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
ref: ${{ github.head_ref }}
token: ${{ steps.app-token.outputs.token }}
- name: Install uv
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.11.3"
python-version: "3.12"
enable-cache: true
- name: Install the project
working-directory: lib/crewai-tools
run: uv sync --dev --all-extras
- name: Generate tool specifications
working-directory: lib/crewai-tools
run: uv run python src/crewai_tools/generate_tool_specs.py
- name: Check for changes and commit
run: |
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git add lib/crewai-tools/tool.specs.json
if git diff --quiet --staged; then
echo "No changes detected in tool.specs.json"
else
echo "Changes detected in tool.specs.json, committing..."
git commit -m "chore: update tool specifications"
git push
fi

View File

@@ -6,21 +6,31 @@ permissions:
contents: read
jobs:
lint:
changes:
name: Detect changes
runs-on: ubuntu-latest
env:
TARGET_BRANCH: ${{ github.event.pull_request.base.ref }}
outputs:
code: ${{ steps.filter.outputs.code }}
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- uses: dorny/paths-filter@d1c1ffe0248fe513906c8e24db8ea791d46f8590 # v3
id: filter
with:
fetch-depth: 0
filters: |
code:
- '!docs/**'
- '!**/*.md'
- name: Fetch Target Branch
run: git fetch origin $TARGET_BRANCH --depth=1
lint-run:
needs: changes
if: needs.changes.outputs.code == 'true'
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- name: Restore global uv cache
id: cache-restore
uses: actions/cache/restore@v4
uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
@@ -31,39 +41,47 @@ jobs:
uv-main-py3.11-
- name: Install uv
uses: astral-sh/setup-uv@v6
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.8.4"
version: "0.11.3"
python-version: "3.11"
enable-cache: false
- name: Install dependencies
run: uv sync --all-groups --all-extras --no-install-project
- name: Get Changed Python Files
id: changed-files
run: |
merge_base=$(git merge-base origin/"$TARGET_BRANCH" HEAD)
changed_files=$(git diff --name-only --diff-filter=ACMRTUB "$merge_base" | grep '\.py$' || true)
echo "files<<EOF" >> $GITHUB_OUTPUT
echo "$changed_files" >> $GITHUB_OUTPUT
echo "EOF" >> $GITHUB_OUTPUT
- name: Ruff check
run: uv run ruff check lib/
- name: Run Ruff on Changed Files
if: ${{ steps.changed-files.outputs.files != '' }}
run: |
echo "${{ steps.changed-files.outputs.files }}" \
| tr ' ' '\n' \
| grep -v 'src/crewai/cli/templates/' \
| grep -v '/tests/' \
| xargs -I{} uv run ruff check "{}"
- name: Ruff format
run: uv run ruff format --check lib/
- name: Save uv caches
if: steps.cache-restore.outputs.cache-hit != 'true'
uses: actions/cache/save@v4
uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
~/.local/share/uv
.venv
key: uv-main-py3.11-${{ hashFiles('uv.lock') }}
# Summary job to provide single status for branch protection
lint:
name: lint
runs-on: ubuntu-latest
needs: [changes, lint-run]
if: always()
steps:
- name: Check results
run: |
if [ "${{ needs.changes.outputs.code }}" != "true" ]; then
echo "Docs-only change, skipping lint"
exit 0
fi
if [ "${{ needs.lint-run.result }}" == "success" ]; then
echo "Lint passed"
else
echo "Lint failed"
exit 1
fi

138
.github/workflows/nightly.yml vendored Normal file
View File

@@ -0,0 +1,138 @@
name: Nightly Canary Release
on:
schedule:
- cron: '0 6 * * *' # daily at 6am UTC
workflow_dispatch:
concurrency:
group: nightly-publish
cancel-in-progress: false
jobs:
check:
name: Check for new commits
runs-on: ubuntu-latest
permissions:
contents: read
outputs:
has_changes: ${{ steps.check.outputs.has_changes }}
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
fetch-depth: 0
- name: Check for recent commits
id: check
run: |
# 25h window absorbs cron-vs-commit timing skew at the boundary.
RECENT=$(git log --since="25 hours ago" --oneline | head -1)
if [ -n "$RECENT" ]; then
echo "has_changes=true" >> "$GITHUB_OUTPUT"
else
echo "has_changes=false" >> "$GITHUB_OUTPUT"
fi
build:
name: Build nightly packages
needs: check
if: needs.check.outputs.has_changes == 'true' || github.event_name == 'workflow_dispatch'
runs-on: ubuntu-latest
permissions:
contents: read
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- name: Install uv
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.11.3"
python-version: "3.12"
enable-cache: false
- name: Stamp nightly versions
run: |
DATE=$(date +%Y%m%d)
# All workspace packages share the same base version and are released together.
BASE=$(python -c "
import re
print(re.search(r'__version__\s*=\s*\"(.*?)\"', open('lib/crewai/src/crewai/__init__.py').read()).group(1))
")
NIGHTLY="${BASE}.dev${DATE}"
echo "Nightly version: ${NIGHTLY}"
for init_file in \
lib/crewai/src/crewai/__init__.py \
lib/crewai-core/src/crewai_core/__init__.py \
lib/crewai-tools/src/crewai_tools/__init__.py \
lib/crewai-files/src/crewai_files/__init__.py \
lib/cli/src/crewai_cli/__init__.py; do
sed -i "s/__version__ = .*/__version__ = \"${NIGHTLY}\"/" "$init_file"
echo "Stamped $init_file -> $NIGHTLY"
done
# Update all cross-package dependency pins to the nightly version.
sed -i "s/\"crewai==[^\"]*\"/\"crewai==${NIGHTLY}\"/" lib/crewai-tools/pyproject.toml
sed -i "s/\"crewai-core==[^\"]*\"/\"crewai-core==${NIGHTLY}\"/" lib/crewai/pyproject.toml
sed -i "s/\"crewai-cli==[^\"]*\"/\"crewai-cli==${NIGHTLY}\"/" lib/crewai/pyproject.toml
sed -i "s/\"crewai-tools==[^\"]*\"/\"crewai-tools==${NIGHTLY}\"/" lib/crewai/pyproject.toml
sed -i "s/\"crewai-files==[^\"]*\"/\"crewai-files==${NIGHTLY}\"/" lib/crewai/pyproject.toml
sed -i "s/\"crewai-core==[^\"]*\"/\"crewai-core==${NIGHTLY}\"/" lib/cli/pyproject.toml
echo "Updated cross-package dependency pins to ${NIGHTLY}"
- name: Build packages
run: |
uv build --all-packages
rm dist/.gitignore
- name: Upload artifacts
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: dist
path: dist/
publish:
name: Publish nightly to PyPI
needs: build
runs-on: ubuntu-latest
environment:
name: pypi
permissions:
id-token: write
contents: read
steps:
- name: Install uv
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.11.3"
python-version: "3.12"
enable-cache: false
- name: Download artifacts
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: dist
path: dist
- name: Publish to PyPI
env:
UV_PUBLISH_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
run: |
failed=0
for package in dist/*; do
if [[ "$package" == *"crewai_devtools"* ]]; then
echo "Skipping private package: $package"
continue
fi
echo "Publishing $package"
# --check-url skips files already on PyPI so manual re-runs on the same day are idempotent.
if ! uv publish --check-url https://pypi.org/simple/ "$package"; then
echo "Failed to publish $package"
failed=1
fi
done
if [ $failed -eq 1 ]; then
echo "Some packages failed to publish"
exit 1
fi

View File

@@ -1,33 +0,0 @@
name: Notify Downstream
on:
push:
branches:
- main
permissions:
contents: read
jobs:
notify-downstream:
runs-on: ubuntu-latest
steps:
- name: Generate GitHub App token
id: app-token
uses: tibdex/github-app-token@v2
with:
app_id: ${{ secrets.OSS_SYNC_APP_ID }}
private_key: ${{ secrets.OSS_SYNC_APP_PRIVATE_KEY }}
- name: Notify Repo B
uses: peter-evans/repository-dispatch@v3
with:
token: ${{ steps.app-token.outputs.token }}
repository: ${{ secrets.OSS_SYNC_DOWNSTREAM_REPO }}
event-type: upstream-commit
client-payload: |
{
"commit_sha": "${{ github.sha }}"
}

32
.github/workflows/pr-size.yml vendored Normal file
View File

@@ -0,0 +1,32 @@
name: PR Size Check
on:
pull_request:
types: [opened, synchronize, reopened]
jobs:
pr-size:
runs-on: ubuntu-latest
permissions:
pull-requests: write
steps:
- uses: codelytv/pr-size-labeler@095a41fca88b8764fd9e008ad269bcdb82bb38b9 # v1
with:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
xs_label: "size/XS"
xs_max_size: 25
s_label: "size/S"
s_max_size: 100
m_label: "size/M"
m_max_size: 250
l_label: "size/L"
l_max_size: 500
xl_label: "size/XL"
fail_if_xl: false
files_to_ignore: |
uv.lock
*.lock
lib/crewai/src/crewai/cli/templates/**
**/*.json
**/test_durations/**
**/cassettes/**

41
.github/workflows/pr-title.yml vendored Normal file
View File

@@ -0,0 +1,41 @@
name: PR Title Check
on:
pull_request:
types: [opened, edited, synchronize, reopened]
permissions:
contents: read
pull-requests: read
jobs:
pr-title:
runs-on: ubuntu-latest
steps:
- uses: amannn/action-semantic-pull-request@e32d7e603df1aa1ba07e981f2a23455dee596825 # v5
continue-on-error: true
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
types: |
feat
fix
refactor
perf
test
docs
chore
ci
style
revert
requireScope: false
subjectPattern: ^[a-z].+[^.]$
subjectPatternError: >
The PR title "{title}" does not follow conventional commit format.
Expected: <type>(<scope>): <lowercase description without trailing period>
Examples:
feat(memory): add lancedb storage backend
fix(agents): resolve deadlock in concurrent execution
chore(deps): bump pydantic to 2.11.9

View File

@@ -1,9 +1,12 @@
name: Publish to PyPI
on:
release:
types: [ published ]
workflow_dispatch:
inputs:
release_tag:
description: 'Release tag to publish'
required: false
type: string
jobs:
build:
@@ -12,15 +15,26 @@ jobs:
permissions:
contents: read
steps:
- uses: actions/checkout@v4
- name: Determine release tag
id: release
run: |
if [ -n "${{ inputs.release_tag }}" ]; then
echo "tag=${{ inputs.release_tag }}" >> $GITHUB_OUTPUT
else
echo "tag=" >> $GITHUB_OUTPUT
fi
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
ref: ${{ steps.release.outputs.tag || github.ref }}
- name: Set up Python
uses: actions/setup-python@v5
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with:
python-version: "3.12"
- name: Install uv
uses: astral-sh/setup-uv@v4
uses: astral-sh/setup-uv@38f3f104447c67c051c4a08e39b64a148898af3a # v4
- name: Build packages
run: |
@@ -28,7 +42,7 @@ jobs:
rm dist/.gitignore
- name: Upload artifacts
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: dist
path: dist/
@@ -44,17 +58,19 @@ jobs:
id-token: write
contents: read
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
ref: ${{ inputs.release_tag || github.ref }}
- name: Install uv
uses: astral-sh/setup-uv@v6
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.8.4"
version: "0.11.3"
python-version: "3.12"
enable-cache: false
- name: Download artifacts
uses: actions/download-artifact@v4
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: dist
path: dist
@@ -79,3 +95,72 @@ jobs:
echo "Some packages failed to publish"
exit 1
fi
- name: Build Slack payload
if: success()
id: slack
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
RELEASE_TAG: ${{ inputs.release_tag }}
run: |
payload=$(uv run python -c "
import json, re, subprocess, sys
with open('lib/crewai/src/crewai/__init__.py') as f:
m = re.search(r\"__version__\s*=\s*[\\\"']([^\\\"']+)\", f.read())
version = m.group(1) if m else 'unknown'
import os
tag = os.environ.get('RELEASE_TAG') or version
try:
r = subprocess.run(['gh','release','view',tag,'--json','body','-q','.body'],
capture_output=True, text=True, check=True)
body = r.stdout.strip()
except Exception:
body = ''
blocks = [
{'type':'section','text':{'type':'mrkdwn',
'text':f':rocket: \`crewai v{version}\` published to PyPI'}},
{'type':'section','text':{'type':'mrkdwn',
'text':f'<https://pypi.org/project/crewai/{version}/|View on PyPI> · <https://github.com/crewAIInc/crewAI/releases/tag/{tag}|Release notes>'}},
{'type':'divider'},
]
if body:
heading, items = '', []
for line in body.split('\n'):
line = line.strip()
if not line: continue
hm = re.match(r'^#{2,3}\s+(.*)', line)
if hm:
if heading and items:
skip = heading in ('What\\'s Changed','') or 'Contributors' in heading
if not skip:
txt = f'*{heading}*\n' + '\n'.join(f'• {i}' for i in items)
blocks.append({'type':'section','text':{'type':'mrkdwn','text':txt}})
heading, items = hm.group(1), []
elif line.startswith('- ') or line.startswith('* '):
items.append(re.sub(r'\*\*([^*]*)\*\*', r'*\1*', line[2:]))
if heading and items:
skip = heading in ('What\\'s Changed','') or 'Contributors' in heading
if not skip:
txt = f'*{heading}*\n' + '\n'.join(f'• {i}' for i in items)
blocks.append({'type':'section','text':{'type':'mrkdwn','text':txt}})
blocks.append({'type':'divider'})
blocks.append({'type':'section','text':{'type':'mrkdwn',
'text':f'\`\`\`uv add \"crewai[tools]=={version}\"\`\`\`'}})
print(json.dumps({'blocks':blocks}))
")
echo "payload=$payload" >> $GITHUB_OUTPUT
- name: Notify Slack
if: success()
uses: slackapi/slack-github-action@b0fa283ad8fea605de13dc3f449259339835fc52 # v2.1.0
with:
webhook: ${{ secrets.SLACK_WEBHOOK_URL }}
webhook-type: incoming-webhook
payload: ${{ steps.slack.outputs.payload }}

View File

@@ -14,7 +14,7 @@ jobs:
stale:
runs-on: ubuntu-latest
steps:
- uses: actions/stale@v9
- uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # v9.1.0
with:
repo-token: ${{ secrets.GITHUB_TOKEN }}
stale-issue-label: 'no-issue-activity'

View File

@@ -5,21 +5,26 @@ on: [pull_request]
permissions:
contents: read
env:
OPENAI_API_KEY: fake-api-key
PYTHONUNBUFFERED: 1
BRAVE_API_KEY: fake-brave-key
SNOWFLAKE_USER: fake-snowflake-user
SNOWFLAKE_PASSWORD: fake-snowflake-password
SNOWFLAKE_ACCOUNT: fake-snowflake-account
SNOWFLAKE_WAREHOUSE: fake-snowflake-warehouse
SNOWFLAKE_DATABASE: fake-snowflake-database
SNOWFLAKE_SCHEMA: fake-snowflake-schema
EMBEDCHAIN_DB_URI: sqlite:///test.db
jobs:
tests:
changes:
name: Detect changes
runs-on: ubuntu-latest
outputs:
code: ${{ steps.filter.outputs.code }}
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- uses: dorny/paths-filter@d1c1ffe0248fe513906c8e24db8ea791d46f8590 # v3
id: filter
with:
filters: |
code:
- '!docs/**'
- '!**/*.md'
tests-matrix:
name: tests (${{ matrix.python-version }})
needs: changes
if: needs.changes.outputs.code == 'true'
runs-on: ubuntu-latest
timeout-minutes: 15
strategy:
@@ -29,13 +34,13 @@ jobs:
group: [1, 2, 3, 4, 5, 6, 7, 8]
steps:
- name: Checkout code
uses: actions/checkout@v4
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
fetch-depth: 0 # Fetch all history for proper diff
- name: Restore global uv cache
id: cache-restore
uses: actions/cache/restore@v4
uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
@@ -46,9 +51,9 @@ jobs:
uv-main-py${{ matrix.python-version }}-
- name: Install uv
uses: astral-sh/setup-uv@v6
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.8.4"
version: "0.11.3"
python-version: ${{ matrix.python-version }}
enable-cache: false
@@ -56,7 +61,7 @@ jobs:
run: uv sync --all-groups --all-extras
- name: Restore test durations
uses: actions/cache/restore@v4
uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: .test_durations_py*
key: test-durations-py${{ matrix.python-version }}
@@ -84,35 +89,49 @@ jobs:
# fi
cd lib/crewai && uv run pytest \
--block-network \
--timeout=30 \
-vv \
--splits 8 \
--group ${{ matrix.group }} \
$DURATIONS_ARG \
--durations=10 \
-n auto \
--maxfail=3
- name: Run tool tests (group ${{ matrix.group }} of 8)
run: |
cd lib/crewai-tools && uv run pytest \
--block-network \
--timeout=30 \
-vv \
--splits 8 \
--group ${{ matrix.group }} \
--durations=10 \
-n auto \
--maxfail=3
- name: Save uv caches
if: steps.cache-restore.outputs.cache-hit != 'true'
uses: actions/cache/save@v4
uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
~/.local/share/uv
.venv
key: uv-main-py${{ matrix.python-version }}-${{ hashFiles('uv.lock') }}
# Summary job to provide single status for branch protection
tests:
name: tests
runs-on: ubuntu-latest
needs: [changes, tests-matrix]
if: always()
steps:
- name: Check results
run: |
if [ "${{ needs.changes.outputs.code }}" != "true" ]; then
echo "Docs-only change, skipping tests"
exit 0
fi
if [ "${{ needs.tests-matrix.result }}" == "success" ]; then
echo "All tests passed"
else
echo "Tests failed"
exit 1
fi

View File

@@ -6,8 +6,25 @@ permissions:
contents: read
jobs:
changes:
name: Detect changes
runs-on: ubuntu-latest
outputs:
code: ${{ steps.filter.outputs.code }}
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- uses: dorny/paths-filter@d1c1ffe0248fe513906c8e24db8ea791d46f8590 # v3
id: filter
with:
filters: |
code:
- '!docs/**'
- '!**/*.md'
type-checker-matrix:
name: type-checker (${{ matrix.python-version }})
needs: changes
if: needs.changes.outputs.code == 'true'
runs-on: ubuntu-latest
strategy:
fail-fast: false
@@ -16,13 +33,11 @@ jobs:
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
fetch-depth: 0 # Fetch all history for proper diff
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- name: Restore global uv cache
id: cache-restore
uses: actions/cache/restore@v4
uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
@@ -33,50 +48,21 @@ jobs:
uv-main-py${{ matrix.python-version }}-
- name: Install uv
uses: astral-sh/setup-uv@v6
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.8.4"
version: "0.11.3"
python-version: ${{ matrix.python-version }}
enable-cache: false
- name: Install dependencies
run: uv sync --all-groups --all-extras
- name: Get changed Python files
id: changed-files
run: |
# Get the list of changed Python files compared to the base branch
echo "Fetching changed files..."
git diff --name-only --diff-filter=ACMRT origin/${{ github.base_ref }}...HEAD -- '*.py' > changed_files.txt
# Filter for files in src/ directory only (excluding tests/)
grep -E "^src/" changed_files.txt > filtered_changed_files.txt || true
# Check if there are any changed files
if [ -s filtered_changed_files.txt ]; then
echo "Changed Python files in src/:"
cat filtered_changed_files.txt
echo "has_changes=true" >> $GITHUB_OUTPUT
# Convert newlines to spaces for mypy command
echo "files=$(cat filtered_changed_files.txt | tr '\n' ' ')" >> $GITHUB_OUTPUT
else
echo "No Python files changed in src/"
echo "has_changes=false" >> $GITHUB_OUTPUT
fi
- name: Run type checks on changed files
if: steps.changed-files.outputs.has_changes == 'true'
run: |
echo "Running mypy on changed files with Python ${{ matrix.python-version }}..."
uv run mypy ${{ steps.changed-files.outputs.files }}
- name: No files to check
if: steps.changed-files.outputs.has_changes == 'false'
run: echo "No Python files in src/ were modified - skipping type checks"
- name: Run type checks
run: uv run mypy lib/
- name: Save uv caches
if: steps.cache-restore.outputs.cache-hit != 'true'
uses: actions/cache/save@v4
uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
@@ -88,14 +74,18 @@ jobs:
type-checker:
name: type-checker
runs-on: ubuntu-latest
needs: type-checker-matrix
needs: [changes, type-checker-matrix]
if: always()
steps:
- name: Check matrix results
- name: Check results
run: |
if [ "${{ needs.type-checker-matrix.result }}" == "success" ] || [ "${{ needs.type-checker-matrix.result }}" == "skipped" ]; then
echo "✅ All type checks passed"
if [ "${{ needs.changes.outputs.code }}" != "true" ]; then
echo "Docs-only change, skipping type checks"
exit 0
fi
if [ "${{ needs.type-checker-matrix.result }}" == "success" ]; then
echo "All type checks passed"
else
echo "Type checks failed"
echo "Type checks failed"
exit 1
fi

View File

@@ -23,11 +23,11 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@v4
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
- name: Restore global uv cache
id: cache-restore
uses: actions/cache/restore@v4
uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
@@ -38,9 +38,9 @@ jobs:
uv-main-py${{ matrix.python-version }}-
- name: Install uv
uses: astral-sh/setup-uv@v6
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.8.4"
version: "0.11.3"
python-version: ${{ matrix.python-version }}
enable-cache: false
@@ -55,14 +55,14 @@ jobs:
- name: Save durations to cache
if: always()
uses: actions/cache/save@v4
uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: .test_durations_py*
key: test-durations-py${{ matrix.python-version }}
- name: Save uv caches
if: steps.cache-restore.outputs.cache-hit != 'true'
uses: actions/cache/save@v4
uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv

105
.github/workflows/vulnerability-scan.yml vendored Normal file
View File

@@ -0,0 +1,105 @@
name: Vulnerability Scan
on:
pull_request:
push:
branches: [main]
schedule:
# Run weekly on Monday at 9:00 UTC
- cron: '0 9 * * 1'
permissions:
contents: read
jobs:
pip-audit:
name: pip-audit
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
persist-credentials: false
- name: Restore global uv cache
id: cache-restore
uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
~/.local/share/uv
.venv
key: uv-main-py3.11-${{ hashFiles('uv.lock') }}
restore-keys: |
uv-main-py3.11-
- name: Install uv
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
version: "0.11.3"
python-version: "3.11"
enable-cache: false
- name: Install dependencies
run: uv sync --all-groups --all-extras --no-install-project
- name: Install pip-audit
run: uv pip install pip-audit
- name: Run pip-audit
run: |
pip_audit_args=(
--desc
--aliases
--skip-editable
--format json
--output pip-audit-report.json
--ignore-vuln PYSEC-2026-597 # nltk 3.9.4 (CVE-2026-12243): no fix available, transitive through crewai-tools[xml] -> unstructured.
--ignore-vuln GHSA-rrmf-rvhw-rf47 # torch 2.12.0 (CVE-2025-3000): local-only memory corruption in torch.jit.script; no fix available.
--ignore-vuln GHSA-f4j7-r4q5-qw2c # chromadb 1.1.1 (CVE-2026-45829): pre-auth RCE in the HTTP server; no fix available.
)
uv run pip-audit "${pip_audit_args[@]}"
continue-on-error: true
- name: Display results
if: always()
run: |
if [ -f pip-audit-report.json ]; then
echo "## pip-audit Results" >> $GITHUB_STEP_SUMMARY
echo '```json' >> $GITHUB_STEP_SUMMARY
cat pip-audit-report.json | python3 -m json.tool >> $GITHUB_STEP_SUMMARY
echo '```' >> $GITHUB_STEP_SUMMARY
# Fail if vulnerabilities found
python3 -c "
import json, sys
with open('pip-audit-report.json') as f:
data = json.load(f)
vulns = [d for d in data.get('dependencies', []) if d.get('vulns')]
if vulns:
print(f'::error::Found vulnerabilities in {len(vulns)} package(s)')
for v in vulns:
for vuln in v['vulns']:
print(f' - {v[\"name\"]}=={v[\"version\"]}: {vuln[\"id\"]}')
sys.exit(1)
print('No known vulnerabilities found')
"
else
echo "::error::pip-audit failed to produce a report. Check the pip-audit step logs."
exit 1
fi
- name: Upload pip-audit report
if: always()
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: pip-audit-report
path: pip-audit-report.json
- name: Save uv caches
if: steps.cache-restore.outputs.cache-hit != 'true'
uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
with:
path: |
~/.cache/uv
~/.local/share/uv
.venv
key: uv-main-py3.11-${{ hashFiles('uv.lock') }}

7
.gitignore vendored
View File

@@ -26,3 +26,10 @@ plan.md
conceptual_plan.md
build_image
chromadb-*.lock
.claude
.crewai/memory
blogs/*
secrets/*
UNKNOWN.egg-info/
demos/*
.crewai/*

View File

@@ -19,9 +19,52 @@ repos:
language: system
pass_filenames: true
types: [python]
exclude: ^(lib/crewai/src/crewai/cli/templates/|lib/crewai/tests/|lib/crewai-tools/tests/)
exclude: ^(lib/crewai/src/crewai/cli/templates/|lib/cli/src/crewai_cli/templates/|lib/cli/tests/|lib/crewai/tests/|lib/crewai-tools/tests/|lib/crewai-files/tests/|lib/devtools/tests/)
- repo: https://github.com/astral-sh/uv-pre-commit
rev: 0.9.3
rev: 0.11.3
hooks:
- id: uv-lock
- repo: local
hooks:
- id: pip-audit
name: pip-audit
# Keep this ignore list in sync with .github/workflows/vulnerability-scan.yml.
entry: >-
bash -c 'source .venv/bin/activate && uv run pip-audit --skip-editable
--ignore-vuln PYSEC-2024-277
--ignore-vuln PYSEC-2026-89
--ignore-vuln PYSEC-2026-97
--ignore-vuln PYSEC-2026-597
--ignore-vuln PYSEC-2025-148
--ignore-vuln PYSEC-2025-183
--ignore-vuln PYSEC-2025-189
--ignore-vuln PYSEC-2025-190
--ignore-vuln PYSEC-2025-191
--ignore-vuln PYSEC-2025-192
--ignore-vuln PYSEC-2025-193
--ignore-vuln PYSEC-2025-194
--ignore-vuln PYSEC-2025-195
--ignore-vuln PYSEC-2025-196
--ignore-vuln PYSEC-2025-197
--ignore-vuln PYSEC-2025-210
--ignore-vuln PYSEC-2026-139
--ignore-vuln GHSA-rrmf-rvhw-rf47
--ignore-vuln PYSEC-2025-211
--ignore-vuln PYSEC-2025-212
--ignore-vuln PYSEC-2025-213
--ignore-vuln PYSEC-2025-214
--ignore-vuln PYSEC-2025-215
--ignore-vuln PYSEC-2025-216
--ignore-vuln PYSEC-2025-217
--ignore-vuln PYSEC-2025-218
--ignore-vuln GHSA-f4j7-r4q5-qw2c' --
language: system
pass_filenames: false
stages: [pre-push, manual]
- repo: https://github.com/commitizen-tools/commitizen
rev: v4.10.1
hooks:
- id: commitizen
- id: commitizen-branch
stages: [ pre-push ]

1
.python-version Normal file
View File

@@ -0,0 +1 @@
3.13

26
AGENTS.md Normal file
View File

@@ -0,0 +1,26 @@
# Agent Instructions for CrewAI OSS
CrewAI is a Python based framework for building AI agents and agentic systems.
Follow these guidelines when contributing:
## Key Guidelines
1. Follow Python best practices and idiomatic patterns.
2. Maintain existing code structure and organization.
3. Write unit tests for new functionality focusing on behaivor and not
implementation.
4. Document public APIs and complex logic.
5. Suggest changes to the `docs/` folder when appropriate
6. Follow software principles such as DRY and YAGNI.
7. Keep diffs as minimal as possible.
## Changing Docs
1. Edit MDX under `docs/edge/en/*` and reference it from `docs/docs.json` if
needed.
2. Do not modify files under `docs/v*/`. Those are frozen release snapshots
managed by devtools.
3. Do not delete or rename files under `docs/images/` as frozen snapshots
may reference them.
4. If you want to preview your changes locally, use `cd docs && mintlify dev`.
To check for broken links, run `cd docs && mintlify broken-links`.

173
README.md
View File

@@ -12,6 +12,8 @@
<p align="center">
<a href="https://crewai.com">Homepage</a>
·
<a href="https://crewai.com/open-source">Open Source</a>
·
<a href="https://docs.crewai.com">Docs</a>
·
<a href="https://app.crewai.com">Start Cloud Trial</a>
@@ -53,20 +55,20 @@
### Fast and Flexible Multi-Agent Automation Framework
> CrewAI is a lean, lightning-fast Python framework built entirely from scratch—completely **independent of LangChain or other agent frameworks**.
> It empowers developers with both high-level simplicity and precise low-level control, ideal for creating autonomous AI agents tailored to any scenario.
> CrewAI is an open-source Python framework with high-level abstractions and low-level APIs for building production-ready multi-agent workflows.
> It gives developers autonomous agent collaboration through Crews and precise, event-driven control through Flows.
- **CrewAI Crews**: Optimize for autonomy and collaborative intelligence.
- **CrewAI Flows**: Enable granular, event-driven control, single LLM calls for precise task orchestration and supports Crews natively
- **CrewAI Crews**: Optimize for autonomy and collaborative intelligence with role-based AI agents.
- **CrewAI Flows**: Build event-driven automations that combine precise workflow control, single LLM calls, and native support for Crews.
With over 100,000 developers certified through our community courses at [learn.crewai.com](https://learn.crewai.com), CrewAI is rapidly becoming the
standard for enterprise-ready AI automation.
standard for production-ready agentic automation.
# CrewAI AOP Suite
# CrewAI AMP Suite
CrewAI AOP Suite is a comprehensive bundle tailored for organizations that require secure, scalable, and easy-to-manage agent-driven automation.
For organizations that need a commercial control plane around CrewAI, [CrewAI AMP Suite](https://www.crewai.com/enterprise) adds managed deployment, observability, governance, security, and enterprise support.
You can try one part of the suite the [Crew Control Plane for free](https://app.crewai.com)
You can try one part of the suite, the [Crew Control Plane, for free](https://app.crewai.com).
## Crew Control Plane Key Features:
@@ -76,18 +78,18 @@ You can try one part of the suite the [Crew Control Plane for free](https://app.
- **Advanced Security**: Built-in robust security and compliance measures ensuring safe deployment and management.
- **Actionable Insights**: Real-time analytics and reporting to optimize performance and decision-making.
- **24/7 Support**: Dedicated enterprise support to ensure uninterrupted operation and quick resolution of issues.
- **On-premise and Cloud Deployment Options**: Deploy CrewAI AOP on-premise or in the cloud, depending on your security and compliance requirements.
- **On-premise and Cloud Deployment Options**: Deploy CrewAI AMP on-premise or in the cloud, depending on your security and compliance requirements.
CrewAI AOP is designed for enterprises seeking a powerful, reliable solution to transform complex business processes into efficient,
CrewAI AMP is designed for enterprises seeking a powerful, reliable solution to transform complex business processes into efficient,
intelligent automations.
## Table of contents
- [Build with AI](#build-with-ai)
- [Why CrewAI?](#why-crewai)
- [Getting Started](#getting-started)
- [Key Features](#key-features)
- [Understanding Flows and Crews](#understanding-flows-and-crews)
- [CrewAI vs LangGraph](#how-crewai-compares)
- [Examples](#examples)
- [Quick Tutorial](#quick-tutorial)
- [Write Job Descriptions](#write-job-descriptions)
@@ -95,11 +97,37 @@ intelligent automations.
- [Stock Analysis](#stock-analysis)
- [Using Crews and Flows Together](#using-crews-and-flows-together)
- [Connecting Your Crew to a Model](#connecting-your-crew-to-a-model)
- [How CrewAI Compares](#how-crewai-compares)
- [Frequently Asked Questions (FAQ)](#frequently-asked-questions-faq)
- [When to Use CrewAI](#when-to-use-crewai)
- [Contribution](#contribution)
- [Telemetry](#telemetry)
- [License](#license)
- [Frequently Asked Questions (FAQ)](#frequently-asked-questions-faq)
## Build with AI
Using an AI coding agent? Teach it CrewAI best practices in one command:
**Claude Code:**
```shell
/plugin marketplace add crewAIInc/skills
/plugin install crewai-skills@crewai-plugins
/reload-plugins
```
Four skills that activate automatically when you ask relevant CrewAI questions:
| Skill | When it runs |
|-------|--------------|
| `getting-started` | Scaffolding new projects, choosing between `LLM.call()` / `Agent` / `Crew` / `Flow`, wiring `crew.py` / `main.py` |
| `design-agent` | Configuring agents — role, goal, backstory, tools, LLMs, memory, guardrails |
| `design-task` | Writing task descriptions, dependencies, structured output (`output_pydantic`, `output_json`), human review |
| `ask-docs` | Querying the live [CrewAI docs MCP server](https://docs.crewai.com/mcp) for up-to-date API details |
**Cursor, Codex, Windsurf, and others ([skills.sh](https://skills.sh/crewaiinc/skills)):**
```shell
npx skills add crewaiinc/skills
```
This installs the official [CrewAI Skills](https://github.com/crewAIInc/skills) — structured instructions that teach coding agents how to scaffold Flows, configure Crews, design agents and tasks, and follow CrewAI patterns.
## Why CrewAI?
@@ -107,15 +135,15 @@ intelligent automations.
<img src="docs/images/asset.png" alt="CrewAI Logo" width="100%">
</div>
CrewAI unlocks the true potential of multi-agent automation, delivering the best-in-class combination of speed, flexibility, and control with either Crews of AI Agents or Flows of Events:
CrewAI unlocks the true potential of multi-agent automation, delivering speed, flexibility, and control through Crews of AI agents and event-driven Flows:
- **Standalone Framework**: Built from scratch, independent of LangChain or any other agent framework.
- **Purpose-built architecture**: Designed specifically for agent orchestration, with a lightweight Python core and clean primitives for real-world automation.
- **High Performance**: Optimized for speed and minimal resource usage, enabling faster execution.
- **Flexible Low Level Customization**: Complete freedom to customize at both high and low levels - from overall workflows and system architecture to granular agent behaviors, internal prompts, and execution logic.
- **Ideal for Every Use Case**: Proven effective for both simple tasks and highly complex, real-world, enterprise-grade scenarios.
- **Flexible Low-Level Customization**: Complete freedom to customize everything from workflows and system architecture to agent behaviors, internal prompts, and execution logic.
- **Ideal for Every Use Case**: Proven effective for simple tasks, complex workflows, and production-grade automation.
- **Robust Community**: Backed by a rapidly growing community of over **100,000 certified** developers offering comprehensive support and resources.
CrewAI empowers developers and enterprises to confidently build intelligent automations, bridging the gap between simplicity, flexibility, and performance.
CrewAI empowers developers and teams to build intelligent automations that balance simplicity, flexibility, and production-grade control.
## Getting Started
@@ -124,7 +152,8 @@ Setup and run your first CrewAI agents by following this tutorial.
[![CrewAI Getting Started Tutorial](https://img.youtube.com/vi/-kSOTtYzgEw/hqdefault.jpg)](https://www.youtube.com/watch?v=-kSOTtYzgEw "CrewAI Getting Started Tutorial")
###
Learning Resources
Learning Resources
Learn CrewAI through our comprehensive courses:
@@ -141,6 +170,7 @@ CrewAI offers two powerful, complementary approaches that work seamlessly togeth
- Dynamic task delegation and collaboration
- Specialized roles with defined goals and expertise
- Flexible problem-solving approaches
2. **Flows**: Production-ready, event-driven workflows that deliver precise control over complex automations. Flows provide:
- Fine-grained control over execution paths for real-world scenarios
@@ -166,13 +196,13 @@ Ensure you have Python >=3.10 <3.14 installed on your system. CrewAI uses [UV](h
First, install CrewAI:
```shell
pip install crewai
uv pip install crewai
```
If you want to install the 'crewai' package along with its optional features that include additional tools for agents, you can do so by using the following command:
```shell
pip install 'crewai[tools]'
uv pip install 'crewai[tools]'
```
The command above installs the basic package and also adds extra components which require more dependencies to function.
@@ -185,14 +215,15 @@ If you encounter issues during installation or usage, here are some common solut
1. **ModuleNotFoundError: No module named 'tiktoken'**
- Install tiktoken explicitly: `pip install 'crewai[embeddings]'`
- If using embedchain or other tools: `pip install 'crewai[tools]'`
- Install tiktoken explicitly: `uv pip install 'crewai[embeddings]'`
- If using embedchain or other tools: `uv pip install 'crewai[tools]'`
2. **Failed building wheel for tiktoken**
- Ensure Rust compiler is installed (see installation steps above)
- For Windows: Verify Visual C++ Build Tools are installed
- Try upgrading pip: `pip install --upgrade pip`
- If issues persist, use a pre-built wheel: `pip install tiktoken --prefer-binary`
- Try upgrading pip: `uv pip install --upgrade pip`
- If issues persist, use a pre-built wheel: `uv pip install tiktoken --prefer-binary`
### 2. Setting Up Your Crew with the YAML Configuration
@@ -270,7 +301,7 @@ reporting_analyst:
**tasks.yaml**
```yaml
````yaml
# src/my_project/config/tasks.yaml
research_task:
description: >
@@ -290,7 +321,7 @@ reporting_task:
Formatted as markdown without '```'
agent: reporting_analyst
output_file: report.md
```
````
**crew.py**
@@ -403,16 +434,17 @@ In addition to the sequential process, you can use the hierarchical process, whi
## Key Features
CrewAI stands apart as a lean, standalone, high-performance multi-AI Agent framework delivering simplicity, flexibility, and precise control—free from the complexity and limitations found in other agent frameworks.
CrewAI gives developers a practical foundation for building agentic systems that move from prototype to production: autonomous collaboration where it helps, explicit workflow control where it matters, and Python-native customization throughout.
- **Standalone & Lean**: Completely independent from other frameworks like LangChain, offering faster execution and lighter resource demands.
- **Flexible & Precise**: Easily orchestrate autonomous agents through intuitive [Crews](https://docs.crewai.com/concepts/crews) or precise [Flows](https://docs.crewai.com/concepts/flows), achieving perfect balance for your needs.
- **Seamless Integration**: Effortlessly combine Crews (autonomy) and Flows (precision) to create complex, real-world automations.
- **Deep Customization**: Tailor every aspect—from high-level workflows down to low-level internal prompts and agent behaviors.
- **Reliable Performance**: Consistent results across simple tasks and complex, enterprise-level automations.
- **Thriving Community**: Backed by robust documentation and over 100,000 certified developers, providing exceptional support and guidance.
- **Crews for autonomy**: Model teams of specialized AI agents with roles, goals, tools, and tasks.
- **Flows for control**: Build event-driven workflows with state, branching, routing, and production logic.
- **Seamless integration**: Combine Crews and Flows to create complex, real-world automations.
- **Python-native customization**: Customize prompts, tools, execution paths, state, and integrations without fighting the framework.
- **Agent-ready capabilities**: Use tools, memory, knowledge, checkpointing, async execution, and MCP/A2A support for more capable production agents.
- **Production-ready patterns**: Add deterministic steps, human input, structured outputs, and checkpointing as your system grows.
- **Thriving community**: Backed by robust documentation and over 100,000 certified developers, providing exceptional support and guidance.
Choose CrewAI to easily build powerful, adaptable, and production-ready AI automations.
Choose CrewAI to build powerful, adaptable, and production-ready AI automations.
## Examples
@@ -550,16 +582,17 @@ CrewAI supports using various LLMs through a variety of connection options. By d
Please refer to the [Connect CrewAI to LLMs](https://docs.crewai.com/how-to/LLM-Connections/) page for details on configuring your agents' connections to models.
## How CrewAI Compares
## When to Use CrewAI
**CrewAI's Advantage**: CrewAI combines autonomous agent intelligence with precise workflow control through its unique Crews and Flows architecture. The framework excels at both high-level orchestration and low-level customization, enabling complex, production-grade systems with granular control.
Use CrewAI when you need more than a single prompt or chatbot: multi-step work, specialized agents, tool use, structured outputs, human review, or workflows that combine autonomous reasoning with explicit business logic.
- **LangGraph**: While LangGraph provides a foundation for building agent workflows, its approach requires significant boilerplate code and complex state management patterns. The framework's tight coupling with LangChain can limit flexibility when implementing custom agent behaviors or integrating with external systems.
CrewAI is especially useful when you want to:
*P.S. CrewAI demonstrates significant performance advantages over LangGraph, executing 5.76x faster in certain cases like this QA task example ([see comparison](https://github.com/crewAIInc/crewAI-examples/tree/main/Notebooks/CrewAI%20Flows%20%26%20Langgraph/QA%20Agent)) while achieving higher evaluation scores with faster completion times in certain coding tasks, like in this example ([detailed analysis](https://github.com/crewAIInc/crewAI-examples/blob/main/Notebooks/CrewAI%20Flows%20%26%20Langgraph/Coding%20Assistant/coding_assistant_eval.ipynb)).*
- **Autogen**: While Autogen excels at creating conversational agents capable of working together, it lacks an inherent concept of process. In Autogen, orchestrating agents' interactions requires additional programming, which can become complex and cumbersome as the scale of tasks grows.
- **ChatDev**: ChatDev introduced the idea of processes into the realm of AI agents, but its implementation is quite rigid. Customizations in ChatDev are limited and not geared towards production environments, which can hinder scalability and flexibility in real-world applications.
- Coordinate multiple agents with clear roles and tasks.
- Wrap agent work in deterministic, event-driven workflows.
- Keep application logic in regular Python.
- Move from experiment to production without changing frameworks.
- Add tools, memory, checkpointing, and async execution as your system grows.
## Contribution
@@ -571,6 +604,19 @@ CrewAI is open-source and we welcome contributions. If you're looking to contrib
- Send a pull request.
- We appreciate your input!
### Contributing to the docs
The site at [docs.crewai.com](https://docs.crewai.com) is published from
`docs/` by [Mintlify](https://www.mintlify.com/). The docs use directory-based
versioning: edits to `docs/edge/<lang>/...` (e.g.
`docs/edge/en/concepts/agents.mdx`) land under the **Edge** version selector
immediately and are frozen into a new versioned snapshot under
`docs/v<X.Y.Z>/` at the next release cut. Frozen snapshots are immutable — CI
rejects PRs that modify them without a `[docs-freeze]` title prefix. The
release CLI (`devtools release`) handles the freeze automatically; see
[`AGENTS.md`](AGENTS.md) for the full contributor guide and
[`RELEASING.md`](RELEASING.md) for the release-cut runbook.
### Installing Dependencies
```bash
@@ -611,7 +657,7 @@ uv build
### Installing Locally
```bash
pip install dist/*.tar.gz
uv pip install dist/*.tar.gz
```
## Telemetry
@@ -655,7 +701,7 @@ CrewAI is released under the [MIT License](https://github.com/crewAIInc/crewAI/b
- [What exactly is CrewAI?](#q-what-exactly-is-crewai)
- [How do I install CrewAI?](#q-how-do-i-install-crewai)
- [Does CrewAI depend on LangChain?](#q-does-crewai-depend-on-langchain)
- [Is CrewAI a standalone framework?](#q-is-crewai-a-standalone-framework)
- [Is CrewAI open-source?](#q-is-crewai-open-source)
- [Does CrewAI collect data from users?](#q-does-crewai-collect-data-from-users)
@@ -664,7 +710,6 @@ CrewAI is released under the [MIT License](https://github.com/crewAIInc/crewAI/b
- [Can CrewAI handle complex use cases?](#q-can-crewai-handle-complex-use-cases)
- [Can I use CrewAI with local AI models?](#q-can-i-use-crewai-with-local-ai-models)
- [What makes Crews different from Flows?](#q-what-makes-crews-different-from-flows)
- [How is CrewAI better than LangChain?](#q-how-is-crewai-better-than-langchain)
- [Does CrewAI support fine-tuning or training custom models?](#q-does-crewai-support-fine-tuning-or-training-custom-models)
### Resources and Community
@@ -674,31 +719,31 @@ CrewAI is released under the [MIT License](https://github.com/crewAIInc/crewAI/b
### Enterprise Features
- [What additional features does CrewAI AOP offer?](#q-what-additional-features-does-crewai-amp-offer)
- [Is CrewAI AOP available for cloud and on-premise deployments?](#q-is-crewai-amp-available-for-cloud-and-on-premise-deployments)
- [Can I try CrewAI AOP for free?](#q-can-i-try-crewai-amp-for-free)
- [What additional features does CrewAI AMP offer?](#q-what-additional-features-does-crewai-amp-offer)
- [Is CrewAI AMP available for cloud and on-premise deployments?](#q-is-crewai-amp-available-for-cloud-and-on-premise-deployments)
- [Can I try CrewAI AMP for free?](#q-can-i-try-crewai-amp-for-free)
### Q: What exactly is CrewAI?
A: CrewAI is a standalone, lean, and fast Python framework built specifically for orchestrating autonomous AI agents. Unlike frameworks like LangChain, CrewAI does not rely on external dependencies, making it leaner, faster, and simpler.
A: CrewAI is a lean, fast Python framework built specifically for orchestrating autonomous AI agents and production-ready agentic workflows.
### Q: How do I install CrewAI?
A: Install CrewAI using pip:
```shell
pip install crewai
uv pip install crewai
```
For additional tools, use:
```shell
pip install 'crewai[tools]'
uv pip install 'crewai[tools]'
```
### Q: Does CrewAI depend on LangChain?
### Q: Is CrewAI a standalone framework?
A: No. CrewAI is built entirely from the ground up, with no dependencies on LangChain or other agent frameworks. This ensures a lean, fast, and flexible experience.
A: Yes. CrewAI is a standalone Python framework with its own primitives for agents, tasks, crews, flows, tools, and orchestration.
### Q: Can CrewAI handle complex use cases?
@@ -712,10 +757,6 @@ A: Absolutely! CrewAI supports various language models, including local ones. To
A: Crews provide autonomous agent collaboration, ideal for tasks requiring flexible decision-making and dynamic interaction. Flows offer precise, event-driven control, ideal for managing detailed execution paths and secure state management. You can seamlessly combine both for maximum effectiveness.
### Q: How is CrewAI better than LangChain?
A: CrewAI provides simpler, more intuitive APIs, faster execution speeds, more reliable and consistent results, robust documentation, and an active community—addressing common criticisms and limitations associated with LangChain.
### Q: Is CrewAI open-source?
A: Yes, CrewAI is open-source and actively encourages community contributions and collaboration.
@@ -732,17 +773,17 @@ A: Check out practical examples in the [CrewAI-examples repository](https://gith
A: Contributions are warmly welcomed! Fork the repository, create your branch, implement your changes, and submit a pull request. See the Contribution section of the README for detailed guidelines.
### Q: What additional features does CrewAI AOP offer?
### Q: What additional features does CrewAI AMP offer?
A: CrewAI AOP provides advanced features such as a unified control plane, real-time observability, secure integrations, advanced security, actionable insights, and dedicated 24/7 enterprise support.
A: CrewAI AMP provides advanced features such as a unified control plane, real-time observability, secure integrations, advanced security, actionable insights, and dedicated 24/7 enterprise support.
### Q: Is CrewAI AOP available for cloud and on-premise deployments?
### Q: Is CrewAI AMP available for cloud and on-premise deployments?
A: Yes, CrewAI AOP supports both cloud-based and on-premise deployment options, allowing enterprises to meet their specific security and compliance requirements.
A: Yes, CrewAI AMP supports both cloud-based and on-premise deployment options, allowing enterprises to meet their specific security and compliance requirements.
### Q: Can I try CrewAI AOP for free?
### Q: Can I try CrewAI AMP for free?
A: Yes, you can explore part of the CrewAI AOP Suite by accessing the [Crew Control Plane](https://app.crewai.com) for free.
A: Yes, you can explore part of the CrewAI AMP Suite by accessing the [Crew Control Plane](https://app.crewai.com) for free.
### Q: Does CrewAI support fine-tuning or training custom models?
@@ -754,15 +795,15 @@ A: Absolutely! CrewAI agents can easily integrate with external tools, APIs, and
### Q: Is CrewAI suitable for production environments?
A: Yes, CrewAI is explicitly designed with production-grade standards, ensuring reliability, stability, and scalability for enterprise deployments.
A: Yes, CrewAI is designed with production-grade patterns that support reliable, stable, and scalable agentic workflows.
### Q: How scalable is CrewAI?
A: CrewAI is highly scalable, supporting simple automations and large-scale enterprise workflows involving numerous agents and complex tasks simultaneously.
A: CrewAI is highly scalable, supporting simple automations and large-scale workflows involving numerous agents and complex tasks simultaneously.
### Q: Does CrewAI offer debugging and monitoring tools?
A: Yes, CrewAI AOP includes advanced debugging, tracing, and real-time observability features, simplifying the management and troubleshooting of your automations.
A: Yes, CrewAI AMP includes advanced debugging, tracing, and real-time observability features, simplifying the management and troubleshooting of your automations.
### Q: What programming languages does CrewAI support?

427
conftest.py Normal file
View File

@@ -0,0 +1,427 @@
"""Pytest configuration for crewAI workspace."""
import base64
from collections.abc import Generator
import gzip
import os
from pathlib import Path
import re
import tempfile
from typing import Any
from dotenv import load_dotenv
import pytest
def _patch_vcrpy_aiohttp_compat() -> None:
"""Keep vcrpy's aiohttp stub working under aiohttp 3.14.0.
aiohttp 3.14.0 (pulled in to fix GHSA-jg22-mg44-37j8 and GHSA-hg6j-4rv6-33pg):
* removed ``aiohttp.streams.AsyncStreamReaderMixin`` (folded into ``StreamReader``),
which vcrpy's ``MockStream`` still subclasses -- vcr's patch machinery then raises
``AttributeError`` at collection time; and
* added a required ``stream_writer`` keyword-only arg to ``ClientResponse.__init__``,
which vcrpy's ``MockClientResponse`` does not pass -- raising ``TypeError`` at
cassette playback.
Restore the mixin, then rebuild ``MockClientResponse``'s ``super().__init__`` call from
the live ``ClientResponse`` signature (defaulting every required keyword-only arg to
``None``, mirroring vcrpy's original call) so it also survives future aiohttp additions.
"""
import asyncio
import inspect
from aiohttp import streams
from aiohttp.client_reqrep import ClientResponse
if not hasattr(streams, "AsyncStreamReaderMixin"):
class AsyncStreamReaderMixin:
__slots__ = ()
def __aiter__(self) -> streams.AsyncStreamIterator[bytes]:
return streams.AsyncStreamIterator(self.readline) # type: ignore[attr-defined]
def iter_chunked(self, n: int) -> streams.AsyncStreamIterator[bytes]:
return streams.AsyncStreamIterator(lambda: self.read(n)) # type: ignore[attr-defined]
def iter_any(self) -> streams.AsyncStreamIterator[bytes]:
return streams.AsyncStreamIterator(self.readany) # type: ignore[attr-defined]
def iter_chunks(self) -> streams.ChunkTupleAsyncStreamIterator:
return streams.ChunkTupleAsyncStreamIterator(self) # type: ignore[arg-type]
streams.AsyncStreamReaderMixin = AsyncStreamReaderMixin # type: ignore[attr-defined]
# Importing the stub builds MockStream/MockClientResponse, so it must run after the
# mixin is restored above.
import vcr.stubs.aiohttp_stubs as aiohttp_stubs # type: ignore[import-untyped]
if getattr(aiohttp_stubs.MockClientResponse, "_crewai_aiohttp_patched", False):
return
keyword_only = [
name
for name, param in inspect.signature(ClientResponse.__init__).parameters.items()
if param.kind is inspect.Parameter.KEYWORD_ONLY
]
class _NullStreamWriter:
# aiohttp 3.14.0 reads stream_writer.output_size in the "request already
# sent" branch (writer is None), so None is not enough -- supply a stub.
output_size = 0
fallback_loop: list[asyncio.AbstractEventLoop] = []
def _resolve_loop() -> asyncio.AbstractEventLoop:
# MockClientResponse is normally built inside aiohttp's running loop, so
# prefer that. In a sync context there is no running loop; avoid
# asyncio.get_event_loop(), which on 3.12+ emits a DeprecationWarning
# (and can RuntimeError) when no current loop is set. Use one cached
# loop instead -- the mock only stores it and calls loop.get_debug().
try:
return asyncio.get_running_loop()
except RuntimeError:
if not fallback_loop:
fallback_loop.append(asyncio.new_event_loop())
return fallback_loop[0]
def _mock_client_response_init(
self: Any, method: str, url: Any, request_info: Any = None
) -> None:
kwargs: dict[str, Any] = dict.fromkeys(keyword_only)
kwargs["request_info"] = request_info
if "loop" in kwargs:
kwargs["loop"] = _resolve_loop()
if "stream_writer" in kwargs:
kwargs["stream_writer"] = _NullStreamWriter()
ClientResponse.__init__(self, method, url, **kwargs)
aiohttp_stubs.MockClientResponse.__init__ = _mock_client_response_init
aiohttp_stubs.MockClientResponse._crewai_aiohttp_patched = True
_patch_vcrpy_aiohttp_compat()
from vcr.request import Request # type: ignore[import-untyped] # noqa: E402
try:
import vcr.stubs.httpx_stubs as httpx_stubs # type: ignore[import-untyped]
except ModuleNotFoundError:
import vcr.stubs.httpcore_stubs as httpx_stubs # type: ignore[import-untyped]
env_test_path = Path(__file__).parent / ".env.test"
load_dotenv(env_test_path, override=False)
load_dotenv(override=False)
BEDROCK_HOST_PLACEHOLDER = "bedrock-runtime.vcr.amazonaws.com"
_BEDROCK_HOST_RE = re.compile(r"^bedrock-runtime\.[a-z0-9-]+\.amazonaws\.com$")
def _normalize_bedrock_host(host: str) -> str:
if _BEDROCK_HOST_RE.match(host):
return BEDROCK_HOST_PLACEHOLDER
return host
def bedrock_host_matcher(r1: Request, r2: Request) -> bool: # type: ignore[no-any-unimported]
"""Match Bedrock requests across AWS regions (CI uses us-east-1, local may use us-west-2)."""
return _normalize_bedrock_host(r1.host or "") == _normalize_bedrock_host(
r2.host or ""
)
def _patched_make_vcr_request(
httpx_request: Any, real_request_body: Any = None, **kwargs: Any
) -> Any:
"""Patched version of VCR's _make_vcr_request that handles binary content.
The original implementation fails on binary request bodies (like file uploads)
because it assumes all content can be decoded as UTF-8.
"""
raw_body = real_request_body if real_request_body is not None else httpx_request.read()
body: Any = raw_body
if isinstance(raw_body, bytes):
try:
body = raw_body.decode("utf-8")
except UnicodeDecodeError:
body = base64.b64encode(raw_body).decode("ascii")
uri = str(httpx_request.url)
headers = dict(httpx_request.headers)
return Request(httpx_request.method, uri, body, headers)
httpx_stubs._make_vcr_request = _patched_make_vcr_request
# Patch the response-side of VCR to fix httpx.ResponseNotRead errors.
# VCR's _from_serialized_response mocks httpx.Response.read(), which prevents
# the response's internal _content attribute from being properly initialized.
# When OpenAI's client (using with_raw_response) accesses response.content,
# httpx raises ResponseNotRead because read() was never actually called.
# This patch ensures _content is explicitly set after response creation.
_original_from_serialized_response = getattr(
httpx_stubs, "_from_serialized_response", None
)
if _original_from_serialized_response is not None:
_from_serialized: Any = _original_from_serialized_response
def _patched_from_serialized_response(
request: Any, serialized_response: Any, history: Any = None
) -> Any:
"""Patched version that ensures response._content is properly set."""
response = _from_serialized(request, serialized_response, history)
# Explicitly set _content to avoid ResponseNotRead errors
# The content was passed to the constructor but the mocked read() prevents
# proper initialization of the internal state
body_content = serialized_response.get("body", {}).get("string", b"")
if isinstance(body_content, str):
body_content = body_content.encode("utf-8")
response._content = body_content
return response
httpx_stubs._from_serialized_response = _patched_from_serialized_response
@pytest.fixture(autouse=True, scope="function")
def cleanup_event_handlers() -> Generator[None, Any, None]:
"""Clean up event bus handlers after each test to prevent test pollution."""
yield
try:
from crewai.events.event_bus import crewai_event_bus
with crewai_event_bus._rwlock.w_locked():
crewai_event_bus._sync_handlers.clear()
crewai_event_bus._async_handlers.clear()
except Exception: # noqa: S110
pass
@pytest.fixture(autouse=True, scope="function")
def reset_event_state() -> None:
"""Reset event system state before each test for isolation."""
from crewai.events.base_events import reset_emission_counter
from crewai.events.event_context import (
EventContextConfig,
_event_context_config,
_event_id_stack,
)
reset_emission_counter()
_event_id_stack.set(())
_event_context_config.set(EventContextConfig())
@pytest.fixture(autouse=True, scope="function")
def setup_test_environment() -> Generator[None, Any, None]:
"""Setup test environment for crewAI workspace."""
with tempfile.TemporaryDirectory() as temp_dir:
storage_dir = Path(temp_dir) / "crewai_test_storage"
storage_dir.mkdir(parents=True, exist_ok=True)
if not storage_dir.exists() or not storage_dir.is_dir():
raise RuntimeError(
f"Failed to create test storage directory: {storage_dir}"
)
try:
test_file = storage_dir / ".permissions_test"
test_file.touch()
test_file.unlink()
except (OSError, IOError) as e:
raise RuntimeError(
f"Test storage directory {storage_dir} is not writable: {e}"
) from e
os.environ["CREWAI_STORAGE_DIR"] = str(storage_dir)
os.environ["CREWAI_TESTING"] = "true"
try:
yield
finally:
os.environ.pop("CREWAI_TESTING", "true")
os.environ.pop("CREWAI_STORAGE_DIR", None)
os.environ.pop("CREWAI_DISABLE_TELEMETRY", "true")
os.environ.pop("OTEL_SDK_DISABLED", "true")
os.environ.pop("OPENAI_BASE_URL", "https://api.openai.com/v1")
os.environ.pop("OPENAI_API_BASE", "https://api.openai.com/v1")
HEADERS_TO_FILTER = {
"authorization": "AUTHORIZATION-XXX",
"content-security-policy": "CSP-FILTERED",
"cookie": "COOKIE-XXX",
"set-cookie": "SET-COOKIE-XXX",
"permissions-policy": "PERMISSIONS-POLICY-XXX",
"referrer-policy": "REFERRER-POLICY-XXX",
"strict-transport-security": "STS-XXX",
"x-content-type-options": "X-CONTENT-TYPE-XXX",
"x-frame-options": "X-FRAME-OPTIONS-XXX",
"x-permitted-cross-domain-policies": "X-PERMITTED-XXX",
"x-request-id": "X-REQUEST-ID-XXX",
"x-runtime": "X-RUNTIME-XXX",
"x-xss-protection": "X-XSS-PROTECTION-XXX",
"x-stainless-arch": "X-STAINLESS-ARCH-XXX",
"x-stainless-os": "X-STAINLESS-OS-XXX",
"x-stainless-read-timeout": "X-STAINLESS-READ-TIMEOUT-XXX",
"cf-ray": "CF-RAY-XXX",
"etag": "ETAG-XXX",
"Strict-Transport-Security": "STS-XXX",
"access-control-expose-headers": "ACCESS-CONTROL-XXX",
"openai-organization": "OPENAI-ORG-XXX",
"openai-project": "OPENAI-PROJECT-XXX",
"x-ratelimit-limit-requests": "X-RATELIMIT-LIMIT-REQUESTS-XXX",
"x-ratelimit-limit-tokens": "X-RATELIMIT-LIMIT-TOKENS-XXX",
"x-ratelimit-remaining-requests": "X-RATELIMIT-REMAINING-REQUESTS-XXX",
"x-ratelimit-remaining-tokens": "X-RATELIMIT-REMAINING-TOKENS-XXX",
"x-ratelimit-reset-requests": "X-RATELIMIT-RESET-REQUESTS-XXX",
"x-ratelimit-reset-tokens": "X-RATELIMIT-RESET-TOKENS-XXX",
"x-goog-api-key": "X-GOOG-API-KEY-XXX",
"api-key": "X-API-KEY-XXX",
"User-Agent": "X-USER-AGENT-XXX",
"apim-request-id:": "X-API-CLIENT-REQUEST-ID-XXX",
"azureml-model-session": "AZUREML-MODEL-SESSION-XXX",
"x-ms-client-request-id": "X-MS-CLIENT-REQUEST-ID-XXX",
"x-ms-region": "X-MS-REGION-XXX",
"apim-request-id": "APIM-REQUEST-ID-XXX",
"x-api-key": "X-API-KEY-XXX",
"anthropic-organization-id": "ANTHROPIC-ORGANIZATION-ID-XXX",
"request-id": "REQUEST-ID-XXX",
"anthropic-ratelimit-input-tokens-limit": "ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX",
"anthropic-ratelimit-input-tokens-remaining": "ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX",
"anthropic-ratelimit-input-tokens-reset": "ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX",
"anthropic-ratelimit-output-tokens-limit": "ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX",
"anthropic-ratelimit-output-tokens-remaining": "ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX",
"anthropic-ratelimit-output-tokens-reset": "ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX",
"anthropic-ratelimit-tokens-limit": "ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX",
"anthropic-ratelimit-tokens-remaining": "ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX",
"anthropic-ratelimit-tokens-reset": "ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX",
"x-amz-date": "X-AMZ-DATE-XXX",
"x-amz-security-token": "X-AMZ-SECURITY-TOKEN-XXX",
"amz-sdk-invocation-id": "AMZ-SDK-INVOCATION-ID-XXX",
"accept-encoding": "ACCEPT-ENCODING-XXX",
"x-amzn-requestid": "X-AMZN-REQUESTID-XXX",
"x-amzn-RequestId": "X-AMZN-REQUESTID-XXX",
"x-a2a-notification-token": "X-A2A-NOTIFICATION-TOKEN-XXX",
"x-a2a-version": "X-A2A-VERSION-XXX",
}
def _filter_request_headers(request: Request) -> Request: # type: ignore[no-any-unimported]
"""Filter sensitive headers from request before recording."""
for header_name, replacement in HEADERS_TO_FILTER.items():
for variant in [header_name, header_name.upper(), header_name.title()]:
if variant in request.headers:
request.headers[variant] = [replacement]
request.method = request.method.upper()
# Normalize Azure OpenAI endpoints to a consistent placeholder for cassette matching.
if request.host and request.host.endswith(".openai.azure.com"):
original_host = request.host
placeholder_host = "fake-azure-endpoint.openai.azure.com"
request.uri = request.uri.replace(original_host, placeholder_host)
# Normalize Bedrock regional endpoints so cassettes work in any AWS region.
if request.host and _BEDROCK_HOST_RE.match(request.host):
request.uri = request.uri.replace(request.host, BEDROCK_HOST_PLACEHOLDER)
return request
def _filter_response_headers(response: dict[str, Any]) -> dict[str, Any] | None:
"""Filter sensitive headers from response before recording.
Returns None to skip recording responses with empty bodies. This handles
duplicate recordings caused by OpenAI's stainless client using
with_raw_response which triggers httpx to re-read the consumed stream.
"""
body = response.get("body", {}).get("string", "")
headers = response.get("headers", {})
content_length = headers.get("content-length", headers.get("Content-Length", []))
if body == "" or body == b"" or content_length == ["0"]:
return None
status_code = response.get("status", {}).get("code")
if isinstance(status_code, int) and status_code >= 400:
# Avoid persisting auth/model errors when re-recording without valid AWS creds.
return None
for encoding_header in ["Content-Encoding", "content-encoding"]:
if encoding_header in headers:
encoding = headers.pop(encoding_header)
if encoding and encoding[0] == "gzip":
body = response.get("body", {}).get("string", b"")
if isinstance(body, bytes) and body.startswith(b"\x1f\x8b"):
response["body"]["string"] = gzip.decompress(body).decode("utf-8")
for header_name, replacement in HEADERS_TO_FILTER.items():
for variant in [header_name, header_name.upper(), header_name.title()]:
if variant in headers:
headers[variant] = [replacement]
return response
@pytest.fixture(scope="module")
def vcr_cassette_dir(request: Any) -> str:
"""Generate cassette directory path based on test module location.
Organizes cassettes to mirror test directory structure within each package:
lib/crewai/tests/llms/google/test_google.py -> lib/crewai/tests/cassettes/llms/google/
lib/crewai-tools/tests/tools/test_search.py -> lib/crewai-tools/tests/cassettes/tools/
"""
test_file = Path(request.fspath)
for parent in test_file.parents:
if (
parent.name
in ("crewai", "crewai-tools", "crewai-files", "cli", "crewai-core")
and parent.parent.name == "lib"
):
package_root = parent
break
else:
package_root = test_file.parent
tests_root = package_root / "tests"
test_dir = test_file.parent
if test_dir != tests_root:
relative_path = test_dir.relative_to(tests_root)
cassette_dir = tests_root / "cassettes" / relative_path
else:
cassette_dir = tests_root / "cassettes"
cassette_dir.mkdir(parents=True, exist_ok=True)
return str(cassette_dir)
def pytest_recording_configure(vcr: Any, config: Any) -> None:
"""Register custom VCR matchers for each test cassette session."""
vcr.register_matcher("bedrock_host", bedrock_host_matcher)
@pytest.fixture(scope="module")
def vcr_config(vcr_cassette_dir: str) -> dict[str, Any]:
"""Configure VCR with organized cassette storage."""
config = {
"cassette_library_dir": vcr_cassette_dir,
"record_mode": os.getenv("PYTEST_VCR_RECORD_MODE", "once"),
"filter_headers": [(k, v) for k, v in HEADERS_TO_FILTER.items()],
"before_record_request": _filter_request_headers,
"before_record_response": _filter_response_headers,
"filter_query_parameters": ["key"],
"match_on": ["method", "scheme", "host", "port", "path"],
}
if os.getenv("GITHUB_ACTIONS") == "true":
config["record_mode"] = "none"
return config

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,8 @@
---
title: "GET /inputs"
description: "الحصول على المدخلات المطلوبة لطاقمك"
openapi: "/enterprise-api.en.yaml GET /inputs"
mode: "wide"
---

View File

@@ -0,0 +1,135 @@
---
title: "مقدمة"
description: "المرجع الكامل لواجهة برمجة تطبيقات CrewAI AMP REST"
icon: "code"
mode: "wide"
---
# واجهة برمجة تطبيقات CrewAI AMP
مرحبًا بك في مرجع واجهة برمجة تطبيقات CrewAI AMP. تتيح لك هذه الواجهة التفاعل برمجيًا مع الأطقم المنشورة، مما يمكّنك من دمجها مع تطبيقاتك وسير عملك وخدماتك.
## البدء السريع
<Steps>
<Step title="الحصول على بيانات اعتماد API">
انتقل إلى صفحة تفاصيل طاقمك في لوحة تحكم CrewAI AMP وانسخ رمز Bearer من علامة تبويب الحالة.
</Step>
<Step title="اكتشاف المدخلات المطلوبة">
استخدم نقطة النهاية `GET /inputs` لمعرفة المعاملات التي يتوقعها طاقمك.
</Step>
<Step title="بدء تنفيذ الطاقم">
استدعِ `POST /kickoff` مع مدخلاتك لبدء تنفيذ الطاقم واستلام
`kickoff_id`.
</Step>
<Step title="مراقبة التقدم">
استخدم `GET /status/{kickoff_id}` للتحقق من حالة التنفيذ واسترجاع النتائج.
</Step>
</Steps>
## المصادقة
تتطلب جميع طلبات API المصادقة باستخدام رمز Bearer. أدرج رمزك في ترويسة `Authorization`:
```bash
curl -H "Authorization: Bearer YOUR_CREW_TOKEN" \
https://your-crew-url.crewai.com/inputs
```
### أنواع الرموز
| نوع الرمز | النطاق | حالة الاستخدام |
| :-------------------- | :------------------------ | :----------------------------------------------------------- |
| **Bearer Token** | وصول على مستوى المؤسسة | عمليات الطاقم الكاملة، مثالي للتكامل بين الخوادم |
| **User Bearer Token** | وصول محدد بالمستخدم | صلاحيات محدودة، مناسب للعمليات الخاصة بالمستخدم |
<Tip>
يمكنك العثور على كلا نوعي الرموز في علامة تبويب الحالة من صفحة تفاصيل طاقمك في
لوحة تحكم CrewAI AMP.
</Tip>
## عنوان URL الأساسي
لكل طاقم منشور نقطة نهاية API فريدة خاصة به:
```
https://your-crew-name.crewai.com
```
استبدل `your-crew-name` بعنوان URL الفعلي لطاقمك من لوحة التحكم.
## سير العمل النموذجي
1. **الاكتشاف**: استدعِ `GET /inputs` لفهم ما يحتاجه طاقمك
2. **التنفيذ**: أرسل المدخلات عبر `POST /kickoff` لبدء المعالجة
3. **المراقبة**: استعلم عن `GET /status/{kickoff_id}` حتى الاكتمال
4. **النتائج**: استخرج المخرجات النهائية من الاستجابة المكتملة
## معالجة الأخطاء
تستخدم الواجهة أكواد حالة HTTP القياسية:
| الكود | المعنى |
| ----- | :----------------------------------------- |
| `200` | نجاح |
| `400` | طلب غير صالح - تنسيق مدخلات غير صحيح |
| `401` | غير مصرّح - رمز bearer غير صالح |
| `404` | غير موجود - المورد غير موجود |
| `422` | خطأ في التحقق - مدخلات مطلوبة مفقودة |
| `500` | خطأ في الخادم - تواصل مع الدعم |
## الاختبار التفاعلي
<Info>
**لماذا لا يوجد زر "إرسال"؟** نظرًا لأن كل مستخدم CrewAI AMP لديه عنوان URL
فريد للطاقم، نستخدم **وضع المرجع** بدلاً من بيئة تفاعلية لتجنب
الالتباس. يوضح لك هذا بالضبط كيف يجب أن تبدو الطلبات بدون
أزرار إرسال غير فعالة.
</Info>
تعرض لك كل صفحة نقطة نهاية:
- **تنسيق الطلب الدقيق** مع جميع المعاملات
- **أمثلة الاستجابة** لحالات النجاح والخطأ
- **عينات الكود** بلغات متعددة (cURL، Python، JavaScript، إلخ)
- **أمثلة المصادقة** بتنسيق رمز Bearer الصحيح
### **لاختبار واجهتك الفعلية:**
<CardGroup cols={2}>
<Card title="نسخ أمثلة cURL" icon="terminal">
انسخ أمثلة cURL واستبدل العنوان URL + الرمز بقيمك الحقيقية
</Card>
<Card title="استخدام Postman/Insomnia" icon="play">
استورد الأمثلة في أداة اختبار API المفضلة لديك
</Card>
</CardGroup>
**مثال على سير العمل:**
1. **انسخ مثال cURL هذا** من أي صفحة نقطة نهاية
2. **استبدل `your-actual-crew-name.crewai.com`** بعنوان URL الحقيقي لطاقمك
3. **استبدل رمز Bearer** برمزك الحقيقي من لوحة التحكم
4. **نفّذ الطلب** في طرفيتك أو عميل API
## هل تحتاج مساعدة؟
<CardGroup cols={2}>
<Card
title="دعم المؤسسات"
icon="headset"
href="mailto:support@crewai.com"
>
احصل على مساعدة في تكامل API واستكشاف الأخطاء وإصلاحها
</Card>
<Card
title="لوحة تحكم المؤسسات"
icon="chart-line"
href="https://app.crewai.com"
>
إدارة أطقمك وعرض سجلات التنفيذ
</Card>
</CardGroup>

View File

@@ -0,0 +1,8 @@
---
title: "POST /kickoff"
description: "بدء تنفيذ الطاقم"
openapi: "/enterprise-api.en.yaml POST /kickoff"
mode: "wide"
---

View File

@@ -0,0 +1,6 @@
---
title: "POST /resume"
description: "استئناف تنفيذ الطاقم مع التغذية الراجعة البشرية"
openapi: "/enterprise-api.en.yaml POST /resume"
mode: "wide"
---

View File

@@ -0,0 +1,6 @@
---
title: "GET /status/{kickoff_id}"
description: "الحصول على حالة التنفيذ"
openapi: "/enterprise-api.en.yaml GET /status/{kickoff_id}"
mode: "wide"
---

2305
docs/edge/ar/changelog.mdx Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,147 @@
---
title: "قدرات الوكيل"
description: "فهم الطرق الخمس لتوسيع وكلاء CrewAI: الأدوات، MCP، التطبيقات، المهارات، والمعرفة."
icon: puzzle-piece
mode: "wide"
---
## نظرة عامة
يمكن توسيع وكلاء CrewAI بـ **خمسة أنواع مميزة من القدرات**، كل منها يخدم غرضًا مختلفًا. فهم متى تستخدم كل نوع — وكيف يعملون معًا — هو المفتاح لبناء وكلاء فعّالين.
<CardGroup cols={2}>
<Card title="الأدوات" icon="wrench" href="/ar/concepts/tools" color="#3B82F6">
**دوال قابلة للاستدعاء** — تمنح الوكلاء القدرة على اتخاذ إجراءات. البحث على الويب، عمليات الملفات، استدعاءات API، تنفيذ الكود.
</Card>
<Card title="خوادم MCP" icon="plug" href="/ar/mcp/overview" color="#8B5CF6">
**خوادم أدوات عن بُعد** — تربط الوكلاء بخوادم أدوات خارجية عبر Model Context Protocol. نفس تأثير الأدوات، لكن مستضافة خارجيًا.
</Card>
<Card title="التطبيقات" icon="grid-2" color="#EC4899">
**تكاملات المنصة** — تربط الوكلاء بتطبيقات SaaS (Gmail، Slack، Jira، Salesforce) عبر منصة CrewAI. تعمل محليًا مع رمز تكامل المنصة.
</Card>
<Card title="المهارات" icon="bolt" href="/ar/concepts/skills" color="#F59E0B">
**خبرة المجال** — تحقن التعليمات والإرشادات والمواد المرجعية في إرشادات الوكلاء. المهارات تخبر الوكلاء *كيف يفكرون*.
</Card>
<Card title="المعرفة" icon="book" href="/ar/concepts/knowledge" color="#10B981">
**حقائق مُسترجعة** — توفر للوكلاء بيانات من المستندات والملفات وعناوين URL عبر البحث الدلالي (RAG). المعرفة تعطي الوكلاء *ما يحتاجون معرفته*.
</Card>
</CardGroup>
---
## التمييز الأساسي
أهم شيء يجب فهمه: **هذه القدرات تنقسم إلى فئتين**.
### قدرات الإجراء (الأدوات، MCP، التطبيقات)
تمنح الوكلاء القدرة على **فعل أشياء** — استدعاء APIs، قراءة الملفات، البحث على الويب، إرسال رسائل البريد الإلكتروني. عند التنفيذ، تتحول الأنواع الثلاثة إلى نفس التنسيق الداخلي (مثيلات `BaseTool`) وتظهر في قائمة أدوات موحدة يمكن للوكيل استدعاؤها.
```python
from crewai import Agent
from crewai_tools import SerperDevTool, FileReadTool
agent = Agent(
role="Researcher",
goal="Find and compile market data",
backstory="Expert market analyst",
tools=[SerperDevTool(), FileReadTool()], # أدوات محلية
mcps=["https://mcp.example.com/sse"], # أدوات خادم MCP عن بُعد
apps=["gmail", "google_sheets"], # تكاملات المنصة
)
```
### قدرات السياق (المهارات، المعرفة)
تُعدّل **إرشادات** الوكيل — بحقن الخبرة أو التعليمات أو البيانات المُسترجعة قبل أن يبدأ الوكيل في التفكير. لا تمنح الوكلاء إجراءات جديدة؛ بل تُشكّل كيف يفكر الوكلاء وما هي المعلومات التي يمكنهم الوصول إليها.
```python
from crewai import Agent
agent = Agent(
role="Security Auditor",
goal="Audit cloud infrastructure for vulnerabilities",
backstory="Expert in cloud security with 10 years of experience",
skills=["./skills/security-audit"], # تعليمات المجال
knowledge_sources=[pdf_source, url_source], # حقائق مُسترجعة
)
```
---
## متى تستخدم ماذا
| تحتاج إلى... | استخدم | مثال |
| :------------------------------------------------------- | :---------------- | :--------------------------------------- |
| الوكيل يبحث على الويب | **الأدوات** | `tools=[SerperDevTool()]` |
| الوكيل يستدعي API عن بُعد عبر MCP | **MCP** | `mcps=["https://api.example.com/sse"]` |
| الوكيل يرسل بريد إلكتروني عبر Gmail | **التطبيقات** | `apps=["gmail"]` |
| الوكيل يتبع إجراءات محددة | **المهارات** | `skills=["./skills/code-review"]` |
| الوكيل يرجع لمستندات الشركة | **المعرفة** | `knowledge_sources=[pdf_source]` |
| الوكيل يبحث على الويب ويتبع إرشادات المراجعة | **الأدوات + المهارات** | استخدم كليهما معًا |
---
## دمج القدرات
في الممارسة العملية، غالبًا ما يستخدم الوكلاء **أنواعًا متعددة من القدرات معًا**. إليك مثال واقعي:
```python
from crewai import Agent
from crewai_tools import SerperDevTool, FileReadTool, CodeInterpreterTool
# وكيل بحث مجهز بالكامل
researcher = Agent(
role="Senior Research Analyst",
goal="Produce comprehensive market analysis reports",
backstory="Expert analyst with deep industry knowledge",
# الإجراء: ما يمكن للوكيل فعله
tools=[
SerperDevTool(), # البحث على الويب
FileReadTool(), # قراءة الملفات المحلية
CodeInterpreterTool(), # تشغيل كود Python للتحليل
],
mcps=["https://data-api.example.com/sse"], # الوصول لـ API بيانات عن بُعد
apps=["google_sheets"], # الكتابة في Google Sheets
# السياق: ما يعرفه الوكيل
skills=["./skills/research-methodology"], # كيفية إجراء البحث
knowledge_sources=[company_docs], # بيانات خاصة بالشركة
)
```
---
## جدول المقارنة
| الميزة | الأدوات | MCP | التطبيقات | المهارات | المعرفة |
| :--- | :---: | :---: | :---: | :---: | :---: |
| **يمنح الوكيل إجراءات** | ✅ | ✅ | ✅ | ❌ | ❌ |
| **يُعدّل الإرشادات** | ❌ | ❌ | ❌ | ✅ | ✅ |
| **يتطلب كود** | نعم | إعداد فقط | إعداد فقط | Markdown فقط | إعداد فقط |
| **يعمل محليًا** | نعم | يعتمد | نعم (مع متغير بيئة) | غير متاح | نعم |
| **يحتاج مفاتيح API** | لكل أداة | لكل خادم | رمز التكامل | لا | المُضمّن فقط |
| **يُعيَّن على Agent** | `tools=[]` | `mcps=[]` | `apps=[]` | `skills=[]` | `knowledge_sources=[]` |
| **يُعيَّن على Crew** | ❌ | ❌ | ❌ | `skills=[]` | `knowledge_sources=[]` |
---
## تعمّق أكثر
هل أنت مستعد لمعرفة المزيد عن كل نوع من أنواع القدرات؟
<CardGroup cols={2}>
<Card title="الأدوات" icon="wrench" href="/ar/concepts/tools">
إنشاء أدوات مخصصة، استخدام كتالوج OSS مع أكثر من 75 خيارًا، تكوين التخزين المؤقت والتنفيذ غير المتزامن.
</Card>
<Card title="تكامل MCP" icon="plug" href="/ar/mcp/overview">
الاتصال بخوادم MCP عبر stdio أو SSE أو HTTP. تصفية الأدوات، تكوين المصادقة.
</Card>
<Card title="المهارات" icon="bolt" href="/ar/concepts/skills">
بناء حزم المهارات مع SKILL.md، حقن خبرة المجال، استخدام الكشف التدريجي.
</Card>
<Card title="المعرفة" icon="book" href="/ar/concepts/knowledge">
إضافة المعرفة من ملفات PDF وCSV وعناوين URL والمزيد. تكوين المُضمّنات والاسترجاع.
</Card>
</CardGroup>

View File

@@ -0,0 +1,383 @@
---
title: الوكلاء
description: دليل تفصيلي حول إنشاء وإدارة الوكلاء ضمن إطار عمل CrewAI.
icon: robot
mode: "wide"
---
## نظرة عامة على الوكيل
في إطار عمل CrewAI، الـ `Agent` هو وحدة مستقلة يمكنها:
- أداء مهام محددة
- اتخاذ قرارات بناءً على دوره وهدفه
- استخدام الأدوات لتحقيق الأهداف
- التواصل والتعاون مع وكلاء آخرين
- الاحتفاظ بذاكرة التفاعلات
- تفويض المهام عند السماح بذلك
<Tip>
فكّر في الوكيل كعضو فريق متخصص بمهارات وخبرات ومسؤوليات محددة.
على سبيل المثال، قد يتفوق وكيل `Researcher` في جمع وتحليل المعلومات،
بينما قد يكون وكيل `Writer` أفضل في إنشاء المحتوى.
</Tip>
<Note type="info" title="تحسين المؤسسات: منشئ الوكلاء المرئي">
يتضمن CrewAI AMP منشئ وكلاء مرئي يبسّط إنشاء وتهيئة الوكلاء بدون كتابة كود. صمم وكلاءك بصريًا واختبرهم في الوقت الفعلي.
![Visual Agent Builder Screenshot](/images/enterprise/crew-studio-interface.png)
يُمكّن منشئ الوكلاء المرئي من:
- تهيئة وكلاء بديهية بواجهات نماذج
- اختبار والتحقق في الوقت الفعلي
- مكتبة قوالب مع أنواع وكلاء مهيأة مسبقًا
- تخصيص سهل لخصائص وسلوكيات الوكيل
</Note>
## خصائص الوكيل
| الخاصية | المعامل | النوع | الوصف |
| :-------------------------------------- | :----------------------- | :------------------------------------ | :------------------------------------------------------------------------------------------------------- |
| **الدور** | `role` | `str` | يحدد وظيفة الوكيل وخبرته ضمن الطاقم. |
| **الهدف** | `goal` | `str` | الهدف الفردي الذي يوجه عملية اتخاذ القرار لدى الوكيل. |
| **الخلفية** | `backstory` | `str` | يوفر سياقًا وشخصية للوكيل، مما يثري التفاعلات. |
| **LLM** _(اختياري)_ | `llm` | `Union[str, LLM, Any]` | نموذج اللغة الذي يشغّل الوكيل. افتراضيًا النموذج المحدد في `OPENAI_MODEL_NAME` أو "gpt-4". |
| **الأدوات** _(اختياري)_ | `tools` | `List[BaseTool]` | القدرات أو الوظائف المتاحة للوكيل. افتراضيًا قائمة فارغة. |
| **LLM استدعاء الدوال** _(اختياري)_ | `function_calling_llm` | `Optional[Any]` | نموذج لغة لاستدعاء الأدوات، يتجاوز LLM الطاقم إذا حُدد. |
| **الحد الأقصى للتكرارات** _(اختياري)_ | `max_iter` | `int` | الحد الأقصى للتكرارات قبل أن يقدم الوكيل أفضل إجابته. الافتراضي 20. |
| **الحد الأقصى لـ RPM** _(اختياري)_ | `max_rpm` | `Optional[int]` | الحد الأقصى للطلبات في الدقيقة لتجنب حدود المعدل. |
| **الحد الأقصى لوقت التنفيذ** _(اختياري)_ | `max_execution_time` | `Optional[int]` | الحد الأقصى للوقت (بالثواني) لتنفيذ المهمة. |
| **الوضع المفصل** _(اختياري)_ | `verbose` | `bool` | تفعيل سجلات التنفيذ المفصلة للتصحيح. الافتراضي False. |
| **السماح بالتفويض** _(اختياري)_ | `allow_delegation` | `bool` | السماح للوكيل بتفويض المهام لوكلاء آخرين. الافتراضي False. |
| **دالة الخطوة** _(اختياري)_ | `step_callback` | `Optional[Any]` | دالة تُستدعى بعد كل خطوة للوكيل، تتجاوز دالة الطاقم. |
| **التخزين المؤقت** _(اختياري)_ | `cache` | `bool` | تفعيل التخزين المؤقت لاستخدام الأدوات. الافتراضي True. |
| **قالب النظام** _(اختياري)_ | `system_template` | `Optional[str]` | قالب أمر نظام مخصص للوكيل. |
| **قالب الأمر** _(اختياري)_ | `prompt_template` | `Optional[str]` | قالب أمر مخصص للوكيل. |
| **قالب الاستجابة** _(اختياري)_ | `response_template` | `Optional[str]` | قالب استجابة مخصص للوكيل. |
| **السماح بتنفيذ الكود** _(اختياري)_ | `allow_code_execution` | `Optional[bool]` | تفعيل تنفيذ الكود للوكيل. الافتراضي False. |
| **الحد الأقصى لإعادة المحاولة** _(اختياري)_ | `max_retry_limit` | `int` | الحد الأقصى لإعادات المحاولة عند حدوث خطأ. الافتراضي 2. |
| **احترام نافذة السياق** _(اختياري)_ | `respect_context_window` | `bool` | إبقاء الرسائل تحت حجم نافذة السياق عبر التلخيص. الافتراضي True. |
| **وضع تنفيذ الكود** _(اختياري)_ | `code_execution_mode` | `Literal["safe", "unsafe"]` | وضع تنفيذ الكود: 'safe' (باستخدام Docker) أو 'unsafe' (مباشر). الافتراضي 'safe'. |
| **متعدد الوسائط** _(اختياري)_ | `multimodal` | `bool` | ما إذا كان الوكيل يدعم القدرات متعددة الوسائط. الافتراضي False. |
| **حقن التاريخ** _(اختياري)_ | `inject_date` | `bool` | ما إذا كان يتم حقن التاريخ الحالي تلقائيًا في المهام. الافتراضي False. |
| **تنسيق التاريخ** _(اختياري)_ | `date_format` | `str` | سلسلة تنسيق التاريخ عند تفعيل inject_date. الافتراضي "%Y-%m-%d" (تنسيق ISO). |
| **الاستدلال** _(اختياري)_ | `reasoning` | `bool` | ما إذا كان يجب على الوكيل التأمل وإنشاء خطة قبل تنفيذ المهمة. الافتراضي False. |
| **الحد الأقصى لمحاولات الاستدلال** _(اختياري)_ | `max_reasoning_attempts` | `Optional[int]` | الحد الأقصى لمحاولات الاستدلال قبل تنفيذ المهمة. إذا None، سيحاول حتى الاستعداد. |
| **المُضمّن** _(اختياري)_ | `embedder` | `Optional[Dict[str, Any]]` | تهيئة المُضمّن المستخدم من قبل الوكيل. |
| **مصادر المعرفة** _(اختياري)_ | `knowledge_sources` | `Optional[List[BaseKnowledgeSource]]` | مصادر المعرفة المتاحة للوكيل. |
| **استخدام أمر النظام** _(اختياري)_ | `use_system_prompt` | `Optional[bool]` | ما إذا كان يُستخدم أمر النظام (لدعم نموذج o1). الافتراضي True. |
## إنشاء الوكلاء
هناك طريقتان شائعتان لإنشاء الوكلاء في CrewAI: باستخدام **تهيئة JSONC (الموصى بها للـ crews الجديدة)** أو تعريفهم **مباشرة في الكود**.
### تهيئة JSONC (موصى بها)
المشاريع الجديدة التي تُنشأ عبر `crewai create crew <name>` تستخدم تهيئة JSON-first. يُعرّف كل Agent في `agents/<agent_name>.jsonc`، ويحدد `crew.jsonc` أي Agents تدخل في الـ crew.
```jsonc agents/researcher.jsonc
{
"role": "{topic} Senior Data Researcher",
"goal": "Uncover cutting-edge developments in {topic}",
"backstory": "You find the most relevant information and present it clearly.",
"llm": "openai/gpt-4o",
"tools": ["SerperDevTool"],
"settings": {
"verbose": true,
"allow_delegation": false
}
}
```
استخدم `{placeholder}` داخل `role` أو `goal` أو `backstory`. ضع القيم الافتراضية في `inputs` داخل `crew.jsonc`؛ وسيطلب `crewai run` أي قيم ناقصة. يمكن وضع حقول السلوك مثل `verbose` و `allow_delegation` و `max_iter` و `memory` و `cache` و `planning_config` في المستوى الأعلى أو داخل `settings`.
<Note>
يدعم JSONC التعليقات والفواصل النهائية. إذا وُجد `agents/<name>.jsonc` و `agents/<name>.json` معًا، يستخدم CrewAI ملف JSONC.
</Note>
### تهيئة YAML الكلاسيكية
المشاريع الكلاسيكية التي تُنشأ عبر `crewai create crew <name> --classic` تستخدم `config/agents.yaml` وفئة `@CrewBase` في `crew.py`.
تظل تهيئة YAML مدعومة للمشاريع الحالية المبنية بـ Python/YAML وللفِرق التي تفضل تعريف الوكلاء من خلال فئة `@CrewBase`.
بعد إنشاء مشروع كلاسيكي، انتقل إلى ملف `src/<project_name>/config/agents.yaml` وعدّل القالب ليتوافق مع متطلباتك.
<Note>
ستُستبدل المتغيرات في ملفات YAML (مثل `{topic}`) بقيم من مدخلاتك عند تشغيل الطاقم:
```python Code
crew.kickoff(inputs={'topic': 'AI Agents'})
```
</Note>
إليك مثالًا على كيفية تهيئة الوكلاء باستخدام YAML:
```yaml agents.yaml
# src/<project_name>/config/agents.yaml
researcher:
role: >
{topic} Senior Data Researcher
goal: >
Uncover cutting-edge developments in {topic}
backstory: >
You're a seasoned researcher with a knack for uncovering the latest
developments in {topic}. Known for your ability to find the most relevant
information and present it in a clear and concise manner.
reporting_analyst:
role: >
{topic} Reporting Analyst
goal: >
Create detailed reports based on {topic} data analysis and research findings
backstory: >
You're a meticulous analyst with a keen eye for detail. You're known for
your ability to turn complex data into clear and concise reports, making
it easy for others to understand and act on the information you provide.
```
لاستخدام تهيئة YAML في الكود، أنشئ فئة طاقم ترث من `CrewBase`:
```python Code
# src/<project_name>/crew.py
from crewai import Agent, Crew, Process
from crewai.project import CrewBase, agent, crew
from crewai_tools import SerperDevTool
@CrewBase
class LatestAiDevelopmentCrew():
"""LatestAiDevelopment crew"""
agents_config = "config/agents.yaml"
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config['researcher'], # type: ignore[index]
verbose=True,
tools=[SerperDevTool()]
)
@agent
def reporting_analyst(self) -> Agent:
return Agent(
config=self.agents_config['reporting_analyst'], # type: ignore[index]
verbose=True
)
```
<Note>
يجب أن تتطابق الأسماء المستخدمة في ملفات YAML (`agents.yaml`) مع أسماء
الطرق في كود Python.
</Note>
### تعريف مباشر في الكود
يمكنك إنشاء الوكلاء مباشرة في الكود بإنشاء فئة `Agent`. إليك مثالًا شاملًا يوضح جميع المعاملات المتاحة:
```python Code
from crewai import Agent
from crewai_tools import SerperDevTool
# إنشاء وكيل بجميع المعاملات المتاحة
agent = Agent(
role="Senior Data Scientist",
goal="Analyze and interpret complex datasets to provide actionable insights",
backstory="With over 10 years of experience in data science and machine learning, "
"you excel at finding patterns in complex datasets.",
llm="gpt-4",
function_calling_llm=None,
verbose=False,
allow_delegation=False,
max_iter=20,
max_rpm=None,
max_execution_time=None,
max_retry_limit=2,
allow_code_execution=False,
code_execution_mode="safe",
respect_context_window=True,
use_system_prompt=True,
multimodal=False,
inject_date=False,
date_format="%Y-%m-%d",
reasoning=False,
max_reasoning_attempts=None,
tools=[SerperDevTool()],
knowledge_sources=None,
embedder=None,
system_template=None,
prompt_template=None,
response_template=None,
step_callback=None,
)
```
دعنا نستعرض بعض تركيبات المعاملات الرئيسية لحالات الاستخدام الشائعة:
#### وكيل بحث أساسي
```python Code
research_agent = Agent(
role="Research Analyst",
goal="Find and summarize information about specific topics",
backstory="You are an experienced researcher with attention to detail",
tools=[SerperDevTool()],
verbose=True
)
```
#### وكيل تطوير الكود
```python Code
dev_agent = Agent(
role="Senior Python Developer",
goal="Write and debug Python code",
backstory="Expert Python developer with 10 years of experience",
allow_code_execution=True,
code_execution_mode="safe",
max_execution_time=300,
max_retry_limit=3
)
```
#### وكيل تحليل طويل المدى
```python Code
analysis_agent = Agent(
role="Data Analyst",
goal="Perform deep analysis of large datasets",
backstory="Specialized in big data analysis and pattern recognition",
memory=True,
respect_context_window=True,
max_rpm=10,
function_calling_llm="gpt-4o-mini"
)
```
### تفاصيل المعاملات
#### المعاملات الحرجة
- `role` و `goal` و `backstory` مطلوبة وتشكّل سلوك الوكيل
- `llm` يحدد نموذج اللغة المستخدم (افتراضي: GPT-4 من OpenAI)
#### الذاكرة والسياق
- `memory`: تفعيل للحفاظ على سجل المحادثة
- `respect_context_window`: يمنع مشاكل حد الرموز
- `knowledge_sources`: إضافة قواعد معرفة خاصة بالمجال
#### التحكم في التنفيذ
- `max_iter`: الحد الأقصى للمحاولات قبل تقديم أفضل إجابة
- `max_execution_time`: المهلة بالثواني
- `max_rpm`: تحديد معدل استدعاءات API
- `max_retry_limit`: إعادات المحاولة عند الخطأ
#### تنفيذ الكود
<Warning>
`allow_code_execution` و`code_execution_mode` مهجوران. تمت إزالة `CodeInterpreterTool` من `crewai-tools`. استخدم خدمة بيئة معزولة مخصصة مثل [E2B](https://e2b.dev) أو [Modal](https://modal.com) لتنفيذ الكود بأمان.
</Warning>
- `allow_code_execution` _(مهجور)_: كان يُمكّن تنفيذ الكود المدمج عبر `CodeInterpreterTool`.
- `code_execution_mode` _(مهجور)_: كان يتحكم في وضع التنفيذ (`"safe"` لـ Docker، `"unsafe"` للتنفيذ المباشر).
#### الميزات المتقدمة
- `multimodal`: تفعيل القدرات متعددة الوسائط لمعالجة النص والمحتوى المرئي
- `reasoning`: تمكين الوكيل من التأمل وإنشاء خطط قبل تنفيذ المهام
- `inject_date`: حقن التاريخ الحالي تلقائيًا في أوصاف المهام
#### القوالب
- `system_template`: يحدد السلوك الأساسي للوكيل
- `prompt_template`: ينظم تنسيق الإدخال
- `response_template`: ينسّق استجابات الوكيل
<Note>
عند استخدام القوالب المخصصة، تأكد من تعريف كل من `system_template` و
`prompt_template`. `response_template` اختياري لكن يُوصى به
لتنسيق مخرجات متسق.
</Note>
## أدوات الوكيل
يمكن تجهيز الوكلاء بأدوات متنوعة لتعزيز قدراتهم. يدعم CrewAI أدوات من:
- [مجموعة أدوات CrewAI](https://github.com/joaomdmoura/crewai-tools)
- [أدوات LangChain](https://python.langchain.com/docs/integrations/tools)
إليك كيفية إضافة أدوات لوكيل:
```python Code
from crewai import Agent
from crewai_tools import SerperDevTool, WikipediaTools
# إنشاء الأدوات
search_tool = SerperDevTool()
wiki_tool = WikipediaTools()
# إضافة أدوات للوكيل
researcher = Agent(
role="AI Technology Researcher",
goal="Research the latest AI developments",
tools=[search_tool, wiki_tool],
verbose=True
)
```
## التفاعل المباشر مع الوكيل عبر `kickoff()`
يمكن استخدام الوكلاء مباشرة بدون المرور بمهمة أو سير عمل طاقم باستخدام طريقة `kickoff()`. يوفر هذا طريقة أبسط للتفاعل مع وكيل عندما لا تحتاج إلى إمكانيات تنسيق الطاقم الكاملة.
```python Code
from crewai import Agent
from crewai_tools import SerperDevTool
# إنشاء وكيل
researcher = Agent(
role="AI Technology Researcher",
goal="Research the latest AI developments",
tools=[SerperDevTool()],
verbose=True
)
# استخدام kickoff() للتفاعل مباشرة مع الوكيل
result = researcher.kickoff("What are the latest developments in language models?")
# الوصول إلى الاستجابة الخام
print(result.raw)
```
## اعتبارات مهمة وأفضل الممارسات
### الأمان وتنفيذ الكود
<Warning>
`allow_code_execution` و`code_execution_mode` مهجوران وتمت إزالة `CodeInterpreterTool`. استخدم خدمة بيئة معزولة مخصصة مثل [E2B](https://e2b.dev) أو [Modal](https://modal.com) لتنفيذ الكود بأمان.
</Warning>
### تحسين الأداء
- استخدم `respect_context_window: true` لمنع مشاكل حد الرموز
- عيّن `max_rpm` مناسبًا لتجنب تحديد المعدل
- فعّل `cache: true` لتحسين الأداء للمهام المتكررة
- اضبط `max_iter` و `max_retry_limit` بناءً على تعقيد المهمة
### إدارة الذاكرة والسياق
- استفد من `knowledge_sources` للمعلومات الخاصة بالمجال
- هيّئ `embedder` عند استخدام نماذج تضمين مخصصة
- استخدم القوالب المخصصة للتحكم الدقيق في سلوك الوكيل
### التعاون بين الوكلاء
- فعّل `allow_delegation: true` عندما يحتاج الوكلاء للعمل معًا
- استخدم `step_callback` لمراقبة وتسجيل تفاعلات الوكلاء
- فكّر في استخدام نماذج LLM مختلفة لأغراض مختلفة
### توافق النموذج
- عيّن `use_system_prompt: false` للنماذج القديمة التي لا تدعم رسائل النظام
- تأكد من أن `llm` المختار يدعم الميزات التي تحتاجها

View File

@@ -0,0 +1,423 @@
---
title: Checkpointing
description: حفظ حالة التنفيذ تلقائيا حتى تتمكن الطواقم والتدفقات والوكلاء من الاستئناف بعد الفشل.
icon: floppy-disk
mode: "wide"
---
الـ Checkpointing يحفظ لقطة من حالة التنفيذ أثناء التشغيل بحيث يمكن لطاقم أو تدفق أو وكيل الاستئناف بعد الفشل أو التفرع إلى فرع بديل.
<CardGroup cols={2}>
<Card title="الشرح" icon="lightbulb" href="#الشرح">
كيف يعمل الـ Checkpointing: الأحداث والتخزين والوراثة.
</Card>
<Card title="درس تطبيقي" icon="graduation-cap" href="#درس-تطبيقي-استئناف-طاقم-فاشل">
دليل 5 دقائق: تشغيل، إيقاف، استئناف.
</Card>
<Card title="ادلة عملية" icon="screwdriver-wrench" href="#ادلة-عملية">
وصفات مركزة على المهام لسير العمل الشائع.
</Card>
<Card title="المرجع" icon="book" href="#المرجع">
`CheckpointConfig` والأحداث والمزودات وسطر الأوامر.
</Card>
</CardGroup>
## الشرح
### ما هي نقطة الحفظ
تلتقط نقطة الحفظ كل ما يحتاجه CrewAI لإعادة إنشاء تشغيل أثناء سيره: الحالة الكاملة للطاقم أو التدفق أو الوكيل — التكوين، وذاكرة الوكلاء ومصادر المعرفة، وتقدم المهام، والمخرجات الوسيطة، والحالة الداخلية والسمات — إلى جانب مدخلات الـ kickoff، وسجل الأحداث حتى تلك النقطة، ومعرف نسب يربط نقطة الحفظ بالتشغيل الذي جاءت منه.
الاستعادة تعيد بناء تلك الحالة وتستمر. تتخطى المهام المكتملة، وتعاد ترطيب الذاكرة والمعرفة، ويعمل العمل التابع على نفس المخرجات التي أنتجها التشغيل الأصلي. التفرع يجري نفس الاستعادة تحت نسب جديد، بحيث يكتب الفرع الجديد والتشغيل الأصلي نقاط الحفظ جنبا إلى جنب دون أن يطمس أحدهما الآخر.
### متى تكتب نقاط الحفظ
الـ Checkpointing مدفوع بالأحداث. يشترك وقت التشغيل في الأحداث التي تحددها عبر `on_events` ويكتب نقطة حفظ عند إطلاق أحدها. الافتراضي `task_completed` ينتج نقطة حفظ لكل مهمة منتهية — توازن معقول بين الدقة واستخدام القرص. الأحداث عالية التردد مثل `llm_call_completed` متاحة للاستعادة الدقيقة لكنها تكتب ملفات أكثر بكثير.
### التخزين
يتضمن CrewAI مزودين:
- `JsonProvider` يكتب ملفا لكل نقطة حفظ. قابل للقراءة وسهل التفقد.
- `SqliteProvider` يكتب إلى قاعدة بيانات SQLite واحدة. أفضل لنقاط الحفظ عالية التردد.
كلاهما يحذف أقدم نقاط الحفظ عند تحديد `max_checkpoints`.
<Note>
كتابة نقاط الحفظ بأفضل جهد. فشل نقطة حفظ يسجل لكنه لا يقاطع التشغيل.
</Note>
### نموذج الوراثة
`Crew` و`Flow` و`Agent` كلها تقبل وسيط `checkpoint`. يرث الأبناء من الأب ما لم يحددوا قيمتهم الخاصة أو يمرروا `False` للانسحاب. فعل الـ Checkpointing مرة واحدة على الطاقم وتشارك كل الوكلاء، أو استبعد وكيلا واحدا بشكل انتقائي.
## درس تطبيقي: استئناف طاقم فاشل
هذا الدليل يستغرق حوالي 5 دقائق. ستشغل طاقما بمهمتين، توقفه في المنتصف، ثم تستأنف من نقطة الحفظ المحفوظة.
<Steps>
<Step title="أنشئ الطاقم مع تفعيل الـ Checkpointing">
```python
from crewai import Agent, Crew, Task
researcher = Agent(role="Researcher", goal="Research", backstory="Expert")
writer = Agent(role="Writer", goal="Write", backstory="Expert")
crew = Crew(
agents=[researcher, writer],
tasks=[
Task(description="Research AI trends", agent=researcher, expected_output="bullets"),
Task(description="Write a summary", agent=writer, expected_output="paragraph"),
],
checkpoint=True,
)
```
</Step>
<Step title="شغله وأوقفه بعد المهمة الأولى">
```python
result = crew.kickoff()
```
اضغط `Ctrl+C` بعد انتهاء المهمة الأولى. في `./.checkpoints/`، الملف بصيغة `<timestamp>_<uuid>.json` هو نقطة الحفظ.
</Step>
<Step title="استأنف من نقطة الحفظ">
```python
from crewai import CheckpointConfig
result = crew.kickoff(
from_checkpoint=CheckpointConfig(
restore_from="./.checkpoints/<timestamp>_<uuid>.json",
),
)
```
يتم تخطي مهمة البحث، ويعمل الكاتب على مخرجات البحث المحفوظة، وينتهي الطاقم.
</Step>
</Steps>
## ادلة عملية
<AccordionGroup>
<Accordion title="تفعيل الـ Checkpointing بالإعدادات الافتراضية" icon="play">
```python
crew = Crew(agents=[...], tasks=[...], checkpoint=True)
```
يكتب إلى `./.checkpoints/` عند كل `task_completed`.
</Accordion>
<Accordion title="تخصيص التخزين والتردد" icon="sliders">
```python
from crewai import Crew, CheckpointConfig
crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
location="./my_checkpoints",
on_events=["task_completed", "crew_kickoff_completed"],
max_checkpoints=5,
),
)
```
</Accordion>
<Accordion title="اختيار مزود التخزين" icon="database">
<CodeGroup>
```python JsonProvider
from crewai import Crew, CheckpointConfig
from crewai.state import JsonProvider
crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
location="./my_checkpoints",
provider=JsonProvider(),
max_checkpoints=5,
),
)
```
```python SqliteProvider
from crewai import Crew, CheckpointConfig
from crewai.state import SqliteProvider
crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
location="./.checkpoints.db",
provider=SqliteProvider(),
max_checkpoints=50,
),
)
```
</CodeGroup>
<Tip>
SQLite يفعل وضع journal WAL للقراءات المتزامنة. يفضل لنقاط الحفظ عالية التردد.
</Tip>
</Accordion>
<Accordion title="استبعاد وكيل واحد" icon="user-slash">
```python
crew = Crew(
agents=[
Agent(role="Researcher", ...),
Agent(role="Writer", ..., checkpoint=False),
],
tasks=[...],
checkpoint=True,
)
```
</Accordion>
<Accordion title="التفرع إلى فرع جديد" icon="code-branch">
`fork()` يستعيد نقطة حفظ تحت نسب جديد بحيث لا يتصادم التشغيل الجديد مع الأصلي.
```python
config = CheckpointConfig(restore_from="./my_checkpoints/<file>.json")
crew = Crew.fork(config, branch="experiment-a")
result = crew.kickoff(inputs={"strategy": "aggressive"})
```
تسمية `branch` اختيارية؛ يتم إنشاء واحدة إذا أغفلت.
</Accordion>
<Accordion title="Checkpointing لـ Crew أو Flow أو Agent" icon="cubes">
<Tabs>
<Tab title="Crew">
```python
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, write_task, review_task],
checkpoint=CheckpointConfig(location="./crew_cp"),
)
```
المشغل الافتراضي: `task_completed`.
</Tab>
<Tab title="Flow">
```python
from crewai.flow.flow import Flow, start, listen
from crewai import CheckpointConfig
class MyFlow(Flow):
@start()
def step_one(self):
return "data"
@listen(step_one)
def step_two(self, data):
return process(data)
flow = MyFlow(
checkpoint=CheckpointConfig(
location="./flow_cp",
on_events=["method_execution_finished"],
),
)
result = flow.kickoff()
```
</Tab>
<Tab title="Agent">
```python
agent = Agent(
role="Researcher",
goal="Research topics",
backstory="Expert researcher",
checkpoint=CheckpointConfig(
location="./agent_cp",
on_events=["lite_agent_execution_completed"],
),
)
result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
```
</Tab>
</Tabs>
</Accordion>
<Accordion title="كتابة نقطة حفظ يدويا" icon="code">
سجل معالجا على أي حدث واستدع `state.checkpoint()`.
<CodeGroup>
```python Sync
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.llm_events import LLMCallCompletedEvent
if TYPE_CHECKING:
from crewai.state.runtime import RuntimeState
@crewai_event_bus.on(LLMCallCompletedEvent)
def on_llm_done(source: Any, event: LLMCallCompletedEvent, state: RuntimeState) -> None:
path = state.checkpoint("./my_checkpoints")
print(f"تم حفظ نقطة الحفظ: {path}")
```
```python Async
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.llm_events import LLMCallCompletedEvent
if TYPE_CHECKING:
from crewai.state.runtime import RuntimeState
@crewai_event_bus.on(LLMCallCompletedEvent)
async def on_llm_done_async(source: Any, event: LLMCallCompletedEvent, state: RuntimeState) -> None:
path = await state.acheckpoint("./my_checkpoints")
print(f"تم حفظ نقطة الحفظ: {path}")
```
</CodeGroup>
يتم تمرير وسيط `state` تلقائيا عندما يقبل المعالج ثلاثة معاملات. راجع [Event Listeners](/ar/concepts/event-listener) لقائمة الأحداث الكاملة.
</Accordion>
<Accordion title="التصفح والاستئناف والتفرع من سطر الأوامر" icon="terminal">
```bash
crewai checkpoint
crewai checkpoint --location ./my_checkpoints
crewai checkpoint --location ./.checkpoints.db
```
<Frame caption="شجرة نقاط الحفظ — الفروع والتفرعات تتداخل تحت أبيها.">
<img src="/images/checkpoint-tui-tree.png" alt="Checkpoint TUI tree view" />
</Frame>
اللوحة اليسرى تجمع نقاط الحفظ حسب الفرع؛ التفرعات تتداخل تحت أبيها. اختيار نقطة حفظ يفتح لوحة التفاصيل مع بياناتها الوصفية وحالة الكيان وتقدم المهام. **Resume** يكمل التشغيل؛ **Fork** يبدأ فرعا جديدا.
<Frame caption="تبويب النظرة العامة — البيانات الوصفية وحالة الكيان وملخص التشغيل.">
<img src="/images/checkpoint-tui-detail-overview.png" alt="Checkpoint detail overview tab" />
</Frame>
لوحة التفاصيل تعرض منطقتين قابلتين للتحرير:
- **Inputs** — مدخلات الـ kickoff الأصلية، معبأة مسبقا وقابلة للتحرير.
<Frame>
<img src="/images/checkpoint-tui-detail-inputs.png" alt="Editable kickoff inputs" />
</Frame>
- **مخرجات المهام** — مخرجات المهام المكتملة. تحرير مخرج والضغط على **Fork** يبطل المهام التابعة لتعاد بالسياق المعدل.
<Frame>
<img src="/images/checkpoint-tui-detail-tasks.png" alt="Editable task outputs" />
</Frame>
<Frame caption="عرض التفرع — تأكيد فرع جديد من نقطة الحفظ المختارة.">
<img src="/images/checkpoint-tui-details-fork.png" alt="Fork confirmation panel" />
</Frame>
<Tip>
مفيد لاستكشاف "ماذا لو": تفرع، عدل، راقب.
</Tip>
</Accordion>
<Accordion title="تفقد نقاط الحفظ بدون TUI" icon="magnifying-glass">
```bash
crewai checkpoint list ./my_checkpoints
crewai checkpoint info ./my_checkpoints/<file>.json
crewai checkpoint info ./.checkpoints.db
```
</Accordion>
</AccordionGroup>
## المرجع
### `CheckpointConfig`
<ParamField path="location" type="str" default='"./.checkpoints"'>
وجهة التخزين. مجلد لـ `JsonProvider`، مسار ملف قاعدة بيانات لـ `SqliteProvider`.
</ParamField>
<ParamField path="on_events" type='list[CheckpointEventType | Literal["*"]]' default='["task_completed"]'>
أنواع الأحداث التي تطلق نقطة حفظ. `CheckpointEventType` هو `Literal` — مدقق الأنواع يكمل تلقائيا ويرفض القيم غير المدعومة. راجع [أنواع الأحداث](#أنواع-الأحداث) للقائمة الكاملة.
</ParamField>
<ParamField path="provider" type="BaseProvider" default="JsonProvider()">
واجهة التخزين. `JsonProvider` أو `SqliteProvider`.
</ParamField>
<ParamField path="max_checkpoints" type="int | None" default="None">
الحد الاقصى لنقاط الحفظ المحتفظ بها. الأقدم تحذف بعد كل كتابة.
</ParamField>
<ParamField path="restore_from" type="Path | str | None" default="None">
نقطة الحفظ المراد استعادتها عند تمريرها عبر `from_checkpoint`.
</ParamField>
### قيم حقل `checkpoint`
مقبولة في `Crew` و`Flow` و`Agent`.
<ParamField path="None" type="افتراضي">
يرث من الأب.
</ParamField>
<ParamField path="True" type="bool">
تفعيل بالإعدادات الافتراضية.
</ParamField>
<ParamField path="False" type="bool">
انسحاب صريح. يوقف الوراثة.
</ParamField>
<ParamField path="CheckpointConfig(...)" type="CheckpointConfig">
إعدادات مخصصة.
</ParamField>
### أنواع الأحداث
يقبل `on_events` أي مجموعة من قيم `CheckpointEventType`. الافتراضي `["task_completed"]` يكتب نقطة حفظ لكل مهمة منتهية، و`["*"]` يطابق جميع الأحداث.
<Warning>
`["*"]` والأحداث عالية التردد مثل `llm_call_completed` تكتب نقاط حفظ كثيرة وقد تضر بالاداء. استخدمها مع `max_checkpoints`.
</Warning>
<Expandable title="جميع الأحداث المدعومة">
- **Task** — `task_started`, `task_completed`, `task_failed`, `task_evaluation`
- **Crew** — `crew_kickoff_started`, `crew_kickoff_completed`, `crew_kickoff_failed`, `crew_train_started`, `crew_train_completed`, `crew_train_failed`, `crew_test_started`, `crew_test_completed`, `crew_test_failed`, `crew_test_result`
- **Agent** — `agent_execution_started`, `agent_execution_completed`, `agent_execution_error`, `lite_agent_execution_started`, `lite_agent_execution_completed`, `lite_agent_execution_error`, `agent_evaluation_started`, `agent_evaluation_completed`, `agent_evaluation_failed`
- **Flow** — `flow_created`, `flow_started`, `flow_finished`, `flow_paused`, `method_execution_started`, `method_execution_finished`, `method_execution_failed`, `method_execution_paused`, `human_feedback_requested`, `human_feedback_received`, `flow_input_requested`, `flow_input_received`
- **LLM** — `llm_call_started`, `llm_call_completed`, `llm_call_failed`, `llm_stream_chunk`, `llm_thinking_chunk`
- **LLM Guardrail** — `llm_guardrail_started`, `llm_guardrail_completed`, `llm_guardrail_failed`
- **Tool** — `tool_usage_started`, `tool_usage_finished`, `tool_usage_error`, `tool_validate_input_error`, `tool_selection_error`, `tool_execution_error`
- **Memory** — `memory_save_started`, `memory_save_completed`, `memory_save_failed`, `memory_query_started`, `memory_query_completed`, `memory_query_failed`, `memory_retrieval_started`, `memory_retrieval_completed`, `memory_retrieval_failed`
- **Knowledge** — `knowledge_search_query_started`, `knowledge_search_query_completed`, `knowledge_query_started`, `knowledge_query_completed`, `knowledge_query_failed`, `knowledge_search_query_failed`
- **Reasoning** — `agent_reasoning_started`, `agent_reasoning_completed`, `agent_reasoning_failed`
- **MCP** — `mcp_connection_started`, `mcp_connection_completed`, `mcp_connection_failed`, `mcp_tool_execution_started`, `mcp_tool_execution_completed`, `mcp_tool_execution_failed`, `mcp_config_fetch_failed`
- **Observation** — `step_observation_started`, `step_observation_completed`, `step_observation_failed`, `plan_refinement`, `plan_replan_triggered`, `goal_achieved_early`
- **Skill** — `skill_discovery_started`, `skill_discovery_completed`, `skill_loaded`, `skill_activated`, `skill_load_failed`
- **Logging** — `agent_logs_started`, `agent_logs_execution`
- **A2A** — `a2a_delegation_started`, `a2a_delegation_completed`, `a2a_conversation_started`, `a2a_conversation_completed`, `a2a_message_sent`, `a2a_response_received`, `a2a_polling_started`, `a2a_polling_status`, `a2a_push_notification_registered`, `a2a_push_notification_received`, `a2a_push_notification_sent`, `a2a_push_notification_timeout`, `a2a_streaming_started`, `a2a_streaming_chunk`, `a2a_agent_card_fetched`, `a2a_authentication_failed`, `a2a_artifact_received`, `a2a_connection_error`, `a2a_server_task_started`, `a2a_server_task_completed`, `a2a_server_task_canceled`, `a2a_server_task_failed`, `a2a_parallel_delegation_started`, `a2a_parallel_delegation_completed`, `a2a_transport_negotiated`, `a2a_content_type_negotiated`, `a2a_context_created`, `a2a_context_expired`, `a2a_context_idle`, `a2a_context_completed`, `a2a_context_pruned`
- **إشارات النظام** — `SIGTERM`, `SIGINT`, `SIGHUP`, `SIGTSTP`, `SIGCONT`
- **حرف بدل** — `"*"` يطابق جميع الأحداث.
</Expandable>
### مزودات التخزين
<ParamField path="JsonProvider" type="provider">
ملف واحد لكل نقطة حفظ بصيغة `<timestamp>_<uuid>.json` داخل `location`.
</ParamField>
<ParamField path="SqliteProvider" type="provider">
ملف قاعدة بيانات واحد في `location` مع journaling WAL.
</ParamField>
### سطر الأوامر
| الامر | الغرض |
|:------|:------|
| `crewai checkpoint` | تشغيل TUI؛ كشف التخزين تلقائيا. |
| `crewai checkpoint --location <path>` | تشغيل TUI على موقع محدد. |
| `crewai checkpoint list <path>` | سرد نقاط الحفظ. |
| `crewai checkpoint info <path>` | تفقد ملف نقطة حفظ أو آخر مدخل في قاعدة بيانات SQLite. |

View File

@@ -0,0 +1,302 @@
---
title: واجهة سطر الأوامر
description: تعرّف على كيفية استخدام واجهة سطر أوامر CrewAI للتفاعل مع CrewAI.
icon: terminal
mode: "wide"
---
<Warning>
منذ الإصدار 0.140.0، بدأ CrewAI AMP عملية نقل مزود تسجيل الدخول.
لذلك، تم تحديث تدفق المصادقة عبر CLI. المستخدمون الذين يسجلون الدخول
باستخدام Google، أو الذين أنشأوا حساباتهم بعد 3 يوليو 2025 لن يتمكنوا
من تسجيل الدخول مع الإصدارات القديمة من مكتبة `crewai`.
</Warning>
## نظرة عامة
توفر واجهة سطر أوامر CrewAI مجموعة من الأوامر للتفاعل مع CrewAI، مما يتيح لك إنشاء وتدريب وتشغيل وإدارة الأطقم والتدفقات.
## التثبيت
لاستخدام واجهة سطر أوامر CrewAI، تأكد من تثبيت CrewAI:
```shell Terminal
pip install crewai
```
## الاستخدام الأساسي
الهيكل الأساسي لأمر CrewAI CLI هو:
```shell Terminal
crewai [COMMAND] [OPTIONS] [ARGUMENTS]
```
## الأوامر المتاحة
### 1. إنشاء
إنشاء طاقم أو تدفق جديد.
```shell Terminal
crewai create [OPTIONS] TYPE NAME
```
- `TYPE`: اختر بين "crew" أو "flow"
- `NAME`: اسم الطاقم أو التدفق
مثال:
```shell Terminal
crewai create crew my_new_crew
crewai create flow my_new_flow
```
افتراضيًا، ينشئ `crewai create crew` مشروعًا JSON-first يحتوي على `crew.jsonc` و `agents/*.jsonc`. استخدم `crewai create crew my_new_crew --classic` فقط إذا أردت البنية القديمة Python/YAML مع `crew.py` و `config/agents.yaml` و `config/tasks.yaml`.
### 2. الإصدار
عرض الإصدار المثبت من CrewAI.
```shell Terminal
crewai version [OPTIONS]
```
- `--tools`: (اختياري) عرض الإصدار المثبت من أدوات CrewAI
### 3. التدريب
تدريب الطاقم لعدد محدد من التكرارات.
```shell Terminal
crewai train [OPTIONS]
```
- `-n, --n_iterations INTEGER`: عدد تكرارات التدريب (افتراضي: 5)
- `-f, --filename TEXT`: مسار ملف مخصص للتدريب (افتراضي: "trained_agents_data.pkl")
### 4. الإعادة
إعادة تنفيذ الطاقم من مهمة محددة.
```shell Terminal
crewai replay [OPTIONS]
```
- `-t, --task_id TEXT`: إعادة تنفيذ الطاقم من معرّف المهمة هذا، بما في ذلك جميع المهام اللاحقة
### 5. سجل مخرجات المهام
استرجاع أحدث مخرجات مهام crew.kickoff().
```shell Terminal
crewai log-tasks-outputs
```
### 6. إعادة تعيين الذاكرة
إعادة تعيين ذاكرة الطاقم (طويلة، قصيرة، الكيانات، أحدث مخرجات التشغيل).
```shell Terminal
crewai reset-memories [OPTIONS]
```
- `-l, --long`: إعادة تعيين الذاكرة طويلة المدى
- `-s, --short`: إعادة تعيين الذاكرة قصيرة المدى
- `-e, --entities`: إعادة تعيين ذاكرة الكيانات
- `-k, --kickoff-outputs`: إعادة تعيين أحدث مخرجات التشغيل
- `-kn, --knowledge`: إعادة تعيين تخزين المعرفة
- `-akn, --agent-knowledge`: إعادة تعيين تخزين معرفة الوكيل
- `-a, --all`: إعادة تعيين جميع الذاكرات
### 7. الاختبار
اختبار الطاقم وتقييم النتائج.
```shell Terminal
crewai test [OPTIONS]
```
- `-n, --n_iterations INTEGER`: عدد تكرارات الاختبار (افتراضي: 3)
- `-m, --model TEXT`: نموذج LLM لتشغيل الاختبارات (افتراضي: "gpt-4o-mini")
### 8. التشغيل
تشغيل الطاقم أو التدفق.
```shell Terminal
crewai run
```
<Note>
بدءًا من الإصدار 0.103.0، يمكن استخدام أمر `crewai run` لتشغيل
كل من الأطقم القياسية والتدفقات. للتدفقات، يكتشف تلقائيًا النوع
من pyproject.toml ويشغّل الأمر المناسب. هذه هي الطريقة الموصى بها
لتشغيل كل من الأطقم والتدفقات.
</Note>
### 9. الدردشة
بدءًا من الإصدار `0.98.0`، عند تشغيل أمر `crewai chat`، تبدأ جلسة تفاعلية مع طاقمك. سيرشدك المساعد الذكي بطلب المدخلات اللازمة لتنفيذ الطاقم. بمجرد توفير جميع المدخلات، سينفذ الطاقم مهامه.
```shell Terminal
crewai chat
```
<Note>
مهم: عيّن خاصية `chat_llm` في تعريف الـ crew لتفعيل هذا الأمر.
للـ crews بنمط JSON-first، أضفها إلى `crew.jsonc`:
```jsonc
{
"name": "My Crew",
"agents": ["researcher"],
"tasks": [],
"chat_llm": "openai/gpt-4o"
}
```
للـ crews الكلاسيكية Python/YAML، عيّنها في `crew.py`:
```python
@crew
def crew(self) -> Crew:
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True,
chat_llm="gpt-4o",
)
```
</Note>
### 10. النشر
نشر الطاقم أو التدفق إلى [CrewAI AMP](https://app.crewai.com).
- **المصادقة**: تحتاج لتكون مصادقًا للنشر إلى CrewAI AMP.
```shell Terminal
crewai login
```
- **إنشاء نشر**:
```shell Terminal
crewai deploy create
```
- **نشر الطاقم**:
```shell Terminal
crewai deploy push
```
- **حالة النشر**:
```shell Terminal
crewai deploy status
```
- **سجلات النشر**:
```shell Terminal
crewai deploy logs
```
- **عرض النشرات**:
```shell Terminal
crewai deploy list
```
- **حذف النشر**:
```shell Terminal
crewai deploy remove
```
### 11. إدارة المؤسسة
إدارة مؤسسات CrewAI AMP.
```shell Terminal
crewai org [COMMAND] [OPTIONS]
```
- `list`: عرض جميع المؤسسات
- `current`: عرض المؤسسة النشطة حاليًا
- `switch`: التبديل إلى مؤسسة محددة
### 12. تسجيل الدخول
المصادقة مع CrewAI AMP باستخدام تدفق رمز الجهاز الآمن.
```shell Terminal
crewai login
```
### 13. إدارة التهيئة
إدارة إعدادات تهيئة CLI لـ CrewAI.
```shell Terminal
crewai config [COMMAND] [OPTIONS]
```
- `list`: عرض جميع معاملات التهيئة
- `set`: تعيين معامل تهيئة
- `reset`: إعادة تعيين جميع المعاملات إلى القيم الافتراضية
### 14. إدارة التتبع
إدارة تفضيلات جمع التتبع لعمليات الطاقم والتدفق.
```shell Terminal
crewai traces [COMMAND]
```
- `enable`: تفعيل جمع التتبع
- `disable`: تعطيل جمع التتبع
- `status`: عرض حالة جمع التتبع الحالية
#### كيف يعمل التتبع
يتم التحكم في جمع التتبع بفحص ثلاثة إعدادات بترتيب الأولوية:
1. **علامة صريحة في الكود** (الأولوية الأعلى):
```python
crew = Crew(agents=[...], tasks=[...], tracing=True) # تفعيل دائمًا
crew = Crew(agents=[...], tasks=[...], tracing=False) # تعطيل دائمًا
crew = Crew(agents=[...], tasks=[...]) # فحص الأولويات الأدنى
```
2. **متغير البيئة** (الأولوية الثانية):
```env
CREWAI_TRACING_ENABLED=true
```
3. **تفضيل المستخدم** (الأولوية الأدنى):
```shell Terminal
crewai traces enable
```
<Note>
**لتفعيل التتبع**، استخدم أيًا من هذه الطرق:
- عيّن `tracing=True` في كود الطاقم/التدفق، أو
- أضف `CREWAI_TRACING_ENABLED=true` إلى ملف `.env`، أو
- شغّل `crewai traces enable`
**لتعطيل التتبع**، استخدم أيًا من هذه الطرق:
- عيّن `tracing=False` في كود الطاقم/التدفق، أو
- أزل أو عيّن `false` لمتغير `CREWAI_TRACING_ENABLED`، أو
- شغّل `crewai traces disable`
</Note>
<Tip>
يتعامل CrewAI CLI مع المصادقة لمستودع الأدوات تلقائيًا عند
إضافة حزم إلى مشروعك. فقط أضف `crewai` قبل أي أمر `uv`
لاستخدامه. مثلًا `crewai uv add requests`.
</Tip>
<Note>
تُخزن إعدادات التهيئة في `~/.config/crewai/settings.json`. بعض
الإعدادات مثل اسم المؤسسة ومعرّفها للقراءة فقط وتُدار من خلال
أوامر المصادقة والمؤسسة.
</Note>

View File

@@ -0,0 +1,363 @@
---
title: التعاون
description: كيفية تمكين الوكلاء من العمل معًا وتفويض المهام والتواصل بفعالية داخل فرق CrewAI.
icon: screen-users
mode: "wide"
---
## نظرة عامة
يُمكّن التعاون في CrewAI الوكلاء من العمل معًا كفريق عن طريق تفويض المهام وطرح الأسئلة للاستفادة من خبرات بعضهم البعض. عندما يكون `allow_delegation=True`، يحصل الوكلاء تلقائيًا على أدوات تعاون قوية.
## البدء السريع: تفعيل التعاون
```python
from crewai import Agent, Crew, Task
# تفعيل التعاون للوكلاء
researcher = Agent(
role="Research Specialist",
goal="Conduct thorough research on any topic",
backstory="Expert researcher with access to various sources",
allow_delegation=True, # الإعداد الرئيسي للتعاون
verbose=True
)
writer = Agent(
role="Content Writer",
goal="Create engaging content based on research",
backstory="Skilled writer who transforms research into compelling content",
allow_delegation=True, # يُمكّن طرح الأسئلة على الوكلاء الآخرين
verbose=True
)
# يمكن للوكلاء الآن التعاون تلقائيًا
crew = Crew(
agents=[researcher, writer],
tasks=[...],
verbose=True
)
```
## كيف يعمل تعاون الوكلاء
عندما يكون `allow_delegation=True`، يوفر CrewAI تلقائيًا للوكلاء أداتين قويتين:
### 1. **أداة تفويض العمل**
تسمح للوكلاء بتعيين مهام لزملاء الفريق ذوي الخبرة المحددة.
```python
# يحصل الوكيل تلقائيًا على هذه الأداة:
# Delegate work to coworker(task: str, context: str, coworker: str)
```
### 2. **أداة طرح الأسئلة**
تُمكّن الوكلاء من طرح أسئلة محددة لجمع المعلومات من الزملاء.
```python
# يحصل الوكيل تلقائيًا على هذه الأداة:
# Ask question to coworker(question: str, context: str, coworker: str)
```
## التعاون في الممارسة
إليك مثالًا كاملًا يوضح تعاون الوكلاء في مهمة إنشاء المحتوى:
```python
from crewai import Agent, Crew, Task, Process
# إنشاء وكلاء تعاونيين
researcher = Agent(
role="Research Specialist",
goal="Find accurate, up-to-date information on any topic",
backstory="""You're a meticulous researcher with expertise in finding
reliable sources and fact-checking information across various domains.""",
allow_delegation=True,
verbose=True
)
writer = Agent(
role="Content Writer",
goal="Create engaging, well-structured content",
backstory="""You're a skilled content writer who excels at transforming
research into compelling, readable content for different audiences.""",
allow_delegation=True,
verbose=True
)
editor = Agent(
role="Content Editor",
goal="Ensure content quality and consistency",
backstory="""You're an experienced editor with an eye for detail,
ensuring content meets high standards for clarity and accuracy.""",
allow_delegation=True,
verbose=True
)
# إنشاء مهمة تشجع التعاون
article_task = Task(
description="""Write a comprehensive 1000-word article about 'The Future of AI in Healthcare'.
The article should include:
- Current AI applications in healthcare
- Emerging trends and technologies
- Potential challenges and ethical considerations
- Expert predictions for the next 5 years
Collaborate with your teammates to ensure accuracy and quality.""",
expected_output="A well-researched, engaging 1000-word article with proper structure and citations",
agent=writer # الكاتب يقود، لكن يمكنه تفويض البحث إلى الباحث
)
# إنشاء طاقم تعاوني
crew = Crew(
agents=[researcher, writer, editor],
tasks=[article_task],
process=Process.sequential,
verbose=True
)
result = crew.kickoff()
```
## أنماط التعاون
### النمط 1: بحث ← كتابة ← تحرير
```python
research_task = Task(
description="Research the latest developments in quantum computing",
expected_output="Comprehensive research summary with key findings and sources",
agent=researcher
)
writing_task = Task(
description="Write an article based on the research findings",
expected_output="Engaging 800-word article about quantum computing",
agent=writer,
context=[research_task] # يحصل على مخرجات البحث كسياق
)
editing_task = Task(
description="Edit and polish the article for publication",
expected_output="Publication-ready article with improved clarity and flow",
agent=editor,
context=[writing_task] # يحصل على مسودة المقال كسياق
)
```
### النمط 2: مهمة واحدة تعاونية
```python
collaborative_task = Task(
description="""Create a marketing strategy for a new AI product.
Writer: Focus on messaging and content strategy
Researcher: Provide market analysis and competitor insights
Work together to create a comprehensive strategy.""",
expected_output="Complete marketing strategy with research backing",
agent=writer # الوكيل القائد، لكن يمكنه التفويض إلى الباحث
)
```
## التعاون الهرمي
للمشاريع المعقدة، استخدم عملية هرمية مع وكيل مدير:
```python
from crewai import Agent, Crew, Task, Process
# وكيل المدير ينسق الفريق
manager = Agent(
role="Project Manager",
goal="Coordinate team efforts and ensure project success",
backstory="Experienced project manager skilled at delegation and quality control",
allow_delegation=True,
verbose=True
)
# وكلاء متخصصون
researcher = Agent(
role="Researcher",
goal="Provide accurate research and analysis",
backstory="Expert researcher with deep analytical skills",
allow_delegation=False, # المتخصصون يركزون على خبرتهم
verbose=True
)
writer = Agent(
role="Writer",
goal="Create compelling content",
backstory="Skilled writer who creates engaging content",
allow_delegation=False,
verbose=True
)
# مهمة يقودها المدير
project_task = Task(
description="Create a comprehensive market analysis report with recommendations",
expected_output="Executive summary, detailed analysis, and strategic recommendations",
agent=manager # المدير سيفوّض إلى المتخصصين
)
# طاقم هرمي
crew = Crew(
agents=[manager, researcher, writer],
tasks=[project_task],
process=Process.hierarchical, # المدير ينسق كل شيء
manager_llm="gpt-4o", # تحديد LLM للمدير
verbose=True
)
```
## أفضل ممارسات التعاون
### 1. **تحديد الأدوار بوضوح**
```python
# جيد: أدوار محددة ومتكاملة
researcher = Agent(role="Market Research Analyst", ...)
writer = Agent(role="Technical Content Writer", ...)
# تجنب: أدوار متداخلة أو غامضة
agent1 = Agent(role="General Assistant", ...)
agent2 = Agent(role="Helper", ...)
```
### 2. **تفعيل التفويض الاستراتيجي**
```python
# فعّل التفويض للمنسقين والعامين
lead_agent = Agent(
role="Content Lead",
allow_delegation=True, # يمكنه التفويض إلى المتخصصين
...
)
# عطّل للمتخصصين المركّزين (اختياري)
specialist_agent = Agent(
role="Data Analyst",
allow_delegation=False, # يركز على الخبرة الأساسية
...
)
```
### 3. **مشاركة السياق**
```python
# استخدم معامل context لاعتماديات المهام
writing_task = Task(
description="Write article based on research",
agent=writer,
context=[research_task], # يشارك نتائج البحث
...
)
```
### 4. **أوصاف المهام الواضحة**
```python
# أوصاف محددة وقابلة للتنفيذ
Task(
description="""Research competitors in the AI chatbot space.
Focus on: pricing models, key features, target markets.
Provide data in a structured format.""",
...
)
# تجنب: أوصاف غامضة لا توجه التعاون
Task(description="Do some research about chatbots", ...)
```
## استكشاف أخطاء التعاون وإصلاحها
### المشكلة: الوكلاء لا يتعاونون
**الأعراض:** يعمل الوكلاء بمعزل، لا يحدث تفويض
```python
# الحل: تأكد من تفعيل التفويض
agent = Agent(
role="...",
allow_delegation=True, # هذا مطلوب!
...
)
```
### المشكلة: كثرة الذهاب والإياب
**الأعراض:** يطرح الوكلاء أسئلة مفرطة، تقدم بطيء
```python
# الحل: وفّر سياقًا أفضل وأدوارًا محددة
Task(
description="""Write a technical blog post about machine learning.
Context: Target audience is software developers with basic ML knowledge.
Length: 1200 words
Include: code examples, practical applications, best practices
If you need specific technical details, delegate research to the researcher.""",
...
)
```
### المشكلة: حلقات التفويض
**الأعراض:** يفوّض الوكلاء ذهابًا وإيابًا بلا نهاية
```python
# الحل: تسلسل هرمي واضح ومسؤوليات
manager = Agent(role="Manager", allow_delegation=True)
specialist1 = Agent(role="Specialist A", allow_delegation=False) # لا إعادة تفويض
specialist2 = Agent(role="Specialist B", allow_delegation=False)
```
## ميزات التعاون المتقدمة
### قواعد التعاون المخصصة
```python
# تعيين إرشادات تعاون محددة في خلفية الوكيل
agent = Agent(
role="Senior Developer",
backstory="""You lead development projects and coordinate with team members.
Collaboration guidelines:
- Delegate research tasks to the Research Analyst
- Ask the Designer for UI/UX guidance
- Consult the QA Engineer for testing strategies
- Only escalate blocking issues to the Project Manager""",
allow_delegation=True
)
```
### مراقبة التعاون
```python
def track_collaboration(output):
"""تتبع أنماط التعاون"""
if "Delegate work to coworker" in output.raw:
print("Delegation occurred")
if "Ask question to coworker" in output.raw:
print("Question asked")
crew = Crew(
agents=[...],
tasks=[...],
step_callback=track_collaboration, # مراقبة التعاون
verbose=True
)
```
## الذاكرة والتعلم
تمكين الوكلاء من تذكر التعاونات السابقة:
```python
agent = Agent(
role="Content Lead",
memory=True, # يتذكر التفاعلات السابقة
allow_delegation=True,
verbose=True
)
```
مع تفعيل الذاكرة، يتعلم الوكلاء من التعاونات السابقة ويحسّنون قرارات التفويض بمرور الوقت.
## الخطوات التالية
- **جرّب الأمثلة**: ابدأ بمثال التعاون الأساسي
- **جرّب أدوارًا مختلفة**: اختبر تركيبات أدوار وكلاء مختلفة
- **راقب التفاعلات**: استخدم `verbose=True` لرؤية التعاون في العمل
- **حسّن أوصاف المهام**: المهام الواضحة تؤدي إلى تعاون أفضل
- **وسّع النطاق**: جرّب العمليات الهرمية للمشاريع المعقدة
يحوّل التعاون وكلاء الذكاء الاصطناعي الفرديين إلى فرق قوية يمكنها معالجة التحديات المعقدة ومتعددة الأوجه معًا.

View File

@@ -0,0 +1,245 @@
---
title: الأطقم
description: فهم واستخدام الأطقم في إطار عمل CrewAI مع خصائص ووظائف شاملة.
icon: people-group
mode: "wide"
---
## نظرة عامة
يمثل الطاقم في CrewAI مجموعة تعاونية من الوكلاء يعملون معًا لتحقيق مجموعة من المهام. يحدد كل طاقم استراتيجية تنفيذ المهام وتعاون الوكلاء وسير العمل العام.
## خصائص الطاقم
| الخاصية | المعامل | الوصف |
| :------------------------------------ | :--------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **المهام** | `tasks` | قائمة المهام المعيّنة للطاقم. |
| **الوكلاء** | `agents` | قائمة الوكلاء الذين يشكلون جزءًا من الطاقم. |
| **العملية** _(اختياري)_ | `process` | تدفق العملية (مثل تسلسلي، هرمي) الذي يتبعه الطاقم. الافتراضي `sequential`. |
| **الوضع المفصل** _(اختياري)_ | `verbose` | مستوى التفصيل في التسجيل أثناء التنفيذ. الافتراضي `False`. |
| **LLM المدير** _(اختياري)_ | `manager_llm` | نموذج اللغة المستخدم بواسطة وكيل المدير في العملية الهرمية. **مطلوب عند استخدام العملية الهرمية.** |
| **LLM استدعاء الدوال** _(اختياري)_ | `function_calling_llm` | إذا مُرر، سيستخدم الطاقم هذا LLM لاستدعاء دوال الأدوات لجميع الوكلاء. يمكن لكل وكيل أن يكون له LLM خاص يتجاوز LLM الطاقم. |
| **التهيئة** _(اختياري)_ | `config` | إعدادات تهيئة اختيارية للطاقم، بتنسيق `Json` أو `Dict[str, Any]`. |
| **الحد الأقصى لـ RPM** _(اختياري)_ | `max_rpm` | الحد الأقصى للطلبات في الدقيقة. الافتراضي `None`. |
| **الذاكرة** _(اختياري)_ | `memory` | تُستخدم لتخزين ذاكرات التنفيذ (قصيرة المدى، طويلة المدى، ذاكرة الكيانات). |
| **التخزين المؤقت** _(اختياري)_ | `cache` | يحدد ما إذا كان يُستخدم تخزين مؤقت لنتائج تنفيذ الأدوات. الافتراضي `True`. |
| **المُضمّن** _(اختياري)_ | `embedder` | تهيئة المُضمّن المستخدم من قبل الطاقم. الافتراضي `{"provider": "openai"}`. |
| **دالة الخطوة** _(اختياري)_ | `step_callback` | دالة تُستدعى بعد كل خطوة لكل وكيل. |
| **دالة المهمة** _(اختياري)_ | `task_callback` | دالة تُستدعى بعد اكتمال كل مهمة. |
| **مشاركة الطاقم** _(اختياري)_ | `share_crew` | ما إذا كنت تريد مشاركة معلومات الطاقم الكاملة وتنفيذه مع فريق CrewAI. |
| **ملف سجل المخرجات** _(اختياري)_ | `output_log_file` | عيّن True لحفظ السجلات كـ logs.txt أو وفّر مسار ملف. الافتراضي `None`. |
| **وكيل المدير** _(اختياري)_ | `manager_agent` | يعيّن وكيلًا مخصصًا سيُستخدم كمدير. |
| **التخطيط** *(اختياري)* | `planning` | يضيف قدرة التخطيط للطاقم. |
| **LLM التخطيط** *(اختياري)* | `planning_llm` | نموذج اللغة المستخدم بواسطة AgentPlanner في عملية التخطيط. |
| **مصادر المعرفة** _(اختياري)_ | `knowledge_sources` | مصادر المعرفة المتاحة على مستوى الطاقم، يمكن لجميع الوكلاء الوصول إليها. |
| **البث** _(اختياري)_ | `stream` | تفعيل مخرجات البث لتلقي تحديثات في الوقت الفعلي. الافتراضي `False`. |
<Tip>
**الحد الأقصى لـ RPM للطاقم**: تعيّن خاصية `max_rpm` الحد الأقصى للطلبات في الدقيقة التي يمكن للطاقم تنفيذها لتجنب حدود المعدل وستتجاوز إعدادات `max_rpm` الفردية للوكلاء إذا عيّنتها.
</Tip>
## إنشاء الأطقم
هناك طريقتان رئيسيتان لإنشاء الأطقم في CrewAI: باستخدام **تهيئة JSONC (الموصى بها للـ crews الجديدة)** أو تعريفها **مباشرة في الكود** للمشاريع الكلاسيكية والحالات المتقدمة.
### تهيئة JSONC (موصى بها)
المشاريع الجديدة التي تُنشأ عبر `crewai create crew <name>` تستخدم `crew.jsonc` لإعدادات الـ crew والمهام، وملفًا منفصلًا لكل Agent داخل `agents/`. يكتشف `crewai run` ملف `crew.jsonc` أو `crew.json`، ويحمّل الـ Agents المشار إليها، ويطلب قيم placeholders الناقصة، ثم يبدأ الـ crew.
```jsonc crew.jsonc
{
"name": "Market Research Crew",
"agents": ["researcher", "analyst"],
"tasks": [
{
"name": "research",
"description": "Research {topic} and collect the most relevant facts.",
"expected_output": "Structured research notes about {topic}.",
"agent": "researcher"
},
{
"name": "analysis",
"description": "Analyze the research and write a concise report.",
"expected_output": "A markdown report with findings and recommendations.",
"agent": "analyst",
"context": ["research"],
"output_file": "output/report.md"
}
],
"process": "sequential",
"verbose": true,
"memory": true,
"inputs": {
"topic": "AI Agents"
}
}
```
كل عنصر في `agents` يُحل أولًا إلى `agents/<name>.jsonc` ثم إلى `agents/<name>.json`. للـ crews الهرمية، استخدم `"process": "hierarchical"` مع `manager_llm` أو `manager_agent`.
<Warning>
شغّل مشاريع JSON crew من مصادر تثق بها فقط. أدوات `custom:<name>` ومراجع `{"python": "module.attribute"}` تنفذ كود Python محليًا عند تحميل الـ crew.
</Warning>
### تهيئة YAML الكلاسيكية
المشاريع الكلاسيكية التي تُنشأ عبر `crewai create crew <name> --classic` تستخدم `crew.py` و `config/agents.yaml` و `config/tasks.yaml` والمزيّنات `@CrewBase` و `@agent` و `@task` و `@crew`.
تظل هذه الطريقة مدعومة للمشاريع الحالية المبنية بـ Python/YAML وللفِرق التي تحتاج تحكمًا صريحًا عبر decorators.
```python code
from crewai import Agent, Crew, Task, Process
from crewai.project import CrewBase, agent, task, crew, before_kickoff, after_kickoff
from crewai.agents.agent_builder.base_agent import BaseAgent
from typing import List
@CrewBase
class YourCrewName:
"""Description of your crew"""
agents: List[BaseAgent]
tasks: List[Task]
agents_config = 'config/agents.yaml'
tasks_config = 'config/tasks.yaml'
@before_kickoff
def prepare_inputs(self, inputs):
inputs['additional_data'] = "Some extra information"
return inputs
@after_kickoff
def process_output(self, output):
output.raw += "\nProcessed after kickoff."
return output
@agent
def agent_one(self) -> Agent:
return Agent(
config=self.agents_config['agent_one'], # type: ignore[index]
verbose=True
)
@task
def task_one(self) -> Task:
return Task(
config=self.tasks_config['task_one'] # type: ignore[index]
)
@crew
def crew(self) -> Crew:
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True,
)
```
<Note>
سيتم تنفيذ المهام بالترتيب الذي عُرّفت به.
</Note>
فئة `CrewBase`، مع هذه المزيّنات، تؤتمت جمع الوكلاء والمهام، مما يقلل الحاجة للإدارة اليدوية.
### تعريف مباشر في الكود (بديل)
بدلاً من ذلك، يمكنك تعريف الطاقم مباشرة في الكود بدون ملفات تهيئة YAML.
## مخرجات الطاقم
تُغلّف مخرجات الطاقم في فئة `CrewOutput`. توفر هذه الفئة طريقة منظمة للوصول إلى نتائج تنفيذ الطاقم، بما في ذلك تنسيقات متنوعة مثل السلاسل النصية الخام وJSON ونماذج Pydantic.
### خصائص مخرجات الطاقم
| الخاصية | المعامل | النوع | الوصف |
| :--------------- | :------------- | :------------------------- | :--------------------------------------------------------------------------------------------------- |
| **Raw** | `raw` | `str` | المخرجات الخام للطاقم. هذا هو التنسيق الافتراضي. |
| **Pydantic** | `pydantic` | `Optional[BaseModel]` | كائن نموذج Pydantic يمثل المخرجات المنظمة. |
| **JSON Dict** | `json_dict` | `Optional[Dict[str, Any]]` | قاموس يمثل مخرجات JSON. |
| **Tasks Output** | `tasks_output` | `List[TaskOutput]` | قائمة كائنات `TaskOutput`، كل منها يمثل مخرجات مهمة. |
| **Token Usage** | `token_usage` | `Dict[str, Any]` | ملخص استخدام الرموز. |
## استخدام الذاكرة
يمكن للأطقم استخدام الذاكرة (قصيرة المدى، طويلة المدى، وذاكرة الكيانات) لتحسين تنفيذها وتعلمها بمرور الوقت.
## استخدام التخزين المؤقت
يمكن استخدام التخزين المؤقت لتخزين نتائج تنفيذ الأدوات، مما يجعل العملية أكثر كفاءة.
## مقاييس استخدام الطاقم
بعد تنفيذ الطاقم، يمكنك الوصول إلى خاصية `usage_metrics` لعرض مقاييس استخدام نموذج اللغة (LLM) لجميع المهام المنفذة.
```python Code
crew = Crew(agents=[agent1, agent2], tasks=[task1, task2])
crew.kickoff()
print(crew.usage_metrics)
```
## عملية تنفيذ الطاقم
- **العملية التسلسلية**: تُنفذ المهام واحدة تلو الأخرى، مما يسمح بتدفق عمل خطي.
- **العملية الهرمية**: ينسق وكيل مدير الطاقم، ويفوّض المهام ويتحقق من النتائج.
### تشغيل الطاقم
بمجرد تجميع طاقمك، ابدأ سير العمل بطريقة `kickoff()`.
```python Code
result = my_crew.kickoff()
print(result)
```
### طرق مختلفة لتشغيل الطاقم
#### الطرق المتزامنة
- `kickoff()`: يبدأ عملية التنفيذ وفقًا لتدفق العملية المحدد.
- `kickoff_for_each()`: ينفذ المهام بالتتابع لكل مدخل.
#### الطرق غير المتزامنة
| الطريقة | النوع | الوصف |
|--------|------|-------------|
| `akickoff()` | غير متزامن أصلي | async/await أصلي عبر سلسلة التنفيذ بأكملها |
| `akickoff_for_each()` | غير متزامن أصلي | تنفيذ غير متزامن أصلي لكل مدخل في قائمة |
| `kickoff_async()` | مبني على الخيوط | يغلّف التنفيذ المتزامن في `asyncio.to_thread` |
| `kickoff_for_each_async()` | مبني على الخيوط | غير متزامن مبني على الخيوط لكل مدخل في قائمة |
<Note>
لأحمال العمل عالية التزامن، يُوصى بـ `akickoff()` و `akickoff_for_each()` لأنها تستخدم async أصلي.
</Note>
### بث تنفيذ الطاقم
للرؤية في الوقت الفعلي لتنفيذ الطاقم، يمكنك تفعيل البث:
```python Code
crew = Crew(
agents=[researcher],
tasks=[task],
stream=True
)
streaming = crew.kickoff(inputs={"topic": "AI"})
for chunk in streaming:
print(chunk.content, end="", flush=True)
result = streaming.result
```
### الإعادة من مهمة محددة
يمكنك الآن الإعادة من مهمة محددة باستخدام أمر CLI `replay`.
```shell
crewai log-tasks-outputs
```
ثم للإعادة من مهمة محددة:
```shell
crewai replay -t <task_id>
```

View File

@@ -0,0 +1,237 @@
---
title: "مستمعو الأحداث"
description: "الاستفادة من أحداث CrewAI لبناء تكاملات مخصصة ومراقبة"
icon: spinner
mode: "wide"
---
## نظرة عامة
يوفر CrewAI نظام أحداث قوي يتيح لك الاستماع والتفاعل مع الأحداث المختلفة التي تحدث أثناء تنفيذ طاقمك. تُمكّنك هذه الميزة من بناء تكاملات مخصصة وحلول مراقبة وأنظمة تسجيل أو أي وظائف أخرى تحتاج للتشغيل بناءً على أحداث CrewAI الداخلية.
## كيف يعمل
يستخدم CrewAI بنية ناقل أحداث لإرسال الأحداث طوال دورة حياة التنفيذ. يُبنى نظام الأحداث على المكونات التالية:
1. **CrewAIEventsBus**: ناقل أحداث فريد يدير تسجيل الأحداث وإرسالها
2. **BaseEvent**: الفئة الأساسية لجميع الأحداث في النظام
3. **BaseEventListener**: فئة أساسية مجردة لإنشاء مستمعي أحداث مخصصين
عندما تحدث إجراءات محددة في CrewAI (مثل بدء تنفيذ طاقم، أو إكمال وكيل لمهمة، أو استخدام أداة)، يرسل النظام أحداثًا مقابلة. يمكنك تسجيل معالجات لهذه الأحداث لتنفيذ كود مخصص عند حدوثها.
<Note type="info" title="تحسين المؤسسات: تتبع الأوامر">
يوفر CrewAI AMP ميزة تتبع أوامر مدمجة تستفيد من نظام الأحداث لتتبع وتخزين وتصور جميع الأوامر والاستكمالات والبيانات الوصفية المرتبطة.
![Prompt Tracing Dashboard](/images/enterprise/traces-overview.png)
مع تتبع الأوامر يمكنك:
- عرض السجل الكامل لجميع الأوامر المرسلة إلى LLM
- تتبع استخدام الرموز والتكاليف
- تصحيح إخفاقات استدلال الوكيل
- مشاركة تسلسلات الأوامر مع فريقك
- مقارنة استراتيجيات الأوامر المختلفة
- تصدير التتبعات للامتثال والتدقيق
</Note>
## إنشاء مستمع أحداث مخصص
لإنشاء مستمع أحداث مخصص، تحتاج إلى:
1. إنشاء فئة ترث من `BaseEventListener`
2. تنفيذ طريقة `setup_listeners`
3. تسجيل معالجات للأحداث التي تهمك
4. إنشاء مثيل من مستمعك في الملف المناسب
إليك مثالًا بسيطًا:
```python
from crewai.events import (
CrewKickoffStartedEvent,
CrewKickoffCompletedEvent,
AgentExecutionCompletedEvent,
)
from crewai.events import BaseEventListener
class MyCustomListener(BaseEventListener):
def __init__(self):
super().__init__()
def setup_listeners(self, crewai_event_bus):
@crewai_event_bus.on(CrewKickoffStartedEvent)
def on_crew_started(source, event):
print(f"Crew '{event.crew_name}' has started execution!")
@crewai_event_bus.on(CrewKickoffCompletedEvent)
def on_crew_completed(source, event):
print(f"Crew '{event.crew_name}' has completed execution!")
print(f"Output: {event.output}")
@crewai_event_bus.on(AgentExecutionCompletedEvent)
def on_agent_execution_completed(source, event):
print(f"Agent '{event.agent.role}' completed task")
print(f"Output: {event.output}")
```
## تسجيل المستمع بشكل صحيح
مجرد تعريف فئة المستمع ليس كافيًا. تحتاج لإنشاء مثيل منه والتأكد من استيراده في تطبيقك.
```python
# في ملف crew.py
from crewai import Agent, Crew, Task
from my_listeners import MyCustomListener
# إنشاء مثيل من المستمع
my_listener = MyCustomListener()
class MyCustomCrew:
def crew(self):
return Crew(
agents=[...],
tasks=[...],
)
```
## أنواع الأحداث المتاحة
يوفر CrewAI مجموعة واسعة من الأحداث يمكنك الاستماع إليها:
### أحداث الطاقم
- **CrewKickoffStartedEvent**: يُرسل عند بدء تنفيذ الطاقم
- **CrewKickoffCompletedEvent**: يُرسل عند اكتمال تنفيذ الطاقم
- **CrewKickoffFailedEvent**: يُرسل عند فشل تنفيذ الطاقم
- **CrewTestStartedEvent**: يُرسل عند بدء اختبار الطاقم
- **CrewTestCompletedEvent**: يُرسل عند اكتمال اختبار الطاقم
- **CrewTestFailedEvent**: يُرسل عند فشل اختبار الطاقم
- **CrewTrainStartedEvent**: يُرسل عند بدء تدريب الطاقم
- **CrewTrainCompletedEvent**: يُرسل عند اكتمال تدريب الطاقم
- **CrewTrainFailedEvent**: يُرسل عند فشل تدريب الطاقم
### أحداث الوكيل
- **AgentExecutionStartedEvent**: يُرسل عند بدء تنفيذ وكيل لمهمة
- **AgentExecutionCompletedEvent**: يُرسل عند اكتمال تنفيذ وكيل لمهمة
- **AgentExecutionErrorEvent**: يُرسل عند مواجهة وكيل لخطأ أثناء التنفيذ
- **LiteAgentExecutionStartedEvent**: يُرسل عند بدء تنفيذ LiteAgent
- **LiteAgentExecutionCompletedEvent**: يُرسل عند اكتمال تنفيذ LiteAgent
### أحداث المهام
- **TaskStartedEvent**: يُرسل عند بدء تنفيذ مهمة
- **TaskCompletedEvent**: يُرسل عند اكتمال تنفيذ مهمة
- **TaskFailedEvent**: يُرسل عند فشل تنفيذ مهمة
### أحداث استخدام الأدوات
- **ToolUsageStartedEvent**: يُرسل عند بدء تنفيذ أداة
- **ToolUsageFinishedEvent**: يُرسل عند اكتمال تنفيذ أداة
- **ToolUsageErrorEvent**: يُرسل عند مواجهة خطأ في تنفيذ أداة
### أحداث MCP
- **MCPConnectionStartedEvent**: يُرسل عند بدء الاتصال بخادم MCP
- **MCPConnectionCompletedEvent**: يُرسل عند اكتمال الاتصال بخادم MCP
- **MCPConnectionFailedEvent**: يُرسل عند فشل الاتصال بخادم MCP
- **MCPToolExecutionStartedEvent**: يُرسل عند بدء تنفيذ أداة MCP
- **MCPToolExecutionCompletedEvent**: يُرسل عند اكتمال تنفيذ أداة MCP
- **MCPToolExecutionFailedEvent**: يُرسل عند فشل تنفيذ أداة MCP
### أحداث المعرفة
- **KnowledgeRetrievalStartedEvent**: يُرسل عند بدء استرجاع المعرفة
- **KnowledgeRetrievalCompletedEvent**: يُرسل عند اكتمال استرجاع المعرفة
- **KnowledgeQueryStartedEvent**: يُرسل عند بدء استعلام المعرفة
- **KnowledgeQueryCompletedEvent**: يُرسل عند اكتمال استعلام المعرفة
- **KnowledgeQueryFailedEvent**: يُرسل عند فشل استعلام المعرفة
### أحداث حواجز LLM
- **LLMGuardrailStartedEvent**: يُرسل عند بدء التحقق من الحاجز
- **LLMGuardrailCompletedEvent**: يُرسل عند اكتمال التحقق من الحاجز
- **LLMGuardrailFailedEvent**: يُرسل عند فشل التحقق من الحاجز
### أحداث التدفق
- **FlowCreatedEvent**: يُرسل عند إنشاء تدفق
- **FlowStartedEvent**: يُرسل عند بدء تنفيذ تدفق
- **FlowFinishedEvent**: يُرسل عند اكتمال تنفيذ تدفق
- **FlowFailedEvent**: يُرسل عند فشل تنفيذ تدفق. يحتوي على اسم التدفق والاستثناء الذي أنهى التنفيذ.
- **FlowPausedEvent**: يُرسل عند إيقاف تدفق مؤقتًا بانتظار ملاحظات بشرية
### أحداث LLM
- **LLMCallStartedEvent**: يُرسل عند بدء استدعاء LLM
- **LLMCallCompletedEvent**: يُرسل عند اكتمال استدعاء LLM
- **LLMCallFailedEvent**: يُرسل عند فشل استدعاء LLM
- **LLMStreamChunkEvent**: يُرسل لكل جزء مستلم أثناء بث استجابات LLM
### أحداث الذاكرة
- **MemoryQueryStartedEvent**: يُرسل عند بدء استعلام الذاكرة
- **MemoryQueryCompletedEvent**: يُرسل عند اكتمال استعلام الذاكرة
- **MemorySaveStartedEvent**: يُرسل عند بدء حفظ الذاكرة
- **MemorySaveCompletedEvent**: يُرسل عند اكتمال حفظ الذاكرة
### أحداث الاستدلال
- **AgentReasoningStartedEvent**: يُرسل عند بدء وكيل الاستدلال حول مهمة
- **AgentReasoningCompletedEvent**: يُرسل عند انتهاء عملية الاستدلال
- **AgentReasoningFailedEvent**: يُرسل عند فشل عملية الاستدلال
### أحداث A2A (وكيل إلى وكيل)
- **A2ADelegationStartedEvent**: يُرسل عند بدء تفويض A2A
- **A2ADelegationCompletedEvent**: يُرسل عند اكتمال تفويض A2A
- **A2AConversationStartedEvent**: يُرسل عند بدء محادثة A2A متعددة الأدوار
- **A2AConversationCompletedEvent**: يُرسل عند انتهاء محادثة A2A
## هيكل معالج الأحداث
يستقبل كل معالج حدث معاملين:
1. **source**: الكائن الذي أرسل الحدث
2. **event**: مثيل الحدث، يحتوي على بيانات خاصة بالحدث
هيكل كائن الحدث يعتمد على نوع الحدث، لكن جميع الأحداث ترث من `BaseEvent` وتتضمن:
- **timestamp**: الوقت الذي أُرسل فيه الحدث
- **type**: معرّف نصي لنوع الحدث
## الاستخدام المتقدم: المعالجات المحددة النطاق
لمعالجة الأحداث المؤقتة، يمكنك استخدام مدير سياق `scoped_handlers`:
```python
from crewai.events import crewai_event_bus, CrewKickoffStartedEvent
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(CrewKickoffStartedEvent)
def temp_handler(source, event):
print("This handler only exists within this context")
# قم بشيء يرسل أحداثًا
# خارج السياق، يتم إزالة المعالج المؤقت
```
## حالات الاستخدام
يمكن استخدام مستمعي الأحداث لأغراض متنوعة:
1. **التسجيل والمراقبة**: تتبع تنفيذ طاقمك وتسجيل الأحداث المهمة
2. **التحليلات**: جمع بيانات عن أداء وسلوك طاقمك
3. **التصحيح**: إعداد مستمعين مؤقتين لتصحيح مشاكل محددة
4. **التكامل**: ربط CrewAI بأنظمة خارجية مثل منصات المراقبة وقواعد البيانات أو خدمات الإشعارات
5. **السلوك المخصص**: تشغيل إجراءات مخصصة بناءً على أحداث محددة
## أفضل الممارسات
1. **اجعل المعالجات خفيفة**: يجب أن تكون معالجات الأحداث خفيفة وتتجنب العمليات الحاجبة
2. **معالجة الأخطاء**: أدرج معالجة أخطاء مناسبة في معالجات الأحداث لمنع الاستثناءات من التأثير على التنفيذ الرئيسي
3. **التنظيف**: إذا خصص مستمعك موارد، تأكد من تنظيفها بشكل صحيح
4. **الاستماع الانتقائي**: استمع فقط للأحداث التي تحتاج فعلاً لمعالجتها
5. **الاختبار**: اختبر مستمعي الأحداث بمعزل لضمان سلوكهم كما هو متوقع
بالاستفادة من نظام أحداث CrewAI، يمكنك توسيع وظائفه ودمجه بسلاسة مع بنيتك التحتية الحالية.

View File

@@ -0,0 +1,267 @@
---
title: الملفات
description: تمرير الصور وملفات PDF والصوت والفيديو والنصوص إلى وكلائك للمعالجة متعددة الوسائط.
icon: file-image
---
## نظرة عامة
يدعم CrewAI مدخلات الملفات متعددة الوسائط الأصلية، مما يتيح لك تمرير الصور وملفات PDF والصوت والفيديو والنصوص مباشرة إلى وكلائك. يتم تنسيق الملفات تلقائيًا وفقًا لمتطلبات API لكل مزود LLM.
<Note type="info" title="اعتمادية اختيارية">
يتطلب دعم الملفات حزمة `crewai-files` الاختيارية. ثبّتها بـ:
```bash
uv add 'crewai[file-processing]'
```
</Note>
<Note type="warning" title="وصول مبكر">
واجهة معالجة الملفات حاليًا في مرحلة الوصول المبكر.
</Note>
## أنواع الملفات
يدعم CrewAI خمسة أنواع ملفات محددة بالإضافة إلى فئة `File` العامة التي تكتشف النوع تلقائيًا:
| النوع | الفئة | حالات الاستخدام |
|:-----|:------|:----------|
| **صورة** | `ImageFile` | صور، لقطات شاشة، مخططات، رسوم بيانية |
| **PDF** | `PDFFile` | مستندات، تقارير، أوراق بحثية |
| **صوت** | `AudioFile` | تسجيلات صوتية، بودكاست، اجتماعات |
| **فيديو** | `VideoFile` | تسجيلات شاشة، عروض تقديمية |
| **نص** | `TextFile` | ملفات كود، سجلات، ملفات بيانات |
| **عام** | `File` | اكتشاف تلقائي للنوع من المحتوى |
```python
from crewai_files import File, ImageFile, PDFFile, AudioFile, VideoFile, TextFile
image = ImageFile(source="screenshot.png")
pdf = PDFFile(source="report.pdf")
audio = AudioFile(source="meeting.mp3")
video = VideoFile(source="demo.mp4")
text = TextFile(source="data.csv")
file = File(source="document.pdf")
```
## مصادر الملفات
يقبل معامل `source` أنواع إدخال متعددة ويكتشف تلقائيًا المعالج المناسب:
### من مسار
```python
from crewai_files import ImageFile
image = ImageFile(source="./images/chart.png")
```
### من عنوان URL
```python
from crewai_files import ImageFile
image = ImageFile(source="https://example.com/image.png")
```
### من بايتات
```python
from crewai_files import ImageFile, FileBytes
image_bytes = download_image_from_api()
image = ImageFile(source=FileBytes(data=image_bytes, filename="downloaded.png"))
image = ImageFile(source=image_bytes)
```
## استخدام الملفات
يمكن تمرير الملفات على مستويات متعددة، حيث تأخذ المستويات الأكثر تحديدًا الأولوية.
### مع الأطقم
مرر الملفات عند تشغيل طاقم:
```python
from crewai import Crew
from crewai_files import ImageFile
crew = Crew(agents=[analyst], tasks=[analysis_task])
result = crew.kickoff(
inputs={"topic": "Q4 Sales"},
input_files={
"chart": ImageFile(source="sales_chart.png"),
"report": PDFFile(source="quarterly_report.pdf"),
}
)
```
### مع المهام
أرفق الملفات بمهام محددة:
```python
from crewai import Task
from crewai_files import ImageFile
task = Task(
description="Analyze the sales chart and identify trends in {chart}",
expected_output="A summary of key trends",
input_files={
"chart": ImageFile(source="sales_chart.png"),
}
)
```
### مع التدفقات
مرر الملفات إلى التدفقات، والتي تنتقل تلقائيًا إلى الأطقم:
```python
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile
class AnalysisFlow(Flow):
@start()
def analyze(self):
return self.analysis_crew.kickoff()
flow = AnalysisFlow()
result = flow.kickoff(
input_files={"image": ImageFile(source="data.png")}
)
```
### مع الوكلاء المستقلين
مرر الملفات مباشرة إلى تشغيل الوكيل:
```python
from crewai import Agent
from crewai_files import ImageFile
agent = Agent(
role="Image Analyst",
goal="Analyze images",
backstory="Expert at visual analysis",
llm="gpt-4o",
)
result = agent.kickoff(
messages="What's in this image?",
input_files={"photo": ImageFile(source="photo.jpg")},
)
```
## أولوية الملفات
عند تمرير الملفات على مستويات متعددة، تتجاوز المستويات الأكثر تحديدًا المستويات الأوسع:
```
Flow input_files < Crew input_files < Task input_files
```
على سبيل المثال، إذا عرّف كل من التدفق والمهمة ملفًا باسم `"chart"`، تُستخدم نسخة المهمة.
## دعم المزودين
تدعم المزودات المختلفة أنواع ملفات مختلفة. يقوم CrewAI تلقائيًا بتنسيق الملفات وفقًا لواجهة كل مزود.
| المزود | صورة | PDF | صوت | فيديو | نص |
|:---------|:-----:|:---:|:-----:|:-----:|:----:|
| **OpenAI** (completions API) | ✓ | | | | |
| **OpenAI** (responses API) | ✓ | ✓ | ✓ | | |
| **Anthropic** (claude-3.x) | ✓ | ✓ | | | |
| **Google Gemini** (gemini-1.5, 2.0, 2.5) | ✓ | ✓ | ✓ | ✓ | ✓ |
| **AWS Bedrock** (claude-3) | ✓ | ✓ | | | |
| **Azure OpenAI** (gpt-4o) | ✓ | | ✓ | | |
<Note type="info" title="Gemini لأقصى دعم للملفات">
تدعم نماذج Google Gemini جميع أنواع الملفات بما في ذلك الفيديو (حتى ساعة واحدة، 2 جيجابايت). استخدم Gemini عندما تحتاج لمعالجة محتوى الفيديو.
</Note>
<Note type="warning" title="أنواع الملفات غير المدعومة">
إذا مررت نوع ملف لا يدعمه المزود (مثل الفيديو إلى OpenAI)، ستتلقى خطأ `UnsupportedFileTypeError`. اختر مزودك بناءً على أنواع الملفات التي تحتاج لمعالجتها.
</Note>
## كيف تُرسل الملفات
يختار CrewAI تلقائيًا الطريقة المثلى لإرسال الملفات إلى كل مزود:
| الطريقة | الوصف | متى تُستخدم |
|:-------|:------------|:----------|
| **Inline Base64** | الملف مضمّن مباشرة في الطلب | ملفات صغيرة (< 5 ميجابايت عادة) |
| **File Upload API** | الملف يُرفع بشكل منفصل، يُشار إليه بمعرّف | ملفات كبيرة تتجاوز العتبة |
| **URL Reference** | عنوان URL مباشر يُمرر إلى النموذج | مصدر الملف هو عنوان URL بالفعل |
### طرق الإرسال حسب المزود
| المزود | Inline Base64 | File Upload API | URL References |
|:---------|:-------------:|:---------------:|:--------------:|
| **OpenAI** | ✓ | ✓ (> 5 MB) | ✓ |
| **Anthropic** | ✓ | ✓ (> 5 MB) | ✓ |
| **Google Gemini** | ✓ | ✓ (> 20 MB) | ✓ |
| **AWS Bedrock** | ✓ | | ✓ (S3 URIs) |
| **Azure OpenAI** | ✓ | | ✓ |
<Note type="info" title="تحسين تلقائي">
لا تحتاج لإدارة هذا بنفسك. يستخدم CrewAI تلقائيًا الطريقة الأكثر كفاءة بناءً على حجم الملف وقدرات المزود. المزودات بدون واجهات رفع الملفات تستخدم inline base64 لجميع الملفات.
</Note>
## أوضاع معالجة الملفات
تحكم في كيفية معالجة الملفات عندما تتجاوز حدود المزود:
```python
from crewai_files import ImageFile, PDFFile
image = ImageFile(source="large.png", mode="strict")
image = ImageFile(source="large.png", mode="auto")
image = ImageFile(source="large.png", mode="warn")
pdf = PDFFile(source="large.pdf", mode="chunk")
```
## قيود المزودين
لكل مزود حدود محددة لأحجام الملفات والأبعاد:
### OpenAI
- **الصور**: حد أقصى 20 ميجابايت، حتى 10 صور لكل طلب
- **PDF**: حد أقصى 32 ميجابايت، حتى 100 صفحة
- **الصوت**: حد أقصى 25 ميجابايت، حتى 25 دقيقة
### Anthropic
- **الصور**: حد أقصى 5 ميجابايت، أقصى 8000x8000 بكسل، حتى 100 صورة
- **PDF**: حد أقصى 32 ميجابايت، حتى 100 صفحة
### Google Gemini
- **الصور**: حد أقصى 100 ميجابايت
- **PDF**: حد أقصى 50 ميجابايت
- **الصوت**: حد أقصى 100 ميجابايت، حتى 9.5 ساعة
- **الفيديو**: حد أقصى 2 جيجابايت، حتى ساعة واحدة
### AWS Bedrock
- **الصور**: حد أقصى 4.5 ميجابايت، أقصى 8000x8000 بكسل
- **PDF**: حد أقصى 3.75 ميجابايت، حتى 100 صفحة
## الإشارة إلى الملفات في الأوامر
استخدم اسم مفتاح الملف في أوصاف المهام للإشارة إلى الملفات:
```python
task = Task(
description="""
Analyze the provided materials:
1. Review the chart in {sales_chart}
2. Cross-reference with data in {quarterly_report}
3. Summarize key findings
""",
expected_output="Analysis summary with key insights",
input_files={
"sales_chart": ImageFile(source="chart.png"),
"quarterly_report": PDFFile(source="report.pdf"),
}
)
```

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,878 @@
---
title: الذاكرة
description: الاستفادة من نظام الذاكرة الموحد في CrewAI لتعزيز قدرات الوكلاء.
icon: database
mode: "wide"
---
## نظرة عامة
يوفر CrewAI **نظام ذاكرة موحد** -- فئة `Memory` واحدة تستبدل أنواع الذاكرة المنفصلة (قصيرة المدى، طويلة المدى، ذاكرة الكيانات، والخارجية) بواجهة برمجة تطبيقات ذكية واحدة. تستخدم الذاكرة LLM لتحليل المحتوى عند الحفظ (استنتاج النطاق والفئات والأهمية) وتدعم الاسترجاع متعدد العمق مع تسجيل مركب يمزج بين التشابه الدلالي والحداثة والأهمية.
يمكنك استخدام الذاكرة بأربع طرق: **مستقلة** (سكربتات، دفاتر ملاحظات)، **مع فرق Crew**، **مع Agents**، أو **داخل التدفقات**.
## البدء السريع
```python
from crewai import Memory
memory = Memory()
# Store -- the LLM infers scope, categories, and importance
memory.remember("We decided to use PostgreSQL for the user database.")
# Retrieve -- results ranked by composite score (semantic + recency + importance)
matches = memory.recall("What database did we choose?")
for m in matches:
print(f"[{m.score:.2f}] {m.record.content}")
# Tune scoring for a fast-moving project
memory = Memory(recency_weight=0.5, recency_half_life_days=7)
# Forget
memory.forget(scope="/project/old")
# Explore the self-organized scope tree
print(memory.tree())
print(memory.info("/"))
```
## أربع طرق لاستخدام الذاكرة
### مستقلة
استخدم الذاكرة في السكربتات ودفاتر الملاحظات وأدوات سطر الأوامر أو كقاعدة معرفة مستقلة -- لا حاجة لوكلاء أو فرق Crew.
```python
from crewai import Memory
memory = Memory()
# Build up knowledge
memory.remember("The API rate limit is 1000 requests per minute.")
memory.remember("Our staging environment uses port 8080.")
memory.remember("The team agreed to use feature flags for all new releases.")
# Later, recall what you need
matches = memory.recall("What are our API limits?", limit=5)
for m in matches:
print(f"[{m.score:.2f}] {m.record.content}")
# Extract atomic facts from a longer text
raw = """Meeting notes: We decided to migrate from MySQL to PostgreSQL
next quarter. The budget is $50k. Sarah will lead the migration."""
facts = memory.extract_memories(raw)
# ["Migration from MySQL to PostgreSQL planned for next quarter",
# "Database migration budget is $50k",
# "Sarah will lead the database migration"]
for fact in facts:
memory.remember(fact)
```
### مع فرق Crew
مرّر `memory=True` للإعدادات الافتراضية، أو مرّر مثيل `Memory` مُعدّ للسلوك المخصص.
```python
from crewai import Crew, Agent, Task, Process, Memory
# Option 1: Default memory
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, writing_task],
process=Process.sequential,
memory=True,
verbose=True,
)
# Option 2: Custom memory with tuned scoring
memory = Memory(
recency_weight=0.4,
semantic_weight=0.4,
importance_weight=0.2,
recency_half_life_days=14,
)
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, writing_task],
memory=memory,
)
```
عند استخدام `memory=True`، ينشئ الفريق مثيل `Memory()` افتراضيًا ويمرر إعداد `embedder` الخاص بالفريق تلقائيًا. يشترك جميع الوكلاء في الفريق في ذاكرة الفريق ما لم يكن لدى الوكيل ذاكرته الخاصة.
بعد كل مهمة، يستخرج الفريق تلقائيًا حقائق منفصلة من مخرجات المهمة ويخزّنها. قبل كل مهمة، يسترجع الوكيل السياق ذا الصلة من الذاكرة ويحقنه في موجّه المهمة.
### مع Agents
يمكن للوكلاء استخدام ذاكرة الفريق المشتركة (افتراضيًا) أو تلقي عرض محدد النطاق للسياق الخاص.
```python
from crewai import Agent, Memory
memory = Memory()
# Researcher gets a private scope -- only sees /agent/researcher
researcher = Agent(
role="Researcher",
goal="Find and analyze information",
backstory="Expert researcher with attention to detail",
memory=memory.scope("/agent/researcher"),
)
# Writer uses crew shared memory (no agent-level memory set)
writer = Agent(
role="Writer",
goal="Produce clear, well-structured content",
backstory="Experienced technical writer",
# memory not set -- uses crew._memory when crew has memory enabled
)
```
يمنح هذا النمط الباحث نتائج خاصة بينما يقرأ الكاتب من ذاكرة الفريق المشتركة.
### مع التدفقات
كل تدفق يحتوي على ذاكرة مدمجة. استخدم `self.remember()` و `self.recall()` و `self.extract_memories()` داخل أي دالة تدفق.
```python
from crewai.flow.flow import Flow, listen, start
class ResearchFlow(Flow):
@start()
def gather_data(self):
findings = "PostgreSQL handles 10k concurrent connections. MySQL caps at 5k."
self.remember(findings, scope="/research/databases")
return findings
@listen(gather_data)
def write_report(self, findings):
# Recall past research to provide context
past = self.recall("database performance benchmarks")
context = "\n".join(f"- {m.record.content}" for m in past)
return f"Report:\nNew findings: {findings}\nPrevious context:\n{context}"
```
انظر [وثائق التدفقات](/concepts/flows) لمزيد من المعلومات حول الذاكرة في التدفقات.
## النطاقات الهرمية
### ما هي النطاقات
يتم تنظيم الذكريات في شجرة هرمية من النطاقات، مشابهة لنظام الملفات. كل نطاق هو مسار مثل `/` أو `/project/alpha` أو `/agent/researcher/findings`.
```
/
/company
/company/engineering
/company/product
/project
/project/alpha
/project/beta
/agent
/agent/researcher
/agent/writer
```
توفر النطاقات **ذاكرة تعتمد على السياق** -- عند الاسترجاع ضمن نطاق، تبحث فقط في ذلك الفرع من الشجرة، مما يحسّن كلًا من الدقة والأداء.
### كيف يعمل استنتاج النطاق
عند استدعاء `remember()` دون تحديد نطاق، يحلل LLM المحتوى وشجرة النطاقات الحالية، ثم يقترح أفضل موضع. إذا لم يكن هناك نطاق حالي مناسب، ينشئ واحدًا جديدًا. بمرور الوقت، تنمو شجرة النطاقات عضويًا من المحتوى نفسه -- لا تحتاج إلى تصميم مخطط مسبقًا.
```python
memory = Memory()
# LLM infers scope from content
memory.remember("We chose PostgreSQL for the user database.")
# -> might be placed under /project/decisions or /engineering/database
# You can also specify scope explicitly
memory.remember("Sprint velocity is 42 points", scope="/team/metrics")
```
### تصوير شجرة النطاقات
```python
print(memory.tree())
# / (15 records)
# /project (8 records)
# /project/alpha (5 records)
# /project/beta (3 records)
# /agent (7 records)
# /agent/researcher (4 records)
# /agent/writer (3 records)
print(memory.info("/project/alpha"))
# ScopeInfo(path='/project/alpha', record_count=5,
# categories=['architecture', 'database'],
# oldest_record=datetime(...), newest_record=datetime(...),
# child_scopes=[])
```
### MemoryScope: عروض الأشجار الفرعية
يقيّد `MemoryScope` جميع العمليات على فرع من الشجرة. يمكن للوكيل أو الكود الذي يستخدمه الرؤية والكتابة فقط ضمن تلك الشجرة الفرعية.
```python
memory = Memory()
# Create a scope for a specific agent
agent_memory = memory.scope("/agent/researcher")
# Everything is relative to /agent/researcher
agent_memory.remember("Found three relevant papers on LLM memory.")
# -> stored under /agent/researcher
agent_memory.recall("relevant papers")
# -> searches only under /agent/researcher
# Narrow further with subscope
project_memory = agent_memory.subscope("project-alpha")
# -> /agent/researcher/project-alpha
```
### أفضل الممارسات لتصميم النطاقات
- **ابدأ بشكل مسطح، ودع LLM ينظّم.** لا تبالغ في هندسة تسلسل النطاقات مسبقًا. ابدأ بـ `memory.remember(content)` ودع استنتاج النطاق في LLM ينشئ الهيكل مع تراكم المحتوى.
- **استخدم أنماط `/{entity_type}/{identifier}`.** تنشأ التسلسلات الطبيعية من أنماط مثل `/project/alpha` و `/agent/researcher` و `/company/engineering` و `/customer/acme-corp`.
- **حدد النطاق حسب الاهتمام، وليس حسب نوع البيانات.** استخدم `/project/alpha/decisions` بدلاً من `/decisions/project/alpha`. هذا يبقي المحتوى ذا الصلة معًا.
- **حافظ على العمق ضحلًا (2-3 مستويات).** النطاقات المتداخلة بعمق تصبح متفرقة جدًا. `/project/alpha/architecture` جيد؛ `/project/alpha/architecture/decisions/databases/postgresql` عميق جدًا.
- **استخدم النطاقات الصريحة عندما تعرف، ودع LLM يستنتج عندما لا تعرف.** إذا كنت تخزّن قرار مشروع معروف، مرّر `scope="/project/alpha/decisions"`. إذا كنت تخزّن مخرجات وكيل حرة الشكل، اترك النطاق ودع LLM يحدده.
### أمثلة حالات الاستخدام
**فريق متعدد المشاريع:**
```python
memory = Memory()
# Each project gets its own branch
memory.remember("Using microservices architecture", scope="/project/alpha/architecture")
memory.remember("GraphQL API for client apps", scope="/project/beta/api")
# Recall across all projects
memory.recall("API design decisions")
# Or within a specific project
memory.recall("API design", scope="/project/beta")
```
**سياق خاص لكل وكيل مع معرفة مشتركة:**
```python
memory = Memory()
# Researcher has private findings
researcher_memory = memory.scope("/agent/researcher")
# Writer can read from both its own scope and shared company knowledge
writer_view = memory.slice(
scopes=["/agent/writer", "/company/knowledge"],
read_only=True,
)
```
**دعم العملاء (سياق لكل عميل):**
```python
memory = Memory()
# Each customer gets isolated context
memory.remember("Prefers email communication", scope="/customer/acme-corp")
memory.remember("On enterprise plan, 50 seats", scope="/customer/acme-corp")
# Shared product docs are accessible to all agents
memory.remember("Rate limit is 1000 req/min on enterprise plan", scope="/product/docs")
```
## شرائح الذاكرة
### ما هي الشرائح
`MemorySlice` هو عرض عبر نطاقات متعددة، ربما متباعدة. على عكس النطاق (الذي يقيّد على شجرة فرعية واحدة)، تتيح لك الشريحة الاسترجاع من عدة فروع في وقت واحد.
### متى تستخدم الشرائح مقابل النطاقات
- **النطاق**: استخدمه عندما يجب تقييد وكيل أو كتلة كود على شجرة فرعية واحدة. مثال: وكيل يرى فقط `/agent/researcher`.
- **الشريحة**: استخدمها عندما تحتاج إلى دمج السياق من عدة فروع. مثال: وكيل يقرأ من نطاقه الخاص بالإضافة إلى معرفة الشركة المشتركة.
### شرائح القراءة فقط
النمط الأكثر شيوعًا: منح وكيل إمكانية القراءة من فروع متعددة دون السماح له بالكتابة في المناطق المشتركة.
```python
memory = Memory()
# Agent can recall from its own scope AND company knowledge,
# but cannot write to company knowledge
agent_view = memory.slice(
scopes=["/agent/researcher", "/company/knowledge"],
read_only=True,
)
matches = agent_view.recall("company security policies", limit=5)
# Searches both /agent/researcher and /company/knowledge, merges and ranks results
agent_view.remember("new finding") # Raises PermissionError (read-only)
```
### شرائح القراءة والكتابة
عند تعطيل القراءة فقط، يمكنك الكتابة في أي من النطاقات المضمّنة، لكن يجب تحديد النطاق صراحة.
```python
view = memory.slice(scopes=["/team/alpha", "/team/beta"], read_only=False)
# Must specify scope when writing
view.remember("Cross-team decision", scope="/team/alpha", categories=["decisions"])
```
## التسجيل المركب
يتم ترتيب نتائج الاسترجاع بواسطة مزيج مرجّح من ثلاث إشارات:
```
composite = semantic_weight * similarity + recency_weight * decay + importance_weight * importance
```
حيث:
- **similarity** = `1 / (1 + distance)` من فهرس المتجهات (0 إلى 1)
- **decay** = `0.5^(age_days / half_life_days)` -- اضمحلال أُسي (1.0 لليوم، 0.5 عند نصف العمر)
- **importance** = درجة أهمية السجل (0 إلى 1)، يتم تعيينها وقت الترميز
قم بإعدادها مباشرة على منشئ `Memory`:
```python
# Sprint retrospective: favor recent memories, short half-life
memory = Memory(
recency_weight=0.5,
semantic_weight=0.3,
importance_weight=0.2,
recency_half_life_days=7,
)
# Architecture knowledge base: favor important memories, long half-life
memory = Memory(
recency_weight=0.1,
semantic_weight=0.5,
importance_weight=0.4,
recency_half_life_days=180,
)
```
يتضمن كل `MemoryMatch` قائمة `match_reasons` حتى تتمكن من رؤية سبب ترتيب نتيجة معينة في موضعها (مثل `["semantic", "recency", "importance"]`).
## طبقة تحليل LLM
تستخدم الذاكرة LLM بثلاث طرق:
1. **عند الحفظ** -- عندما تحذف النطاق أو الفئات أو الأهمية، يحلل LLM المحتوى ويقترح النطاق والفئات والأهمية والبيانات الوصفية (الكيانات والتواريخ والموضوعات).
2. **عند الاسترجاع** -- للاسترجاع العميق/التلقائي، يحلل LLM الاستعلام (الكلمات المفتاحية، تلميحات الوقت، النطاقات المقترحة، التعقيد) لتوجيه الاسترجاع.
3. **استخراج الذكريات** -- `extract_memories(content)` يقسم النص الخام (مثل مخرجات المهمة) إلى عبارات ذاكرة منفصلة. يستخدم الوكلاء هذا قبل استدعاء `remember()` على كل عبارة حتى يتم تخزين حقائق ذرية بدلاً من كتلة كبيرة واحدة.
جميع التحليلات تتدهور بسلاسة عند فشل LLM -- انظر [سلوك الفشل](#سلوك-الفشل).
## توحيد الذاكرة
عند حفظ محتوى جديد، يتحقق خط أنابيب الترميز تلقائيًا من وجود سجلات مماثلة في التخزين. إذا كان التشابه أعلى من `consolidation_threshold` (الافتراضي 0.85)، يقرر LLM ما يجب فعله:
- **keep** -- السجل الحالي لا يزال دقيقًا وغير مكرر.
- **update** -- يجب تحديث السجل الحالي بمعلومات جديدة (يوفر LLM المحتوى المدمج).
- **delete** -- السجل الحالي قديم أو تم استبداله أو تناقضه.
- **insert_new** -- ما إذا كان يجب إدراج المحتوى الجديد أيضًا كسجل منفصل.
هذا يمنع تراكم النسخ المكررة. على سبيل المثال، إذا حفظت "CrewAI ensures reliable operation" ثلاث مرات، يتعرف التوحيد على النسخ المكررة ويحتفظ بسجل واحد فقط.
### إزالة التكرار داخل الدفعة
عند استخدام `remember_many()`، تتم مقارنة العناصر داخل نفس الدفعة مع بعضها البعض قبل الوصول إلى التخزين. إذا كان تشابه جيب التمام >= `batch_dedup_threshold` (الافتراضي 0.98)، يتم إسقاط العنصر الأحدث بصمت. هذا يلتقط النسخ المكررة الدقيقة أو شبه الدقيقة داخل دفعة واحدة دون أي استدعاءات LLM (رياضيات متجهات خالصة).
```python
# Only 2 records are stored (the third is a near-duplicate of the first)
memory.remember_many([
"CrewAI supports complex workflows.",
"Python is a great language.",
"CrewAI supports complex workflows.", # dropped by intra-batch dedup
])
```
## الحفظ غير الحاجب
`remember_many()` **غير حاجب** -- يقدم خط أنابيب الترميز إلى خيط خلفي ويعود فورًا. هذا يعني أن الوكيل يمكنه المتابعة إلى المهمة التالية بينما يتم حفظ الذكريات.
```python
# Returns immediately -- save happens in background
memory.remember_many(["Fact A.", "Fact B.", "Fact C."])
# recall() automatically waits for pending saves before searching
matches = memory.recall("facts") # sees all 3 records
```
### حاجز القراءة
كل استدعاء `recall()` يستدعي تلقائيًا `drain_writes()` قبل البحث، مما يضمن أن الاستعلام يرى دائمًا أحدث السجلات المستمرة. هذا شفاف -- لا تحتاج أبدًا إلى التفكير فيه.
### إيقاف الفريق
عند انتهاء الفريق، يستنزف `kickoff()` جميع عمليات حفظ الذاكرة المعلقة في كتلة `finally` الخاصة به، لذا لا تُفقد أي عمليات حفظ حتى لو اكتمل الفريق بينما عمليات الحفظ الخلفية قيد التنفيذ.
### الاستخدام المستقل
للسكربتات أو دفاتر الملاحظات حيث لا توجد دورة حياة فريق، استدعِ `drain_writes()` أو `close()` صراحة:
```python
memory = Memory()
memory.remember_many(["Fact A.", "Fact B."])
# Option 1: Wait for pending saves
memory.drain_writes()
# Option 2: Drain and shut down the background pool
memory.close()
```
## المصدر والخصوصية
يمكن لكل سجل ذاكرة أن يحمل علامة `source` لتتبع المصدر وعلامة `private` للتحكم في الوصول.
### تتبع المصدر
يحدد معامل `source` من أين جاءت الذاكرة:
```python
# Tag memories with their origin
memory.remember("User prefers dark mode", source="user:alice")
memory.remember("System config updated", source="admin")
memory.remember("Agent found a bug", source="agent:debugger")
# Recall only memories from a specific source
matches = memory.recall("user preferences", source="user:alice")
```
### الذكريات الخاصة
الذكريات الخاصة مرئية فقط للاسترجاع عندما يتطابق `source`:
```python
# Store a private memory
memory.remember("Alice's API key is sk-...", source="user:alice", private=True)
# This recall sees the private memory (source matches)
matches = memory.recall("API key", source="user:alice")
# This recall does NOT see it (different source)
matches = memory.recall("API key", source="user:bob")
# Admin access: see all private records regardless of source
matches = memory.recall("API key", include_private=True)
```
هذا مفيد بشكل خاص في النشرات متعددة المستخدمين أو المؤسسية حيث يجب عزل ذكريات المستخدمين المختلفين.
## RecallFlow (الاسترجاع العميق)
يدعم `recall()` عمقين:
- **`depth="shallow"`** -- بحث متجهي مباشر مع تسجيل مركب. سريع (~200 مللي ثانية)، بدون استدعاءات LLM.
- **`depth="deep"` (افتراضي)** -- يشغل RecallFlow متعدد الخطوات: تحليل الاستعلام، اختيار النطاق، بحث متجهي متوازٍ، توجيه قائم على الثقة، واستكشاف متكرر اختياري عندما تكون الثقة منخفضة.
**تخطي LLM الذكي**: الاستعلامات الأقصر من `query_analysis_threshold` (الافتراضي 200 حرف) تتخطى تحليل LLM للاستعلام بالكامل، حتى في الوضع العميق. الاستعلامات القصيرة مثل "ما قاعدة البيانات التي نستخدمها؟" هي بالفعل عبارات بحث جيدة -- تحليل LLM يضيف قيمة قليلة. هذا يوفر ~1-3 ثوانٍ لكل استرجاع للاستعلامات القصيرة النموذجية. فقط الاستعلامات الأطول (مثل أوصاف المهام الكاملة) تمر عبر تقطير LLM إلى استعلامات فرعية مستهدفة.
```python
# Shallow: pure vector search, no LLM
matches = memory.recall("What did we decide?", limit=10, depth="shallow")
# Deep (default): intelligent retrieval with LLM analysis for long queries
matches = memory.recall(
"Summarize all architecture decisions from this quarter",
limit=10,
depth="deep",
)
```
عتبات الثقة التي تتحكم في موجّه RecallFlow قابلة للإعداد:
```python
memory = Memory(
confidence_threshold_high=0.9, # Only synthesize when very confident
confidence_threshold_low=0.4, # Explore deeper more aggressively
exploration_budget=2, # Allow up to 2 exploration rounds
query_analysis_threshold=200, # Skip LLM for queries shorter than this
)
```
## إعداد المُضمِّن
تحتاج الذاكرة إلى نموذج تضمين لتحويل النص إلى متجهات للبحث الدلالي. يمكنك إعداده بثلاث طرق.
### التمرير إلى Memory مباشرة
```python
from crewai import Memory
# As a config dict
memory = Memory(embedder={"provider": "openai", "config": {"model_name": "text-embedding-3-small"}})
# As a pre-built callable
from crewai.rag.embeddings.factory import build_embedder
embedder = build_embedder({"provider": "ollama", "config": {"model_name": "mxbai-embed-large"}})
memory = Memory(embedder=embedder)
```
### عبر إعداد مُضمِّن Crew
عند استخدام `memory=True`، يتم تمرير إعداد `embedder` الخاص بالفريق:
```python
from crewai import Crew
crew = Crew(
agents=[...],
tasks=[...],
memory=True,
embedder={"provider": "openai", "config": {"model_name": "text-embedding-3-small"}},
)
```
### أمثلة المزودين
<AccordionGroup>
<Accordion title="OpenAI (افتراضي)">
```python
memory = Memory(embedder={
"provider": "openai",
"config": {
"model_name": "text-embedding-3-small",
# "api_key": "sk-...", # or set OPENAI_API_KEY env var
},
})
```
</Accordion>
<Accordion title="Ollama (محلي، خاص)">
```python
memory = Memory(embedder={
"provider": "ollama",
"config": {
"model_name": "mxbai-embed-large",
"url": "http://localhost:11434/api/embeddings",
},
})
```
</Accordion>
<Accordion title="Azure OpenAI">
```python
memory = Memory(embedder={
"provider": "azure",
"config": {
"deployment_id": "your-embedding-deployment",
"api_key": "your-azure-api-key",
"api_base": "https://your-resource.openai.azure.com",
"api_version": "2024-02-01",
},
})
```
</Accordion>
<Accordion title="Google AI">
```python
memory = Memory(embedder={
"provider": "google-generativeai",
"config": {
"model_name": "gemini-embedding-001",
# "api_key": "...", # or set GOOGLE_API_KEY env var
},
})
```
</Accordion>
<Accordion title="Google Vertex AI">
```python
memory = Memory(embedder={
"provider": "google-vertex",
"config": {
"model_name": "gemini-embedding-001",
"project_id": "your-gcp-project-id",
"location": "us-central1",
},
})
```
</Accordion>
<Accordion title="Cohere">
```python
memory = Memory(embedder={
"provider": "cohere",
"config": {
"model_name": "embed-english-v3.0",
# "api_key": "...", # or set COHERE_API_KEY env var
},
})
```
</Accordion>
<Accordion title="VoyageAI">
```python
memory = Memory(embedder={
"provider": "voyageai",
"config": {
"model": "voyage-3",
# "api_key": "...", # or set VOYAGE_API_KEY env var
},
})
```
</Accordion>
<Accordion title="AWS Bedrock">
```python
memory = Memory(embedder={
"provider": "amazon-bedrock",
"config": {
"model_name": "amazon.titan-embed-text-v1",
# Uses default AWS credentials (boto3 session)
},
})
```
</Accordion>
<Accordion title="Hugging Face">
```python
memory = Memory(embedder={
"provider": "huggingface",
"config": {
"model_name": "sentence-transformers/all-MiniLM-L6-v2",
},
})
```
</Accordion>
<Accordion title="Jina">
```python
memory = Memory(embedder={
"provider": "jina",
"config": {
"model_name": "jina-embeddings-v2-base-en",
# "api_key": "...", # or set JINA_API_KEY env var
},
})
```
</Accordion>
<Accordion title="IBM WatsonX">
```python
memory = Memory(embedder={
"provider": "watsonx",
"config": {
"model_id": "ibm/slate-30m-english-rtrvr",
"api_key": "your-watsonx-api-key",
"project_id": "your-project-id",
"url": "https://us-south.ml.cloud.ibm.com",
},
})
```
</Accordion>
<Accordion title="مُضمِّن مخصص">
```python
# Pass any callable that takes a list of strings and returns a list of vectors
def my_embedder(texts: list[str]) -> list[list[float]]:
# Your embedding logic here
return [[0.1, 0.2, ...] for _ in texts]
memory = Memory(embedder=my_embedder)
```
</Accordion>
</AccordionGroup>
### مرجع المزودين
| المزود | المفتاح | النموذج النموذجي | ملاحظات |
| :--- | :--- | :--- | :--- |
| OpenAI | `openai` | `text-embedding-3-small` | افتراضي. عيّن `OPENAI_API_KEY`. |
| Ollama | `ollama` | `mxbai-embed-large` | محلي، لا حاجة لمفتاح API. |
| Azure OpenAI | `azure` | `text-embedding-ada-002` | يتطلب `deployment_id`. |
| Google AI | `google-generativeai` | `gemini-embedding-001` | عيّن `GOOGLE_API_KEY`. |
| Google Vertex | `google-vertex` | `gemini-embedding-001` | يتطلب `project_id`. |
| Cohere | `cohere` | `embed-english-v3.0` | دعم قوي متعدد اللغات. |
| VoyageAI | `voyageai` | `voyage-3` | محسّن للاسترجاع. |
| AWS Bedrock | `amazon-bedrock` | `amazon.titan-embed-text-v1` | يستخدم بيانات اعتماد boto3. |
| Hugging Face | `huggingface` | `all-MiniLM-L6-v2` | sentence-transformers محلي. |
| Jina | `jina` | `jina-embeddings-v2-base-en` | عيّن `JINA_API_KEY`. |
| IBM WatsonX | `watsonx` | `ibm/slate-30m-english-rtrvr` | يتطلب `project_id`. |
| Sentence Transformer | `sentence-transformer` | `all-MiniLM-L6-v2` | محلي، لا حاجة لمفتاح API. |
| مخصص | `custom` | -- | يتطلب `embedding_callable`. |
## إعداد LLM
تستخدم الذاكرة LLM لتحليل الحفظ (استنتاج النطاق والفئات والأهمية)، وقرارات التوحيد، وتحليل استعلام الاسترجاع العميق. يمكنك إعداد النموذج المُستخدم.
```python
from crewai import Memory, LLM
# Default: gpt-4o-mini
memory = Memory()
# Use a different OpenAI model
memory = Memory(llm="gpt-4o")
# Use Anthropic
memory = Memory(llm="anthropic/claude-3-haiku-20240307")
# Use Ollama for fully local/private analysis
memory = Memory(llm="ollama/llama3.2")
# Use Google Gemini
memory = Memory(llm="gemini/gemini-2.0-flash")
# Pass a pre-configured LLM instance with custom settings
llm = LLM(model="gpt-4o", temperature=0)
memory = Memory(llm=llm)
```
يتم تهيئة LLM **بشكل كسول** -- يتم إنشاؤه فقط عند الحاجة لأول مرة. هذا يعني أن `Memory()` لا يفشل أبدًا في وقت الإنشاء، حتى لو لم تكن مفاتيح API مُعيّنة. تظهر الأخطاء فقط عند استدعاء LLM فعليًا (مثلاً عند الحفظ بدون نطاق/فئات صريحة، أو أثناء الاسترجاع العميق).
للتشغيل المحلي/الخاص بالكامل، استخدم نموذجًا محليًا لكل من LLM والمُضمِّن:
```python
memory = Memory(
llm="ollama/llama3.2",
embedder={"provider": "ollama", "config": {"model_name": "mxbai-embed-large"}},
)
```
## واجهة التخزين
- **الافتراضي**: LanceDB، مخزّن تحت `./.crewai/memory` (أو `$CREWAI_STORAGE_DIR/memory` إذا تم تعيين متغير البيئة، أو المسار الذي تمرره كـ `storage="path/to/dir"`).
- **واجهة مخصصة**: نفّذ بروتوكول `StorageBackend` (انظر `crewai.memory.storage.backend`) ومرّر مثيلًا إلى `Memory(storage=your_backend)`.
## الاستكشاف
فحص التسلسل الهرمي للنطاقات والفئات والسجلات:
```python
memory.tree() # Formatted tree of scopes and record counts
memory.tree("/project", max_depth=2) # Subtree view
memory.info("/project") # ScopeInfo: record_count, categories, oldest/newest
memory.list_scopes("/") # Immediate child scopes
memory.list_categories() # Category names and counts
memory.list_records(scope="/project/alpha", limit=20) # Records in a scope, newest first
```
## سلوك الفشل
إذا فشل LLM أثناء التحليل (خطأ شبكة، حد معدل، استجابة غير صالحة)، تتدهور الذاكرة بسلاسة:
- **تحليل الحفظ** -- يتم تسجيل تحذير ولا يزال يتم تخزين الذاكرة مع النطاق الافتراضي `/`، فئات فارغة، وأهمية `0.5`.
- **استخراج الذكريات** -- يتم تخزين المحتوى الكامل كذاكرة واحدة حتى لا يُفقد شيء.
- **تحليل الاستعلام** -- يتراجع الاسترجاع إلى اختيار نطاق بسيط وبحث متجهي حتى تستمر في الحصول على نتائج.
لا يتم رفع أي استثناء لفشل التحليل هذه؛ فقط فشل التخزين أو المُضمِّن سيرفع استثناءً.
## ملاحظة حول الخصوصية
يتم إرسال محتوى الذاكرة إلى LLM المُعدّ للتحليل (النطاق/الفئات/الأهمية عند الحفظ، تحليل الاستعلام والاسترجاع العميق الاختياري). للبيانات الحساسة، استخدم LLM محليًا (مثل Ollama) أو تأكد من أن مزودك يلبي متطلبات الامتثال الخاصة بك.
## أحداث الذاكرة
جميع عمليات الذاكرة تُصدر أحداثًا مع `source_type="unified_memory"`. يمكنك الاستماع للتوقيت والأخطاء والمحتوى.
| الحدث | الوصف | الخصائص الرئيسية |
| :---- | :---------- | :------------- |
| **MemoryQueryStartedEvent** | بداية الاستعلام | `query`, `limit` |
| **MemoryQueryCompletedEvent** | نجاح الاستعلام | `query`, `results`, `query_time_ms` |
| **MemoryQueryFailedEvent** | فشل الاستعلام | `query`, `error` |
| **MemorySaveStartedEvent** | بداية الحفظ | `value`, `metadata` |
| **MemorySaveCompletedEvent** | نجاح الحفظ | `value`, `save_time_ms` |
| **MemorySaveFailedEvent** | فشل الحفظ | `value`, `error` |
| **MemoryRetrievalStartedEvent** | بداية استرجاع الوكيل | `task_id` |
| **MemoryRetrievalCompletedEvent** | اكتمال استرجاع الوكيل | `task_id`, `memory_content`, `retrieval_time_ms` |
مثال: مراقبة وقت الاستعلام:
```python
from crewai.events import BaseEventListener, MemoryQueryCompletedEvent
class MemoryMonitor(BaseEventListener):
def setup_listeners(self, crewai_event_bus):
@crewai_event_bus.on(MemoryQueryCompletedEvent)
def on_done(source, event):
if getattr(event, "source_type", None) == "unified_memory":
print(f"Query '{event.query}' completed in {event.query_time_ms:.0f}ms")
```
## استكشاف المشاكل
**الذاكرة لا تستمر؟**
- تأكد من أن مسار التخزين قابل للكتابة (الافتراضي `./.crewai/memory`). مرّر `storage="./your_path"` لاستخدام مجلد مختلف، أو عيّن متغير البيئة `CREWAI_STORAGE_DIR`.
- عند استخدام فريق، تأكد من تعيين `memory=True` أو `memory=Memory(...)`.
**الاسترجاع بطيء؟**
- استخدم `depth="shallow"` لسياق الوكيل الروتيني. احتفظ بـ `depth="deep"` للاستعلامات المعقدة.
- زد `query_analysis_threshold` لتخطي تحليل LLM لمزيد من الاستعلامات.
**أخطاء تحليل LLM في السجلات؟**
- لا تزال الذاكرة تحفظ/تسترجع بإعدادات افتراضية آمنة. تحقق من مفاتيح API وحدود المعدل وتوفر النموذج إذا كنت تريد تحليل LLM كاملاً.
**أخطاء حفظ خلفية في السجلات؟**
- عمليات حفظ الذاكرة تعمل في خيط خلفي. تُصدر الأخطاء كـ `MemorySaveFailedEvent` لكنها لا تعطل الوكيل. تحقق من السجلات للسبب الجذري (عادة مشاكل اتصال LLM أو المُضمِّن).
**تعارضات الكتابة المتزامنة؟**
- عمليات LanceDB مُتسلسلة بقفل مشترك وتُعاد تلقائيًا عند التعارض. هذا يتعامل مع مثيلات `Memory` المتعددة التي تشير إلى نفس قاعدة البيانات (مثل ذاكرة وكيل + ذاكرة فريق). لا حاجة لإجراء.
**تصفح الذاكرة من الطرفية:**
```bash
crewai memory # Opens the TUI browser
crewai memory --storage-path ./my_memory # Point to a specific directory
```
**إعادة تعيين الذاكرة (مثلاً للاختبارات):**
```python
crew.reset_memories(command_type="memory") # Resets unified memory
# Or on a Memory instance:
memory.reset() # All scopes
memory.reset(scope="/project/old") # Only that subtree
```
## مرجع الإعداد
جميع الإعدادات تُمرر كمعاملات كلمة مفتاحية إلى `Memory(...)`. كل معامل له قيمة افتراضية معقولة.
| المعامل | الافتراضي | الوصف |
| :--- | :--- | :--- |
| `llm` | `"gpt-4o-mini"` | LLM للتحليل (اسم نموذج أو مثيل `BaseLLM`). |
| `storage` | `"lancedb"` | واجهة التخزين (`"lancedb"`، سلسلة مسار، أو مثيل `StorageBackend`). |
| `embedder` | `None` (افتراضي OpenAI) | المُضمِّن (قاموس إعداد، دالة قابلة للاستدعاء، أو `None` لافتراضي OpenAI). |
| `recency_weight` | `0.3` | وزن الحداثة في الدرجة المركبة. |
| `semantic_weight` | `0.5` | وزن التشابه الدلالي في الدرجة المركبة. |
| `importance_weight` | `0.2` | وزن الأهمية في الدرجة المركبة. |
| `recency_half_life_days` | `30` | أيام لتنصيف درجة الحداثة (اضمحلال أُسي). |
| `consolidation_threshold` | `0.85` | التشابه الذي يُشغّل فوقه التوحيد عند الحفظ. عيّن إلى `1.0` للتعطيل. |
| `consolidation_limit` | `5` | أقصى عدد سجلات حالية للمقارنة أثناء التوحيد. |
| `default_importance` | `0.5` | الأهمية المُعيّنة عندما لا تُوفَّر ويتم تخطي تحليل LLM. |
| `batch_dedup_threshold` | `0.98` | تشابه جيب التمام لإسقاط النسخ شبه المكررة داخل دفعة `remember_many()`. |
| `confidence_threshold_high` | `0.8` | ثقة الاسترجاع التي تُعاد فوقها النتائج مباشرة. |
| `confidence_threshold_low` | `0.5` | ثقة الاسترجاع التي يُشغّل تحتها استكشاف أعمق. |
| `complex_query_threshold` | `0.7` | للاستعلامات المعقدة، استكشف أعمق تحت هذه الثقة. |
| `exploration_budget` | `1` | عدد جولات الاستكشاف المدفوعة بـ LLM أثناء الاسترجاع العميق. |
| `query_analysis_threshold` | `200` | الاستعلامات الأقصر من هذا (بالأحرف) تتخطى تحليل LLM أثناء الاسترجاع العميق. |

View File

@@ -0,0 +1,155 @@
---
title: التخطيط
description: تعرّف على كيفية إضافة التخطيط إلى طاقم CrewAI وتحسين أدائه.
icon: ruler-combined
mode: "wide"
---
## نظرة عامة
تتيح لك ميزة التخطيط في CrewAI إضافة قدرة التخطيط إلى طاقمك. عند تفعيلها، قبل كل تكرار للطاقم،
يتم إرسال جميع معلومات الطاقم إلى AgentPlanner الذي يخطط للمهام خطوة بخطوة، ويُضاف هذا المخطط إلى وصف كل مهمة.
### استخدام ميزة التخطيط
البدء بميزة التخطيط سهل جدًا، الخطوة الوحيدة المطلوبة هي إضافة `planning=True` إلى طاقمك:
<CodeGroup>
```python Code
from crewai import Crew, Agent, Task, Process
# تجميع طاقمك مع قدرات التخطيط
my_crew = Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
planning=True,
)
```
</CodeGroup>
من هذه النقطة فصاعدًا، سيكون التخطيط مفعّلًا في طاقمك، وسيتم تخطيط المهام قبل كل تكرار.
<Warning>
عند تفعيل التخطيط، سيستخدم CrewAI `gpt-4o-mini` كنموذج LLM افتراضي للتخطيط، مما يتطلب مفتاح API صالحًا من OpenAI. نظرًا لأن وكلاءك قد يستخدمون نماذج LLM مختلفة، فقد يسبب ذلك ارتباكًا إذا لم يكن لديك مفتاح OpenAI API مهيأ أو إذا كنت تواجه سلوكًا غير متوقع متعلقًا باستدعاءات LLM API.
</Warning>
#### LLM التخطيط
يمكنك الآن تحديد نموذج LLM الذي سيُستخدم لتخطيط المهام.
عند تشغيل مثال الحالة الأساسية، سترى شيئًا مشابهًا للمخرجات أدناه، والتي تمثل مخرجات `AgentPlanner`
المسؤول عن إنشاء المنطق التدريجي لإضافته إلى مهام الوكلاء.
<CodeGroup>
```python Code
from crewai import Crew, Agent, Task, Process
# تجميع طاقمك مع قدرات التخطيط ونموذج LLM مخصص
my_crew = Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
planning=True,
planning_llm="gpt-4o"
)
# تشغيل الطاقم
my_crew.kickoff()
```
```markdown Result
[2024-07-15 16:49:11][INFO]: Planning the crew execution
**Step-by-Step Plan for Task Execution**
**Task Number 1: Conduct a thorough research about AI LLMs**
**Agent:** AI LLMs Senior Data Researcher
**Agent Goal:** Uncover cutting-edge developments in AI LLMs
**Task Expected Output:** A list with 10 bullet points of the most relevant information about AI LLMs
**Task Tools:** None specified
**Agent Tools:** None specified
**Step-by-Step Plan:**
1. **Define Research Scope:**
- Determine the specific areas of AI LLMs to focus on, such as advancements in architecture, use cases, ethical considerations, and performance metrics.
2. **Identify Reliable Sources:**
- List reputable sources for AI research, including academic journals, industry reports, conferences (e.g., NeurIPS, ACL), AI research labs (e.g., OpenAI, Google AI), and online databases (e.g., IEEE Xplore, arXiv).
3. **Collect Data:**
- Search for the latest papers, articles, and reports published in 2024 and early 2025.
- Use keywords like "Large Language Models 2025", "AI LLM advancements", "AI ethics 2025", etc.
4. **Analyze Findings:**
- Read and summarize the key points from each source.
- Highlight new techniques, models, and applications introduced in the past year.
5. **Organize Information:**
- Categorize the information into relevant topics (e.g., new architectures, ethical implications, real-world applications).
- Ensure each bullet point is concise but informative.
6. **Create the List:**
- Compile the 10 most relevant pieces of information into a bullet point list.
- Review the list to ensure clarity and relevance.
**Expected Output:**
A list with 10 bullet points of the most relevant information about AI LLMs.
---
**Task Number 2: Review the context you got and expand each topic into a full section for a report**
**Agent:** AI LLMs Reporting Analyst
**Agent Goal:** Create detailed reports based on AI LLMs data analysis and research findings
**Task Expected Output:** A fully fledged report with the main topics, each with a full section of information. Formatted as markdown without '```'
**Task Tools:** None specified
**Agent Tools:** None specified
**Step-by-Step Plan:**
1. **Review the Bullet Points:**
- Carefully read through the list of 10 bullet points provided by the AI LLMs Senior Data Researcher.
2. **Outline the Report:**
- Create an outline with each bullet point as a main section heading.
- Plan sub-sections under each main heading to cover different aspects of the topic.
3. **Research Further Details:**
- For each bullet point, conduct additional research if necessary to gather more detailed information.
- Look for case studies, examples, and statistical data to support each section.
4. **Write Detailed Sections:**
- Expand each bullet point into a comprehensive section.
- Ensure each section includes an introduction, detailed explanation, examples, and a conclusion.
- Use markdown formatting for headings, subheadings, lists, and emphasis.
5. **Review and Edit:**
- Proofread the report for clarity, coherence, and correctness.
- Make sure the report flows logically from one section to the next.
- Format the report according to markdown standards.
6. **Finalize the Report:**
- Ensure the report is complete with all sections expanded and detailed.
- Double-check formatting and make any necessary adjustments.
**Expected Output:**
A fully fledged report with the main topics, each with a full section of information. Formatted as markdown without '```'.
```
</CodeGroup>

View File

@@ -0,0 +1,66 @@
---
title: العمليات
description: دليل تفصيلي حول إدارة سير العمل من خلال العمليات في CrewAI، مع تفاصيل التنفيذ المحدّثة.
icon: bars-staggered
mode: "wide"
---
## نظرة عامة
<Tip>
تنسّق العمليات تنفيذ المهام بواسطة الوكلاء، على غرار إدارة المشاريع في الفرق البشرية.
تضمن هذه العمليات توزيع المهام وتنفيذها بكفاءة، وفقًا لاستراتيجية محددة مسبقًا.
</Tip>
## تنفيذات العمليات
- **تسلسلي**: ينفذ المهام بالتتابع، مما يضمن إكمال المهام بتقدم منظم.
- **هرمي**: ينظم المهام في تسلسل إداري هرمي، حيث يتم تفويض المهام وتنفيذها بناءً على سلسلة أوامر منظمة. يجب تحديد نموذج لغة المدير (`manager_llm`) أو وكيل مدير مخصص (`manager_agent`) في الطاقم لتفعيل العملية الهرمية، مما يسهّل إنشاء وإدارة المهام من قبل المدير.
## دور العمليات في العمل الجماعي
تُمكّن العمليات الوكلاء الأفراد من العمل كوحدة متماسكة، مما يبسّط جهودهم لتحقيق أهداف مشتركة بكفاءة وتناسق.
## تعيين العمليات للطاقم
لتعيين عملية لطاقم، حدد نوع العملية عند إنشاء الطاقم لتعيين استراتيجية التنفيذ. للعملية الهرمية، تأكد من تحديد `manager_llm` أو `manager_agent` لوكيل المدير.
```python
from crewai import Crew, Process
# مثال: إنشاء طاقم بعملية تسلسلية
crew = Crew(
agents=my_agents,
tasks=my_tasks,
process=Process.sequential
)
# مثال: إنشاء طاقم بعملية هرمية
# تأكد من توفير manager_llm أو manager_agent
crew = Crew(
agents=my_agents,
tasks=my_tasks,
process=Process.hierarchical,
manager_llm="gpt-4o"
# أو
# manager_agent=my_manager_agent
)
```
**ملاحظة:** تأكد من تعريف `my_agents` و `my_tasks` قبل إنشاء كائن `Crew`، وللعملية الهرمية، يُعد `manager_llm` أو `manager_agent` مطلوبًا أيضًا.
## العملية التسلسلية
تعكس هذه الطريقة سير عمل الفريق الديناميكي، وتتقدم عبر المهام بطريقة مدروسة ومنهجية. يتبع تنفيذ المهام الترتيب المحدد مسبقًا في قائمة المهام، حيث يعمل ناتج مهمة واحدة كسياق للمهمة التالية.
لتخصيص سياق المهمة، استخدم معامل `context` في فئة `Task` لتحديد المخرجات التي يجب استخدامها كسياق للمهام اللاحقة.
## العملية الهرمية
تحاكي التسلسل الهرمي المؤسسي، حيث يسمح CrewAI بتحديد وكيل مدير مخصص أو إنشاء واحد تلقائيًا، مما يتطلب تحديد نموذج لغة المدير (`manager_llm`). يشرف هذا الوكيل على تنفيذ المهام، بما في ذلك التخطيط والتفويض والتحقق. لا يتم تعيين المهام مسبقًا؛ يخصص المدير المهام للوكلاء بناءً على قدراتهم، ويراجع المخرجات، ويقيّم اكتمال المهام.
## فئة Process: نظرة عامة مفصلة
تم تنفيذ فئة `Process` كتعداد (`Enum`)، مما يضمن أمان الأنواع ويقيّد قيم العملية على الأنواع المحددة (`sequential`، `hierarchical`).
## الخلاصة
التعاون المنظم الذي تسهّله العمليات داخل CrewAI ضروري لتمكين العمل الجماعي المنهجي بين الوكلاء.
تم تحديث هذه الوثائق لتعكس أحدث الميزات والتحسينات، مما يضمن وصول المستخدمين إلى أحدث المعلومات وأكثرها شمولاً.

View File

@@ -0,0 +1,162 @@
---
title: بنية الإنتاج
description: أفضل الممارسات لبناء تطبيقات ذكاء اصطناعي جاهزة للإنتاج مع CrewAI
icon: server
mode: "wide"
---
# عقلية التدفق أولاً
عند بناء تطبيقات ذكاء اصطناعي إنتاجية مع CrewAI، **نوصي بالبدء بتدفق (Flow)**.
بينما يمكن تشغيل أطقم أو وكلاء فرديين، فإن تغليفهم في تدفق يوفر الهيكل اللازم لتطبيق متين وقابل للتوسع.
## لماذا التدفقات؟
1. **إدارة الحالة**: توفر التدفقات طريقة مدمجة لإدارة الحالة عبر مراحل مختلفة من تطبيقك. هذا ضروري لتمرير البيانات بين الأطقم والحفاظ على السياق ومعالجة مدخلات المستخدم.
2. **التحكم**: تتيح لك التدفقات تحديد مسارات تنفيذ دقيقة، بما في ذلك الحلقات والشرطيات ومنطق التفريع. هذا أساسي لمعالجة الحالات الاستثنائية وضمان سلوك تطبيقك بشكل متوقع.
3. **المراقبة**: توفر التدفقات هيكلًا واضحًا يسهّل تتبع التنفيذ وتصحيح الأخطاء ومراقبة الأداء. نوصي باستخدام [تتبع CrewAI](/ar/observability/tracing) للحصول على رؤى تفصيلية. ما عليك سوى تشغيل `crewai login` لتفعيل ميزات المراقبة المجانية.
## البنية
يبدو تطبيق CrewAI الإنتاجي النموذجي هكذا:
```mermaid
graph TD
Start((Start)) --> Flow[Flow Orchestrator]
Flow --> State{State Management}
State --> Step1[Step 1: Data Gathering]
Step1 --> Crew1[Research Crew]
Crew1 --> State
State --> Step2{Condition Check}
Step2 -- "Valid" --> Step3[Step 3: Execution]
Step3 --> Crew2[Action Crew]
Step2 -- "Invalid" --> End((End))
Crew2 --> End
```
### 1. فئة التدفق
فئة `Flow` هي نقطة الدخول. تحدد مخطط الحالة والطرق التي تنفذ منطقك.
```python
from crewai.flow.flow import Flow, listen, start
from pydantic import BaseModel
class AppState(BaseModel):
user_input: str = ""
research_results: str = ""
final_report: str = ""
class ProductionFlow(Flow[AppState]):
@start()
def gather_input(self):
# ... منطق الحصول على المدخلات ...
pass
@listen(gather_input)
def run_research_crew(self):
# ... تشغيل طاقم ...
pass
```
### 2. إدارة الحالة
استخدم نماذج Pydantic لتعريف حالتك. يضمن هذا أمان الأنواع ويوضح البيانات المتاحة في كل مرحلة.
- **اجعلها بسيطة**: خزّن فقط ما تحتاجه للاستمرار بين المراحل.
- **استخدم بيانات منظمة**: تجنب القواميس غير المنظمة قدر الإمكان.
### 3. الأطقم كوحدات عمل
فوّض المهام المعقدة إلى الأطقم. يجب أن يكون الطاقم مركّزًا على هدف محدد (مثل "البحث في موضوع"، "كتابة مقال مدونة").
- **لا تبالغ في هندسة الأطقم**: اجعلها مركّزة.
- **مرر الحالة بشكل صريح**: مرر البيانات الضرورية من حالة التدفق إلى مدخلات الطاقم.
```python
@listen(gather_input)
def run_research_crew(self):
crew = ResearchCrew()
result = crew.kickoff(inputs={"topic": self.state.user_input})
self.state.research_results = result.raw
```
## عناصر التحكم الأولية
استفد من عناصر التحكم الأولية في CrewAI لإضافة المتانة والتحكم إلى أطقمك.
### 1. حواجز المهام
استخدم [حواجز المهام](/ar/concepts/tasks#task-guardrails) للتحقق من مخرجات المهام قبل قبولها. يضمن هذا أن وكلاءك ينتجون نتائج عالية الجودة.
```python
def validate_content(result: TaskOutput) -> Tuple[bool, Any]:
if len(result.raw) < 100:
return (False, "Content is too short. Please expand.")
return (True, result.raw)
task = Task(
...,
guardrail=validate_content
)
```
### 2. المخرجات المنظمة
استخدم دائمًا المخرجات المنظمة (`output_pydantic` أو `output_json`) عند تمرير البيانات بين المهام أو إلى تطبيقك. يمنع هذا أخطاء التحليل ويضمن أمان الأنواع.
```python
class ResearchResult(BaseModel):
summary: str
sources: List[str]
task = Task(
...,
output_pydantic=ResearchResult
)
```
### 3. خطافات LLM
استخدم [خطافات LLM](/ar/learn/llm-hooks) لفحص أو تعديل الرسائل قبل إرسالها إلى LLM، أو لتنقية الاستجابات.
```python
@before_llm_call
def log_request(context):
print(f"Agent {context.agent.role} is calling the LLM...")
```
## أنماط النشر
عند نشر تدفقك، ضع في اعتبارك ما يلي:
### CrewAI Enterprise
أسهل طريقة لنشر تدفقك هي استخدام CrewAI Enterprise. تتعامل مع البنية التحتية والمصادقة والمراقبة نيابة عنك.
راجع [دليل النشر](https://docs-platform.crewai.com/platform/ar/guides/deploy-to-amp) للبدء.
```bash
crewai deploy create
```
### التنفيذ غير المتزامن
للمهام طويلة التشغيل، استخدم `kickoff_async` لتجنب حظر واجهتك البرمجية.
### الاستمرارية
استخدم مزيّن `@persist` لحفظ حالة تدفقك في قاعدة بيانات. يتيح لك هذا استئناف التنفيذ إذا تعطلت العملية أو إذا كنت بحاجة لانتظار مدخلات بشرية.
```python
@persist
class ProductionFlow(Flow[AppState]):
# ...
```
افتراضيًا، يستأنف `@persist` تدفقًا عند توفير `kickoff(inputs={"id": <uuid>})`، مما يمدّ نفس تاريخ `flow_uuid`. لـ **تفرع** تدفق مستمر إلى نسبٍ جديد — ترطيب الحالة من تشغيل سابق ولكن الكتابة تحت `state.id` جديد — مرّر `restore_from_state_id`:
```python
flow.kickoff(restore_from_state_id="<previous-run-state-id>")
```
يحصل التشغيل الجديد على `state.id` جديد (مولّد تلقائيًا، أو `inputs["id"]` إذا تم تثبيته) لذا لا تمتد كتابات `@persist` الخاصة به إلى تاريخ المصدر. الجمع مع `from_checkpoint` يطلق `ValueError`؛ اختر مصدر ترطيب واحدًا.
## الخلاصة
- **ابدأ بتدفق.**
- **حدد حالة واضحة.**
- **استخدم الأطقم للمهام المعقدة.**
- **انشر مع API واستمرارية.**

View File

@@ -0,0 +1,148 @@
---
title: الاستدلال
description: "تعرّف على كيفية تفعيل واستخدام استدلال الوكيل لتحسين تنفيذ المهام."
icon: brain
mode: "wide"
---
## نظرة عامة
استدلال الوكيل هو ميزة تتيح للوكلاء التأمل في المهمة وإنشاء خطة قبل التنفيذ. يساعد هذا الوكلاء على التعامل مع المهام بشكل أكثر منهجية ويضمن استعدادهم لأداء العمل المطلوب.
## الاستخدام
لتفعيل الاستدلال لوكيل، ما عليك سوى تعيين `reasoning=True` عند إنشاء الوكيل:
```python
from crewai import Agent
agent = Agent(
role="Data Analyst",
goal="Analyze complex datasets and provide insights",
backstory="You are an experienced data analyst with expertise in finding patterns in complex data.",
reasoning=True, # تفعيل الاستدلال
max_reasoning_attempts=3 # اختياري: تعيين حد أقصى لمحاولات الاستدلال
)
```
## كيف يعمل
عند تفعيل الاستدلال، قبل تنفيذ المهمة، سيقوم الوكيل بما يلي:
1. التأمل في المهمة وإنشاء خطة مفصلة
2. تقييم ما إذا كان مستعدًا لتنفيذ المهمة
3. تحسين الخطة حسب الحاجة حتى يصبح مستعدًا أو يصل إلى max_reasoning_attempts
4. حقن خطة الاستدلال في وصف المهمة قبل التنفيذ
تساعد هذه العملية الوكيل على تقسيم المهام المعقدة إلى خطوات يمكن إدارتها وتحديد التحديات المحتملة قبل البدء.
## خيارات التهيئة
<ParamField body="reasoning" type="bool" default="False">
تفعيل أو تعطيل الاستدلال
</ParamField>
<ParamField body="max_reasoning_attempts" type="int" default="None">
الحد الأقصى لعدد المحاولات لتحسين الخطة قبل المتابعة بالتنفيذ. إذا كانت القيمة None (الافتراضي)، سيستمر الوكيل في التحسين حتى يصبح مستعدًا.
</ParamField>
## مثال
إليك مثالًا كاملًا:
```python
from crewai import Agent, Task, Crew
# إنشاء وكيل مع تفعيل الاستدلال
analyst = Agent(
role="Data Analyst",
goal="Analyze data and provide insights",
backstory="You are an expert data analyst.",
reasoning=True,
max_reasoning_attempts=3 # اختياري: تعيين حد لمحاولات الاستدلال
)
# إنشاء مهمة
analysis_task = Task(
description="Analyze the provided sales data and identify key trends.",
expected_output="A report highlighting the top 3 sales trends.",
agent=analyst
)
# إنشاء طاقم وتشغيل المهمة
crew = Crew(agents=[analyst], tasks=[analysis_task])
result = crew.kickoff()
print(result)
```
## معالجة الأخطاء
صُممت عملية الاستدلال لتكون متينة، مع معالجة أخطاء مدمجة. إذا حدث خطأ أثناء الاستدلال، سيتابع الوكيل تنفيذ المهمة بدون خطة الاستدلال. يضمن هذا إمكانية تنفيذ المهام حتى في حالة فشل عملية الاستدلال.
إليك كيفية التعامل مع الأخطاء المحتملة في الكود الخاص بك:
```python
from crewai import Agent, Task
import logging
# إعداد التسجيل لالتقاط أي أخطاء في الاستدلال
logging.basicConfig(level=logging.INFO)
# إنشاء وكيل مع تفعيل الاستدلال
agent = Agent(
role="Data Analyst",
goal="Analyze data and provide insights",
reasoning=True,
max_reasoning_attempts=3
)
# إنشاء مهمة
task = Task(
description="Analyze the provided sales data and identify key trends.",
expected_output="A report highlighting the top 3 sales trends.",
agent=agent
)
# تنفيذ المهمة
# إذا حدث خطأ أثناء الاستدلال، سيتم تسجيله وسيستمر التنفيذ
result = agent.execute_task(task)
```
## مثال على مخرجات الاستدلال
إليك مثالًا على شكل خطة الاستدلال لمهمة تحليل البيانات:
```
Task: Analyze the provided sales data and identify key trends.
Reasoning Plan:
I'll analyze the sales data to identify the top 3 trends.
1. Understanding of the task:
I need to analyze sales data to identify key trends that would be valuable for business decision-making.
2. Key steps I'll take:
- First, I'll examine the data structure to understand what fields are available
- Then I'll perform exploratory data analysis to identify patterns
- Next, I'll analyze sales by time periods to identify temporal trends
- I'll also analyze sales by product categories and customer segments
- Finally, I'll identify the top 3 most significant trends
3. Approach to challenges:
- If the data has missing values, I'll decide whether to fill or filter them
- If the data has outliers, I'll investigate whether they're valid data points or errors
- If trends aren't immediately obvious, I'll apply statistical methods to uncover patterns
4. Use of available tools:
- I'll use data analysis tools to explore and visualize the data
- I'll use statistical tools to identify significant patterns
- I'll use knowledge retrieval to access relevant information about sales analysis
5. Expected outcome:
A concise report highlighting the top 3 sales trends with supporting evidence from the data.
READY: I am ready to execute the task.
```
تساعد خطة الاستدلال هذه الوكيل على تنظيم نهجه تجاه المهمة، والنظر في التحديات المحتملة، وضمان تقديم المخرجات المتوقعة.

View File

@@ -0,0 +1,373 @@
---
title: المهارات
description: حزم المهارات المبنية على نظام الملفات التي تحقن خبرة المجال والتعليمات في إرشادات الوكلاء.
icon: bolt
mode: "wide"
---
## نظرة عامة
المهارات هي مجلدات مستقلة توفر للوكلاء **تعليمات وإرشادات ومواد مرجعية خاصة بالمجال**. تُعرّف كل مهارة بملف `SKILL.md` يحتوي على بيانات وصفية YAML ومحتوى Markdown.
عند التفعيل، يتم حقن تعليمات المهارة مباشرة في إرشادات مهمة الوكيل — مما يمنح الوكيل خبرة دون الحاجة لأي تغييرات في الكود.
<Note type="info" title="المهارات مقابل الأدوات — التمييز الأساسي">
**المهارات ليست أدوات.** هذه هي نقطة الارتباك الأكثر شيوعًا.
- **المهارات** تحقن *تعليمات وسياق* في إرشادات الوكيل. تخبر الوكيل *كيف يفكر* في مشكلة ما.
- **الأدوات** تمنح الوكيل *دوال قابلة للاستدعاء* لاتخاذ إجراءات (البحث، قراءة الملفات، استدعاء APIs).
غالبًا ما تحتاج **كليهما**: مهارات للخبرة، وأدوات للإجراء. يتم تكوينهما بشكل مستقل ويُكمّلان بعضهما.
</Note>
---
## البداية السريعة
### 1. إنشاء مهارة باستخدام سطر الأوامر (CLI)
واجهة سطر الأوامر هي الطريقة المدعومة لإنشاء مهارة — فهي تُنشئ لك هيكل المجلد وملف `SKILL.md` صالحًا:
```shell Terminal
crewai skill create code-review
```
داخل مشروع طاقم (حيث يوجد `pyproject.toml`) يُنشئ هذا الأمر `./skills/code-review/`؛ وخارج المشروع يُنشئ `./code-review/` في المجلد الحالي (يمكنك فرض هذا السلوك باستخدام `--no-project`):
```
skills/
└── code-review/
├── SKILL.md # Required — instructions (pre-filled template)
├── references/ # Optional — reference docs
├── scripts/ # Optional — executable scripts
└── assets/ # Optional — static files
```
### 2. كتابة SKILL.md الخاص بك
```markdown
---
name: code-review
description: Guidelines for conducting thorough code reviews with focus on security and performance.
metadata:
author: your-team
version: "1.0"
---
## إرشادات مراجعة الكود
عند مراجعة الكود، اتبع قائمة التحقق هذه:
1. **الأمان**: تحقق من ثغرات الحقن وتجاوز المصادقة وكشف البيانات
2. **الأداء**: ابحث عن استعلامات N+1 والتخصيصات غير الضرورية والاستدعاءات المحظورة
3. **القابلية للقراءة**: تأكد من وضوح التسمية والتعليقات المناسبة والأسلوب المتسق
4. **الاختبارات**: تحقق من تغطية اختبار كافية للوظائف الجديدة
### مستويات الخطورة
- **حرج**: ثغرات أمنية، مخاطر فقدان البيانات → حظر الدمج
- **رئيسي**: مشاكل أداء، أخطاء منطقية → طلب تغييرات
- **ثانوي**: مسائل أسلوبية، اقتراحات تسمية → الموافقة مع تعليقات
```
### 3. ربطها بوكيل
```python
from crewai import Agent
from crewai_tools import GithubSearchTool, FileReadTool
reviewer = Agent(
role="Senior Code Reviewer",
goal="Review pull requests for quality and security issues",
backstory="Staff engineer with expertise in secure coding practices.",
skills=["./skills"], # يحقن إرشادات المراجعة
tools=[GithubSearchTool(), FileReadTool()], # يسمح للوكيل بقراءة الكود
)
```
الوكيل الآن لديه **خبرة** (من المهارة) و**قدرات** (من الأدوات) معًا.
---
## المهارات + الأدوات: العمل معًا
إليك أنماط شائعة توضح كيف تُكمّل المهارات والأدوات بعضهما:
### النمط 1: مهارات فقط (خبرة المجال، بدون إجراءات مطلوبة)
استخدم عندما يحتاج الوكيل لتعليمات محددة لكن لا يحتاج لاستدعاء خدمات خارجية:
```python
agent = Agent(
role="Technical Writer",
goal="Write clear API documentation",
backstory="Expert technical writer",
skills=["./skills/api-docs-style"], # إرشادات وقوالب الكتابة
# لا حاجة لأدوات — الوكيل يكتب بناءً على السياق المقدم
)
```
### النمط 2: أدوات فقط (إجراءات، بدون خبرة خاصة)
استخدم عندما يحتاج الوكيل لاتخاذ إجراءات لكن لا يحتاج لتعليمات مجال محددة:
```python
from crewai_tools import SerperDevTool, ScrapeWebsiteTool
agent = Agent(
role="Web Researcher",
goal="Find information about a topic",
backstory="Skilled at finding information online",
tools=[SerperDevTool(), ScrapeWebsiteTool()], # يمكنه البحث والاستخراج
# لا حاجة لمهارات — البحث العام لا يحتاج إرشادات خاصة
)
```
### النمط 3: مهارات + أدوات (خبرة وإجراءات)
النمط الأكثر شيوعًا في العالم الحقيقي. المهارة توفر *كيف* تقترب من العمل؛ الأدوات توفر *ما* يمكن للوكيل فعله:
```python
from crewai_tools import SerperDevTool, FileReadTool, CodeInterpreterTool
analyst = Agent(
role="Security Analyst",
goal="Audit infrastructure for vulnerabilities",
backstory="Expert in cloud security and compliance",
skills=["./skills/security-audit"], # منهجية وقوائم تحقق التدقيق
tools=[
SerperDevTool(), # البحث عن ثغرات معروفة
FileReadTool(), # قراءة ملفات التكوين
CodeInterpreterTool(), # تشغيل سكربتات التحليل
],
)
```
### النمط 4: مهارات + MCP
المهارات تعمل مع خوادم MCP بنفس الطريقة التي تعمل بها مع الأدوات:
```python
agent = Agent(
role="Data Analyst",
goal="Analyze customer data and generate reports",
backstory="Expert data analyst with strong statistical background",
skills=["./skills/data-analysis"], # منهجية التحليل
mcps=["https://data-warehouse.example.com/sse"], # وصول بيانات عن بُعد
)
```
### النمط 5: مهارات + تطبيقات
المهارات يمكن أن توجّه كيف يستخدم الوكيل تكاملات المنصة:
```python
agent = Agent(
role="Customer Support Agent",
goal="Respond to customer inquiries professionally",
backstory="Experienced support representative",
skills=["./skills/support-playbook"], # قوالب الردود وقواعد التصعيد
apps=["gmail", "zendesk"], # يمكنه إرسال رسائل بريد وتحديث التذاكر
)
```
---
## إنشاء المهارات ونشرها وتثبيتها
للمهارات دورة حياة كاملة تُدار عبر واجهة سطر الأوامر: **أنشئها باستخدام `crewai skill create`، وانشرها باستخدام `crewai skill publish`** — إنشاء المجلدات يدويًا يصلح للتجارب المحلية، لكن واجهة سطر الأوامر هي سير العمل المقصود، وهي تحافظ على صحة هيكل المهارة وبياناتها الوصفية.
### الإنشاء
```shell Terminal
crewai skill create my-skill
```
يُنشئ هذا الأمر المجلد (داخل `./skills/` في مشروع الطاقم) مع قالب `SKILL.md`، بالإضافة إلى مجلدات فارغة `scripts/` و `references/` و `assets/`. عدّل `SKILL.md` لتعريف التعليمات.
### النشر
نفّذ الأمر من داخل مجلد المهارة (حيث يوجد `SKILL.md`):
```shell Terminal
cd skills/my-skill
crewai skill publish
```
يقرأ النشر الحقول `name` و `description` و `metadata.version` من البيانات الوصفية في مقدمة `SKILL.md` ويدفع المهارة إلى سجل CrewAI. **المهارات المنشورة تكون دائمًا مقيّدة بنطاق مؤسستك** — مثل الأدوات، لا يستطيع رؤيتها وتثبيتها إلا أعضاء المؤسسة الناشرة؛ ولا توجد رؤية عامة. أعلام مفيدة:
| العلم | التأثير |
| :--- | :--- |
| `--org <slug>` | النشر تحت مؤسسة محددة (يتجاوز الإعدادات). |
| `--force` | تخطي التحقق من حالة git (تغييرات غير مُثبتة، إلخ). |
### التثبيت
ثبّت مهارة منشورة عبر مرجعها `@org/name`:
```shell Terminal
crewai skill install @acme/code-review
```
داخل مشروع الطاقم تُثبَّت المهارة في `./skills/{name}/`؛ وخارج المشروع تذهب إلى ذاكرة التخزين المؤقتة المشتركة في `~/.crewai/skills/{org}/{name}/`.
يمكن للوكلاء أيضًا الإشارة إلى مهارات السجل مباشرة — يتم حلّها من ذاكرة التخزين المؤقتة المحلية (أو من مجلد `skills/` في المشروع) وقت التشغيل:
```python
agent = Agent(
role="Senior Code Reviewer",
goal="Review pull requests for quality and security issues",
backstory="Staff engineer with expertise in secure coding practices.",
skills=["@acme/code-review"], # registry ref, resolved locally
)
```
### عرض القائمة
```shell Terminal
crewai skill list
```
يعرض المهارات المثبّتة من مجلد المشروع `./skills/` ومن ذاكرة التخزين المؤقتة العامة معًا، مع إصداراتها ومساراتها.
---
## المهارات على مستوى الطاقم
يمكن تعيين المهارات على الطاقم لتُطبّق على **جميع الوكلاء**:
```python
from crewai import Crew
crew = Crew(
agents=[researcher, writer, reviewer],
tasks=[research_task, write_task, review_task],
skills=["./skills"], # جميع الوكلاء يحصلون على هذه المهارات
)
```
المهارات على مستوى الوكيل لها الأولوية — إذا تم اكتشاف نفس المهارة في كلا المستويين، يتم استخدام نسخة الوكيل.
---
## تنسيق SKILL.md
```markdown
---
name: my-skill
description: وصف قصير لما تفعله هذه المهارة ومتى تُستخدم.
license: Apache-2.0 # اختياري
compatibility: crewai>=0.1.0 # اختياري
metadata: # اختياري
author: your-name
version: "1.0"
allowed-tools: web-search file-read # اختياري، تجريبي
---
التعليمات للوكيل تُكتب هنا. يتم حقن محتوى Markdown هذا
في إرشادات الوكيل عند تفعيل المهارة.
```
### حقول البيانات الوصفية
| الحقل | مطلوب | الوصف |
| :-------------- | :------- | :----------------------------------------------------------------------- |
| `name` | نعم | 1-64 حرف. أحرف صغيرة أبجدية رقمية وشرطات. يجب أن يطابق اسم المجلد. |
| `description` | نعم | 1-1024 حرف. يصف ما تفعله المهارة ومتى تُستخدم. |
| `license` | لا | اسم الترخيص أو مرجع لملف ترخيص مضمّن. |
| `compatibility` | لا | حد أقصى 500 حرف. متطلبات البيئة (منتجات، حزم، شبكة). |
| `metadata` | لا | تعيين مفتاح-قيمة نصي عشوائي. |
| `allowed-tools` | لا | قائمة أدوات معتمدة مسبقًا مفصولة بمسافات. تجريبي. |
---
## هيكل المجلد
```
my-skill/
├── SKILL.md # مطلوب — البيانات الوصفية + التعليمات
├── scripts/ # اختياري — سكربتات قابلة للتنفيذ
├── references/ # اختياري — مستندات مرجعية
└── assets/ # اختياري — ملفات ثابتة (إعدادات، بيانات)
```
يجب أن يتطابق اسم المجلد مع حقل `name` في `SKILL.md`. مجلدات `scripts/` و `references/` و `assets/` متاحة في مسار المهارة `path` للوكلاء الذين يحتاجون للإشارة إلى الملفات مباشرة.
---
## المهارات المحمّلة مسبقًا
للمزيد من التحكم، يمكنك اكتشاف المهارات وتفعيلها برمجيًا:
```python
from pathlib import Path
from crewai.skills import discover_skills, activate_skill
# اكتشاف جميع المهارات في مجلد
skills = discover_skills(Path("./skills"))
# تفعيلها (تحميل محتوى SKILL.md الكامل)
activated = [activate_skill(s) for s in skills]
# تمرير إلى وكيل
agent = Agent(
role="Researcher",
goal="Find relevant information",
backstory="An expert researcher.",
skills=activated,
)
```
---
## كيف يتم تحميل المهارات
تستخدم المهارات **الكشف التدريجي** — تحمّل فقط ما هو مطلوب في كل مرحلة:
| المرحلة | ما يتم تحميله | متى |
| :--------- | :------------------------------------ | :------------------ |
| الاكتشاف | الاسم، الوصف، حقول البيانات الوصفية | `discover_skills()` |
| التفعيل | نص محتوى SKILL.md الكامل | `activate_skill()` |
أثناء التنفيذ العادي للوكيل (تمرير مسارات المجلدات عبر `skills=["./skills"]`)، يتم اكتشاف المهارات وتفعيلها تلقائيًا. التحميل التدريجي مهم فقط عند استخدام الواجهة البرمجية.
---
## المهارات مقابل المعرفة
كلا المهارات والمعرفة تُعدّل إرشادات الوكيل، لكنهما يخدمان أغراضًا مختلفة:
| الجانب | المهارات | المعرفة |
| :--- | :--- | :--- |
| **ما توفره** | تعليمات، إجراءات، إرشادات | حقائق، بيانات، معلومات |
| **كيف تُخزّن** | ملفات Markdown (SKILL.md) | مُضمّنة في مخزن متجهي (ChromaDB) |
| **كيف تُسترجع** | يتم حقن المحتوى الكامل في الإرشادات | البحث الدلالي يجد الأجزاء ذات الصلة |
| **الأفضل لـ** | المنهجيات، قوائم التحقق، أدلة الأسلوب | مستندات الشركة، معلومات المنتج، بيانات مرجعية |
| **يُعيّن عبر** | `skills=["./skills"]` | `knowledge_sources=[source]` |
**القاعدة العامة:** إذا كان الوكيل يحتاج لاتباع *عملية*، استخدم مهارة. إذا كان يحتاج للرجوع إلى *بيانات*، استخدم المعرفة.
---
## الأسئلة الشائعة
<AccordionGroup>
<Accordion title="هل أحتاج لتعيين المهارات والأدوات معًا؟">
يعتمد على حالة الاستخدام. المهارات والأدوات **مستقلتان** — يمكنك استخدام أيّ منهما أو كليهما أو لا شيء.
- **مهارات فقط**: عندما يحتاج الوكيل خبرة لكن لا يحتاج إجراءات خارجية (مثال: الكتابة بإرشادات أسلوبية)
- **أدوات فقط**: عندما يحتاج الوكيل إجراءات لكن لا يحتاج منهجية خاصة (مثال: بحث بسيط على الويب)
- **كليهما**: عندما يحتاج الوكيل خبرة وإجراءات (مثال: تدقيق أمني بقوائم تحقق محددة وقدرة على فحص الكود)
</Accordion>
<Accordion title="هل توفر المهارات أدوات تلقائيًا؟">
**لا.** حقل `allowed-tools` في SKILL.md هو بيانات وصفية تجريبية فقط — لا يُنشئ أو يحقن أي أدوات. يجب عليك دائمًا تعيين الأدوات بشكل منفصل عبر `tools=[]` أو `mcps=[]` أو `apps=[]`.
</Accordion>
<Accordion title="ماذا يحدث إذا عيّنت نفس المهارة على كل من الوكيل والطاقم؟">
المهارة على مستوى الوكيل لها الأولوية. يتم إزالة التكرار حسب الاسم — مهارات الوكيل تُعالج أولاً، لذا إذا ظهر نفس اسم المهارة في كلا المستويين، تُستخدم نسخة الوكيل.
</Accordion>
<Accordion title="ما الحجم الأقصى لمحتوى SKILL.md؟">
هناك تحذير ناعم عند 50,000 حرف، لكن بدون حد صارم. حافظ على تركيز المهارات وإيجازها للحصول على أفضل النتائج — الحقن الكبيرة في الإرشادات قد تُشتت انتباه الوكيل.
</Accordion>
</AccordionGroup>

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,49 @@
---
title: الاختبار
description: تعرّف على كيفية اختبار طاقم CrewAI وتقييم أدائه.
icon: vial
mode: "wide"
---
## نظرة عامة
يُعد الاختبار جزءًا حيويًا من عملية التطوير، ومن الضروري التأكد من أن طاقمك يعمل كما هو متوقع. مع CrewAI، يمكنك اختبار طاقمك وتقييم أدائه بسهولة باستخدام إمكانيات الاختبار المدمجة.
### استخدام ميزة الاختبار
أضفنا أمر CLI `crewai test` لتسهيل اختبار طاقمك. سيقوم هذا الأمر بتشغيل طاقمك لعدد محدد من التكرارات وتوفير مقاييس أداء مفصلة. المعاملات هي `n_iterations` و `model`، وهي اختيارية وتكون قيمها الافتراضية 2 و `gpt-4o-mini` على التوالي. حاليًا، المزود الوحيد المتاح هو OpenAI.
```bash
crewai test
```
إذا أردت تشغيل المزيد من التكرارات أو استخدام نموذج مختلف، يمكنك تحديد المعاملات هكذا:
```bash
crewai test --n_iterations 5 --model gpt-4o
```
أو باستخدام الصيغة المختصرة:
```bash
crewai test -n 5 -m gpt-4o
```
عند تشغيل أمر `crewai test`، سيتم تنفيذ الطاقم للعدد المحدد من التكرارات، وستُعرض مقاييس الأداء في نهاية التشغيل.
سيظهر جدول الدرجات في النهاية لعرض أداء الطاقم من حيث المقاييس التالية:
<center>**درجات المهام (1-10 الأعلى أفضل)**</center>
| المهام/الطاقم/الوكلاء | التشغيل 1 | التشغيل 2 | المجموع المتوسط | الوكلاء | معلومات إضافية |
|:------------------|:-----:|:-----:|:----------:|:------------------------------:|:---------------------------------|
| المهمة 1 | 9.0 | 9.5 | **9.2** | Professional Insights | |
| | | | | Researcher | |
| المهمة 2 | 9.0 | 10.0 | **9.5** | Company Profile Investigator | |
| المهمة 3 | 9.0 | 9.0 | **9.0** | Automation Insights | |
| | | | | Specialist | |
| المهمة 4 | 9.0 | 9.0 | **9.0** | Final Report Compiler | Automation Insights Specialist |
| الطاقم | 9.00 | 9.38 | **9.2** | | |
| زمن التنفيذ (ثانية) | 126 | 145 | **135** | | |
يوضح المثال أعلاه نتائج الاختبار لتشغيلين للطاقم مع مهمتين، مع الدرجة الإجمالية المتوسطة لكل مهمة والطاقم ككل.

View File

@@ -0,0 +1,290 @@
---
title: الأدوات
description: فهم واستخدام الأدوات ضمن إطار عمل CrewAI لتعاون الوكلاء وتنفيذ المهام.
icon: screwdriver-wrench
mode: "wide"
---
## نظرة عامة
تُمكّن أدوات CrewAI الوكلاء بقدرات تتراوح من البحث على الويب وتحليل البيانات إلى التعاون وتفويض المهام بين الزملاء.
توضح هذه الوثائق كيفية إنشاء هذه الأدوات ودمجها والاستفادة منها ضمن إطار عمل CrewAI، بما في ذلك التركيز على أدوات التعاون.
<Note type="info" title="الأدوات هي أحد أنواع قدرات الوكيل الخمسة">
الأدوات تمنح الوكلاء **دوال قابلة للاستدعاء** لاتخاذ إجراءات. تعمل جنبًا إلى جنب مع [MCP](/ar/mcp/overview) (خوادم أدوات عن بُعد) و[التطبيقات](/ar/concepts/agent-capabilities) (تكاملات المنصة) و[المهارات](/ar/concepts/skills) (خبرة المجال) و[المعرفة](/ar/concepts/knowledge) (حقائق مُسترجعة). راجع نظرة عامة على [قدرات الوكيل](/ar/concepts/agent-capabilities) لفهم متى تستخدم كل نوع.
</Note>
## ما هي الأداة؟
الأداة في CrewAI هي مهارة أو وظيفة يمكن للوكلاء استخدامها لأداء إجراءات مختلفة.
يشمل ذلك أدوات من [مجموعة أدوات CrewAI](https://github.com/joaomdmoura/crewai-tools) و[أدوات LangChain](https://python.langchain.com/docs/integrations/tools)،
مما يُمكّن كل شيء من عمليات البحث البسيطة إلى التفاعلات المعقدة والعمل الجماعي الفعال بين الوكلاء.
<Note type="info" title="تحسين المؤسسات: مستودع الأدوات">
يوفر CrewAI AMP مستودع أدوات شامل مع تكاملات جاهزة لأنظمة الأعمال الشائعة وواجهات API. انشر الوكلاء مع أدوات المؤسسة في دقائق بدلاً من أيام.
يتضمن مستودع أدوات المؤسسة:
- موصلات جاهزة لأنظمة المؤسسة الشائعة
- واجهة إنشاء أدوات مخصصة
- إمكانيات التحكم في الإصدارات والمشاركة
- ميزات الأمان والامتثال
</Note>
## الخصائص الرئيسية للأدوات
- **المنفعة**: مصممة لمهام مثل البحث على الويب وتحليل البيانات وإنشاء المحتوى وتعاون الوكلاء.
- **التكامل**: تعزز قدرات الوكلاء من خلال دمج الأدوات بسلاسة في سير عملهم.
- **القابلية للتخصيص**: توفر المرونة لتطوير أدوات مخصصة أو استخدام الأدوات الموجودة، لتلبية الاحتياجات المحددة للوكلاء.
- **معالجة الأخطاء**: تتضمن آليات معالجة أخطاء قوية لضمان التشغيل السلس.
- **آلية التخزين المؤقت**: تتميز بتخزين مؤقت ذكي لتحسين الأداء وتقليل العمليات المتكررة.
- **الدعم غير المتزامن**: تتعامل مع الأدوات المتزامنة وغير المتزامنة، مما يُمكّن العمليات غير الحاجبة.
## استخدام أدوات CrewAI
لتعزيز قدرات وكلائك بأدوات CrewAI، ابدأ بتثبيت حزمة الأدوات الإضافية:
```bash
pip install 'crewai[tools]'
```
إليك مثالًا يوضح استخدامها:
```python Code
import os
from crewai import Agent, Task, Crew
# استيراد أدوات crewAI
from crewai_tools import (
DirectoryReadTool,
FileReadTool,
SerperDevTool,
WebsiteSearchTool
)
# إعداد مفاتيح API
os.environ["SERPER_API_KEY"] = "Your Key" # serper.dev API key
os.environ["OPENAI_API_KEY"] = "Your Key"
# إنشاء الأدوات
docs_tool = DirectoryReadTool(directory='./blog-posts')
file_tool = FileReadTool()
search_tool = SerperDevTool()
web_rag_tool = WebsiteSearchTool()
# إنشاء الوكلاء
researcher = Agent(
role='Market Research Analyst',
goal='Provide up-to-date market analysis of the AI industry',
backstory='An expert analyst with a keen eye for market trends.',
tools=[search_tool, web_rag_tool],
verbose=True
)
writer = Agent(
role='Content Writer',
goal='Craft engaging blog posts about the AI industry',
backstory='A skilled writer with a passion for technology.',
tools=[docs_tool, file_tool],
verbose=True
)
# تعريف المهام
research = Task(
description='Research the latest trends in the AI industry and provide a summary.',
expected_output='A summary of the top 3 trending developments in the AI industry with a unique perspective on their significance.',
agent=researcher
)
write = Task(
description='Write an engaging blog post about the AI industry, based on the research analyst\'s summary. Draw inspiration from the latest blog posts in the directory.',
expected_output='A 4-paragraph blog post formatted in markdown with engaging, informative, and accessible content, avoiding complex jargon.',
agent=writer,
output_file='blog-posts/new_post.md'
)
# تجميع طاقم مع تفعيل التخطيط
crew = Crew(
agents=[researcher, writer],
tasks=[research, write],
verbose=True,
planning=True,
)
# تنفيذ المهام
crew.kickoff()
```
## أدوات CrewAI المتاحة
- **معالجة الأخطاء**: جميع الأدوات مبنية بقدرات معالجة الأخطاء، مما يسمح للوكلاء بإدارة الاستثناءات بسلاسة ومتابعة مهامهم.
- **آلية التخزين المؤقت**: جميع الأدوات تدعم التخزين المؤقت، مما يُمكّن الوكلاء من إعادة استخدام النتائج المحصلة سابقًا بكفاءة، مما يقلل الحمل على الموارد الخارجية ويسرّع وقت التنفيذ. يمكنك أيضًا تحديد تحكم أدق في آلية التخزين المؤقت باستخدام خاصية `cache_function` على الأداة.
إليك قائمة بالأدوات المتاحة وأوصافها:
| الأداة | الوصف |
| :------------------------------- | :--------------------------------------------------------------------------------------------- |
| **ApifyActorsTool** | أداة تدمج Apify Actors مع سير عملك لمهام استخراج البيانات من الويب والأتمتة. |
| **BrowserbaseLoadTool** | أداة للتفاعل مع المتصفحات واستخراج البيانات منها. |
| **CodeDocsSearchTool** | أداة RAG محسّنة للبحث في وثائق الكود والمستندات التقنية ذات الصلة. |
| **CodeInterpreterTool** | أداة لتفسير كود Python. |
| **ComposioTool** | تُمكّن استخدام أدوات Composio. |
| **CSVSearchTool** | أداة RAG مصممة للبحث في ملفات CSV، مخصصة للتعامل مع البيانات المنظمة. |
| **DALL-E Tool** | أداة لإنشاء الصور باستخدام DALL-E API. |
| **DirectorySearchTool** | أداة RAG للبحث في المجلدات، مفيدة للتنقل في أنظمة الملفات. |
| **DOCXSearchTool** | أداة RAG للبحث في مستندات DOCX، مثالية لمعالجة ملفات Word. |
| **DirectoryReadTool** | تسهّل قراءة ومعالجة هياكل المجلدات ومحتوياتها. |
| **ExaSearchTool** | أداة مصممة لإجراء عمليات بحث شاملة عبر مصادر بيانات متنوعة. |
| **FileReadTool** | تُمكّن قراءة واستخراج البيانات من الملفات، مع دعم تنسيقات ملفات متنوعة. |
| **FirecrawlSearchTool** | أداة للبحث في صفحات الويب باستخدام Firecrawl وإرجاع النتائج. |
| **FirecrawlCrawlWebsiteTool** | أداة لزحف صفحات الويب باستخدام Firecrawl. |
| **FirecrawlScrapeWebsiteTool** | أداة لاستخراج محتوى عناوين URL لصفحات الويب باستخدام Firecrawl. |
| **GithubSearchTool** | أداة RAG للبحث في مستودعات GitHub، مفيدة لبحث الكود والوثائق. |
| **SerperDevTool** | أداة متخصصة لأغراض التطوير، مع وظائف محددة قيد التطوير. |
| **TXTSearchTool** | أداة RAG مركّزة على البحث في ملفات النص (.txt)، مناسبة للبيانات غير المنظمة. |
| **JSONSearchTool** | أداة RAG مصممة للبحث في ملفات JSON، تخدم التعامل مع البيانات المنظمة. |
| **LlamaIndexTool** | تُمكّن استخدام أدوات LlamaIndex. |
| **MDXSearchTool** | أداة RAG مخصصة للبحث في ملفات Markdown (MDX)، مفيدة للوثائق. |
| **PDFSearchTool** | أداة RAG للبحث في مستندات PDF، مثالية لمعالجة المستندات الممسوحة ضوئيًا. |
| **PGSearchTool** | أداة RAG محسّنة للبحث في قواعد بيانات PostgreSQL، مناسبة لاستعلامات قواعد البيانات. |
| **Vision Tool** | أداة لإنشاء الصور باستخدام DALL-E API. |
| **RagTool** | أداة RAG للأغراض العامة قادرة على التعامل مع مصادر وأنواع بيانات متنوعة. |
| **ScrapeElementFromWebsiteTool** | تُمكّن استخراج عناصر محددة من المواقع، مفيدة لاستخراج البيانات المستهدف. |
| **ScrapeWebsiteTool** | تسهّل استخراج المواقع بالكامل، مثالية لجمع البيانات الشامل. |
| **WebsiteSearchTool** | أداة RAG للبحث في محتوى المواقع، محسّنة لاستخراج بيانات الويب. |
| **XMLSearchTool** | أداة RAG مصممة للبحث في ملفات XML، مناسبة لتنسيقات البيانات المنظمة. |
| **YoutubeChannelSearchTool** | أداة RAG للبحث في قنوات YouTube، مفيدة لتحليل محتوى الفيديو. |
| **YoutubeVideoSearchTool** | أداة RAG للبحث في مقاطع فيديو YouTube، مثالية لاستخراج بيانات الفيديو. |
## إنشاء أدواتك الخاصة
<Tip>
يمكن للمطورين إنشاء `أدوات مخصصة` مصممة خصيصًا لاحتياجات وكلائهم أو
استخدام الخيارات الجاهزة.
</Tip>
هناك طريقتان رئيسيتان لإنشاء أداة CrewAI:
### الوراثة من `BaseTool`
```python Code
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
class MyToolInput(BaseModel):
"""Input schema for MyCustomTool."""
argument: str = Field(..., description="Description of the argument.")
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "What this tool does. It's vital for effective utilization."
args_schema: Type[BaseModel] = MyToolInput
def _run(self, argument: str) -> str:
# منطق أداتك هنا
return "Tool's result"
```
## دعم الأدوات غير المتزامنة
يدعم CrewAI الأدوات غير المتزامنة، مما يتيح لك تنفيذ أدوات تجري عمليات غير حاجبة مثل طلبات الشبكة وعمليات الإدخال/الإخراج على الملفات أو عمليات async أخرى بدون حجب مسار التنفيذ الرئيسي.
### إنشاء أدوات غير متزامنة
يمكنك إنشاء أدوات غير متزامنة بطريقتين:
#### 1. استخدام مزيّن `tool` مع دوال Async
```python Code
from crewai.tools import tool
@tool("fetch_data_async")
async def fetch_data_async(query: str) -> str:
"""Asynchronously fetch data based on the query."""
# محاكاة عملية غير متزامنة
await asyncio.sleep(1)
return f"Data retrieved for {query}"
```
#### 2. تنفيذ طرق Async في فئات الأدوات المخصصة
```python Code
from crewai.tools import BaseTool
class AsyncCustomTool(BaseTool):
name: str = "async_custom_tool"
description: str = "An asynchronous custom tool"
async def _run(self, query: str = "") -> str:
"""Asynchronously run the tool"""
# تنفيذك غير المتزامن هنا
await asyncio.sleep(1)
return f"Processed {query} asynchronously"
```
### استخدام الأدوات غير المتزامنة
تعمل الأدوات غير المتزامنة بسلاسة في كل من سير عمل الطاقم القياسي وسير عمل التدفق:
```python Code
# في طاقم قياسي
agent = Agent(role="researcher", tools=[async_custom_tool])
# في تدفق
class MyFlow(Flow):
@start()
async def begin(self):
crew = Crew(agents=[agent])
result = await crew.kickoff_async()
return result
```
يتعامل إطار عمل CrewAI تلقائيًا مع تنفيذ الأدوات المتزامنة وغير المتزامنة، لذا لا تحتاج للقلق بشأن كيفية استدعائها بشكل مختلف.
### استخدام مزيّن `tool`
```python Code
from crewai.tools import tool
@tool("Name of my tool")
def my_tool(question: str) -> str:
"""Clear description for what this tool is useful for, your agent will need this information to use it."""
# منطق الدالة هنا
return "Result from your custom tool"
```
### آلية التخزين المؤقت المخصصة
<Tip>
يمكن للأدوات اختياريًا تنفيذ `cache_function` لضبط سلوك
التخزين المؤقت. تحدد هذه الدالة متى يتم تخزين النتائج مؤقتًا بناءً على شروط
محددة، مما يوفر تحكمًا دقيقًا في منطق التخزين المؤقت.
</Tip>
```python Code
from crewai.tools import tool
@tool
def multiplication_tool(first_number: int, second_number: int) -> str:
"""Useful for when you need to multiply two numbers together."""
return first_number * second_number
def cache_func(args, result):
# في هذه الحالة، نخزّن النتيجة مؤقتًا فقط إذا كانت من مضاعفات 2
cache = result % 2 == 0
return cache
multiplication_tool.cache_function = cache_func
writer1 = Agent(
role="Writer",
goal="You write lessons of math for kids.",
backstory="You're an expert in writing and you love to teach kids but you know nothing of math.",
tools=[multiplication_tool],
allow_delegation=False,
)
#...
```
## الخلاصة
الأدوات محورية في توسيع قدرات وكلاء CrewAI، مما يمكّنهم من تنفيذ مجموعة واسعة من المهام والتعاون بفعالية.
عند بناء حلول مع CrewAI، استفد من كل من الأدوات المخصصة والموجودة لتمكين وكلائك وتعزيز نظام الذكاء الاصطناعي البيئي. فكّر في استخدام معالجة الأخطاء وآليات التخزين المؤقت ومرونة معاملات الأدوات لتحسين أداء وقدرات وكلائك.

View File

@@ -0,0 +1,197 @@
---
title: التدريب
description: تعرّف على كيفية تدريب وكلاء CrewAI من خلال تقديم ملاحظات مبكرة والحصول على نتائج متسقة.
icon: dumbbell
mode: "wide"
---
## نظرة عامة
تتيح لك ميزة التدريب في CrewAI تدريب وكلاء الذكاء الاصطناعي باستخدام واجهة سطر الأوامر (CLI).
بتشغيل الأمر `crewai train -n <n_iterations>`، يمكنك تحديد عدد التكرارات لعملية التدريب.
أثناء التدريب، يستخدم CrewAI تقنيات لتحسين أداء وكلائك مع التغذية الراجعة البشرية.
يساعد هذا الوكلاء على تحسين فهمهم واتخاذ القرارات وحل المشكلات.
### تدريب طاقمك باستخدام CLI
لاستخدام ميزة التدريب، اتبع الخطوات التالية:
1. افتح الطرفية أو موجه الأوامر.
2. انتقل إلى المجلد حيث يقع مشروع CrewAI.
3. شغّل الأمر التالي:
```shell
crewai train -n <n_iterations> -f <filename.pkl>
```
<Tip>
استبدل `<n_iterations>` بعدد تكرارات التدريب المرغوب و`<filename>` باسم الملف المناسب المنتهي بـ `.pkl`.
</Tip>
<Note>
إذا حذفت `-f`، فإن المخرجات تُحفظ افتراضيًا في `trained_agents_data.pkl` في مجلد العمل الحالي. يمكنك تمرير مسار مطلق للتحكم في مكان كتابة الملف.
</Note>
### تدريب طاقمك برمجيًا
لتدريب طاقمك برمجيًا، استخدم الخطوات التالية:
1. حدد عدد التكرارات للتدريب.
2. حدد معاملات الإدخال لعملية التدريب.
3. نفّذ أمر التدريب داخل كتلة try-except للتعامل مع الأخطاء المحتملة.
```python Code
n_iterations = 2
inputs = {"topic": "CrewAI Training"}
filename = "your_model.pkl"
try:
YourCrewName_Crew().crew().train(
n_iterations=n_iterations,
inputs=inputs,
filename=filename
)
except Exception as e:
raise Exception(f"An error occurred while training the crew: {e}")
```
## كيف تُستخدم بيانات التدريب من قبل الوكلاء
يستخدم CrewAI مخرجات التدريب بطريقتين: أثناء التدريب لدمج ملاحظاتك البشرية، وبعد التدريب لتوجيه الوكلاء باقتراحات موحدة.
### تدفق بيانات التدريب
```mermaid
flowchart TD
A["Start training<br/>CLI: crewai train -n -f<br/>or Python: crew.train(...)"] --> B["Setup training mode<br/>- task.human_input = true<br/>- disable delegation<br/>- init training_data.pkl + trained file"]
subgraph "Iterations"
direction LR
C["Iteration i<br/>initial_output"] --> D["User human_feedback"]
D --> E["improved_output"]
E --> F["Append to training_data.pkl<br/>by agent_id and iteration"]
end
B --> C
F --> G{"More iterations?"}
G -- "Yes" --> C
G -- "No" --> H["Evaluate per agent<br/>aggregate iterations"]
H --> I["Consolidate<br/>suggestions[] + quality + final_summary"]
I --> J["Save by agent role to trained file<br/>(default: trained_agents_data.pkl)"]
J --> K["Normal (non-training) runs"]
K --> L["Auto-load suggestions<br/>from trained_agents_data.pkl"]
L --> M["Append to prompt<br/>for consistent improvements"]
```
### أثناء تشغيلات التدريب
- في كل تكرار، يسجل النظام لكل وكيل:
- `initial_output`: الإجابة الأولى للوكيل
- `human_feedback`: ملاحظاتك المضمّنة عند الطلب
- `improved_output`: إجابة المتابعة للوكيل بعد الملاحظات
- تُخزن هذه البيانات في ملف عمل باسم `training_data.pkl` مفهرس بمعرّف الوكيل الداخلي والتكرار.
- أثناء نشاط التدريب، يُلحق الوكيل تلقائيًا ملاحظاتك البشرية السابقة بأمره لتطبيق تلك التعليمات في المحاولات اللاحقة ضمن جلسة التدريب.
التدريب تفاعلي: تُعيّن المهام `human_input = true`، لذا سيتوقف التشغيل في بيئة غير تفاعلية بانتظار مدخلات المستخدم.
### بعد اكتمال التدريب
- عند انتهاء `train(...)`، يقيّم CrewAI بيانات التدريب المجمعة لكل وكيل وينتج نتيجة موحدة تحتوي على:
- `suggestions`: تعليمات واضحة وقابلة للتنفيذ مستخلصة من ملاحظاتك والفرق بين المخرجات الأولية/المحسنة
- `quality`: درجة من 0-10 تعكس التحسن
- `final_summary`: مجموعة خطوات عمل تفصيلية للمهام المستقبلية
- تُحفظ هذه النتائج الموحدة في اسم الملف الذي تمرره إلى `train(...)` (الافتراضي عبر CLI هو `trained_agents_data.pkl`). تُفهرس الإدخالات بدور الوكيل `role` لتطبيقها عبر الجلسات.
- أثناء التنفيذ العادي (غير التدريب)، يحمّل كل وكيل تلقائيًا `suggestions` الموحدة ويلحقها بأمر المهمة كتعليمات إلزامية. يمنحك هذا تحسينات متسقة بدون تغيير تعريفات الوكلاء.
### ملخص الملفات
- `training_data.pkl` (مؤقت، لكل جلسة):
- الهيكل: `agent_id -> { iteration_number: { initial_output, human_feedback, improved_output } }`
- الغرض: التقاط البيانات الخام والملاحظات البشرية أثناء التدريب
- الموقع: يُحفظ في مجلد العمل الحالي (CWD)
- `trained_agents_data.pkl` (أو اسم ملفك المخصص):
- الهيكل: `agent_role -> { suggestions: string[], quality: number, final_summary: string }`
- الغرض: استمرار التوجيه الموحد للتشغيلات المستقبلية
- الموقع: يُكتب في CWD افتراضيًا؛ استخدم `-f` لتعيين مسار مخصص (بما في ذلك المطلق)
## اعتبارات نماذج اللغة الصغيرة
<Warning>
عند استخدام نماذج لغة أصغر (≤7 مليار معامل) لتقييم بيانات التدريب، كن على علم أنها قد تواجه تحديات في إنتاج مخرجات منظمة واتباع التعليمات المعقدة.
</Warning>
### قيود النماذج الصغيرة في تقييم التدريب
<CardGroup cols={2}>
<Card title="دقة مخرجات JSON" icon="triangle-exclamation">
غالبًا ما تواجه النماذج الأصغر صعوبة في إنتاج استجابات JSON صالحة مطلوبة لتقييمات التدريب المنظمة، مما يؤدي إلى أخطاء تحليل وبيانات غير مكتملة.
</Card>
<Card title="جودة التقييم" icon="chart-line">
قد توفر النماذج تحت 7 مليار معامل تقييمات أقل دقة مع عمق استدلال محدود مقارنة بالنماذج الأكبر.
</Card>
<Card title="اتباع التعليمات" icon="list-check">
قد لا تُتبع معايير تقييم التدريب المعقدة بالكامل أو تُراعى من قبل النماذج الأصغر.
</Card>
<Card title="الاتساق" icon="rotate">
قد تفتقر التقييمات عبر تكرارات تدريب متعددة إلى الاتساق مع النماذج الأصغر.
</Card>
</CardGroup>
### توصيات للتدريب
<Tabs>
<Tab title="أفضل ممارسة">
لجودة تدريب مثالية وتقييمات موثوقة، نوصي بشدة باستخدام نماذج بحد أدنى 7 مليار معامل أو أكبر:
```python
from crewai import Agent, Crew, Task, LLM
# الحد الأدنى الموصى به لتقييم التدريب
llm = LLM(model="mistral/open-mistral-7b")
# خيارات أفضل لتقييم تدريب موثوق
llm = LLM(model="anthropic/claude-3-sonnet-20240229-v1:0")
llm = LLM(model="gpt-4o")
# استخدم هذا LLM مع وكلائك
agent = Agent(
role="Training Evaluator",
goal="Provide accurate training feedback",
llm=llm
)
```
<Tip>
توفر النماذج الأكثر قوة ملاحظات أعلى جودة مع استدلال أفضل، مما يؤدي إلى تكرارات تدريب أكثر فعالية.
</Tip>
</Tab>
<Tab title="استخدام النماذج الصغيرة">
إذا كان يجب عليك استخدام نماذج أصغر لتقييم التدريب، كن على علم بهذه القيود:
```python
# استخدام نموذج أصغر (توقع بعض القيود)
llm = LLM(model="huggingface/microsoft/Phi-3-mini-4k-instruct")
```
<Warning>
بينما يتضمن CrewAI تحسينات للنماذج الصغيرة، توقع نتائج تقييم أقل موثوقية ودقة قد تتطلب تدخلاً بشريًا أكبر أثناء التدريب.
</Warning>
</Tab>
</Tabs>
### نقاط مهمة يجب ملاحظتها
- **متطلب العدد الصحيح الموجب:** تأكد من أن عدد التكرارات (`n_iterations`) هو عدد صحيح موجب. سيرمي الكود `ValueError` إذا لم يتحقق هذا الشرط.
- **متطلب اسم الملف:** تأكد من أن اسم الملف ينتهي بـ `.pkl`. سيرمي الكود `ValueError` إذا لم يتحقق هذا الشرط.
- **معالجة الأخطاء:** يتعامل الكود مع أخطاء العمليات الفرعية والاستثناءات غير المتوقعة، ويوفر رسائل خطأ للمستخدم.
- يُطبق التوجيه المدرّب في وقت الأمر؛ لا يعدّل تهيئة وكيل Python/YAML.
- يحمّل الوكلاء تلقائيًا الاقتراحات المدربة من ملف باسم `trained_agents_data.pkl` الموجود في مجلد العمل الحالي. إذا درّبت إلى اسم ملف مختلف، أعد تسميته إلى `trained_agents_data.pkl` قبل التشغيل، أو اضبط المحمّل في الكود.
- يمكنك تغيير اسم ملف المخرجات عند استدعاء `crewai train` بـ `-f/--filename`. المسارات المطلقة مدعومة إذا أردت الحفظ خارج CWD.
من المهم ملاحظة أن عملية التدريب قد تستغرق بعض الوقت، اعتمادًا على تعقيد وكلائك وستتطلب أيضًا ملاحظاتك في كل تكرار.
بمجرد اكتمال التدريب، سيكون وكلاؤك مجهزين بقدرات ومعرفة محسّنة، وجاهزين لمعالجة المهام المعقدة وتقديم رؤى أكثر اتساقًا وقيمة.
تذكر تحديث وإعادة تدريب وكلائك بانتظام لضمان بقائهم على اطلاع بأحدث المعلومات والتطورات في المجال.

View File

@@ -0,0 +1,49 @@
---
title: كتب وصفات CrewAI
description: بدايات سريعة ودفاتر ملاحظات مركّزة على الميزات لتعلم الأنماط بسرعة.
icon: book
mode: "wide"
---
## بدايات سريعة وعروض توضيحية
<CardGroup cols={3}>
<Card title="التعاون" icon="people-arrows" href="https://github.com/crewAIInc/crewAI-quickstarts/blob/main/Collaboration/crewai_collaboration.ipynb">
تنسيق عدة Agents على مهام مشتركة. يتضمن دفتر ملاحظات بنمط تعاون شامل.
</Card>
<Card title="التخطيط" icon="timeline" href="https://github.com/crewAIInc/crewAI-quickstarts/blob/main/Planning/crewai_planning.ipynb">
تعليم الـ Agents التفكير في خطط متعددة المراحل قبل التنفيذ باستخدام أدوات التخطيط.
</Card>
<Card title="الاستدلال" icon="lightbulb" href="https://github.com/crewAIInc/crewAI-quickstarts/blob/main/Reasoning/crewai_reasoning.ipynb">
استكشاف حلقات التأمل الذاتي، ومطالبات النقد، وأنماط التفكير المنظم.
</Card>
</CardGroup>
<CardGroup cols={3}>
<Card title="حواجز الحماية المنظمة" icon="shield-check" href="https://github.com/crewAIInc/crewAI-quickstarts/blob/main/Guardrails/task_guardrails.ipynb">
تطبيق حواجز حماية على مستوى المهام مع إعادة المحاولة ودوال التحقق والبدائل الآمنة.
</Card>
<Card title="بحث وتأريض Gemini" icon="magnifying-glass" href="https://github.com/crewAIInc/crewAI-quickstarts/blob/main/Custom%20LLM/gemini_search_grounding_crewai.ipynb">
ربط CrewAI بـ Gemini مع تأريض البحث للحصول على مخرجات واقعية غنية بالاستشهادات.
</Card>
<Card title="ملخصات فيديو Gemini" icon="video" href="https://github.com/crewAIInc/crewAI-quickstarts/blob/main/Custom%20LLM/summarize_video_gemini_crewai.ipynb">
إنشاء ملخصات فيديو باستخدام نموذج Gemini متعدد الوسائط وتنسيق CrewAI.
</Card>
</CardGroup>
<CardGroup cols={2}>
<Card title="تصفح البدايات السريعة" icon="bolt" href="https://github.com/crewAIInc/crewAI-quickstarts">
عرض جميع دفاتر الملاحظات والعروض التوضيحية التي تستعرض إمكانيات CrewAI المحددة.
</Card>
<Card title="اطلب كتاب وصفات" icon="message-plus" href="https://community.crewai.com">
هل يفتقد نمط معين؟ أرسل طلبًا في منتدى المجتمع وسنوسّع المكتبة.
</Card>
</CardGroup>
<Tip>
استخدم كتب الوصفات لتعلم نمط بسرعة، ثم انتقل إلى الأمثلة الكاملة للتطبيقات الجاهزة للإنتاج.
</Tip>

View File

@@ -0,0 +1,86 @@
---
title: أمثلة CrewAI
description: استكشف أمثلة منسّقة مرتبة حسب Crews وFlows والتكاملات ودفاتر الملاحظات.
icon: rocket-launch
mode: "wide"
---
## Crews
<CardGroup cols={3}>
<Card title="استراتيجية التسويق" icon="bullhorn" href="https://github.com/crewAIInc/crewAI-examples/tree/main/crews/marketing_strategy">
تخطيط حملات تسويقية متعددة الـ Agents.
</Card>
<Card title="رحلة مفاجئة" icon="plane" href="https://github.com/crewAIInc/crewAI-examples/tree/main/crews/surprise_trip">
تخطيط رحلات مفاجئة مخصصة.
</Card>
<Card title="مطابقة الملف الشخصي بالوظائف" icon="id-card" href="https://github.com/crewAIInc/crewAI-examples/tree/main/crews/match_profile_to_positions">
مطابقة السيرة الذاتية بالوظائف باستخدام البحث المتجهي.
</Card>
<Card title="نشر وظيفة" icon="newspaper" href="https://github.com/crewAIInc/crewAI-examples/tree/main/crews/job-posting">
إنشاء أوصاف وظيفية آلية.
</Card>
<Card title="فريق بناء الألعاب" icon="gamepad" href="https://github.com/crewAIInc/crewAI-examples/tree/main/crews/game-builder-crew">
فريق متعدد الـ Agents يصمم ويبني ألعاب Python.
</Card>
<Card title="التوظيف" icon="user-group" href="https://github.com/crewAIInc/crewAI-examples/tree/main/crews/recruitment">
استقطاب المرشحين وتقييمهم.
</Card>
<Card title="تصفح جميع الـ Crews" icon="users" href="https://github.com/crewAIInc/crewAI-examples/tree/main/crews">
عرض القائمة الكاملة لأمثلة الـ Crews.
</Card>
</CardGroup>
## Flows
<CardGroup cols={3}>
<Card title="Flow إنشاء المحتوى" icon="pen" href="https://github.com/crewAIInc/crewAI-examples/tree/main/flows/content_creator_flow">
إنشاء محتوى متعدد الـ Crews مع التوجيه.
</Card>
<Card title="الرد التلقائي على البريد الإلكتروني" icon="envelope" href="https://github.com/crewAIInc/crewAI-examples/tree/main/flows/email_auto_responder_flow">
مراقبة البريد الإلكتروني والرد الآلي.
</Card>
<Card title="Flow تقييم العملاء المحتملين" icon="chart-line" href="https://github.com/crewAIInc/crewAI-examples/tree/main/flows/lead_score_flow">
تأهيل العملاء المحتملين مع تدخل بشري.
</Card>
<Card title="Flow مساعد الاجتماعات" icon="calendar" href="https://github.com/crewAIInc/crewAI-examples/tree/main/flows/meeting_assistant_flow">
معالجة الملاحظات مع التكاملات.
</Card>
<Card title="حلقة التقييم الذاتي" icon="rotate" href="https://github.com/crewAIInc/crewAI-examples/tree/main/flows/self_evaluation_loop_flow">
سير عمل التحسين الذاتي التكراري.
</Card>
<Card title="كتابة كتاب (Flows)" icon="book" href="https://github.com/crewAIInc/crewAI-examples/tree/main/flows/write_a_book_with_flows">
إنشاء الفصول بالتوازي.
</Card>
<Card title="تصفح جميع الـ Flows" icon="diagram-project" href="https://github.com/crewAIInc/crewAI-examples/tree/main/flows">
عرض القائمة الكاملة لأمثلة الـ Flows.
</Card>
</CardGroup>
## التكاملات
<CardGroup cols={3}>
<Card title="CrewAI ↔ LangGraph" icon="link" href="https://github.com/crewAIInc/crewAI-examples/tree/main/integrations/crewai-langgraph">
التكامل مع إطار عمل LangGraph.
</Card>
<Card title="Azure OpenAI" icon="cloud" href="https://github.com/crewAIInc/crewAI-examples/tree/main/integrations/azure_model">
استخدام CrewAI مع Azure OpenAI.
</Card>
<Card title="نماذج NVIDIA" icon="microchip" href="https://github.com/crewAIInc/crewAI-examples/tree/main/integrations/nvidia_models">
تكاملات منظومة NVIDIA.
</Card>
<Card title="تصفح التكاملات" icon="puzzle-piece" href="https://github.com/crewAIInc/crewAI-examples/tree/main/integrations">
عرض جميع أمثلة التكاملات.
</Card>
</CardGroup>
## دفاتر الملاحظات
<CardGroup cols={2}>
<Card title="Simple QA Crew + Flow" icon="book" href="https://github.com/crewAIInc/crewAI-examples/tree/main/Notebooks/Simple%20QA%20Crew%20%2B%20Flow">
Simple QA Crew + Flow.
</Card>
<Card title="جميع دفاتر الملاحظات" icon="book" href="https://github.com/crewAIInc/crewAI-examples/tree/main/Notebooks">
أمثلة تفاعلية للتعلم والتجريب.
</Card>
</CardGroup>

View File

@@ -0,0 +1,331 @@
---
title: تخصيص المطالبات
description: تعمّق في تخصيص المطالبات على المستوى المنخفض في CrewAI، مما يتيح حالات استخدام مخصصة ومعقدة لنماذج ولغات مختلفة.
icon: message-pen
mode: "wide"
---
## لماذا نخصص المطالبات؟
على الرغم من أن مطالبات CrewAI الافتراضية تعمل بشكل جيد في كثير من السيناريوهات، إلا أن التخصيص على المستوى المنخفض يفتح الباب أمام سلوك أكثر مرونة وقوة للـ Agent. إليك لماذا قد ترغب في الاستفادة من هذا التحكم العميق:
1. **التحسين لنماذج LLM محددة** تزدهر النماذج المختلفة (مثل GPT-4 وClaude وLlama) مع تنسيقات مطالبات مصممة لبنيتها الفريدة.
2. **تغيير اللغة** بناء Agents تعمل حصريًا بلغات غير الإنجليزية مع التعامل مع الفروق الدقيقة بدقة.
3. **التخصص في مجالات معقدة** تكييف المطالبات لصناعات متخصصة للغاية مثل الرعاية الصحية والمالية والقانون.
4. **ضبط النبرة والأسلوب** جعل الـ Agents أكثر رسمية أو عفوية أو إبداعية أو تحليلية.
5. **دعم حالات استخدام مخصصة للغاية** استخدام هياكل وتنسيقات مطالبات متقدمة لتلبية متطلبات معقدة خاصة بالمشروع.
يستكشف هذا الدليل كيفية الوصول إلى مطالبات CrewAI على مستوى أعمق، مما يمنحك تحكمًا دقيقًا في كيفية تفكير الـ Agents وتفاعلها.
## فهم نظام المطالبات في CrewAI
تحت الغطاء، يستخدم CrewAI نظام مطالبات معياري يمكنك تخصيصه على نطاق واسع:
- **قوالب الـ Agent** تحكم في نهج كل Agent تجاه دوره المعيّن.
- **شرائح المطالبات** تتحكم في السلوكيات المتخصصة مثل المهام واستخدام الأدوات وهيكل المخرجات.
- **معالجة الأخطاء** توجيه كيفية استجابة الـ Agents للإخفاقات والاستثناءات وحالات انتهاء المهلة.
- **مطالبات خاصة بالأدوات** تعريف تعليمات مفصلة لكيفية استدعاء الأدوات أو استخدامها.
اطلع على [قوالب المطالبات الأصلية في مستودع CrewAI](https://github.com/crewAIInc/crewAI/blob/main/src/crewai/translations/en.json) لمعرفة كيفية تنظيم هذه العناصر. من هناك، يمكنك تجاوزها أو تكييفها حسب الحاجة لفتح سلوكيات متقدمة.
## فهم تعليمات النظام الافتراضية
<Warning>
**مشكلة شفافية الإنتاج**: يحقن CrewAI تلقائيًا تعليمات افتراضية في مطالباتك قد لا تكون على علم بها. يشرح هذا القسم ما يحدث تحت الغطاء وكيفية الحصول على تحكم كامل.
</Warning>
عندما تعرّف Agent بـ `role` و`goal` و`backstory`، يضيف CrewAI تلقائيًا تعليمات نظام إضافية تتحكم في التنسيق والسلوك. فهم هذه الحقن الافتراضية أمر بالغ الأهمية لأنظمة الإنتاج التي تحتاج شفافية كاملة في المطالبات.
### ما يحقنه CrewAI تلقائيًا
بناءً على تهيئة الـ Agent، يضيف CrewAI تعليمات افتراضية مختلفة:
#### للـ Agents بدون أدوات
```text
"I MUST use these formats, my job depends on it!"
```
#### للـ Agents مع أدوات
```text
"IMPORTANT: Use the following format in your response:
Thought: you should always think about what to do
Action: the action to take, only one name of [tool_names]
Action Input: the input to the action, just a simple JSON object...
```
#### للمخرجات المنظمة (JSON/Pydantic)
```text
"Ensure your final answer contains only the content in the following format: {output_format}
Ensure the final output does not include any code block markers like ```json or ```python."
```
### عرض مطالبة النظام الكاملة
لمعرفة المطالبة المرسلة بالضبط إلى LLM، يمكنك فحص المطالبة المولّدة:
```python
from crewai import Agent, Crew, Task
from crewai.utilities.prompts import Prompts
# Create your agent
agent = Agent(
role="Data Analyst",
goal="Analyze data and provide insights",
backstory="You are an expert data analyst with 10 years of experience.",
verbose=True
)
# Create a sample task
task = Task(
description="Analyze the sales data and identify trends",
expected_output="A detailed analysis with key insights and trends",
agent=agent
)
# Create the prompt generator
prompt_generator = Prompts(
agent=agent,
has_tools=len(agent.tools) > 0,
use_system_prompt=agent.use_system_prompt
)
# Generate and inspect the actual prompt
generated_prompt = prompt_generator.task_execution()
# Print the complete system prompt that will be sent to the LLM
if "system" in generated_prompt:
print("=== SYSTEM PROMPT ===")
print(generated_prompt["system"])
print("\n=== USER PROMPT ===")
print(generated_prompt["user"])
else:
print("=== COMPLETE PROMPT ===")
print(generated_prompt["prompt"])
# You can also see how the task description gets formatted
print("\n=== TASK CONTEXT ===")
print(f"Task Description: {task.description}")
print(f"Expected Output: {task.expected_output}")
```
### تجاوز التعليمات الافتراضية
لديك عدة خيارات للحصول على تحكم كامل في المطالبات:
#### الخيار 1: القوالب المخصصة (مُوصى به)
```python
from crewai import Agent
# Define your own system template without default instructions
custom_system_template = """You are {role}. {backstory}
Your goal is: {goal}
Respond naturally and conversationally. Focus on providing helpful, accurate information."""
custom_prompt_template = """Task: {input}
Please complete this task thoughtfully."""
agent = Agent(
role="Research Assistant",
goal="Help users find accurate information",
backstory="You are a helpful research assistant.",
system_template=custom_system_template,
prompt_template=custom_prompt_template,
use_system_prompt=True # Use separate system/user messages
)
```
#### الخيار 2: ملف مطالبات مخصص
أنشئ ملف `custom_prompts.json` لتجاوز شرائح مطالبات محددة:
```json
{
"slices": {
"no_tools": "\nProvide your best answer in a natural, conversational way.",
"tools": "\nYou have access to these tools: {tools}\n\nUse them when helpful, but respond naturally.",
"formatted_task_instructions": "Format your response as: {output_format}"
}
}
```
ثم استخدمه في Crew:
```python
crew = Crew(
agents=[agent],
tasks=[task],
prompt_file="custom_prompts.json",
verbose=True
)
```
<Note>
يُحتفظ بـ `agent.i18n` للتوافق مع الإصدارات السابقة فقط، وقد تم إهماله. لتخصيص المطالبات أثناء التشغيل، مرّر `prompt_file` إلى `Crew`. وللوصول البرمجي المباشر إلى شرائح المطالبات، استخدم أداة i18n مباشرة:
</Note>
```python
from crewai.utilities.i18n import get_i18n
i18n = get_i18n("custom_prompts.json")
format_slice = i18n.slice("format")
tool_prompt = i18n.tools("ask_question")
```
#### الخيار 3: تعطيل مطالبات النظام لنماذج o1
```python
agent = Agent(
role="Analyst",
goal="Analyze data",
backstory="Expert analyst",
use_system_prompt=False # Disables system prompt separation
)
```
### التصحيح باستخدام أدوات المراقبة
لشفافية الإنتاج، استخدم منصات المراقبة لمتابعة جميع المطالبات وتفاعلات LLM. يتيح لك ذلك رؤية المطالبات المرسلة بالضبط (بما في ذلك التعليمات الافتراضية) إلى نماذج LLM.
راجع [توثيق المراقبة](/ar/observability/overview) للحصول على أدلة تكامل مفصلة مع منصات متعددة بما في ذلك Langfuse وMLflow وWeights & Biases وحلول التسجيل المخصصة.
### أفضل الممارسات للإنتاج
1. **افحص المطالبات المولّدة دائمًا** قبل النشر في الإنتاج
2. **استخدم قوالب مخصصة** عندما تحتاج تحكمًا كاملاً في محتوى المطالبات
3. **دمج أدوات المراقبة** للمتابعة المستمرة للمطالبات (راجع [توثيق المراقبة](/ar/observability/overview))
4. **اختبر مع نماذج LLM مختلفة** حيث قد تعمل التعليمات الافتراضية بشكل مختلف عبر النماذج
5. **وثّق تخصيصات المطالبات** لشفافية الفريق
<Tip>
التعليمات الافتراضية موجودة لضمان سلوك Agent متسق، لكنها قد تتعارض مع المتطلبات الخاصة بالمجال. استخدم خيارات التخصيص أعلاه للحفاظ على تحكم كامل في سلوك Agent في أنظمة الإنتاج.
</Tip>
## أفضل الممارسات لإدارة ملفات المطالبات
عند الانخراط في تخصيص المطالبات على المستوى المنخفض، اتبع هذه الإرشادات للحفاظ على التنظيم وسهولة الصيانة:
1. **احتفظ بالملفات منفصلة** خزّن المطالبات المخصصة في ملفات JSON مخصصة خارج قاعدة الكود الرئيسية.
2. **التحكم في الإصدارات** تتبع التغييرات داخل المستودع مع ضمان توثيق واضح لتعديلات المطالبات بمرور الوقت.
3. **التنظيم حسب النموذج أو اللغة** استخدم تسميات مثل `prompts_llama.json` أو `prompts_es.json` لتحديد التهيئات المتخصصة بسرعة.
4. **توثيق التغييرات** قدم تعليقات أو حافظ على ملف يوضح غرض ونطاق تخصيصاتك.
5. **قلل التعديلات** تجاوز فقط الشرائح المحددة التي تحتاج حقًا لتعديلها مع الحفاظ على الوظائف الافتراضية لكل شيء آخر.
## أبسط طريقة لتخصيص المطالبات
إحدى الطرق المباشرة هي إنشاء ملف JSON للمطالبات التي تريد تجاوزها ثم توجيه Crew إلى ذلك الملف:
1. أنشئ ملف JSON بشرائح المطالبات المحدّثة.
2. أشر إلى ذلك الملف عبر معامل `prompt_file` في Crew.
يدمج CrewAI بعد ذلك تخصيصاتك مع الإعدادات الافتراضية، فلا تحتاج لإعادة تعريف كل مطالبة. إليك الطريقة:
بالنسبة للكود الذي يحتاج إلى قراءة شرائح المطالبات مباشرة، استخدم `crewai.utilities.i18n.get_i18n()` مع ملف المطالبات نفسه بدلًا من قراءة `agent.i18n`.
### مثال: تخصيص أساسي للمطالبات
أنشئ ملف `custom_prompts.json` بالمطالبات التي تريد تعديلها. تأكد من إدراج جميع المطالبات عالية المستوى التي يجب أن يحتويها، وليس فقط تغييراتك:
```json
{
"slices": {
"format": "When responding, follow this structure:\n\nTHOUGHTS: Your step-by-step thinking\nACTION: Any tool you're using\nRESULT: Your final answer or conclusion"
}
}
```
ثم ادمجه هكذا:
```python
from crewai import Agent, Crew, Task, Process
# Create agents and tasks as normal
researcher = Agent(
role="Research Specialist",
goal="Find information on quantum computing",
backstory="You are a quantum physics expert",
verbose=True
)
research_task = Task(
description="Research quantum computing applications",
expected_output="A summary of practical applications",
agent=researcher
)
# Create a crew with your custom prompt file
crew = Crew(
agents=[researcher],
tasks=[research_task],
prompt_file="path/to/custom_prompts.json",
verbose=True
)
# Run the crew
result = crew.kickoff()
```
بهذه التعديلات البسيطة، تحصل على تحكم منخفض المستوى في كيفية تواصل الـ Agents وحل المهام.
## التحسين لنماذج محددة
تزدهر النماذج المختلفة مع مطالبات منظمة بطرق مختلفة. إجراء تعديلات أعمق يمكن أن يعزز الأداء بشكل كبير من خلال مواءمة مطالباتك مع خصائص النموذج.
### مثال: قالب مطالبات Llama 3.3
على سبيل المثال، عند التعامل مع Llama 3.3 من Meta، قد يعكس التخصيص على المستوى الأعمق الهيكل الموصى به الموضح في:
https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1/#prompt-template
إليك مثالاً يوضح كيف يمكنك ضبط Agent للاستفادة من Llama 3.3 في الكود:
```python
from crewai import Agent, Crew, Task, Process
from crewai_tools import DirectoryReadTool, FileReadTool
# Define templates for system, user (prompt), and assistant (response) messages
system_template = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ .System }}<|eot_id|>"""
prompt_template = """<|start_header_id|>user<|end_header_id|>{{ .Prompt }}<|eot_id|>"""
response_template = """<|start_header_id|>assistant<|end_header_id|>{{ .Response }}<|eot_id|>"""
# Create an Agent using Llama-specific layouts
principal_engineer = Agent(
role="Principal Engineer",
goal="Oversee AI architecture and make high-level decisions",
backstory="You are the lead engineer responsible for critical AI systems",
verbose=True,
llm="groq/llama-3.3-70b-versatile", # Using the Llama 3 model
system_template=system_template,
prompt_template=prompt_template,
response_template=response_template,
tools=[DirectoryReadTool(), FileReadTool()]
)
# Define a sample task
engineering_task = Task(
description="Review AI implementation files for potential improvements",
expected_output="A summary of key findings and recommendations",
agent=principal_engineer
)
# Create a Crew for the task
llama_crew = Crew(
agents=[principal_engineer],
tasks=[engineering_task],
process=Process.sequential,
verbose=True
)
# Execute the crew
result = llama_crew.kickoff()
print(result.raw)
```
من خلال هذه التهيئة العميقة، يمكنك ممارسة تحكم شامل منخفض المستوى في سير العمل القائمة على Llama دون الحاجة إلى ملف JSON منفصل.
## الخلاصة
يفتح تخصيص المطالبات على المستوى المنخفض في CrewAI الباب أمام حالات استخدام مخصصة ومعقدة للغاية. من خلال إنشاء ملفات مطالبات منظمة (أو قوالب مضمّنة مباشرة)، يمكنك استيعاب نماذج ولغات ومجالات متخصصة متنوعة. يضمن هذا المستوى من المرونة أنك تستطيع صياغة سلوك الذكاء الاصطناعي الذي تحتاجه بالضبط، مع العلم أن CrewAI لا يزال يوفر إعدادات افتراضية موثوقة عندما لا تتجاوزها.
<Check>
لديك الآن الأساس لتخصيصات المطالبات المتقدمة في CrewAI. سواء كنت تتكيف مع هياكل خاصة بالنموذج أو قيود خاصة بالمجال، يتيح لك هذا النهج المنخفض المستوى تشكيل تفاعلات الـ Agent بطرق متخصصة للغاية.
</Check>

View File

@@ -0,0 +1,134 @@
---
title: البصمات الرقمية
description: تعلم كيفية استخدام نظام البصمات الرقمية في CrewAI لتحديد وتتبع المكونات بشكل فريد طوال دورة حياتها.
icon: fingerprint
mode: "wide"
---
## نظرة عامة
توفر البصمات الرقمية في CrewAI طريقة لتحديد وتتبع المكونات بشكل فريد طوال دورة حياتها. يتلقى كل `Agent` و`Crew` و`Task` بصمة رقمية فريدة تلقائيًا عند الإنشاء، ولا يمكن تجاوزها يدويًا.
يمكن استخدام هذه البصمات لـ:
- تدقيق وتتبع استخدام المكونات
- ضمان سلامة هوية المكونات
- إرفاق بيانات وصفية بالمكونات
- إنشاء سلسلة عمليات قابلة للتتبع
## كيف تعمل البصمات الرقمية
البصمة الرقمية هي نسخة من فئة `Fingerprint` من وحدة `crewai.security`. تحتوي كل بصمة على:
- سلسلة UUID: معرّف فريد للمكون يتم إنشاؤه تلقائيًا ولا يمكن تعيينه يدويًا
- طابع زمني للإنشاء: متى تم إنشاء البصمة، يُعيَّن تلقائيًا ولا يمكن تعديله يدويًا
- بيانات وصفية: قاموس معلومات إضافية يمكن تخصيصه
تُنشأ البصمات الرقمية وتُعيَّن تلقائيًا عند إنشاء المكون. يكشف كل مكون بصمته من خلال خاصية للقراءة فقط.
## الاستخدام الأساسي
### الوصول إلى البصمات الرقمية
```python
from crewai import Agent, Crew, Task
# Create components - fingerprints are automatically generated
agent = Agent(
role="Data Scientist",
goal="Analyze data",
backstory="Expert in data analysis"
)
crew = Crew(
agents=[agent],
tasks=[]
)
task = Task(
description="Analyze customer data",
expected_output="Insights from data analysis",
agent=agent
)
# Access the fingerprints
agent_fingerprint = agent.fingerprint
crew_fingerprint = crew.fingerprint
task_fingerprint = task.fingerprint
# Print the UUID strings
print(f"Agent fingerprint: {agent_fingerprint.uuid_str}")
print(f"Crew fingerprint: {crew_fingerprint.uuid_str}")
print(f"Task fingerprint: {task_fingerprint.uuid_str}")
```
### العمل مع البيانات الوصفية للبصمة
يمكنك إضافة بيانات وصفية إلى البصمات لسياق إضافي:
```python
# Add metadata to the agent's fingerprint
agent.security_config.fingerprint.metadata = {
"version": "1.0",
"department": "Data Science",
"project": "Customer Analysis"
}
# Access the metadata
print(f"Agent metadata: {agent.fingerprint.metadata}")
```
## استمرارية البصمة
صُممت البصمات لتبقى ثابتة دون تغيير طوال دورة حياة المكون. إذا عدّلت مكونًا، تظل البصمة كما هي:
```python
original_fingerprint = agent.fingerprint.uuid_str
# Modify the agent
agent.goal = "New goal for analysis"
# The fingerprint remains unchanged
assert agent.fingerprint.uuid_str == original_fingerprint
```
## البصمات الحتمية
بينما لا يمكنك تعيين UUID والطابع الزمني مباشرة، يمكنك إنشاء بصمات حتمية باستخدام طريقة `generate` مع بذرة:
```python
from crewai.security import Fingerprint
# Create a deterministic fingerprint using a seed string
deterministic_fingerprint = Fingerprint.generate(seed="my-agent-id")
# The same seed always produces the same fingerprint
same_fingerprint = Fingerprint.generate(seed="my-agent-id")
assert deterministic_fingerprint.uuid_str == same_fingerprint.uuid_str
# You can also set metadata
custom_fingerprint = Fingerprint.generate(
seed="my-agent-id",
metadata={"version": "1.0"}
)
```
## الاستخدام المتقدم
### هيكل البصمة
لكل بصمة الهيكل التالي:
```python
from crewai.security import Fingerprint
fingerprint = agent.fingerprint
# UUID string - the unique identifier (auto-generated)
uuid_str = fingerprint.uuid_str # e.g., "123e4567-e89b-12d3-a456-426614174000"
# Creation timestamp (auto-generated)
created_at = fingerprint.created_at # A datetime object
# Metadata - for additional information (can be customized)
metadata = fingerprint.metadata # A dictionary, defaults to {}
```

View File

@@ -0,0 +1,453 @@
---
title: صياغة Agents فعّالة
description: تعلم أفضل الممارسات لتصميم Agents ذكاء اصطناعي قوية ومتخصصة تتعاون بفعالية لحل المشكلات المعقدة.
icon: robot
mode: "wide"
---
## فن وعلم تصميم الـ Agent
في قلب CrewAI يكمن الـ Agent - كيان ذكاء اصطناعي متخصص مصمم لأداء أدوار محددة ضمن إطار تعاوني. بينما إنشاء Agents أساسية أمر بسيط، فإن صياغة Agents فعّالة حقًا تنتج نتائج استثنائية يتطلب فهم مبادئ التصميم الأساسية وأفضل الممارسات.
سيساعدك هذا الدليل على إتقان فن تصميم الـ Agent، مما يمكّنك من إنشاء شخصيات AI متخصصة تتعاون بفعالية وتفكر بشكل نقدي وتنتج مخرجات عالية الجودة مصممة لاحتياجاتك المحددة.
### لماذا يهم تصميم الـ Agent
الطريقة التي تعرّف بها الـ Agents تؤثر بشكل كبير على:
1. **جودة المخرجات**: الـ Agents المصممة جيدًا تنتج نتائج أكثر صلة وجودة
2. **فعالية التعاون**: الـ Agents ذات المهارات المكملة تعمل معًا بكفاءة أكبر
3. **أداء المهام**: الـ Agents ذات الأدوار والأهداف الواضحة تنفذ المهام بفعالية أكبر
4. **قابلية التوسع**: الـ Agents المصممة بعناية يمكن إعادة استخدامها عبر Crews وسياقات متعددة
لنستكشف أفضل الممارسات لإنشاء Agents تتفوق في هذه الأبعاد.
## قاعدة 80/20: ركّز على المهام أكثر من الـ Agents
عند بناء أنظمة AI فعّالة، تذكر هذا المبدأ الحاسم: **80% من جهدك يجب أن يذهب لتصميم المهام، و20% فقط لتعريف الـ Agents**.
لماذا؟ لأن حتى أفضل Agent معرّف سيفشل مع مهام مصممة بشكل سيئ، لكن المهام المصممة جيدًا يمكنها رفع مستوى حتى Agent بسيط. هذا يعني:
- اقضِ معظم وقتك في كتابة تعليمات مهام واضحة
- حدد المدخلات والمخرجات المتوقعة بالتفصيل
- أضف أمثلة وسياقًا لتوجيه التنفيذ
- خصص الوقت المتبقي لدور Agent وهدفه وخلفيته
هذا لا يعني أن تصميم الـ Agent ليس مهمًا - بل هو مهم بالتأكيد. لكن تصميم المهام هو حيث تحدث معظم إخفاقات التنفيذ، لذا رتّب أولوياتك وفقًا لذلك.
## المبادئ الأساسية لتصميم Agent فعّال
### 1. إطار الدور-الهدف-الخلفية
أقوى الـ Agents في CrewAI مبنية على أساس قوي من ثلاثة عناصر رئيسية:
#### الدور: الوظيفة المتخصصة للـ Agent
يحدد الدور ما يفعله الـ Agent ومجال خبرته. عند صياغة الأدوار:
- **كن محددًا ومتخصصًا**: بدلاً من "كاتب"، استخدم "متخصص في التوثيق التقني" أو "راوي قصص إبداعي"
- **تماشَ مع المهن الواقعية**: ابنِ الأدوار على نماذج مهنية معروفة
- **تضمين خبرة المجال**: حدد مجال معرفة الـ Agent (مثل "محلل مالي متخصص في اتجاهات السوق")
**أمثلة على أدوار فعّالة:**
```yaml
role: "Senior UX Researcher specializing in user interview analysis"
role: "Full-Stack Software Architect with expertise in distributed systems"
role: "Corporate Communications Director specializing in crisis management"
```
#### الهدف: غرض الـ Agent ودافعه
يوجه الهدف جهود الـ Agent ويشكّل عملية صنع القرار. الأهداف الفعّالة يجب أن:
- **تكون واضحة ومركّزة على النتائج**: حدد ما يحاول الـ Agent تحقيقه
- **تؤكد على معايير الجودة**: تضمين توقعات حول جودة العمل
- **تتضمن معايير النجاح**: ساعد الـ Agent على فهم ما يعنيه "الجيد"
**أمثلة على أهداف فعّالة:**
```yaml
goal: "Uncover actionable user insights by analyzing interview data and identifying recurring patterns, unmet needs, and improvement opportunities"
goal: "Design robust, scalable system architectures that balance performance, maintainability, and cost-effectiveness"
goal: "Craft clear, empathetic crisis communications that address stakeholder concerns while protecting organizational reputation"
```
#### الخلفية: تجربة الـ Agent ومنظوره
تمنح الخلفية عمقًا لشخصية الـ Agent، مؤثرة في كيفية تعامله مع المشكلات وتفاعله مع الآخرين. الخلفيات الجيدة:
- **تؤسس الخبرة والتجربة**: تشرح كيف اكتسب الـ Agent مهاراته
- **تحدد أسلوب العمل والقيم**: تصف كيف يتعامل الـ Agent مع عمله
- **تنشئ شخصية متماسكة**: تضمن أن جميع عناصر الخلفية تتماشى مع الدور والهدف
**أمثلة على خلفيات فعّالة:**
```yaml
backstory: "You have spent 15 years conducting and analyzing user research for top tech companies. You have a talent for reading between the lines and identifying patterns that others miss. You believe that good UX is invisible and that the best insights come from listening to what users don't say as much as what they do say."
backstory: "With 20+ years of experience building distributed systems at scale, you've developed a pragmatic approach to software architecture. You've seen both successful and failed systems and have learned valuable lessons from each. You balance theoretical best practices with practical constraints and always consider the maintenance and operational aspects of your designs."
backstory: "As a seasoned communications professional who has guided multiple organizations through high-profile crises, you understand the importance of transparency, speed, and empathy in crisis response. You have a methodical approach to crafting messages that address concerns while maintaining organizational credibility."
```
### 2. المتخصصون أفضل من العموميين
يؤدي الـ Agents أداءً أفضل بشكل ملحوظ عند منحهم أدوارًا متخصصة بدلاً من عامة. الـ Agent المركّز بشدة ينتج مخرجات أكثر دقة وصلة:
**عام (أقل فعالية):**
```yaml
role: "Writer"
```
**متخصص (أكثر فعالية):**
```yaml
role: "Technical Blog Writer specializing in explaining complex AI concepts to non-technical audiences"
```
**فوائد التخصص:**
- فهم أوضح للمخرجات المتوقعة
- أداء أكثر اتساقًا
- توافق أفضل مع المهام المحددة
- قدرة محسّنة على إصدار أحكام خاصة بالمجال
### 3. التوازن بين التخصص والمرونة
الـ Agents الفعّالة تحقق التوازن الصحيح بين التخصص (القيام بشيء واحد بشكل ممتاز) والمرونة (التكيف مع مواقف متنوعة):
- **تخصص في الدور، مرونة في التطبيق**: أنشئ Agents بمهارات متخصصة يمكن تطبيقها عبر سياقات متعددة
- **تجنب التعريفات الضيقة جدًا**: تأكد من أن الـ Agents يمكنها التعامل مع التنوعات ضمن مجال خبرتها
- **ضع في الاعتبار السياق التعاوني**: صمم Agents تكمّل تخصصاتها الـ Agents الأخرى التي ستعمل معها
### 4. تعيين مستويات الخبرة المناسبة
مستوى الخبرة الذي تعيّنه للـ Agent يشكّل كيفية تعامله مع المهام:
- **Agents مبتدئة**: جيدة للمهام المباشرة والعصف الذهني والمسودات الأولية
- **Agents متوسطة**: مناسبة لمعظم المهام القياسية مع تنفيذ موثوق
- **Agents خبيرة**: الأفضل للمهام المعقدة والمتخصصة التي تتطلب عمقًا ودقة
- **Agents على مستوى عالمي**: محجوزة للمهام الحرجة حيث الجودة الاستثنائية مطلوبة
اختر مستوى الخبرة المناسب بناءً على تعقيد المهمة ومتطلبات الجودة. لمعظم Crews التعاونية، غالبًا ما يعمل مزيج من مستويات الخبرة بشكل أفضل، مع تعيين خبرة أعلى للوظائف المتخصصة الأساسية.
## أمثلة عملية: قبل وبعد
لنلقِ نظرة على بعض أمثلة تعريفات الـ Agent قبل وبعد تطبيق أفضل الممارسات:
### مثال 1: Agent إنشاء المحتوى
**قبل:**
```yaml
role: "Writer"
goal: "Write good content"
backstory: "You are a writer who creates content for websites."
```
**بعد:**
```yaml
role: "B2B Technology Content Strategist"
goal: "Create compelling, technically accurate content that explains complex topics in accessible language while driving reader engagement and supporting business objectives"
backstory: "You have spent a decade creating content for leading technology companies, specializing in translating technical concepts for business audiences. You excel at research, interviewing subject matter experts, and structuring information for maximum clarity and impact. You believe that the best B2B content educates first and sells second, building trust through genuine expertise rather than marketing hype."
```
### مثال 2: Agent البحث
**قبل:**
```yaml
role: "Researcher"
goal: "Find information"
backstory: "You are good at finding information online."
```
**بعد:**
```yaml
role: "Academic Research Specialist in Emerging Technologies"
goal: "Discover and synthesize cutting-edge research, identifying key trends, methodologies, and findings while evaluating the quality and reliability of sources"
backstory: "With a background in both computer science and library science, you've mastered the art of digital research. You've worked with research teams at prestigious universities and know how to navigate academic databases, evaluate research quality, and synthesize findings across disciplines. You're methodical in your approach, always cross-referencing information and tracing claims to primary sources before drawing conclusions."
```
## صياغة مهام فعّالة للـ Agents
بينما تصميم الـ Agent مهم، تصميم المهام حاسم للتنفيذ الناجح. إليك أفضل الممارسات لتصميم مهام تهيئ الـ Agents للنجاح:
### تشريح المهمة الفعّالة
المهمة المصممة جيدًا لها مكونان رئيسيان يخدمان أغراضًا مختلفة:
#### وصف المهمة: العملية
يجب أن يركز الوصف على ماذا تفعل وكيف تفعله، بما في ذلك:
- تعليمات مفصلة للتنفيذ
- سياق ومعلومات خلفية
- النطاق والقيود
- خطوات العملية المتبعة
#### المخرجات المتوقعة: التسليم
يجب أن تحدد المخرجات المتوقعة شكل النتيجة النهائية:
- مواصفات التنسيق (markdown، JSON، إلخ)
- متطلبات الهيكل
- معايير الجودة
- أمثلة على مخرجات جيدة (عند الإمكان)
### أفضل ممارسات تصميم المهام
#### 1. غرض واحد، مخرج واحد
تؤدي المهام أفضل أداء عند التركيز على هدف واضح واحد:
**مثال سيئ (واسع جدًا):**
```yaml
task_description: "Research market trends, analyze the data, and create a visualization."
```
**مثال جيد (مركّز):**
```yaml
# Task 1
research_task:
description: "Research the top 5 market trends in the AI industry for 2024."
expected_output: "A markdown list of the 5 trends with supporting evidence."
# Task 2
analysis_task:
description: "Analyze the identified trends to determine potential business impacts."
expected_output: "A structured analysis with impact ratings (High/Medium/Low)."
# Task 3
visualization_task:
description: "Create a visual representation of the analyzed trends."
expected_output: "A description of a chart showing trends and their impact ratings."
```
#### 2. كن صريحًا بشأن المدخلات والمخرجات
حدد دائمًا بوضوح ما المدخلات التي ستستخدمها المهمة وكيف يجب أن تبدو المخرجات:
**مثال:**
```yaml
analysis_task:
description: >
Analyze the customer feedback data from the CSV file.
Focus on identifying recurring themes related to product usability.
Consider sentiment and frequency when determining importance.
expected_output: >
A markdown report with the following sections:
1. Executive summary (3-5 bullet points)
2. Top 3 usability issues with supporting data
3. Recommendations for improvement
```
#### 3. تضمين الغرض والسياق
اشرح لماذا تهم المهمة وكيف تتناسب مع سير العمل الأكبر:
**مثال:**
```yaml
competitor_analysis_task:
description: >
Analyze our three main competitors' pricing strategies.
This analysis will inform our upcoming pricing model revision.
Focus on identifying patterns in how they price premium features
and how they structure their tiered offerings.
```
#### 4. استخدام أدوات المخرجات المنظمة
للمخرجات القابلة للقراءة آليًا، حدد التنسيق بوضوح:
**مثال:**
```yaml
data_extraction_task:
description: "Extract key metrics from the quarterly report."
expected_output: "JSON object with the following keys: revenue, growth_rate, customer_acquisition_cost, and retention_rate."
```
## أخطاء شائعة يجب تجنبها
بناءً على الدروس المستفادة من التطبيقات الواقعية، إليك أكثر المزالق شيوعًا في تصميم الـ Agent والمهام:
### 1. تعليمات مهام غير واضحة
**المشكلة:** تفتقر المهام لتفاصيل كافية مما يصعّب على الـ Agents تنفيذها بفعالية.
**مثال تصميم سيئ:**
```yaml
research_task:
description: "Research AI trends."
expected_output: "A report on AI trends."
```
**نسخة محسّنة:**
```yaml
research_task:
description: >
Research the top emerging AI trends for 2024 with a focus on:
1. Enterprise adoption patterns
2. Technical breakthroughs in the past 6 months
3. Regulatory developments affecting implementation
For each trend, identify key companies, technologies, and potential business impacts.
expected_output: >
A comprehensive markdown report with:
- Executive summary (5 bullet points)
- 5-7 major trends with supporting evidence
- For each trend: definition, examples, and business implications
- References to authoritative sources
```
### 2. "مهام إلهية" تحاول فعل الكثير
**المشكلة:** مهام تجمع عمليات معقدة متعددة في مجموعة تعليمات واحدة.
**مثال تصميم سيئ:**
```yaml
comprehensive_task:
description: "Research market trends, analyze competitor strategies, create a marketing plan, and design a launch timeline."
```
**نسخة محسّنة:**
قسّمها إلى مهام متسلسلة ومركّزة:
```yaml
# Task 1: Research
market_research_task:
description: "Research current market trends in the SaaS project management space."
expected_output: "A markdown summary of key market trends."
# Task 2: Competitive Analysis
competitor_analysis_task:
description: "Analyze strategies of the top 3 competitors based on the market research."
expected_output: "A comparison table of competitor strategies."
context: [market_research_task]
# Continue with additional focused tasks...
```
### 3. عدم توافق الوصف والمخرجات المتوقعة
**المشكلة:** وصف المهمة يطلب شيئًا بينما المخرجات المتوقعة تحدد شيئًا مختلفًا.
**مثال تصميم سيئ:**
```yaml
analysis_task:
description: "Analyze customer feedback to find areas of improvement."
expected_output: "A marketing plan for the next quarter."
```
**نسخة محسّنة:**
```yaml
analysis_task:
description: "Analyze customer feedback to identify the top 3 areas for product improvement."
expected_output: "A report listing the 3 priority improvement areas with supporting customer quotes and data points."
```
### 4. عدم فهم العملية بنفسك
**المشكلة:** مطالبة الـ Agents بتنفيذ مهام لا تفهمها أنت بالكامل.
**الحل:**
1. حاول تنفيذ المهمة يدويًا أولاً
2. وثّق عمليتك ونقاط القرار ومصادر المعلومات
3. استخدم هذا التوثيق كأساس لوصف مهمتك
### 5. الاستخدام المبكر للهياكل الهرمية
**المشكلة:** إنشاء هرميات Agents معقدة بلا داعٍ حيث تعمل العمليات المتسلسلة بشكل أفضل.
**الحل:** ابدأ بالعمليات المتسلسلة وانتقل إلى النماذج الهرمية فقط عندما يتطلب تعقيد سير العمل ذلك حقًا.
### 6. تعريفات Agent غامضة أو عامة
**المشكلة:** تعريفات Agent العامة تؤدي لمخرجات عامة.
**مثال تصميم سيئ:**
```yaml
agent:
role: "Business Analyst"
goal: "Analyze business data"
backstory: "You are good at business analysis."
```
**نسخة محسّنة:**
```yaml
agent:
role: "SaaS Metrics Specialist focusing on growth-stage startups"
goal: "Identify actionable insights from business data that can directly impact customer retention and revenue growth"
backstory: "With 10+ years analyzing SaaS business models, you've developed a keen eye for the metrics that truly matter for sustainable growth. You've helped numerous companies identify the leverage points that turned around their business trajectory. You believe in connecting data to specific, actionable recommendations rather than general observations."
```
## استراتيجيات متقدمة لتصميم الـ Agent
### التصميم للتعاون
عند إنشاء Agents ستعمل معًا في Crew، ضع في اعتبارك:
- **مهارات مكملة**: صمم Agents بقدرات مميزة ومكملة
- **نقاط التسليم**: حدد واجهات واضحة لكيفية انتقال العمل بين الـ Agents
- **توتر بنّاء**: أحيانًا، إنشاء Agents بمنظورات مختلفة قليلاً يمكن أن يؤدي لنتائج أفضل من خلال حوار منتج
على سبيل المثال، قد يتضمن Crew إنشاء محتوى:
```yaml
# Research Agent
role: "Research Specialist for technical topics"
goal: "Gather comprehensive, accurate information from authoritative sources"
backstory: "You are a meticulous researcher with a background in library science..."
# Writer Agent
role: "Technical Content Writer"
goal: "Transform research into engaging, clear content that educates and informs"
backstory: "You are an experienced writer who excels at explaining complex concepts..."
# Editor Agent
role: "Content Quality Editor"
goal: "Ensure content is accurate, well-structured, and polished while maintaining consistency"
backstory: "With years of experience in publishing, you have a keen eye for detail..."
```
### إنشاء مستخدمي أدوات متخصصين
يمكن تصميم بعض الـ Agents خصيصًا للاستفادة من أدوات معينة بفعالية:
```yaml
role: "Data Analysis Specialist"
goal: "Derive meaningful insights from complex datasets through statistical analysis"
backstory: "With a background in data science, you excel at working with structured and unstructured data..."
tools: [PythonREPLTool, DataVisualizationTool, CSVAnalysisTool]
```
### تكييف الـ Agents مع قدرات LLM
للنماذج المختلفة نقاط قوة مختلفة. صمم الـ Agents مع وضع هذه القدرات في الاعتبار:
```yaml
# For complex reasoning tasks
analyst:
role: "Data Insights Analyst"
goal: "..."
backstory: "..."
llm: openai/gpt-4o
# For creative content
writer:
role: "Creative Content Writer"
goal: "..."
backstory: "..."
llm: anthropic/claude-3-opus
```
## اختبار تصميم الـ Agent والتكرار عليه
تصميم الـ Agent غالبًا عملية تكرارية. إليك نهجًا عمليًا:
1. **ابدأ بنموذج أولي**: أنشئ تعريف Agent أولي
2. **اختبر مع مهام نموذجية**: قيّم الأداء على مهام تمثيلية
3. **حلل المخرجات**: حدد نقاط القوة والضعف
4. **صقل التعريف**: اضبط الدور والهدف والخلفية بناءً على الملاحظات
5. **اختبر في بيئة تعاونية**: قيّم كيف يعمل الـ Agent في إعداد Crew
## الخلاصة
صياغة Agents فعّالة هي فن وعلم في آن واحد. من خلال تعريف الأدوار والأهداف والخلفيات بعناية بما يتماشى مع احتياجاتك المحددة، ودمجها مع مهام مصممة جيدًا، يمكنك إنشاء متعاونين AI متخصصين ينتجون نتائج استثنائية.
تذكر أن تصميم الـ Agent والمهام عملية تكرارية. ابدأ بأفضل الممارسات هذه، وراقب الـ Agents أثناء العمل، وصقل نهجك بناءً على ما تتعلمه. وتذكر دائمًا قاعدة 80/20 - ركّز معظم جهدك على إنشاء مهام واضحة ومركّزة للحصول على أفضل النتائج من الـ Agents.
<Check>
تهانينا! أنت الآن تفهم مبادئ وممارسات تصميم Agent الفعّال. طبّق هذه التقنيات لإنشاء Agents قوية ومتخصصة تعمل معًا بسلاسة لإنجاز مهام معقدة.
</Check>
## الخطوات التالية
- جرّب تهيئات Agent مختلفة لحالة استخدامك المحددة
- تعلم عن [بناء أول Crew](/ar/guides/crews/first-crew) لمعرفة كيف تعمل الـ Agents معًا
- استكشف [CrewAI Flows](/ar/guides/flows/first-flow) لتنسيق أكثر تقدمًا

View File

@@ -0,0 +1,61 @@
---
title: أدوات البرمجة
description: استخدم AGENTS.md لتوجيه أدوات البرمجة وبيئات التطوير عبر مشاريع CrewAI.
icon: terminal
mode: "wide"
---
## لماذا AGENTS.md
`AGENTS.md` هو ملف تعليمات خفيف محلي للمستودع يمنح أدوات البرمجة توجيهات متسقة خاصة بالمشروع. ضعه في جذر المشروع واعتبره المصدر الموثوق لكيفية عمل المساعدين: الاصطلاحات والأوامر وملاحظات البنية والحدود.
## إنشاء مشروع باستخدام CLI
استخدم CLI الخاص بـ CrewAI لإنشاء هيكل مشروع، وسيُضاف `AGENTS.md` تلقائيًا في الجذر.
```bash
# Crew
crewai create crew my_crew
# Flow
crewai create flow my_flow
# Tool repository
crewai tool create my_tool
```
## إعداد الأدوات: توجيه المساعدين إلى AGENTS.md
### Codex
يمكن توجيه Codex بملفات `AGENTS.md` الموضوعة في مستودعك. استخدمها لتوفير سياق مشروع مستمر مثل الاصطلاحات والأوامر وتوقعات سير العمل.
### Claude Code
يخزّن Claude Code ذاكرة المشروع في `CLAUDE.md`. يمكنك تهيئته بـ `/init` وتحريره باستخدام `/memory`. يدعم Claude Code أيضًا الاستيرادات داخل `CLAUDE.md`، فيمكنك إضافة سطر واحد مثل `@AGENTS.md` لسحب التعليمات المشتركة دون تكرارها.
يمكنك ببساطة استخدام:
```bash
mv AGENTS.md CLAUDE.md
```
### Gemini CLI وGoogle Antigravity
يقوم Gemini CLI وAntigravity بتحميل ملف سياق المشروع (الافتراضي: `GEMINI.md`) من جذر المستودع والمجلدات الأصلية. يمكنك تهيئته لقراءة `AGENTS.md` بدلاً من ذلك (أو بالإضافة إليه) بتعيين `context.fileName` في إعدادات Gemini CLI. على سبيل المثال، عيّنه إلى `AGENTS.md` فقط، أو أدرج كلاً من `AGENTS.md` و`GEMINI.md` إذا أردت الاحتفاظ بتنسيق كل أداة.
يمكنك ببساطة استخدام:
```bash
mv AGENTS.md GEMINI.md
```
### Cursor
يدعم Cursor ملف `AGENTS.md` كملف تعليمات مشروع. ضعه في جذر المشروع لتوفير توجيهات لمساعد البرمجة في Cursor.
### Windsurf
يوفر Claude Code تكاملاً رسميًا مع Windsurf. إذا كنت تستخدم Claude Code داخل Windsurf، اتبع توجيهات Claude Code أعلاه واستورد `AGENTS.md` من `CLAUDE.md`.
إذا كنت تستخدم مساعد Windsurf الأصلي، هيّئ ميزة قواعد أو تعليمات المشروع (إذا كانت متاحة) لقراءة `AGENTS.md` أو الصق المحتويات مباشرة.

View File

@@ -0,0 +1,214 @@
---
title: "البناء باستخدام الذكاء الاصطناعي"
description: "كل ما يحتاجه وكلاء البرمجة بالذكاء الاصطناعي للبناء والنشر والتوسع مع CrewAI — المهارات، وثائق مقروءة آلياً، النشر، وميزات المؤسسات."
icon: robot
mode: "wide"
---
# البناء باستخدام الذكاء الاصطناعي
CrewAI مُصمَّم أصلاً للعمل مع الذكاء الاصطناعي. تجمع هذه الصفحة ما يحتاجه وكيل البرمجة بالذكاء الاصطناعي للبناء مع CrewAI — سواءً كان Claude Code أو Codex أو Cursor أو Gemini CLI أو أي مساعد آخر يساعد المطوّر على إيصال الـ crews والـ flows.
### وكلاء البرمجة المدعومون
<CardGroup cols={5}>
<Card title="Claude Code" icon="message-bot" color="#D97706" />
<Card title="Cursor" icon="arrow-pointer" color="#3B82F6" />
<Card title="Codex" icon="terminal" color="#10B981" />
<Card title="Windsurf" icon="wind" color="#06B6D4" />
<Card title="Gemini CLI" icon="sparkles" color="#8B5CF6" />
</CardGroup>
<Note>
صُممت هذه الصفحة للبشر وللمساعدين الذكيين على حدٍّ سواء. إذا كنت وكيل برمجة، ابدأ بـ **Skills** للحصول على سياق CrewAI، ثم استخدم **llms.txt** للوصول الكامل إلى الوثائق.
</Note>
---
## 1. Skills — علِّم وكيلك CrewAI
**Skills** حزم تعليمات تمنح وكلاء البرمجة معرفة عميقة بـ CrewAI — كيفية إنشاء هيكل Flows، وضبط Crews، استخدام الأدوات، واتباع اتفاقيات الإطار.
<Tabs>
<Tab title="Claude Code (سوق الإضافات)">
<img src="https://cdn.simpleicons.org/anthropic/D97706" alt="Anthropic" width="28" style={{display: "inline", verticalAlign: "middle", marginRight: "8px"}} />
مهارات CrewAI متاحة في **سوق إضافات Claude Code** — نفس قناة التوزيع التي تستخدمها شركات رائدة في مجال الذكاء الاصطناعي:
```shell
/plugin marketplace add crewAIInc/skills
/plugin install crewai-skills@crewai-plugins
/reload-plugins
```
تُفعَّل أربع مهارات تلقائياً عند طرح أسئلة متعلقة بـ CrewAI:
| المهارة | متى تُستخدم |
|---------|-------------|
| `getting-started` | مشاريع جديدة، الاختيار بين `LLM.call()` / `Agent` / `Crew` / `Flow`، ربط `crew.jsonc` / `main.py` |
| `design-agent` | ضبط الوكلاء — الدور، الهدف، الخلفية، الأدوات، نماذج اللغة، الذاكرة، الحدود الآمنة |
| `design-task` | وصف المهام، التبعيات، المخرجات المنظمة (`output_pydantic`، `output_json`)، المراجعة البشرية |
| `ask-docs` | الاستعلام من [خادم CrewAI docs MCP](https://docs.crewai.com/mcp) للحصول على تفاصيل واجهة البرمجة الحالية |
</Tab>
<Tab title="npx (أي وكيل)">
يعمل مع Claude Code أو Codex أو Cursor أو Gemini CLI أو أي وكيل برمجة:
```shell
npx skills add crewaiinc/skills
```
يُجلب من [سجل skills.sh](https://skills.sh/crewaiinc/skills).
</Tab>
</Tabs>
<Steps>
<Step title="ثبِّت حزمة المهارات الرسمية">
استخدم إحدى الطريقتين أعلاه — سوق إضافات Claude Code أو `npx skills add`. كلاهما يثبّت الحزمة الرسمية [crewAIInc/skills](https://github.com/crewAIInc/skills).
</Step>
<Step title="يحصل وكيلك فوراً على خبرة CrewAI">
تعلّم الحزمة وكيلك:
- **Flows** — تطبيقات ذات حالة، خطوات، وتشغيل crews
- **Crews والوكلاء** — أنماط JSON-first (`crew.jsonc` و `agents/*.jsonc`)، الأدوار، المهام، التفويض
- **الأدوات والتكاملات** — البحث، واجهات API، خوادم MCP، وأدوات CrewAI الشائعة
- **هيكل المشروع** — هياكل CLI واتفاقيات المستودع
- **أنماط محدثة** — يتماشى مع وثائق CrewAI الحالية وأفضل الممارسات
</Step>
<Step title="ابدأ البناء">
يمكن لوكيلك الآن إنشاء هيكل وبناء مشاريع CrewAI دون أن تعيد شرح الإطار في كل جلسة.
</Step>
</Steps>
<CardGroup cols={2}>
<Card title="مفهوم Skills" icon="bolt" href="/ar/concepts/skills">
كيف تعمل المهارات في وكلاء CrewAI — الحقن، التفعيل، والأنماط.
</Card>
<Card title="صفحة Skills" icon="wand-magic-sparkles" href="/ar/skills">
نظرة على حزمة crewAIInc/skills وما تتضمنه.
</Card>
<Card title="AGENTS.md والأدوات" icon="terminal" href="/ar/guides/coding-tools/agents-md">
إعداد AGENTS.md لـ Claude Code وCodex وCursor وGemini CLI.
</Card>
<Card title="سجل skills.sh" icon="globe" href="https://skills.sh/crewaiinc/skills">
القائمة الرسمية — المهارات، إحصاءات التثبيت، والتدقيق.
</Card>
</CardGroup>
---
## 2. llms.txt — وثائق مقروءة آلياً
ينشر CrewAI ملف `llms.txt` يمنح المساعدين الذكيين وصولاً مباشراً إلى الوثائق الكاملة بصيغة مقروءة آلياً.
```
https://docs.crewai.com/llms.txt
```
<Tabs>
<Tab title="ما هو llms.txt؟">
[`llms.txt`](https://llmstxt.org/) معيار ناشئ لجعل الوثائق قابلة للاستهلاك من قبل نماذج اللغة الكبيرة. بدلاً من استخراج HTML، يمكن لوكيلك جلب ملف نصي واحد منظم بكل المحتوى المطلوب.
ملف `llms.txt` الخاص بـ CrewAI **متاح فعلياً** — يمكن لوكيلك استخدامه الآن.
</Tab>
<Tab title="كيفية الاستخدام">
وجِّه وكيل البرمجة إلى عنوان URL عندما يحتاج إلى مرجع CrewAI:
```
Fetch https://docs.crewai.com/llms.txt for CrewAI documentation.
```
يمكن للعديد من وكلاء البرمجة (Claude Code، Cursor، وغيرهما) جلب عناوين URL مباشرة. يحتوي الملف على وثائق منظمة تغطي مفاهيم CrewAI وواجهات البرمجة والأدلة.
</Tab>
<Tab title="لماذا يهم">
- **دون استخراج ويب** — محتوى نظيف ومنظم في طلب واحد
- **دائماً محدث** — يُقدَّم مباشرة من docs.crewai.com
- **محسّن لنماذج اللغة** — مُنسَّق لنوافذ السياق لا للمتصفحات
- **يُكمّل Skills** — المهارات تعلّم الأنماط، وllms.txt يوفّر المرجع
</Tab>
</Tabs>
---
## 3. النشر للمؤسسات
انتقل من crew محلي إلى الإنتاج على **CrewAI AMP** (منصة إدارة الوكلاء) في دقائق.
<Steps>
<Step title="ابنِ محلياً">
أنشئ الهيكل واختبر crew أو flow:
```bash
crewai create crew my_crew
cd my_crew
crewai run
```
</Step>
<Step title="جهّز للنشر">
تأكد أن هيكل مشروعك جاهز:
```bash
crewai deploy --prepare
```
راجع [دليل التحضير](https://docs-platform.crewai.com/platform/ar/guides/prepare-for-deployment) لتفاصيل الهيكل والمتطلبات.
</Step>
<Step title="انشر على AMP">
ادفع إلى منصة CrewAI AMP:
```bash
crewai deploy
```
يمكنك أيضاً النشر عبر [تكامل GitHub](https://docs-platform.crewai.com/platform/ar/guides/deploy-to-amp) أو [Crew Studio](https://docs-platform.crewai.com/platform/ar/guides/enable-crew-studio).
</Step>
<Step title="الوصول عبر API">
يحصل الـ crew المنشور على نقطة نهاية REST. دمجه في أي تطبيق:
```bash
curl -X POST https://app.crewai.com/api/v1/crews/<crew-id>/kickoff \
-H "Authorization: Bearer $CREWAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"inputs": {"topic": "AI agents"}}'
```
</Step>
</Steps>
<CardGroup cols={2}>
<Card title="النشر على AMP" icon="rocket" href="https://docs-platform.crewai.com/platform/ar/guides/deploy-to-amp">
دليل النشر الكامل — CLI وGitHub وCrew Studio.
</Card>
<Card title="مقدمة عن AMP" icon="globe" href="https://docs-platform.crewai.com/platform/ar/introduction">
نظرة على المنصة — ما يوفّره AMP لـ crews في الإنتاج.
</Card>
</CardGroup>
---
## 4. ميزات المؤسسات
CrewAI AMP مُصمَّم لفرق الإنتاج. إليك ما تحصل عليه بعد النشر.
<CardGroup cols={2}>
<Card title="المراقبة والرصد" icon="chart-line">
مسارات تنفيذ مفصّلة، وسجلات، ومقاييس أداء لكل تشغيل crew. راقب قرارات الوكلاء، استدعاءات الأدوات، وإكمال المهام في الوقت الفعلي.
</Card>
<Card title="Crew Studio" icon="paintbrush">
واجهة منخفضة/بدون كود لإنشاء crews وتخصيصها ونشرها بصرياً — ثم التصدير إلى الشيفرة أو النشر مباشرة.
</Card>
<Card title="بث الويبهوك" icon="webhook">
بث أحداث فورية من تنفيذات الـ crews إلى أنظمتك. تكامل مع Slack أو Zapier أو أي مستهلك ويبهوك.
</Card>
<Card title="إدارة الفريق" icon="users">
SSO وRBAC وضوابط على مستوى المؤسسة. أدر من يمكنه إنشاء crews ونشرها والوصول إليها.
</Card>
<Card title="مستودع الأدوات" icon="toolbox">
انشر وشارك أدواتاً مخصصة عبر مؤسستك. ثبّت أدوات المجتمع من السجل.
</Card>
<Card title="Factory (استضافة ذاتية)" icon="server">
شغّل CrewAI AMP على بنيتك التحتية. قدرات المنصة كاملة مع ضوابط إقامة البيانات والامتثال.
</Card>
</CardGroup>
<AccordionGroup>
<Accordion title="لمن مخصص AMP؟">
لفرق تحتاج نقل سير عمل وكلاء الذكاء الاصطناعي من النماذج الأولية إلى الإنتاج — مع المراقبة وضوابط الوصول والبنية التحتية القابلة للتوسع. سواءً كنت ناشئاً أو مؤسسة كبيرة، يتولى AMP التعقيد التشغيلي لتتفرغ لبناء الوكلاء.
</Accordion>
<Accordion title="ما خيارات النشر المتاحة؟">
- **السحابة (app.crewai.com)** — تُدار من CrewAI، أسرع طريق إلى الإنتاج
- **Factory (استضافة ذاتية)** — على بنيتك التحتية لسيطرة كاملة على البيانات
- **هجين** — دمج السحابة والاستضافة الذاتية حسب حساسية البيانات
</Accordion>
</AccordionGroup>
<Card title="استكشف CrewAI AMP →" icon="arrow-right" href="https://app.crewai.com">
سجّل وانشر أول crew لك في الإنتاج.
</Card>

View File

@@ -0,0 +1,485 @@
---
title: تقييم حالات الاستخدام لـ CrewAI
description: تعلم كيفية تقييم احتياجات تطبيقات الذكاء الاصطناعي واختيار النهج الصحيح بين Crews وFlows بناءً على متطلبات التعقيد والدقة.
icon: scale-balanced
mode: "wide"
---
## فهم إطار القرار
عند بناء تطبيقات ذكاء اصطناعي مع CrewAI، أحد أهم القرارات التي ستتخذها هو اختيار النهج الصحيح لحالة الاستخدام المحددة. هل يجب استخدام Crew؟ أم Flow؟ أم مزيج من كليهما؟ سيساعدك هذا الدليل على تقييم متطلباتك واتخاذ قرارات معمارية مدروسة.
في جوهر هذا القرار فهم العلاقة بين **التعقيد** و**الدقة** في تطبيقك:
<Frame caption="مصفوفة التعقيد مقابل الدقة لتطبيقات CrewAI">
<img src="/images/complexity_precision.png" alt="مصفوفة التعقيد مقابل الدقة" />
</Frame>
تساعد هذه المصفوفة في تصور كيف تتوافق النهج المختلفة مع متطلبات متفاوتة للتعقيد والدقة. لنستكشف ما يعنيه كل ربع وكيف يوجه خياراتك المعمارية.
## شرح مصفوفة التعقيد-الدقة
### ما هو التعقيد؟
في سياق تطبيقات CrewAI، يشير **التعقيد** إلى:
- عدد الخطوات أو العمليات المميزة المطلوبة
- تنوع المهام التي يجب تنفيذها
- التبعيات المتبادلة بين المكونات المختلفة
- الحاجة للمنطق الشرطي والتفرع
- تطور سير العمل الكلي
### ما هي الدقة؟
**الدقة** في هذا السياق تشير إلى:
- الدقة المطلوبة في المخرجات النهائية
- الحاجة لنتائج منظمة وقابلة للتنبؤ
- أهمية إمكانية التكرار
- مستوى التحكم المطلوب في كل خطوة
- تحمّل التباين في المخرجات
### الأرباع الأربعة
#### 1. تعقيد منخفض، دقة منخفضة
**الخصائص:**
- مهام بسيطة ومباشرة
- تحمّل بعض التباين في المخرجات
- عدد محدود من الخطوات
- تطبيقات إبداعية أو استكشافية
**النهج الموصى به:** Crews بسيطة مع عدد قليل من الـ Agents
**أمثلة على حالات الاستخدام:**
- إنشاء محتوى أساسي
- العصف الذهني
- مهام التلخيص البسيطة
- مساعدة الكتابة الإبداعية
#### 2. تعقيد منخفض، دقة عالية
**الخصائص:**
- سير عمل بسيطة تتطلب مخرجات دقيقة ومنظمة
- حاجة لنتائج قابلة للتكرار
- خطوات محدودة مع متطلبات دقة عالية
- غالبًا تتضمن معالجة أو تحويل بيانات
**النهج الموصى به:** Flows مع استدعاءات LLM مباشرة أو Crews بسيطة مع مخرجات منظمة
**أمثلة على حالات الاستخدام:**
- استخراج البيانات وتحويلها
- ملء النماذج والتحقق منها
- إنشاء محتوى منظم (JSON، XML)
- مهام التصنيف البسيطة
#### 3. تعقيد عالٍ، دقة منخفضة
**الخصائص:**
- عمليات متعددة المراحل بخطوات كثيرة
- مخرجات إبداعية أو استكشافية
- تفاعلات معقدة بين المكونات
- تحمّل التباين في النتائج النهائية
**النهج الموصى به:** Crews معقدة مع عدة Agents متخصصة
**أمثلة على حالات الاستخدام:**
- البحث والتحليل
- خطوط إنتاج المحتوى
- تحليل البيانات الاستكشافي
- حل المشكلات الإبداعي
#### 4. تعقيد عالٍ، دقة عالية
**الخصائص:**
- سير عمل معقدة تتطلب مخرجات منظمة
- خطوات مترابطة متعددة مع متطلبات دقة صارمة
- حاجة لمعالجة متطورة ونتائج دقيقة معًا
- غالبًا تطبيقات حرجة المهمة
**النهج الموصى به:** Flows تنسّق عدة Crews مع خطوات تحقق
**أمثلة على حالات الاستخدام:**
- أنظمة دعم القرار المؤسسية
- خطوط معالجة بيانات معقدة
- معالجة مستندات متعددة المراحل
- تطبيقات الصناعات المنظمة
## الاختيار بين Crews وFlows
### متى تختار Crews
الـ Crews مثالية عندما:
1. **تحتاج ذكاء تعاوني** - عدة Agents بتخصصات مختلفة تحتاج للعمل معًا
2. **المشكلة تتطلب تفكيرًا ناشئًا** - الحل يستفيد من منظورات ونُهج مختلفة
3. **المهمة إبداعية أو تحليلية بالأساس** - العمل يتضمن بحثًا أو إنشاء محتوى أو تحليل
4. **تقدّر القدرة على التكيف على الهيكل الصارم** - سير العمل يمكن أن يستفيد من استقلالية الـ Agent
5. **تنسيق المخرجات يمكن أن يكون مرنًا نوعًا ما** - بعض التباين في هيكل المخرجات مقبول
```python
# Example: Research Crew for market analysis
from crewai import Agent, Crew, Process, Task
# Create specialized agents
researcher = Agent(
role="Market Research Specialist",
goal="Find comprehensive market data on emerging technologies",
backstory="You are an expert at discovering market trends and gathering data."
)
analyst = Agent(
role="Market Analyst",
goal="Analyze market data and identify key opportunities",
backstory="You excel at interpreting market data and spotting valuable insights."
)
# Define their tasks
research_task = Task(
description="Research the current market landscape for AI-powered healthcare solutions",
expected_output="Comprehensive market data including key players, market size, and growth trends",
agent=researcher
)
analysis_task = Task(
description="Analyze the market data and identify the top 3 investment opportunities",
expected_output="Analysis report with 3 recommended investment opportunities and rationale",
agent=analyst,
context=[research_task]
)
# Create the crew
market_analysis_crew = Crew(
agents=[researcher, analyst],
tasks=[research_task, analysis_task],
process=Process.sequential,
verbose=True
)
# Run the crew
result = market_analysis_crew.kickoff()
```
### متى تختار Flows
الـ Flows مثالية عندما:
1. **تحتاج تحكمًا دقيقًا في التنفيذ** - سير العمل يتطلب تسلسلًا دقيقًا وإدارة حالة
2. **التطبيق له متطلبات حالة معقدة** - تحتاج لصيانة وتحويل الحالة عبر خطوات متعددة
3. **تحتاج مخرجات منظمة وقابلة للتنبؤ** - التطبيق يتطلب نتائج متسقة ومنسّقة
4. **سير العمل يتضمن منطقًا شرطيًا** - مسارات مختلفة يجب اتخاذها بناءً على نتائج وسيطة
5. **تحتاج الجمع بين AI وكود إجرائي** - الحل يتطلب قدرات AI وبرمجة تقليدية معًا
```python
# Example: Customer Support Flow with structured processing
from crewai.flow.flow import Flow, listen, router, start
from pydantic import BaseModel
from typing import List, Dict
# Define structured state
class SupportTicketState(BaseModel):
ticket_id: str = ""
customer_name: str = ""
issue_description: str = ""
category: str = ""
priority: str = "medium"
resolution: str = ""
satisfaction_score: int = 0
class CustomerSupportFlow(Flow[SupportTicketState]):
@start()
def receive_ticket(self):
self.state.ticket_id = "TKT-12345"
self.state.customer_name = "Alex Johnson"
self.state.issue_description = "Unable to access premium features after payment"
return "Ticket received"
@listen(receive_ticket)
def categorize_ticket(self, _):
from crewai import LLM
llm = LLM(model="openai/gpt-4o-mini")
prompt = f"""
Categorize the following customer support issue into one of these categories:
- Billing
- Account Access
- Technical Issue
- Feature Request
- Other
Issue: {self.state.issue_description}
Return only the category name.
"""
self.state.category = llm.call(prompt).strip()
return self.state.category
@router(categorize_ticket)
def route_by_category(self, category):
return category.lower().replace(" ", "_")
@listen("billing")
def handle_billing_issue(self):
self.state.priority = "high"
return "Billing issue handled"
@listen("account_access")
def handle_access_issue(self):
self.state.priority = "high"
return "Access issue handled"
@listen("billing", "account_access", "technical_issue", "feature_request", "other")
def resolve_ticket(self, resolution_info):
self.state.resolution = f"Issue resolved: {resolution_info}"
return self.state.resolution
# Run the flow
support_flow = CustomerSupportFlow()
result = support_flow.kickoff()
```
### متى تجمع بين Crews وFlows
أكثر التطبيقات تطورًا غالبًا تستفيد من الجمع بين Crews وFlows:
1. **عمليات معقدة متعددة المراحل** - استخدم Flows لتنسيق العملية الكلية وCrews للمهام الفرعية المعقدة
2. **تطبيقات تتطلب إبداعًا وهيكلاً معًا** - استخدم Crews للمهام الإبداعية وFlows للمعالجة المنظمة
3. **تطبيقات AI مؤسسية** - استخدم Flows لإدارة الحالة وتدفق العمليات مع الاستفادة من Crews للعمل المتخصص
```python
# Example: Content Production Pipeline combining Crews and Flows
from crewai.flow.flow import Flow, listen, start
from crewai import Agent, Crew, Process, Task
from pydantic import BaseModel
from typing import List, Dict
class ContentState(BaseModel):
topic: str = ""
target_audience: str = ""
content_type: str = ""
outline: Dict = {}
draft_content: str = ""
final_content: str = ""
seo_score: int = 0
class ContentProductionFlow(Flow[ContentState]):
@start()
def initialize_project(self):
self.state.topic = "Sustainable Investing"
self.state.target_audience = "Millennial Investors"
self.state.content_type = "Blog Post"
return "Project initialized"
@listen(initialize_project)
def create_outline(self, _):
researcher = Agent(
role="Content Researcher",
goal=f"Research {self.state.topic} for {self.state.target_audience}",
backstory="You are an expert researcher with deep knowledge of content creation."
)
outliner = Agent(
role="Content Strategist",
goal=f"Create an engaging outline for a {self.state.content_type}",
backstory="You excel at structuring content for maximum engagement."
)
research_task = Task(
description=f"Research {self.state.topic} focusing on what would interest {self.state.target_audience}",
expected_output="Comprehensive research notes with key points and statistics",
agent=researcher
)
outline_task = Task(
description=f"Create an outline for a {self.state.content_type} about {self.state.topic}",
expected_output="Detailed content outline with sections and key points",
agent=outliner,
context=[research_task]
)
outline_crew = Crew(
agents=[researcher, outliner],
tasks=[research_task, outline_task],
process=Process.sequential,
verbose=True
)
result = outline_crew.kickoff()
import json
try:
self.state.outline = json.loads(result.raw)
except:
self.state.outline = {"sections": result.raw}
return "Outline created"
@listen(create_outline)
def write_content(self, _):
writer = Agent(
role="Content Writer",
goal=f"Write engaging content for {self.state.target_audience}",
backstory="You are a skilled writer who creates compelling content."
)
editor = Agent(
role="Content Editor",
goal="Ensure content is polished, accurate, and engaging",
backstory="You have a keen eye for detail and a talent for improving content."
)
writing_task = Task(
description=f"Write a {self.state.content_type} about {self.state.topic} following this outline: {self.state.outline}",
expected_output="Complete draft content in markdown format",
agent=writer
)
editing_task = Task(
description="Edit and improve the draft content for clarity, engagement, and accuracy",
expected_output="Polished final content in markdown format",
agent=editor,
context=[writing_task]
)
writing_crew = Crew(
agents=[writer, editor],
tasks=[writing_task, editing_task],
process=Process.sequential,
verbose=True
)
result = writing_crew.kickoff()
self.state.final_content = result.raw
return "Content created"
@listen(write_content)
def optimize_for_seo(self, _):
from crewai import LLM
llm = LLM(model="openai/gpt-4o-mini")
prompt = f"""
Analyze this content for SEO effectiveness for the keyword "{self.state.topic}".
Rate it on a scale of 1-100 and provide 3 specific recommendations for improvement.
Content: {self.state.final_content[:1000]}... (truncated for brevity)
Format your response as JSON with the following structure:
{{
"score": 85,
"recommendations": [
"Recommendation 1",
"Recommendation 2",
"Recommendation 3"
]
}}
"""
seo_analysis = llm.call(prompt)
import json
try:
analysis = json.loads(seo_analysis)
self.state.seo_score = analysis.get("score", 0)
return analysis
except:
self.state.seo_score = 50
return {"score": 50, "recommendations": ["Unable to parse SEO analysis"]}
# Run the flow
content_flow = ContentProductionFlow()
result = content_flow.kickoff()
```
## إطار التقييم العملي
لتحديد النهج الصحيح لحالة استخدامك المحددة، اتبع إطار التقييم التدريجي هذا:
### الخطوة 1: تقييم التعقيد
قيّم تعقيد تطبيقك على مقياس من 1-10 من خلال النظر في:
1. **عدد الخطوات**: كم عدد العمليات المميزة المطلوبة؟
- 1-3 خطوات: تعقيد منخفض (1-3)
- 4-7 خطوات: تعقيد متوسط (4-7)
- 8+ خطوات: تعقيد عالٍ (8-10)
2. **التبعيات المتبادلة**: ما مدى ترابط الأجزاء المختلفة؟
- تبعيات قليلة: تعقيد منخفض (1-3)
- بعض التبعيات: تعقيد متوسط (4-7)
- تبعيات معقدة كثيرة: تعقيد عالٍ (8-10)
3. **المنطق الشرطي**: ما مقدار التفرع وصنع القرار المطلوب؟
- عملية خطية: تعقيد منخفض (1-3)
- بعض التفرع: تعقيد متوسط (4-7)
- أشجار قرار معقدة: تعقيد عالٍ (8-10)
4. **المعرفة التخصصية**: ما مدى تخصص المعرفة المطلوبة؟
- معرفة عامة: تعقيد منخفض (1-3)
- بعض المعرفة المتخصصة: تعقيد متوسط (4-7)
- خبرة عميقة في مجالات متعددة: تعقيد عالٍ (8-10)
احسب متوسط درجتك لتحديد التعقيد الكلي.
### الخطوة 2: تقييم متطلبات الدقة
قيّم متطلبات الدقة على مقياس من 1-10 من خلال النظر في:
1. **هيكل المخرجات**: ما مدى التنظيم المطلوب في المخرجات؟
- نص حر: دقة منخفضة (1-3)
- شبه منظم: دقة متوسطة (4-7)
- منسّق بشكل صارم (JSON، XML): دقة عالية (8-10)
2. **احتياجات الدقة**: ما أهمية الدقة الواقعية؟
- محتوى إبداعي: دقة منخفضة (1-3)
- محتوى معلوماتي: دقة متوسطة (4-7)
- معلومات حرجة: دقة عالية (8-10)
3. **إمكانية التكرار**: ما مدى اتساق النتائج عبر التشغيلات؟
- التباين مقبول: دقة منخفضة (1-3)
- بعض الاتساق مطلوب: دقة متوسطة (4-7)
- تكرار دقيق مطلوب: دقة عالية (8-10)
4. **تحمّل الأخطاء**: ما تأثير الأخطاء؟
- تأثير منخفض: دقة منخفضة (1-3)
- تأثير معتدل: دقة متوسطة (4-7)
- تأثير عالٍ: دقة عالية (8-10)
احسب متوسط درجتك لتحديد متطلبات الدقة الكلية.
### الخطوة 3: التعيين على المصفوفة
ارسم درجات التعقيد والدقة على المصفوفة:
- **تعقيد منخفض (1-4)، دقة منخفضة (1-4)**: Crews بسيطة
- **تعقيد منخفض (1-4)، دقة عالية (5-10)**: Flows مع استدعاءات LLM مباشرة
- **تعقيد عالٍ (5-10)، دقة منخفضة (1-4)**: Crews معقدة
- **تعقيد عالٍ (5-10)، دقة عالية (5-10)**: Flows تنسّق Crews
### الخطوة 4: مراعاة عوامل إضافية
بالإضافة إلى التعقيد والدقة، ضع في اعتبارك:
1. **وقت التطوير**: غالبًا ما تكون Crews أسرع في النماذج الأولية
2. **احتياجات الصيانة**: توفر Flows قابلية صيانة أفضل على المدى الطويل
3. **خبرة الفريق**: ضع في اعتبارك ألفة فريقك مع النُهج المختلفة
4. **متطلبات التوسع**: عادةً ما تتوسع Flows بشكل أفضل للتطبيقات المعقدة
5. **احتياجات التكامل**: ضع في اعتبارك كيف سيتكامل الحل مع الأنظمة الحالية
## الخلاصة
الاختيار بين Crews وFlows — أو الجمع بينهما — قرار معماري حاسم يؤثر على فعالية وقابلية صيانة وتوسع تطبيق CrewAI. من خلال تقييم حالة الاستخدام على أبعاد التعقيد والدقة، يمكنك اتخاذ قرارات مدروسة تتماشى مع متطلباتك المحددة.
تذكر أن أفضل نهج غالبًا يتطور مع نضج تطبيقك. ابدأ بأبسط حل يلبي احتياجاتك، وكن مستعدًا لصقل بنيتك مع اكتساب الخبرة ووضوح المتطلبات.
<Check>
لديك الآن إطار لتقييم حالات استخدام CrewAI واختيار النهج الصحيح بناءً على متطلبات التعقيد والدقة. سيساعدك هذا في بناء تطبيقات AI أكثر فعالية وقابلية للصيانة والتوسع.
</Check>
## الخطوات التالية
- تعلم المزيد عن [صياغة Agents فعّالة](/ar/guides/agents/crafting-effective-agents)
- استكشف [بناء أول Crew](/ar/guides/crews/first-crew)
- تعمّق في [إتقان إدارة حالة Flow](/ar/guides/flows/mastering-flow-state)
- اطلع على [المفاهيم الأساسية](/ar/concepts/agents) لفهم أعمق

View File

@@ -0,0 +1,140 @@
---
title: ابنِ أول Crew
description: دليل خطوة بخطوة لإنشاء فريق AI تعاوني باستخدام تهيئة JSON-first.
icon: users-gear
mode: "wide"
---
## بناء Crew للبحث
في هذا الدليل ستنشئ crew من Agentين: واحد للبحث وآخر لكتابة تقرير markdown. مشاريع الـ crew الجديدة هي JSON-first: تُعرّف الـ Agents في `agents/*.jsonc`، وتُعرّف المهام وإعدادات الـ crew في `crew.jsonc`، ويحمّل `crewai run` هذا التعريف مباشرة.
### المتطلبات
1. تثبيت CrewAI من [دليل التثبيت](/ar/installation)
2. إعداد مفتاح LLM من [دليل LLMs](/ar/concepts/llms#setting-up-your-llm)
3. مفتاح [Serper.dev](https://serper.dev/) إذا أردت استخدام البحث على الويب
## الخطوة 1: إنشاء Crew جديدة
```bash
crewai create crew research_crew
cd research_crew
```
البنية الناتجة:
```text
research_crew/
├── .gitignore
├── .env
├── agents/
│ └── researcher.jsonc
├── crew.jsonc
├── knowledge/
├── pyproject.toml
├── README.md
├── skills/
└── tools/
```
<Tip>
إذا احتجت إلى البنية القديمة التي تحتوي على `crew.py` و `config/agents.yaml` و `config/tasks.yaml`، استخدم `crewai create crew research_crew --classic`.
</Tip>
## الخطوة 2: تعريف الـ Agents
عدّل ملف `agents/researcher.jsonc` الذي أنشأه القالب، ثم أضف `agents/analyst.jsonc`. يجب أن تطابق أسماء الملفات الأسماء المشار إليها في `crew.jsonc`.
```jsonc agents/researcher.jsonc
{
"role": "Senior Research Specialist for {topic}",
"goal": "Find comprehensive and accurate information about {topic}, with a focus on recent developments and key insights.",
"backstory": "You are an experienced research specialist who organizes complex information into clear, useful notes.",
// استبدله بالنموذج الذي تستخدمه، مثل "openai/gpt-4o".
"llm": "provider/model-id",
"tools": ["SerperDevTool"],
"settings": {
"verbose": true,
"allow_delegation": false
}
}
```
```jsonc agents/analyst.jsonc
{
"role": "Report Analyst for {topic}",
"goal": "Turn research findings into a clear, well-structured report.",
"backstory": "You are a careful analyst with strong technical writing skills and a talent for extracting useful insights.",
// استبدله بالنموذج الذي تستخدمه، مثل "openai/gpt-4o".
"llm": "provider/model-id",
"settings": {
"verbose": true,
"allow_delegation": false
}
}
```
استبدل `provider/model-id` بالنموذج الذي تستخدمه، مثل `openai/gpt-4o` أو `anthropic/claude-sonnet-4-6` أو `gemini/gemini-2.0-flash-001`.
## الخطوة 3: تعريف المهام وإعدادات الـ Crew
استبدل `crew.jsonc` بما يلي:
```jsonc crew.jsonc
{
"name": "Research Crew",
"agents": ["researcher", "analyst"],
"tasks": [
{
"name": "research_task",
"description": "Conduct thorough research on {topic}. Focus on key concepts, recent developments, major challenges, notable applications, and future outlook.",
"expected_output": "A comprehensive research document with organized sections, specific facts, and useful examples about {topic}.",
"agent": "researcher"
},
{
"name": "analysis_task",
"description": "Analyze the research findings and create a polished report on {topic}. Include an executive summary, key insights, trend analysis, and recommendations.",
"expected_output": "A professional markdown report with clear headings, a concise summary, main findings, and recommendations.",
"agent": "analyst",
"context": ["research_task"],
"output_file": "output/report.md",
"markdown": true
}
],
"process": "sequential",
"verbose": true,
"memory": true,
"inputs": {
"topic": "Artificial Intelligence in Healthcare"
}
}
```
يشير `context` إلى أسماء مهام سابقة، لذلك يحصل analyst على مخرجات مهمة البحث. يوفر `inputs` قيمة افتراضية لـ `{topic}`. إذا حذفت القيمة الافتراضية، سيطلبها `crewai run`.
## الخطوة 4: متغيرات البيئة
عدّل `.env`:
```sh
SERPER_API_KEY=your_serper_api_key
# أضف مفتاح مزود النموذج أيضًا.
```
## الخطوة 5: التثبيت والتشغيل
```bash
crewai install
crewai run
```
بعد انتهاء التشغيل، افتح `output/report.md`.
<Warning>
شغّل مشاريع JSON crew من مصادر تثق بها فقط. أدوات `custom:<name>` ومراجع `{"python": "module.attribute"}` تنفذ Python محليًا عند تحميل الـ crew.
</Warning>
<Check>
أصبحت لديك crew تعمل بأسلوب JSON-first تبحث في موضوع وتكتب تقريرًا.
</Check>

View File

@@ -0,0 +1,473 @@
---
title: تدفقات المحادثة
description: أنشئ تطبيقات دردشة متعددة الجولات مع kickoff لكل جولة وسجل الرسائل وتوجيه النية والتتبع وجسور WebSocket.
icon: comments
mode: "wide"
---
## نظرة عامة
تعامل التطبيقات المحادثية مع كل سطر من المستخدم كـ **تشغيل flow جديد** بنفس **معرّف الجلسة**. توفر CrewAI مساعدات لسجل الرسائل وتصنيف النية الاختياري وتأجيل التتبع وجسور الواجهة، إضافة إلى REPL محلي `flow.chat()` للتدفقات المحادثية.
| المفهوم | التنفيذ |
|---------|---------|
| معرّف الجلسة | `handle_turn(..., session_id=...)` → `kickoff(inputs={"id": ...})` → `state.id` |
| سطر المستخدم | `handle_turn(message)` يضيف الرسالة إلى `state.messages` قبل تشغيل الرسم |
| اكتمال الجولة | `FlowFinished` لهذا **التشغيل** فقط؛ تستمر المحادثة في `handle_turn` التالي |
| تتبع الجلسة | `ConversationConfig(defer_trace_finalization=True)` + `finalize_session_traces()` |
## واجهات الجولات
استخدم **`flow.handle_turn(message, session_id=...)`** لكل رسالة مستخدم من REST أو WebSocket أو الاختبارات أو الواجهات المخصصة. استخدم **`flow.chat()`** عندما تريد حلقة دردشة محلية في الطرفية لـ `Flow` محادثي.
لا يقبل `Flow.kickoff()` الوسيطين `user_message=` أو `session_id=`. في التدفقات المحادثية، يخزن `handle_turn()` الرسالة المعلقة ويستدعي داخلياً `kickoff(inputs={"id": session_id})`.
| API | الاستخدام |
|-----|-----------|
| `handle_turn(message, session_id=...)` | غلاف مريح لجولة واحدة في `Flow` محادثي |
| `chat()` | REPL محلي في الطرفية لـ `Flow` محادثي |
| `kickoff(inputs={...})` | تشغيل متقدم للـ flow بدون معالجة جولة محادثية |
| `ask()` | مطالبة حاجزة **داخل** خطوة واحدة |
| `@human_feedback` | الموافقة/الرفض على **مخرجات خطوة** — وليس السطر التالي |
| `ChatSession.handle_turn(...)` | طبقة نقل فوق `handle_turn` |
## بداية سريعة
```python
from uuid import uuid4
from crewai import Flow
from crewai.flow import listen
from crewai.experimental.conversational import (
ConversationConfig,
ConversationState,
)
@ConversationConfig(defer_trace_finalization=True)
class SupportFlow(Flow[ConversationState]):
conversational = True
def route_turn(self, context):
message = (self.state.current_user_message or "").lower()
if "طلب" in message or "order" in message:
return "order"
if "وداع" in message or "goodbye" in message:
return "goodbye"
return "help"
@listen("order")
def handle_order(self):
reply = "طلبك في الطريق."
self.append_assistant_message(reply)
return reply
@listen("help")
def handle_help(self):
reply = "كيف يمكنني المساعدة؟"
self.append_assistant_message(reply)
return reply
@listen("goodbye")
def handle_goodbye(self):
reply = "وداعاً!"
self.append_assistant_message(reply)
return reply
session_id = str(uuid4())
flow = SupportFlow()
try:
flow.handle_turn("أين طلبي؟", session_id=session_id)
flow.handle_turn("وماذا عن الإرجاع؟", session_id=session_id)
finally:
flow.finalize_session_traces()
```
## دورة حياة الجولة
كل `handle_turn` يشغّل:
1. **`_configure_conversational_kickoff`** — دمج `session_id` / `user_message` في `inputs` وتطبيق `ConversationalConfig`.
2. **استعادة الحالة** — عند وجود `inputs["id"]` و`@persist`.
3. **`FlowStarted`** — في أول جولة للجلسة المؤجلة فقط.
4. **`prepare_conversational_turn`** — إضافة رسالة المستخدم و`last_user_message` وتصنيف اختياري.
5. **تنفيذ الرسم** — `@start` → `@router` → معالجات `@listen`.
6. **نهاية التشغيل** — يُتخطى `flow_finished` والتتبع لكل جولة عند التأجيل؛ `Agent.kickoff()` / crews لا تغلق دفعة الأب.
استدعِ **`append_assistant_message(reply)`** في المعالجات. سطر المستخدم محفوظ عبر `handle_turn` — لا تُضفه مرة أخرى.
## `ConversationalConfig` (افتراضيات على مستوى الصنف)
عيّن على صنف `Flow` كـ `conversational_config: ClassVar[ConversationalConfig | None]`.
| الحقل | الافتراضي | الغرض |
|-------|-----------|--------|
| `default_intents` | `None` | تسميات outcome للتصنيف التلقائي قبل kickoff |
| `intent_llm` | `None` | نموذج التصنيف (مطلوب عند وجود intents) |
| `interactive_prompt` | `"You: "` | مطالبة `kickoff(interactive=True)` |
| `interactive_timeout` | `None` | مهلة لكل سطر في الوضع التفاعلي |
| `exit_commands` | `exit`, `quit` | كلمات إنهاء الوضع التفاعلي |
| `defer_trace_finalization` | `True` | إبقاء دفعة trace واحدة مفتوحة بين الجولات |
يمكن التجاوز لكل kickoff عبر `intents=` و`intent_llm=`.
## `ChatState` (شكل الحالة الموصى به للحفظ)
```python
from crewai.flow import ChatState
class MyChatState(ChatState):
# موروث: id, messages, last_user_message, last_intent, session_ready
research_turn_count: int = 0
custom_flag: bool = False
```
| الحقل | الدور |
|-------|------|
| `id` | UUID الجلسة (مثل `session_id` / `inputs["id"]`) |
| `messages` | قائمة `{role, content}` لسجل LLM |
| `last_user_message` | آخر سطر مستخدم في هذه الجولة |
| `last_intent` | تسمية المسار بعد التصنيف (إن وُجد) |
| `session_ready` | علم bootstrap لمرة واحدة |
`ConversationalInputs` هو `TypedDict` لـ `kickoff(inputs={...})`: `id`, `user_message`, `last_intent`.
## API المحادثة على `Flow`
### معاملات `kickoff` / `kickoff_async`
| المعامل | الغرض |
|---------|--------|
| `user_message` | نص هذه الجولة (أو `{"role": "user", "content": "..."}`) |
| `session_id` | UUID المحادثة → `inputs["id"]` / `state.id` |
| `intents` | تسميات outcome لـ `classify_intent` قبل kickoff |
| `intent_llm` | LLM للتصنيف (مطلوب مع `intents`) |
| `interactive` | حلقة CLI عبر `ask()` (للعروض المحلية فقط) |
| `interactive_prompt` | مطالبة الوضع التفاعلي |
| `interactive_timeout` | مهلة `ask()` لكل سطر |
| `exit_commands` | كلمات إنهاء الوضع التفاعلي |
| `inputs` | حقول حالة إضافية |
| `restore_from_state_id` | استنساخ من flow محفوظ آخر |
### سمات المثيل
| السمة | الغرض |
|-------|--------|
| `conversational_config` | افتراضيات `ConversationalConfig` على مستوى الصنف |
| `defer_trace_finalization` | علم المثيل؛ يُضبط تلقائياً من config عند kickoff |
| `suppress_flow_events` | يخفي لوحات console؛ **التتبع يُسجّل** |
| `stream` | بث؛ مع `ChatSession.handle_turn(..., stream=True)` |
### طرق وخصائص
| الاسم | الوصف |
|------|--------|
| `append_message(role, content, **extra)` | إضافة إلى `state.messages` |
| `conversation_messages` | سجل للقراءة فقط لاستدعاءات LLM |
| `classify_intent(text, outcomes, *, llm, context=None)` | تعيين outcome |
| `receive_user_message(text, *, outcomes=None, llm=None)` | إضافة رسالة مستخدم؛ `last_intent` اختياري |
| `finalize_session_traces()` | إصدار `flow_finished` المؤجل وإنهاء دفعة trace |
| `_should_defer_trace_finalization()` | هل يُؤجل إنهاء trace لكل جولة |
| `input_history` | سجل تدقيق مطالبات وردود `ask()` |
### مساعدات الوحدة (`crewai.flow.conversation`)
| الدالة | الوصف |
|--------|--------|
| `normalize_kickoff_inputs(...)` | دمج kwargs المحادثة في `inputs` |
| `get_conversation_messages(flow)` | قراءة الرسائل من الحالة أو المخزن |
| `append_message(flow, ...)` | مثل طريقة المثيل |
| `prepare_conversational_turn(flow, ...)` | تهيئة الجولة (عادةً kickoff يستدعيها) |
| `receive_user_message(flow, ...)` | مثل طريقة المثيل |
| `set_state_field(flow, name, value)` | تعيين حقل dict أو Pydantic |
| `get_conversational_config(flow)` | قراءة `conversational_config` |
| `input_history_to_messages(entries)` | تحويل `input_history` لصيغة رسائل LLM |
## أنماط توجيه النية
### أ. تصنيف مسبق عبر `ConversationalConfig` (الأبسط)
عيّن `default_intents` و`intent_llm`. كل kickoff يصنّف قبل `@router`؛ اقرأ `self.state.last_intent` في `route()`.
### ب. تصنيف داخل `@router` (مطالبات أغنى)
عيّن `default_intents=None` ليضيف kickoff الرسالة فقط. في `route()` استدعِ `classify_intent`:
```python
@router(bootstrap)
def route(self):
intent = self.classify_intent(
self._routing_prompt(self.state.last_user_message),
("GREETING", "ORDER", "RESEARCH", "GOODBYE"),
llm=self.conversational_config.intent_llm or "gpt-4o-mini",
)
self.state.last_intent = intent
return intent
```
للبحث على الويب أو أدوات متعددة الخطوات استخدم **`@listen("RESEARCH")`** مع `Agent.kickoff()` وأدوات — وليس `LLM.call()` فقط.
## عندما ينتهي الـ flow ويستمر المستخدم
`FlowFinished` يعني أن **تنفيذ الرسم هذا** اكتمل. تستمر المحادثة بـ `kickoff` آخر ونفس `session_id`. `@persist` يستعيد `messages` والأعلام والسياق.
**نمط الحفظ:** يُفضّل `@persist` على **خطوة نهائية واحدة** (مثل `finalize`) وليس على صنف `Flow` بالكامل. الحفظ على مستوى الصنف بعد كل method قد يفقد تحديثات المعالجات في نفس الجولة.
لا تستخدم `@human_feedback` لأسطر المتابعة في الدردشة إلا عند الحاجة لموافقة بشرية على مخرجات خطوة محددة.
## `Flow` المحادثاتي (تجريبي)
<Warning>
**ميزة تجريبية.** سطح `Flow` المحادثاتي (`conversational = True`،
`handle_turn`، `ConversationConfig`، `RouterConfig`،
`ConversationState`، الرسم البياني المدمج والمساعدات) يقع تحت
`crewai.experimental` وقد يتغير شكله قبل التخرج. ثبّت إصدار CrewAI إذا
كنت تعتمد على سلوك محدد، وراقب changelog للتحديثات الكاسرة. الملاحظات
والمشاكل مرحب بها.
</Warning>
فعّل الرسم المحادثاتي بتعيين `conversational = True` على صنف فرعي من `Flow`. عندئذٍ يُظهر `Flow` الأساسي رسم `@start` / `@router` / `converse_turn` / `end_conversation` مدمجاً، ويدير `state.messages`، ويُشغّل LLM التوجيه، ويبقي دفعة trace مفتوحة عبر الجولات. أنت تكتب **المسارات المخصصة** فقط؛ والإطار يتولى الباقي.
استخدمه عندما تريد دردشة متعددة الجولات مع موجّه قائم على LLM ومعالجات لكل مسار دون توصيل دورة الحياة يدوياً. استخدم `Flow[ChatState]` (النمط الأدنى مستوى في الأعلى) عندما تحتاج تحكماً كاملاً.
### مثال سريع
```python
from crewai import LLM, Flow
from crewai.flow import listen
from crewai.experimental.conversational import (
ConversationConfig,
ConversationState,
RouterConfig,
)
ROUTER_LLM = LLM(model="gpt-4o-mini")
@ConversationConfig(
system_prompt="A multi-agent assistant for ordinary chat and tool-backed tasks.",
llm=ROUTER_LLM,
router=RouterConfig(), # المسارات + الأوصاف تُكتشف تلقائياً من معالجات @listen
)
class SupportFlow(Flow[ConversationState]):
conversational = True
@listen("INTERNET_SEARCH")
def handle_internet_search(self) -> str:
"""Fresh web research, current news, real-time lookups."""
...
self.append_assistant_message(reply)
return reply
@listen("CREWAI_DOCS")
def handle_crewai_docs(self) -> str:
"""Look up the CrewAI documentation for framework/API questions."""
...
self.append_assistant_message(reply)
return reply
flow = SupportFlow()
try:
flow.handle_turn("ماذا يمكنك أن تفعل؟") # يوجَّه إلى converse (مدمج)
flow.handle_turn("ابحث في الويب عن أخبار الذكاء الاصطناعي.") # يوجَّه إلى INTERNET_SEARCH
flow.handle_turn("لخص النتيجة الأولى.") # يعود إلى converse
finally:
flow.finalize_session_traces()
```
للدردشة المحلية في الطرفية، استخدم `chat()`:
```python
def kickoff() -> None:
SupportFlow().chat()
```
يلف `chat()` استدعاءات `handle_turn()` داخل REPL، ويخرج عند `exit` / `quit`، ويتجاهل الأسطر الفارغة افتراضياً، ويستدعي `finalize_session_traces()` عند انتهاء الجلسة.
### `ConversationConfig`
مزخرف صنف يُلحق افتراضيات الدردشة على مستوى الصنف.
| الحقل | الافتراضي | الغرض |
|-------|-----------|-------|
| `system_prompt` | `slices.conversational_system_prompt` من i18n | رسالة system يستخدمها `converse_turn` المدمج. مرر `""` للتعطيل التام. |
| `llm` | `None` | LLM المحادثة (يستخدمه `converse_turn` وكاحتياطي للموجّه). |
| `router` | `None` | `RouterConfig` للتوجيه عبر LLM. بدونه، يسقط الـ flow دائماً إلى `converse`. |
| `answer_from_history_prompt` | افتراضي الإطار | رسالة system للمسار الاختياري `answer_from_history`. |
| `answer_from_history_llm` | `None` | يُفعّل الاختصار `answer_from_history` عند تعيينه. |
| `intent_llm` | `None` | LLM لمسار التصنيف المسبق القديم `intents=`/`default_intents`. |
| `default_intents` | `None` | تسميات النتائج للتصنيف المسبق القديم. |
| `visible_agent_outputs` | `None` | `"all"` أو قائمة بأسماء الـ agents الذين تُرفع مخرجاتهم من `append_agent_result()` إلى رسائل عامة. |
| `defer_trace_finalization` | `True` | يبقي دفعة trace واحدة مفتوحة عبر استدعاءات `handle_turn()`. |
### `RouterConfig` وفهرس المسارات المُولَّد تلقائياً
```python
RouterConfig(
prompt="تأطير اختياري للنطاق (سياسة، صوت، شخصية).",
response_format=MyRoute, # اختياري؛ يُولَّد تلقائياً عند الإغفال
llm=ROUTER_LLM, # يسقط إلى ConversationConfig.llm
routes=["INTERNET_SEARCH", "CREWAI_DOCS"], # اختياري؛ يُستنتج من المستمعين
route_descriptions={
"INTERNET_SEARCH": "تجاوز الـ docstring لهذا المسار فقط.",
},
default_intent="converse", # يُستخدم عند فشل LLM أو غيابه
fallback_intent="converse", # يُستخدم عندما يعيد LLM مساراً غير صالح
intent_field="intent",
)
```
تُبنى رسالة الموجّه إلى LLM تلقائياً. لكل مسار يختار الإطار وصفاً بهذا الترتيب من الأولوية:
1. `RouterConfig.route_descriptions[label]` — تجاوز صريح.
2. `Flow.builtin_route_descriptions[label]` — نص جاهز من الإطار لـ `converse` و`end` و`answer_from_history` (مصاغ لـ LLM التوجيه).
3. أول سطر غير فارغ من docstring معالج `@listen(label)`.
4. فارغ (المسار يظهر في الفهرس بلا وصف).
عملياً، **إضافة مسار جديد = `@listen("X")` + docstring من سطر واحد**:
```python
@listen("INTERNET_SEARCH")
def handle_internet_search(self) -> str:
"""Fresh web research, current news, real-time lookups."""
...
```
…وسيرى LLM التوجيه:
```
Routes:
- CREWAI_DOCS: Look up the CrewAI documentation for framework/API questions.
- INTERNET_SEARCH: Fresh web research, current news, real-time lookups.
- converse: Ordinary chat, follow-ups, summaries, clarifications…
- end: User signals the conversation is finished (goodbye, exit, done).
```
`RouterConfig.prompt` مخصص لـ **تأطير النطاق** (شخصية المساعد، قواعد العمل، النبرة). فهرس المسارات يُبنى تلقائياً — لا تُدرج المسارات في `prompt`؛ سيختل التزامن لحظة إضافة معالج جديد.
### المسارات المدمجة
| المسار | المعالج | الغرض |
|--------|---------|-------|
| `converse` | `converse_turn` | معالج الدردشة الافتراضي. يستدعي `ConversationConfig.llm` بـ system prompt + التاريخ القانوني للرسائل. |
| `end` | `end_conversation` | يضبط `state.ended = True` ويُصدر رد إنهاء. |
| `answer_from_history` | `answer_from_history_turn` | اختياري. يُوجَّه إليه عندما يكون `ConversationConfig.answer_from_history_llm` مُعيَّناً ويمكن الإجابة على الرسالة من التاريخ فقط. |
يمكنك تجاوز أي من هذه بتعريف معالج بنفس الاسم في الصنف الفرعي.
### دلالات `handle_turn()`
`flow.handle_turn(message)` يُشغّل جولة واحدة:
1. يعيد ضبط تعقّب التنفيذ لكل جولة (`_completed_methods`, `_method_outputs`) ليُعاد تشغيل الرسم — بدون ذلك، استدعاءات `kickoff` المتكررة على نفس النسخة ستُحدث دائرة قصر من الجولة الثانية لأن `Flow.kickoff_async` يعتبر `inputs={"id": ...}` استعادة من نقطة تفتيش.
2. يُلحق رسالة المستخدم بـ `state.messages` ويضبط `current_user_message` / `last_user_message`. يُحافَظ على `last_intent` **من الجولة السابقة** كي يستخدمها LLM التوجيه كإشارة.
3. يُشغّل `conversation_start` → `route_conversation` → معالج `@listen` المختار.
4. يخزّن الموجّه قراره في `state.last_intent` (يكون مرئياً لسياق التوجيه في الجولة التالية).
5. إذا أعاد معالجك سلسلة نصية ولم يستدعِ `append_assistant_message`، فإن `handle_turn` يُلحقها نيابةً عنك.
استدعِ `handle_turn()` لرسائل الدردشة. استدعاء `kickoff(inputs={"id": ...})` مباشرةً يشغل الرسم بدون غلاف الجولة المحادثية.
### `chat()` للـ REPL المحلي
`flow.chat()` هو غلاف الطرفية الجاهز فوق `handle_turn()`:
```python
flow = SupportFlow()
flow.chat()
```
يتولى الحلقة المحلية الشائعة:
1. يطلب رسالة من المستخدم.
2. يتوقف عند `exit` / `quit` أو `EOFError` أو `KeyboardInterrupt`.
3. يستدعي `handle_turn(message, session_id=...)`.
4. يطبع نتيجة المساعد.
5. ينهي traces الجلسة المؤجلة داخل كتلة `finally`.
خصص سلوك الطرفية عبر I/O قابل للحقن:
```python
flow.chat(
session_id="demo-session",
prompt="You: ",
assistant_prefix="Assistant: ",
exit_commands=("exit", "quit", "bye"),
)
```
لتطبيقات الويب والـ workers الخلفية والاختبارات ووسائط النقل المخصصة، استمر في استخدام `handle_turn()` مباشرةً.
### سلوك موجّه مخصص
لتشغيل آثار جانبية (إعداد ناقل أحداث، قياس عن بُعد) في كل قرار توجيه، تجاوز `route_turn`:
```python
class SupportFlow(Flow[ConversationState]):
conversational = True
def route_turn(self, context: dict[str, Any]) -> str | None:
self.event_bus = MyBus(self)
return super().route_turn(context)
```
لتجاوز موجّه LLM واختيار مسار برمجياً، أعد سلسلة نصية من `route_turn`؛ إعادة `None` تسقط إلى `_route_with_config(...)`.
### `append_assistant_message` و`append_agent_result`
داخل معالج `@listen(label)`، اختر:
- `self.append_assistant_message(text)` — يضيف جولة مساعد مرئية للمستخدم إلى `state.messages`. سيراها `converse_turn` في الجولة التالية.
- `self.append_agent_result(agent_name, result, visibility="private")` — يسجّل حدثاً منظماً في `state.events` وموضوعاً في `state.agent_threads[agent_name]`. الرؤية العامة تستدعي `append_assistant_message` أيضاً. استخدم النتائج الخاصة للعمل الجانبي الذي يجب ألا يلوث التاريخ القانوني.
يمكن لـ `ConversationConfig.visible_agent_outputs` رفع النتائج الخاصة لـ agents محددين إلى عامة عالمياً (`"all"` أو قائمة بالأسماء).
## التتبع عبر الجولات
مع `defer_trace_finalization=True` (افتراضي في `ConversationalConfig`):
- **دفعة trace واحدة** لجلسة الدردشة.
- **`flow_started`** في الجولة الأولى فقط؛ **`flow_finished`** مرة في `finalize_session_traces()`.
- **`kickoff` لكل جولة** لا يطبع "Trace batch finalized".
- **العمل المتداخل** (`Agent.kickoff()`, crews, Exa) يُلحق بدفعة **الأب**؛ flow داخلي من `AgentExecutor` لا يغلق دفعة الجلسة مبكراً.
```python
flow.chat(session_id=session_id)
```
`flow.chat()` يستدعي `finalize_session_traces()` نيابةً عنك. عندما تملك الحلقة عبر `handle_turn()` أو `kickoff(...)`، استدعِ `finalize_session_traces()` عند انتهاء الجلسة.
`suppress_flow_events=True` يخفي لوحات Rich فقط؛ أحداث trace والـ methods تُصدر.
### دورة حياة trace لـ `Flow` المحادثاتي
يستخدم [`Flow` المحادثاتي](#flow-المحادثاتي-تجريبي) التجريبي نفس دورة حياة tracing: `defer_trace_finalization` افتراضياً `True`، فيبقي كل `handle_turn()` أثر الجلسة مفتوحاً. أنهِ دوماً عند نهاية الجلسة — لُف حلقتك بـ `try/finally` واستدعِ `flow.finalize_session_traces()` عند الخروج. بدون ذلك، تبقى الدفعة مفتوحة وقد لا تُصدَّر آخر محادثة أبداً.
## البث
اضبط `stream = True` على صنف `Flow`. عندئذٍ يُصدر `kickoff(...)` أحداث `assistant_delta` (وما يرتبط بها) عبر ناقل الأحداث القياسي.
## الاستيراد
```python
from crewai.flow import (
ChatState,
ConversationalConfig,
ConversationalInputs,
Flow,
listen,
persist,
router,
start,
)
```
## مراجع
- [إتقان إدارة حالة Flow](/ar/guides/flows/mastering-flow-state)
- [أنشئ أول Flow](/ar/guides/flows/first-flow)
- Demo: `lib/crewai/runner_conversational_flow_simple.py` — REPL بسيط مع `RESEARCH` ووكيل Exa

View File

@@ -0,0 +1,222 @@
---
title: ابنِ أول Flow لك
description: تعلم كيفية إنشاء سير عمل منظمة قائمة على الأحداث مع تحكم دقيق في التنفيذ.
icon: diagram-project
mode: "wide"
---
## التحكم في سير عمل AI مع Flows
تمثل CrewAI Flows المستوى التالي في تنسيق AI - الجمع بين القوة التعاونية لفرق Agents AI مع دقة ومرونة البرمجة الإجرائية. بينما تتفوق Crews في تعاون الـ Agents، تمنحك Flows تحكمًا دقيقًا في كيفية ووقت تفاعل المكونات المختلفة لنظام AI.
في هذا الدليل، سنمشي عبر إنشاء CrewAI Flow قوي ينشئ دليلًا تعليميًا شاملاً حول أي موضوع.
### ما يجعل Flows قوية
تمكّنك Flows من:
1. **الجمع بين أنماط تفاعل AI مختلفة** - استخدام Crews للمهام التعاونية المعقدة واستدعاءات LLM المباشرة للعمليات الأبسط والكود العادي للمنطق الإجرائي
2. **بناء أنظمة قائمة على الأحداث** - تحديد كيفية استجابة المكونات لأحداث وتغييرات بيانات محددة
3. **الحفاظ على الحالة عبر المكونات** - مشاركة وتحويل البيانات بين أجزاء مختلفة من تطبيقك
4. **التكامل مع الأنظمة الخارجية** - ربط سير عمل AI بسلاسة مع قواعد البيانات وواجهات API وواجهات المستخدم
5. **إنشاء مسارات تنفيذ معقدة** - تصميم فروع شرطية ومعالجة متوازية وسير عمل ديناميكية
### المتطلبات المسبقة
قبل البدء، تأكد من:
1. تثبيت CrewAI باتباع [دليل التثبيت](/ar/installation)
2. إعداد مفتاح API لنموذج LLM في بيئتك، باتباع [دليل إعداد LLM](/ar/concepts/llms#setting-up-your-llm)
3. فهم أساسي لـ Python
## الخطوة 1: إنشاء مشروع CrewAI Flow جديد
```bash
crewai create flow guide_creator_flow
cd guide_creator_flow
```
<Frame caption="نظرة عامة على إطار عمل CrewAI">
<img src="/images/flows.png" alt="نظرة عامة على إطار عمل CrewAI" />
</Frame>
## الخطوة 2: فهم هيكل المشروع
يستخدم الـ crew المبدئي المضمّن في مشروع Flow بنية Python/YAML الكلاسيكية. لاستخدام crew بنمط JSON-first داخل Flow، أنشئ `crew.jsonc` و `agents/*.jsonc` داخل مجلد الـ crew وحمّله عبر `crewai.project.load_crew` كما في [Flows](/ar/concepts/flows#building-your-crews).
```
guide_creator_flow/
├── .gitignore
├── pyproject.toml
├── README.md
├── .env
└── src/
└── guide_creator_flow/
├── __init__.py
├── main.py
├── crews/
│ └── poem_crew/
│ ├── config/
│ │ ├── agents.yaml
│ │ └── tasks.yaml
│ └── poem_crew.py
└── tools/
└── custom_tool.py
```
يوفر هذا الهيكل فصلاً واضحًا بين مكونات Flow المختلفة. سنعدّل هذا الهيكل لإنشاء Flow منشئ الدليل.
## الخطوة 3: إضافة Crew كتابة المحتوى
```bash
crewai flow add-crew content-crew
```
## الخطوة 4: تهيئة Crew كتابة المحتوى
سنهيئ crew كتابة المحتوى باستخدام JSONC. سنعرّف Agent للكتابة وAgent للمراجعة، ثم نحمّل `crew.jsonc` من خطوة Flow.
1. أنشئ `src/guide_creator_flow/crews/content_crew/agents/content_writer.jsonc`:
```jsonc
{
"role": "Educational Content Writer",
"goal": "Create engaging, informative content that thoroughly explains the assigned topic and provides valuable insights to the reader.",
"backstory": "You are a talented educational writer who explains complex concepts in accessible language and organizes information clearly.",
"llm": "provider/model-id",
"settings": {
"verbose": true
}
}
```
2. أنشئ `src/guide_creator_flow/crews/content_crew/agents/content_reviewer.jsonc`:
```jsonc
{
"role": "Educational Content Reviewer and Editor",
"goal": "Ensure content is accurate, comprehensive, well-structured, and consistent with previously written sections.",
"backstory": "You are a meticulous editor with an eye for detail, clarity, and coherence.",
"llm": "provider/model-id",
"settings": {
"verbose": true
}
}
```
استبدل `provider/model-id` بالنموذج الذي تستخدمه، مثل `openai/gpt-4o` أو `gemini/gemini-2.0-flash-001` أو `anthropic/claude-sonnet-4-6`.
3. أنشئ `src/guide_creator_flow/crews/content_crew/crew.jsonc`:
```jsonc
{
"name": "Content Crew",
"agents": ["content_writer", "content_reviewer"],
"tasks": [
{
"name": "write_section_task",
"description": "Write a comprehensive section on the topic: \"{section_title}\".\n\nSection description: {section_description}\nTarget audience: {audience_level} level learners\n\nYour content should begin with a brief introduction, explain key concepts clearly with examples, include practical applications where appropriate, end with a summary, and be approximately 500-800 words.\n\nPreviously written sections:\n{previous_sections}",
"expected_output": "A well-structured, comprehensive section in Markdown format that thoroughly explains the topic and is appropriate for the target audience.",
"agent": "content_writer",
"markdown": true
},
{
"name": "review_section_task",
"description": "Review and improve this section on \"{section_title}\":\n\n{draft_content}\n\nTarget audience: {audience_level} level learners\nPreviously written sections:\n{previous_sections}\n\nFix errors, improve clarity, verify consistency, enhance structure, and add missing key information.",
"expected_output": "An improved, polished version of the section that maintains the original structure but enhances clarity, accuracy, and consistency.",
"agent": "content_reviewer",
"context": ["write_section_task"],
"markdown": true
}
],
"process": "sequential",
"verbose": true
}
```
4. استبدل `src/guide_creator_flow/crews/content_crew/content_crew.py` بمحمل صغير:
```python
from pathlib import Path
from crewai.project import load_crew
def kickoff_content_crew(inputs: dict):
crew, default_inputs = load_crew(Path(__file__).with_name("crew.jsonc"))
return crew.kickoff(inputs={**default_inputs, **inputs})
```
## الخطوة 5: إنشاء Flow
الآن الجزء المثير - إنشاء Flow الذي سينسّق عملية إنشاء الدليل بالكامل. راجع الملف الإنجليزي الأصلي للكود الكامل لـ `main.py` حيث أن الكود يبقى كما هو.
## الخطوة 6: إعداد متغيرات البيئة
أنشئ ملف `.env` في جذر مشروعك بمفاتيح API. راجع [دليل إعداد LLM](/ar/concepts/llms#setting-up-your-llm) لتفاصيل تهيئة المزود.
```sh .env
OPENAI_API_KEY=your_openai_api_key
# or
GEMINI_API_KEY=your_gemini_api_key
# or
ANTHROPIC_API_KEY=your_anthropic_api_key
```
## الخطوة 7: تثبيت التبعيات
```bash
crewai install
```
## الخطوة 8: تشغيل Flow
```bash
crewai run
```
عند تشغيل هذا الأمر، ستشاهد Flow يعمل:
1. سيطلب منك موضوعًا ومستوى الجمهور
2. سينشئ مخططًا منظمًا لدليلك
3. سيعالج كل قسم مع تعاون الكاتب والمراجع
4. أخيرًا سيجمع كل شيء في دليل شامل
## الخطوة 9: تصوير Flow
```bash
crewai flow plot
```
سينشئ ملف HTML يوضح هيكل Flow بما في ذلك العلاقات بين الخطوات المختلفة.
## الخطوة 10: مراجعة المخرجات
بمجرد اكتمال Flow، ستجد ملفين في مجلد `output`:
1. `guide_outline.json`: يحتوي على المخطط المنظم للدليل
2. `complete_guide.md`: الدليل الشامل بجميع الأقسام
## الميزات الرئيسية الموضّحة
يوضح Flow منشئ الدليل عدة ميزات قوية لـ CrewAI:
1. **تفاعل المستخدم**: يجمع Flow مدخلات مباشرة من المستخدم
2. **استدعاءات LLM المباشرة**: يستخدم فئة LLM لتفاعلات AI فعّالة وأحادية الغرض
3. **بيانات منظمة مع Pydantic**: يستخدم نماذج Pydantic لضمان سلامة الأنواع
4. **معالجة تسلسلية مع سياق**: يكتب الأقسام بالترتيب ويوفر الأقسام السابقة كسياق
5. **Crews متعددة الـ Agents**: يستفيد من Agents متخصصة (كاتب ومراجع) لإنشاء المحتوى
6. **إدارة الحالة**: يحافظ على الحالة عبر خطوات العملية المختلفة
7. **بنية قائمة على الأحداث**: يستخدم مزخرف `@listen` للاستجابة للأحداث
## الخطوات التالية
1. جرّب هياكل Flow أكثر تعقيدًا وأنماطًا
2. جرّب استخدام `@router()` لإنشاء فروع شرطية
3. استكشف دوال `and_` و`or_` لتنفيذ متوازٍ أكثر تعقيدًا
4. اربط Flow بواجهات API خارجية وقواعد بيانات وواجهات مستخدم
5. ادمج عدة Crews متخصصة في Flow واحد
6. أنشئ تطبيقات دردشة متعددة الجولات مع [تدفقات المحادثة](/ar/guides/flows/conversational-flows) (`kickoff` لكل رسالة، `ChatSession`، تأجيل التتبع)
<Check>
تهانينا! لقد بنيت بنجاح أول CrewAI Flow يجمع بين الكود العادي واستدعاءات LLM المباشرة ومعالجة Crew لإنشاء دليل شامل. هذه المهارات الأساسية تمكّنك من إنشاء تطبيقات AI متطورة بشكل متزايد.
</Check>

View File

@@ -0,0 +1,102 @@
---
title: "الانتقال من inputs.id إلى restore_from_state_id"
description: "نقل تدفقات @persist من ترطيب inputs.id المهجور إلى حقل restore_from_state_id المدعوم"
icon: "arrow-right-arrow-left"
---
<Warning>
تمرير `id` داخل `inputs` لترطيب تدفق `@persist` هو **مهجور** ومقرر إزالته في إصدار مستقبلي. البديل، `restore_from_state_id`، متاح في CrewAI **v1.14.5 وما بعده** — الخطوات أدناه تنطبق بمجرد أن تقوم بالتحديث.
</Warning>
## نظرة عامة
الطريقة الموثقة لترطيب تدفق `@persist` من تنفيذ سابق هي تمرير UUID لذلك التنفيذ كـ `inputs.id`. الآن، تكشف CrewAI عن حقل مخصص، `restore_from_state_id`، الذي يقوم بنفس الترطيب دون تحميل حمولة `inputs` — ودون ربط مفتاح الترطيب بهوية التنفيذ الجديد.
## الانتقال
إذا كنت حالياً تبدأ تدفق `@persist` باستخدام `inputs={"id": ...}`:
```python
# مهجور
flow = CounterFlow()
flow.kickoff(inputs={"id": "abcd1234-5678-90ef-ghij-klmnopqrstuv"})
```
انتقل إلى `restore_from_state_id`:
```python
# مدعوم
flow = CounterFlow()
flow.kickoff(restore_from_state_id="abcd1234-5678-90ef-ghij-klmnopqrstuv")
```
تتمتع الوضعيتان بمعاني سلالة مختلفة:
- `inputs={"id": <uuid>}` (مهجور) — **استئناف**: تكتب الكتابات تحت المعرف المقدم، مما يمدد نفس تاريخ `flow_uuid`.
- `restore_from_state_id=<uuid>` — **تفرع**: يترطب الحالة من اللقطة، ثم يكتب تحت `state.id` جديدة. يتم الحفاظ على تاريخ التدفق المصدر.
لأغلب سيناريوهات الإنتاج — إعادة تشغيل تدفق تم تهيئته من حالة سابقة — فإن التفرع هو ما تريده. راجع [إتقان حالة التدفق](/ar/guides/flows/mastering-flow-state) للحصول على النموذج الذهني الكامل.
إذا كنت تبدأ تدفقك عبر واجهة برمجة تطبيقات CrewAI AMP REST، راجع [AMP](#amp) أدناه لهجرة الحمولة المعادلة.
## لماذا نقوم بإهمال `inputs.id` لـ `@persist`
`inputs.id` هو حالياً الطريقة الموثقة لاستئناف تدفق `@persist` من تنفيذ سابق. المشكلة هي أن نفس UUID يقوم بوظيفتين في وقت واحد:
1. **يحدد أي لقطة يترطب منها `@persist`** — تحميل الحالة المحفوظة تحت ذلك UUID.
2. **يصبح معرف تنفيذ التدفق الجديد** (`state.id` في SDK؛ يظهر كـ `flow_id` في بعض السياقات) — كل كتابة `@persist` من هذه البداية أيضاً تقع تحت نفس UUID.
هذه الوظيفة المزدوجة هي السبب الجذري للمشاكل التي يصفها هذا الدليل. لأن UUID المقدم هو أيضاً معرف التنفيذ الجديد، فإن بدايتين تمرران نفس `inputs.id` ليست تنفيذين متميزين — إنهما تشتركان في معرف، وتشاركان في سجل الاستمرارية، و(على AMP) تشتركان في صف في قائمة التنفيذات. لا توجد طريقة للقول "ترطب من هذه اللقطة، ولكن سجل هذا التشغيل بشكل منفصل" دون تقسيم المسؤوليتين.
`restore_from_state_id` هو هذا الانقسام. إنه يخبر `@persist` من أي لقطة يترطب، بينما يترك التنفيذ الجديد حراً لاستلام `state.id` جديدة. لم يعد مصدر الترطيب والتشغيل المسجل نفس UUID — وهو ما تريده معظم سيناريوهات الإنتاج فعلياً.
## جدول إزالة
من المقرر إزالة `inputs.id` لترطيب `@persist` في إصدار مستقبلي من CrewAI. لا يوجد قطع صارم فوري — تظل التدفقات الحالية تعمل — ولكن بمجرد أن تقوم بالتحديث إلى v1.14.5 أو ما بعده، يجب أن يستخدم الكود الجديد `restore_from_state_id`، ويجب أن تهاجر التدفقات الحالية في الفرصة المناسبة التالية.
## AMP
إذا كنت تنشر تدفقك إلى CrewAI AMP، فإن الهجرة تمتد إلى الحمولة التي تبدأ بها المرسلة إلى طاقمك المنشور، وتظهر الأعراض المرئية لإعادة استخدام `inputs.id` على لوحة معلومات النشر. تغطي القسمان الفرعيان أدناه كلاهما.
### هجرة حمولة البداية
إذا كنت حالياً تبدأ تدفقاً منشوراً عن طريق تضمين `id` في `inputs`:
```bash
# مهجور
curl -X POST \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_CREW_TOKEN" \
-d '{"inputs": {"id": "abcd1234-5678-90ef-ghij-klmnopqrstuv", "topic": "AI Agent Frameworks"}}' \
https://your-crew-url.crewai.com/kickoff
```
نقل UUID إلى حقل `restoreFromStateId` في المستوى الأعلى:
```bash
# مدعوم
curl -X POST \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_CREW_TOKEN" \
-d '{
"inputs": {"topic": "AI Agent Frameworks"},
"restoreFromStateId": "abcd1234-5678-90ef-ghij-klmnopqrstuv"
}' \
https://your-crew-url.crewai.com/kickoff
```
يجلس `restoreFromStateId` بجانب `inputs` في حمولة البداية، وليس داخلها. الآن، يحمل كائن `inputs` فقط القيم التي تستهلكها تدفقك فعلياً.
### ماذا يحدث عند إعادة استخدام `inputs.id`
عندما تتلقى AMP بداية لتدفق يتطابق `inputs.id` الخاص به مع تنفيذ موجود، فإنه يحل إلى السجل الموجود بدلاً من إنشاء سجل جديد. من لوحة معلومات النشر سترى:
- **حالة التنفيذ** — حالة التشغيل الجديد تحل محل حالة التشغيل السابق. يمكن أن تعود تنفيذات مكتملة إلى `جارية`، أو يمكن أن تتحول تشغيلات `مكتملة` إلى `خطأ` إذا فشلت البداية الجديدة — في كلتا الحالتين، لم تعد لوحة المعلومات تعكس التشغيل الأصلي.
- **التتبع** — تتراكم تتبعات OTel عبر البدايات لأنها تشترك في نفس معرف التنفيذ؛ تتبعات التشغيل السابق إما تُستبدل بـ، أو تُخلط مع، تشغيل الجديد. لم يعد إعادة التشغيل خطوة بخطوة يتوافق مع تنفيذ واحد.
- **قائمة التنفيذات** — البدايات التي يجب أن تظهر كصفوف منفصلة تتقلص إلى إدخال واحد، مما يخفي التاريخ.
تساعد الهجرة إلى `restoreFromStateId` في الحفاظ على كل بداية كتنفيذ خاص بها — مع حالتها الخاصة، وتتبعها، وصفها في القائمة — بينما لا تزال ترطب الحالة من تشغيل سابق.
<Card title="هل تحتاج مساعدة؟" icon="headset" href="mailto:support@crewai.com">
اتصل بفريق الدعم لدينا إذا لم تكن متأكداً من أي وضع يحتاجه تدفقك أو واجهت مشاكل أثناء الهجرة.
</Card>

View File

@@ -0,0 +1,228 @@
---
title: إتقان إدارة حالة Flow
description: دليل شامل لإدارة الحالة وحفظها والاستفادة منها في CrewAI Flows لبناء تطبيقات AI قوية.
icon: diagram-project
mode: "wide"
---
## فهم قوة الحالة في Flows
إدارة الحالة هي العمود الفقري لأي سير عمل AI متطور. في CrewAI Flows، يتيح لك نظام الحالة الحفاظ على السياق ومشاركة البيانات بين الخطوات وبناء منطق تطبيق معقد. إتقان إدارة الحالة ضروري لإنشاء تطبيقات AI موثوقة وقابلة للصيانة وقوية.
### لماذا تهم إدارة الحالة
تمكّنك إدارة الحالة الفعّالة من:
1. **الحفاظ على السياق عبر خطوات التنفيذ** - تمرير المعلومات بسلاسة بين مراحل سير العمل المختلفة
2. **بناء منطق شرطي معقد** - اتخاذ قرارات بناءً على البيانات المتراكمة
3. **إنشاء تطبيقات مستمرة** - حفظ واستعادة تقدم سير العمل
4. **معالجة الأخطاء بلطف** - تنفيذ أنماط استرداد لتطبيقات أكثر قوة
5. **توسيع تطبيقاتك** - دعم سير العمل المعقدة بتنظيم بيانات مناسب
6. **تمكين التطبيقات الحوارية** - تخزين والوصول إلى سجل المحادثات للتفاعلات الواعية بالسياق
للدردشة متعددة الجولات (`kickoff` لكل سطر مستخدم، `ChatState`، توجيه النية، تأجيل التتبع، و`ChatSession`)، راجع [تدفقات المحادثة](/ar/guides/flows/conversational-flows).
## أساسيات إدارة الحالة
### نهجان لإدارة الحالة
يوفر CrewAI طريقتين لإدارة الحالة في Flows:
1. **الحالة غير المنظمة** - استخدام كائنات شبيهة بالقاموس للمرونة
2. **الحالة المنظمة** - استخدام نماذج Pydantic لسلامة الأنواع والتحقق
### مثال الحالة غير المنظمة
```python
from crewai.flow.flow import Flow, listen, start
class UnstructuredStateFlow(Flow):
@start()
def initialize_data(self):
self.state["user_name"] = "Alex"
self.state["preferences"] = {"theme": "dark", "language": "English"}
self.state["items"] = []
return "Initialized"
@listen(initialize_data)
def process_data(self, previous_result):
user = self.state["user_name"]
self.state["items"].append("item1")
self.state["processed"] = True
return "Processed"
flow = UnstructuredStateFlow()
result = flow.kickoff()
```
### مثال الحالة المنظمة
```python
from crewai.flow.flow import Flow, listen, start
from pydantic import BaseModel, Field
from typing import List, Dict, Optional
class AppState(BaseModel):
user_name: str = ""
items: List[str] = []
processed: bool = False
completion_percentage: float = 0.0
class StructuredStateFlow(Flow[AppState]):
@start()
def initialize_data(self):
self.state.user_name = "Taylor"
return "Initialized"
@listen(initialize_data)
def process_data(self, previous_result):
self.state.items.append("item1")
self.state.processed = True
self.state.completion_percentage = 50.0
return "Processed"
flow = StructuredStateFlow()
result = flow.kickoff()
```
### فوائد الحالة المنظمة
1. **سلامة الأنواع** - اكتشاف أخطاء الأنواع في وقت التطوير
2. **توثيق ذاتي** - نموذج الحالة يوثّق بوضوح البيانات المتاحة
3. **التحقق** - التحقق التلقائي من أنواع البيانات والقيود
4. **دعم IDE** - إكمال تلقائي وتوثيق مضمّن
5. **قيم افتراضية** - تعريف بدائل سهلة للبيانات المفقودة
## حفظ حالة Flow
يوفر مزخرف `@persist()` حفظ حالة تلقائي عند نقاط رئيسية في التنفيذ.
```python
from crewai.flow.flow import Flow, listen, start
from crewai.flow.persistence import persist
from pydantic import BaseModel
class CounterState(BaseModel):
value: int = 0
@persist()
class PersistentCounterFlow(Flow[CounterState]):
@start()
def increment(self):
self.state.value += 1
return self.state.value
@listen(increment)
def double(self, value):
self.state.value = value * 2
return self.state.value
```
#### تفرع الحالة المستمرة
يدعم `@persist` نمطين متميزين للترطيب في `kickoff` / `kickoff_async`. استخدم **استئناف** (`inputs["id"]`) لمواصلة نفس النسب؛ استخدم **تفرع** (`restore_from_state_id`) لبدء نسبٍ جديد من لقطة:
| | `state.id` بعد kickoff | كتابات `@persist` تذهب إلى |
|---|---|---|
| `inputs["id"]` (استئناف) | المعرّف المقدم | المعرّف المقدم (يمد التاريخ) |
| `restore_from_state_id` (تفرع) | معرّف جديد، أو `inputs["id"]` إذا ثُبّت | المعرّف الجديد (المصدر محفوظ) |
```python
from crewai.flow.flow import Flow, start
from crewai.flow.persistence import persist
from pydantic import BaseModel
class CounterState(BaseModel):
id: str = ""
counter: int = 0
@persist
class CounterFlow(Flow[CounterState]):
@start()
def step(self):
self.state.counter += 1
# التشغيل 1: حالة جديدة، العداد 0 -> 1
flow_1 = CounterFlow()
flow_1.kickoff()
# التفرع: الترطيب من أحدث لقطة لـ flow_1، لكن الكتابة تحت state.id جديد
flow_2 = CounterFlow()
flow_2.kickoff(restore_from_state_id=flow_1.state.id)
# يبدأ flow_2 بـ counter=1 (مرطّب)، ثم تزيده step() إلى 2.
# تاريخ flow_uuid لـ flow_1 لم يتغيّر.
```
ملاحظات السلوك:
- `restore_from_state_id` غير موجود في الاستمرارية → يعود kickoff بصمت إلى السلوك الافتراضي (يعكس سلوك `inputs["id"]` عند عدم العثور عليه). لا يُطلق أي استثناء.
- الجمع بين `restore_from_state_id` و `from_checkpoint` يطلق `ValueError` — يستهدفان نظامي حالة مختلفين (`@persist` مقابل Checkpointing) ولا يمكن الجمع بينهما.
- `restore_from_state_id=None` (افتراضي) متطابق بايت ببايت مع kickoff بدون المعامل.
- تثبيت `inputs["id"]` أثناء التفرع يعني أن التشغيل الجديد يشارك مفتاح الاستمرارية مع تدفق آخر — عادةً ما تريد فقط `restore_from_state_id`.
## أنماط حالة متقدمة
### المنطق الشرطي المبني على الحالة
```python
from crewai.flow.flow import Flow, listen, router, start
from pydantic import BaseModel
class PaymentState(BaseModel):
amount: float = 0.0
is_approved: bool = False
retry_count: int = 0
class PaymentFlow(Flow[PaymentState]):
@start()
def process_payment(self):
self.state.amount = 100.0
self.state.is_approved = self.state.amount < 1000
return "Payment processed"
@router(process_payment)
def check_approval(self, previous_result):
if self.state.is_approved:
return "approved"
elif self.state.retry_count < 3:
return "retry"
else:
return "rejected"
@listen("approved")
def handle_approval(self):
return f"Payment of ${self.state.amount} approved!"
@listen("retry")
def handle_retry(self):
self.state.retry_count += 1
return "Retry initiated"
@listen("rejected")
def handle_rejection(self):
return f"Payment of ${self.state.amount} rejected after {self.state.retry_count} retries."
```
## أفضل الممارسات لإدارة الحالة
1. **اجعل الحالة مركّزة** - صمم الحالة لتحتوي فقط على ما هو ضروري
2. **استخدم الحالة المنظمة للـ Flows المعقدة** - مع نمو التعقيد تصبح الحالة المنظمة أكثر قيمة
3. **وثّق انتقالات الحالة** - للـ Flows المعقدة، وثّق كيف تتغير الحالة عبر التنفيذ
4. **عالج أخطاء الحالة بلطف** - طبّق معالجة أخطاء للوصول إلى الحالة
5. **استخدم الحالة لتتبع التقدم** - استفد من الحالة لتتبع التقدم في Flows طويلة التشغيل
6. **استخدم العمليات غير المتغيرة عند الإمكان** - خاصة مع الحالة المنظمة
## الخلاصة
إتقان إدارة الحالة في CrewAI Flows يمنحك القدرة على بناء تطبيقات AI متطورة وقوية تحافظ على السياق وتتخذ قرارات معقدة وتقدم نتائج متسقة.
<Check>
لقد أتقنت الآن مفاهيم وممارسات إدارة الحالة في CrewAI Flows! بهذه المعرفة، يمكنك إنشاء سير عمل AI قوية تحافظ على السياق بفعالية وتشارك البيانات بين الخطوات وتبني منطق تطبيق متطور.
</Check>
## الخطوات التالية
- جرّب الحالة المنظمة وغير المنظمة في Flows
- جرّب تطبيق حفظ الحالة لسير العمل طويلة التشغيل
- استكشف [بناء أول Crew](/ar/guides/crews/first-crew) لمعرفة كيف تعمل Crews وFlows معًا
- اطلع على [توثيق مرجع Flow](/ar/concepts/flows) لمزيد من الميزات المتقدمة

View File

@@ -0,0 +1,103 @@
---
title: "الانتقال من LangGraph إلى CrewAI: دليل عملي للمهندسين"
description: إذا كنت قد بنيت بالفعل مع LangGraph، تعلم كيفية نقل مشاريعك بسرعة إلى CrewAI
icon: switch
mode: "wide"
---
لقد بنيت Agents مع LangGraph. لقد تعاملت مع `StateGraph`، وربطت الحواف الشرطية، وصححت أخطاء قواميس الحالة في الثانية صباحًا. إنه يعمل — لكن في مرحلة ما، بدأت تتساءل عما إذا كان هناك مسار أفضل نحو الإنتاج.
هناك بالفعل. **CrewAI Flows** يمنحك نفس القوة — تنسيق قائم على الأحداث، توجيه شرطي، حالة مشتركة — مع نموذج كود أبسط بشكل كبير ونموذج ذهني يتماشى مع طريقة تفكيرك الفعلية في سير عمل AI متعدد الخطوات.
تمشي هذه المقالة عبر المفاهيم الأساسية جنبًا إلى جنب، وتعرض مقارنات كود حقيقية، وتوضح لماذا CrewAI Flows هو إطار العمل الذي ستريد الوصول إليه بعد ذلك.
---
## تحول النموذج الذهني
LangGraph يطلب منك التفكير في **رسوم بيانية**: عقد وحواف وقواميس حالة. كل سير عمل هو رسم بياني موجّه تربط فيه الانتقالات صراحةً بين خطوات الحساب.
CrewAI Flows يطلب منك التفكير في **أحداث**: طرق تبدأ الأشياء، وطرق تستمع للنتائج، وطرق توجّه التنفيذ. طوبولوجيا سير العمل تنبثق من تعليقات المزخرفات بدلاً من بناء رسم بياني صريح.
إليك الخريطة الأساسية:
| مفهوم LangGraph | المكافئ في CrewAI Flows |
| --- | --- |
| `StateGraph` class | `Flow` class |
| `add_node()` | طرق مزخرفة بـ `@start`، `@listen` |
| `add_edge()` / `add_conditional_edges()` | مزخرفات `@listen()` / `@router()` |
| `TypedDict` state | حالة Pydantic `BaseModel` |
| `START` / `END` constants | مزخرف `@start()` / إرجاع طبيعي للطريقة |
| `graph.compile()` | `flow.kickoff()` |
| Checkpointer / persistence | ذاكرة مدمجة (مدعومة بـ LanceDB) |
---
## العرض 1: خط أنابيب تسلسلي بسيط
تخيل أنك تبني خط أنابيب يأخذ موضوعًا، ويبحث فيه، ويكتب ملخصًا، وينسّق المخرجات. راجع الملف الإنجليزي الأصلي لأمثلة الكود الكاملة لكلا النهجين.
الفرق الرئيسي: لا بناء رسم بياني، لا ربط حواف، لا خطوة ترجمة. ترتيب التنفيذ مُعلَن مباشرة حيث يوجد المنطق. `@start()` يحدد نقطة الدخول، و`@listen(method_name)` يربط الخطوات.
---
## العرض 2: التوجيه الشرطي
مزخرف `@router()` يحوّل طريقة إلى نقطة قرار. يعيد سلسلة تطابق مستمعًا — بلا قواميس تعيين، بلا دوال توجيه منفصلة. منطق التفرع يُقرأ كتعبير `if` في Python لأنه كذلك فعلاً.
---
## العرض 3: دمج فرق Agents AI في Flows
هنا تتجلى القوة الحقيقية لـ CrewAI. الـ Flows لا تقتصر على ربط استدعاءات LLM — بل تنسّق **Crews** كاملة من Agents مستقلة.
الفكرة الرئيسية: **الـ Flows توفر طبقة التنسيق، والـ Crews توفر طبقة الذكاء.** كل خطوة في Flow يمكنها تشغيل فريق كامل من Agents متعاونة.
---
## العرض 4: التنفيذ المتوازي والمزامنة
المشغّل `and_()` على مزخرف `@listen` يضمن أن الطريقة تُنفَّذ فقط بعد اكتمال *جميع* الطرق السابقة. هناك أيضًا `or_()` للمتابعة بمجرد اكتمال *أي* مهمة سابقة.
---
## لماذا CrewAI Flows للإنتاج
- **حفظ حالة مدمج.** حالة Flow مدعومة بـ LanceDB.
- **إدارة حالة آمنة الأنواع.** نماذج Pydantic توفر التحقق والتسلسل ودعم IDE.
- **تنسيق Agents أصلي.** الـ Crews بنية أساسية أصلية.
- **نموذج ذهني أبسط.** المزخرفات تعلن عن النية.
- **تكامل CLI.** شغّل Flows بـ `crewai run`.
---
## ورقة الغش للترحيل
1. **عيّن حالتك.** حوّل `TypedDict` إلى Pydantic `BaseModel`.
2. **حوّل العقد إلى طرق.** كل دالة `add_node` تصبح طريقة على فئة `Flow` الفرعية.
3. **استبدل الحواف بمزخرفات.** `add_edge(START, "first_node")` يصبح `@start()`. `add_edge("a", "b")` يصبح `@listen(a)`.
4. **استبدل الحواف الشرطية بـ `@router`.** دالة التوجيه و`add_conditional_edges()` تصبح طريقة `@router()` واحدة.
5. **استبدل compile + invoke بـ kickoff.** احذف `graph.compile()`. استدعِ `flow.kickoff()` بدلاً منه.
6. **فكّر أين تناسب الـ Crews.** أي عقدة بها منطق Agent معقد متعدد الخطوات هي مرشحة لاستخراجها في Crew.
---
## البدء
```bash
pip install crewai
crewai create flow my_first_flow
cd my_first_flow
```
```bash
crewai run
```
---
## أفكار أخيرة
LangGraph علّم المنظومة أن سير عمل AI تحتاج هيكلاً. كان ذلك درسًا مهمًا. لكن CrewAI Flows يأخذ ذلك الدرس ويقدمه في شكل أسرع في الكتابة وأسهل في القراءة وأقوى في الإنتاج — خاصة عندما تتضمن سير عملك عدة Agents متعاونة.
ابدأ بـ `crewai create flow`. لن تنظر للخلف.

View File

@@ -0,0 +1,190 @@
---
title: "ترقية CrewAI"
description: "كيفية ترقية CrewAI في مشروعك والتكيّف مع التغييرات الجذرية بين الإصدارات."
icon: "arrow-up-circle"
---
## نظرة عامة
تجلب إصدارات CrewAI قدرات جديدة بانتظام. يرشدك هذا الدليل خلال الخطوات العملية للحفاظ على تثبيتك محدّثًا — سواء أداة سطر الأوامر أو البيئة الافتراضية لمشروعك.
إذا كنت تبدأ من الصفر، راجع [التثبيت](/ar/installation). إذا كنت قادمًا من إطار عمل آخر، راجع [الترحيل من LangGraph](/ar/guides/migration/migrating-from-langgraph).
---
## الشيئان اللذان قد ترغب في ترقيتهما
يوجد CrewAI في مكانين على جهازك، ويتم ترقيتهما بشكل مستقل:
| ماذا | كيف يُثبَّت | كيف تتم الترقية |
|---|---|---|
| **أداة سطر الأوامر العامة `crewai`** | `uv tool install crewai` | `uv tool install crewai --upgrade` |
| **بيئة venv للمشروع** (حيث يعمل الكود) | `crewai install` / `uv sync` | `uv add "crewai[...]>=X.Y.Z"` ثم `crewai install` |
يمكن لهما — وغالبًا ما يحدث — أن يخرجا عن التزامن. تشغيل `crewai --version` يُظهر إصدار سطر الأوامر. تشغيل `uv pip show crewai` داخل مشروعك يُظهر إصدار venv. إذا اختلفا، فهذا طبيعي؛ ما يهم بالنسبة للكود قيد التشغيل هو إصدار venv.
## لماذا لا يقوم `crewai install` وحده بالترقية
`crewai install` هو غلاف رفيع حول `uv sync`. يُثبّت بالضبط ما يقوله ملف `uv.lock` الحالي — وهو **لا** يرفع أي قيود إصدار.
إذا كان `pyproject.toml` يقول `crewai>=1.11.1` وقد قام ملف القفل بحلّه إلى `1.11.1`، فإن تشغيل `crewai install` سيُبقيك على `1.11.1` للأبد، حتى وإن كان الإصدار `1.14.4` متاحًا.
للترقية فعلًا، عليك:
1. تحديث قيد الإصدار في `pyproject.toml`
2. إعادة حلّ ملف القفل
3. مزامنة venv
`uv add` يقوم بالثلاثة في خطوة واحدة.
## كيفية ترقية مشروعك
```bash
# يرفع القيد ويعيد القفل في أمر واحد
uv add "crewai[tools]>=1.14.4"
# يزامن venv (crewai install يستدعي uv sync تحت الغطاء)
crewai install
# تحقّق
uv pip show crewai
# → Version: 1.14.4
```
استبدل `[tools]` بأي إضافات يستخدمها مشروعك (مثلًا `[tools,anthropic]`). تحقّق من قائمة `dependencies` في `pyproject.toml` إن لم تكن متأكدًا.
<Note>
يحدّث `uv add` كلا من `pyproject.toml` **و** `uv.lock` بشكل ذرّي. إذا قمت بتحرير `pyproject.toml` يدويًا، فإنك لا تزال بحاجة إلى تشغيل `uv lock --upgrade-package crewai` لإعادة حلّ ملف القفل قبل أن يلتقط `crewai install` الإصدار الجديد.
</Note>
## ترقية أداة سطر الأوامر العامة
أداة سطر الأوامر العامة منفصلة عن مشروعك. قم بترقيتها عبر:
```bash
uv tool install crewai --upgrade
```
إذا حذّرك الـ shell بشأن `PATH` بعد الترقية، قم بتحديثه:
```bash
uv tool update-shell
```
هذا **لا** يمسّ بيئة venv الخاصة بمشروعك — لا تزال بحاجة إلى `uv add` + `crewai install` داخل المشروع.
## التحقق من تزامن الاثنين
```bash
# إصدار سطر الأوامر العام
crewai --version
# إصدار venv للمشروع
uv pip show crewai | grep Version
```
ليس من الضروري أن يتطابقا — لكن إصدار venv للمشروع هو ما يهم لسلوك التشغيل.
<Note>
يتطلب CrewAI `Python >=3.10, <3.14`. إذا كان `uv` مثبَّتًا مقابل مفسّر أقدم، فأعد إنشاء venv للمشروع باستخدام إصدار Python مدعوم قبل تشغيل `crewai install`.
</Note>
---
## التغييرات الجذرية وملاحظات الترحيل
تتطلب معظم الترقيات تعديلات صغيرة فقط. المناطق أدناه هي تلك التي تنكسر بصمت أو بتتبعات مكدّس مربكة.
### مسارات الاستيراد: tools و`BaseTool`
الموقع الرسمي لاستيراد الـ tools هو `crewai.tools`. لا تزال المسارات القديمة تظهر في الدروس لكن يجب تحديثها.
```python
# قبل
from crewai_tools import BaseTool
from crewai.agents.tools import tool
# بعد
from crewai.tools import BaseTool, tool
```
كلٌ من المُزخرف `@tool` والفئة الفرعية `BaseTool` يقعان في `crewai.tools`. `AgentFinish` والرموز الأخرى الداخلية للوكيل لم تعد جزءًا من السطح العام — إذا كنت تستوردها، فانتقل إلى event listeners أو callbacks الـ `Task` بدلًا منها.
### تغييرات معاملات `Agent`
```python
from crewai import Agent
agent = Agent(
role="Researcher",
goal="Find authoritative sources on {topic}",
backstory="You are a careful, source-driven researcher.",
llm="gpt-4o-mini", # اسم نموذج كسلسلة نصية أو كائن LLM
verbose=True, # bool وليس مستوى عددي صحيح
max_iter=15, # تغيّر الافتراضي بين الإصدارات — حدّده بشكل صريح
allow_delegation=False,
)
```
- يقبل `llm` إما اسم نموذج كسلسلة نصية (يُحلَّ عبر المزوّد المهيّأ) أو كائن `LLM` للتحكم الدقيق.
- `verbose` هو `bool` بسيط. تمرير عدد صحيح لم يعد يبدّل مستويات السجل.
- تغيّرت افتراضات `max_iter` بين الإصدارات. إذا توقف وكيلك بصمت عن التكرار بعد أول استدعاء tool، فحدّد `max_iter` صراحةً.
### معاملات `Crew`
```python
from crewai import Crew, Process
crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential, # أو Process.hierarchical
memory=True,
cache=True,
embedder={"provider": "openai", "config": {"model": "text-embedding-3-small"}},
)
```
- يتطلب `process=Process.hierarchical` إما `manager_llm=` أو `manager_agent=`. بدون أحدهما، يرفع kickoff خطأً عند التحقّق.
- `memory=True` مع مزوّد embedding غير افتراضي يحتاج إلى قاموس `embedder` — راجع [إعداد الذاكرة وembedder](#memory-embedder-config) أدناه.
### الإخراج المُهيكل لـ `Task`
استخدم `output_pydantic` أو `output_json` أو `output_file` لإلزام نتيجة المهمة بشكل مكتوب الأنواع:
```python
from pydantic import BaseModel
from crewai import Task
class Article(BaseModel):
title: str
body: str
write = Task(
description="Write an article about {topic}",
expected_output="A short article with a title and body",
agent=writer,
output_pydantic=Article, # الفئة، وليس مثيلًا منها
output_file="output/article.md",
)
```
`output_pydantic` يأخذ **الفئة** نفسها. تمرير `Article(title="", body="")` خطأ شائع ويفشل بخطأ تحقّق مربك.
### إعداد الذاكرة وembedder {#memory-embedder-config}
إذا كان `memory=True` وأنت لا تستخدم embeddings الافتراضية الخاصة بـ OpenAI، فيجب أن تمرّر `embedder`:
```python
crew = Crew(
agents=[...],
tasks=[...],
memory=True,
embedder={
"provider": "ollama",
"config": {"model": "nomic-embed-text"},
},
)
```
ضع بيانات اعتماد المزوّد المعنيّة (`OPENAI_API_KEY`, `OLLAMA_HOST`, إلخ) في ملف `.env`. مسارات تخزين الذاكرة محلية بالنسبة للمشروع افتراضيًا — احذف مجلد ذاكرة المشروع إذا غيّرت embedders، لأن الأبعاد لا تختلط.

View File

@@ -0,0 +1,96 @@
---
title: نشر أدوات مخصصة
description: كيفية بناء وتعبئة ونشر أدواتك الخاصة المتوافقة مع CrewAI على PyPI ليتمكن أي مستخدم CrewAI من تثبيتها واستخدامها.
icon: box-open
mode: "wide"
---
## نظرة عامة
نظام الأدوات في CrewAI مصمم للتوسيع. إذا بنيت أداة يمكن أن تفيد الآخرين، يمكنك تعبئتها كمكتبة Python مستقلة ونشرها على PyPI وإتاحتها لأي مستخدم CrewAI — دون الحاجة لطلب سحب إلى مستودع CrewAI.
يمشي هذا الدليل عبر العملية الكاملة: تنفيذ عقد الأدوات، وهيكلة حزمتك، والنشر على PyPI.
<Note type="info" title="لا تبحث عن النشر؟">
إذا كنت تحتاج فقط أداة مخصصة لمشروعك، راجع دليل [إنشاء أدوات مخصصة](/ar/learn/create-custom-tools) بدلاً من ذلك.
</Note>
## عقد الأدوات
كل أداة CrewAI يجب أن تستوفي إحدى الواجهتين:
### الخيار 1: وراثة `BaseTool`
ورث من `crewai.tools.BaseTool` وطبّق طريقة `_run`. عرّف `name` و`description` واختياريًا `args_schema` للتحقق من المدخلات.
```python
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
class GeolocateInput(BaseModel):
"""Input schema for GeolocateTool."""
address: str = Field(..., description="The street address to geolocate.")
class GeolocateTool(BaseTool):
name: str = "Geolocate"
description: str = "Converts a street address into latitude/longitude coordinates."
args_schema: type[BaseModel] = GeolocateInput
def _run(self, address: str) -> str:
return f"40.7128, -74.0060"
```
### الخيار 2: استخدام مزخرف `@tool`
للأدوات الأبسط، يحوّل مزخرف `@tool` دالة إلى أداة CrewAI. يجب أن تحتوي الدالة على سلسلة توثيق (تُستخدم كوصف الأداة) وتعليقات أنواع.
```python
from crewai.tools import tool
@tool("Geolocate")
def geolocate(address: str) -> str:
"""Converts a street address into latitude/longitude coordinates."""
return "40.7128, -74.0060"
```
### المتطلبات الأساسية
بغض النظر عن النهج الذي تستخدمه، يجب أن تحتوي أداتك على:
- **`name`** — معرّف قصير ووصفي.
- **`description`** — يخبر الـ Agent متى وكيف يستخدم الأداة.
- **`_run`** (BaseTool) أو **جسم الدالة** (@tool) — منطق التنفيذ المتزامن.
- **تعليقات أنواع** على جميع المعاملات وقيم الإرجاع.
- إرجاع نتيجة **نصية** (أو شيء يمكن تحويله لنص).
## هيكل الحزمة
```
crewai-geolocate/
├── pyproject.toml
├── LICENSE
├── README.md
└── src/
└── crewai_geolocate/
├── __init__.py
└── tools.py
```
## النشر على PyPI
```bash
# Build the package
uv build
# Publish to PyPI
uv publish
```
بعد النشر، يمكن للمستخدمين تثبيت أداتك بـ:
```bash
uv add crewai-geolocate
```

105
docs/edge/ar/index.mdx Normal file
View File

@@ -0,0 +1,105 @@
---
title: "توثيق CrewAI"
description: "ابنِ Agents ذكاء اصطناعي تعاونية وCrews وFlows — جاهزة للإنتاج من اليوم الأول."
icon: "house"
mode: "wide"
---
<div
style={{
display: 'flex',
flexDirection: 'column',
alignItems: 'center',
gap: 20,
textAlign: 'center',
padding: '48px 24px',
borderRadius: 16,
background: 'linear-gradient(180deg, rgba(235,102,88,0.12) 0%, rgba(201,76,60,0.08) 100%)',
border: '1px solid rgba(235,102,88,0.18)'
}}
>
<img src="/images/crew_only_logo.png" alt="CrewAI" width="250" height="100" />
<div style={{ maxWidth: 720 }}>
<h1 style={{ marginBottom: 12 }}>أطلق أنظمة متعددة الـ Agents بثقة</h1>
<p style={{ color: 'var(--mint-text-2)' }}>
صمم Agents، ونسّق Crews، وأتمت Flows مع حواجز حماية وذاكرة ومعرفة ومراقبة مدمجة.
</p>
</div>
<div style={{ display: 'flex', flexWrap: 'wrap', gap: 12, justifyContent: 'center' }}>
<a className="button button-primary" href="/ar/quickstart">ابدأ الآن</a>
<a className="button" href="/ar/changelog">سجل التغييرات</a>
<a className="button" href="/ar/api-reference/introduction">مرجع API</a>
</div>
</div>
<div style={{ marginTop: 32 }} />
## ابدأ
<CardGroup cols={3}>
<Card title="مقدمة" href="/ar/introduction" icon="sparkles">
نظرة عامة على مفاهيم CrewAI وبنيته المعمارية وما يمكنك بناؤه باستخدام Agents وCrews وFlows.
</Card>
<Card title="التثبيت" href="/ar/installation" icon="wrench">
التثبيت عبر `uv`، وإعداد مفاتيح API، وتهيئة CLI للتطوير المحلي.
</Card>
<Card title="البداية السريعة" href="/ar/quickstart" icon="rocket">
أنشئ أول Crew لك في دقائق. تعلم بيئة التشغيل الأساسية وهيكل المشروع ودورة التطوير.
</Card>
</CardGroup>
## ابنِ الأساسيات
<CardGroup cols={3}>
<Card title="Agents" href="/ar/concepts/agents" icon="users">
أنشئ Agents بأدوات وذاكرة ومعرفة ومخرجات منظمة باستخدام Pydantic. يتضمن قوالب وأفضل الممارسات.
</Card>
<Card title="Flows" href="/ar/concepts/flows" icon="arrow-progress">
نسّق خطوات start/listen/router، وأدر الحالة، واحفظ التنفيذ، واستأنف سير العمل الطويل.
</Card>
<Card title="المهام والعمليات" href="/ar/concepts/tasks" icon="check">
حدد عمليات متسلسلة أو هرمية أو مختلطة مع حواجز حماية واستدعاءات راجعة ومحفزات تدخل بشري.
</Card>
</CardGroup>
## رحلة المؤسسات
<CardGroup cols={3}>
<Card title="نشر الأتمتة" href="https://docs-platform.crewai.com/platform/ar/features/automations" icon="server">
إدارة البيئات وإعادة النشر بأمان ومراقبة التشغيل المباشر من لوحة تحكم المؤسسات.
</Card>
<Card title="المحفزات والـ Flows" href="https://docs-platform.crewai.com/platform/ar/guides/automation-triggers" icon="bolt">
ربط Gmail وSlack وSalesforce والمزيد. تمرير بيانات المحفزات إلى Crews وFlows تلقائيًا.
</Card>
<Card title="إدارة الفريق" href="https://docs-platform.crewai.com/platform/ar/guides/team-management" icon="users-gear">
دعوة أعضاء الفريق وتهيئة التحكم في الوصول المبني على الأدوار وإدارة الوصول إلى أتمتة الإنتاج.
</Card>
</CardGroup>
## ما الجديد
<CardGroup cols={2}>
<Card title="نظرة عامة على المحفزات" href="https://docs-platform.crewai.com/platform/ar/guides/automation-triggers" icon="sparkles">
نظرة شاملة موحدة على Gmail وDrive وOutlook وTeams وOneDrive وHubSpot والمزيد — الآن مع نماذج بيانات وCrews.
</Card>
<Card title="أدوات التكامل" href="/ar/tools/integration/overview" icon="plug">
استدعاء أتمتة CrewAI الحالية أو Amazon Bedrock Agents مباشرة من Crews باستخدام مجموعة أدوات التكامل المحدّثة.
</Card>
</CardGroup>
<Callout title="استكشف الأنماط الواقعية" icon="github">
تصفح <a href="/ar/examples/cookbooks">الأمثلة وكتب الوصفات</a> للحصول على تطبيقات مرجعية شاملة عبر Agents وFlows وأتمتة المؤسسات.
</Callout>
## ابقَ على تواصل
<CardGroup cols={2}>
<Card title="امنحنا نجمة على GitHub" href="https://github.com/crewAIInc/crewAI" icon="star">
إذا ساعدك CrewAI في الإطلاق بشكل أسرع، امنحنا نجمة وشارك مشاريعك مع المجتمع.
</Card>
<Card title="انضم إلى المجتمع" href="https://community.crewai.com" icon="comments">
اطرح أسئلة واعرض سير العمل واطلب ميزات جديدة جنبًا إلى جنب مع المطورين الآخرين.
</Card>
</CardGroup>

View File

@@ -0,0 +1,216 @@
---
title: التثبيت
description: ابدأ مع CrewAI - التثبيت والتهيئة وبناء أول فريق AI
icon: wrench
mode: "wide"
---
### شاهد: بناء Agents و Flows في CrewAI باستخدام Coding Agent Skills
قم بتثبيت مهارات وكيل البرمجة الخاصة بنا (Claude Code، Codex، ...) لتشغيل وكلاء البرمجة بسرعة مع CrewAI.
يمكنك تثبيتها باستخدام `npx skills add crewaiinc/skills`
<iframe src="https://www.loom.com/embed/befb9f68b81f42ad8112bfdd95a780af" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style={{width: "100%", height: "400px"}}></iframe>
## فيديو تعليمي
شاهد هذا الفيديو التعليمي لعرض تفصيلي لعملية التثبيت:
<iframe
className="w-full aspect-video rounded-xl"
src="https://www.youtube.com/embed/-kSOTtYzgEw"
title="CrewAI Installation Guide"
frameBorder="0"
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
allowFullScreen
></iframe>
## دليل نصي
<Note>
**متطلبات إصدار Python**
يتطلب CrewAI إصدار `Python >=3.10 and <3.14`. إليك كيفية التحقق من إصدارك:
```bash
python3 --version
```
إذا كنت بحاجة لتحديث Python، قم بزيارة [python.org/downloads](https://python.org/downloads)
</Note>
<Note>
**متطلبات OpenAI SDK**
يتطلب CrewAI 0.175.0 إصدار `openai >= 1.13.3`. إذا كنت تدير التبعيات بنفسك، تأكد من أن بيئتك تستوفي هذا الشرط لتجنب مشاكل الاستيراد/التشغيل.
</Note>
يستخدم CrewAI أداة `uv` لإدارة التبعيات والحزم. وهي تبسّط إعداد المشروع وتنفيذه وتوفر تجربة سلسة.
إذا لم تكن قد ثبّتت `uv` بعد، اتبع **الخطوة 1** لإعدادها بسرعة على نظامك، وإلا يمكنك الانتقال إلى **الخطوة 2**.
<Steps>
<Step title="تثبيت uv">
- **على macOS/Linux:**
استخدم `curl` لتحميل السكريبت وتنفيذه عبر `sh`:
```shell
curl -LsSf https://astral.sh/uv/install.sh | sh
```
إذا لم يكن `curl` متاحًا على نظامك، يمكنك استخدام `wget`:
```shell
wget -qO- https://astral.sh/uv/install.sh | sh
```
- **على Windows:**
استخدم `irm` لتحميل السكريبت و`iex` لتنفيذه:
```shell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```
إذا واجهت أي مشاكل، راجع [دليل تثبيت UV](https://docs.astral.sh/uv/getting-started/installation/) لمزيد من المعلومات.
</Step>
<Step title="تثبيت CrewAI">
- شغّل الأمر التالي لتثبيت واجهة سطر أوامر `crewai`:
```shell
uv tool install crewai
```
<Warning>
إذا ظهر تحذير بشأن `PATH`، شغّل هذا الأمر لتحديث الصدفة:
```shell
uv tool update-shell
```
</Warning>
<Warning>
إذا واجهت خطأ بناء `chroma-hnswlib==0.7.6` (`fatal error C1083: Cannot open include file: 'float.h'`) على Windows، ثبّت [Visual Studio Build Tools](https://visualstudio.microsoft.com/downloads/) مع خيار *Desktop development with C++*.
</Warning>
- للتحقق من تثبيت `crewai`، شغّل:
```shell
uv tool list
```
- يجب أن ترى شيئًا مثل:
```shell
crewai v0.102.0
- crewai
```
- إذا كنت بحاجة لتحديث `crewai`، شغّل:
```shell
uv tool install crewai --upgrade
```
<Check>تم التثبيت بنجاح! أنت جاهز لإنشاء أول Crew!</Check>
</Step>
</Steps>
# إنشاء مشروع CrewAI
يقوم `crewai create crew` الآن بإنشاء مشروع crew بأسلوب JSON-first. توضع الـ Agents في `agents/*.jsonc`، وتوضع المهام وإعدادات الـ crew في `crew.jsonc`، ويحمّل `crewai run` هذا التعريف مباشرة.
<Steps>
<Step title="إنشاء هيكل المشروع">
- شغّل أمر `crewai` عبر CLI:
```shell
crewai create crew <your_project_name>
```
- سينشئ هذا مشروعًا جديدًا بالهيكل التالي:
```
my_project/
├── .gitignore
├── .env
├── agents/
│ └── researcher.jsonc
├── crew.jsonc
├── knowledge/
├── pyproject.toml
├── README.md
├── skills/
└── tools/
```
- إذا احتجت إلى البنية القديمة Python/YAML التي تحتوي على `crew.py` و `config/agents.yaml` و `config/tasks.yaml`، شغّل:
```shell
crewai create crew <your_project_name> --classic
```
</Step>
<Step title="تخصيص مشروعك">
- سيحتوي مشروعك على هذه الملفات الأساسية:
| الملف | الغرض |
| --- | --- |
| `crew.jsonc` | إعداد الـ crew وترتيب المهام والعملية وقيم الإدخال الافتراضية |
| `agents/*.jsonc` | تعريف دور كل Agent وهدفه و backstory والـ LLM والأدوات والسلوك |
| `.env` | تخزين مفاتيح API ومتغيرات البيئة |
| `tools/` | ملفات Python اختيارية لأدوات `custom:<name>` |
| `knowledge/` | ملفات معرفة اختيارية للـ Agents |
| `skills/` | ملفات skills اختيارية تطبق على الـ crew |
- ابدأ بتحرير `crew.jsonc` والملفات داخل `agents/` لتعريف سلوك الـ crew.
- استخدم قيم `{placeholder}` في نصوص الـ Agents والمهام، ثم ضع القيم الافتراضية في `inputs` داخل `crew.jsonc`. عند تشغيل `crewai run` ستطلب CLI أي قيم ناقصة.
- احتفظ بالمعلومات الحساسة مثل مفاتيح API في `.env`.
</Step>
<Step title="تشغيل الـ Crew">
- قبل تشغيل الـ Crew، تأكد من تنفيذ:
```bash
crewai install
```
- إذا كنت بحاجة لتثبيت حزم إضافية، استخدم:
```shell
uv add <package-name>
```
- لتشغيل الـ Crew، نفّذ الأمر التالي في جذر مشروعك:
```bash
crewai run
```
</Step>
</Steps>
## خيارات التثبيت للمؤسسات
<Note type="info">
للفرق والمؤسسات، يوفر CrewAI خيارات نشر مؤسسية تزيل تعقيد الإعداد:
### CrewAI AMP (SaaS)
- لا يتطلب أي تثبيت - فقط سجّل مجانًا على [app.crewai.com](https://app.crewai.com)
- تحديثات وصيانة تلقائية
- بنية تحتية مُدارة وقابلة للتوسع
- بناء Crews بدون كتابة كود
### CrewAI Factory (استضافة ذاتية)
- نشر بالحاويات على بنيتك التحتية
- يدعم أي مزود سحابي بما في ذلك النشر المحلي
- تكامل مع أنظمة الأمان الحالية
<Card title="استكشف خيارات المؤسسات" icon="building" href="https://share.hsforms.com/1Ooo2UViKQ22UOzdr7i77iwr87kg">
تعرّف على عروض CrewAI للمؤسسات وجدول عرضًا توضيحيًا
</Card>
</Note>
## الخطوات التالية
<CardGroup cols={2}>
<Card title="بدء سريع: Flow + وكيل" icon="code" href="/ar/quickstart">
اتبع البداية السريعة لإنشاء Flow وتشغيل طاقم بوكيل واحد وإنتاج تقرير.
</Card>
<Card
title="انضم إلى المجتمع"
icon="comments"
href="https://community.crewai.com"
>
تواصل مع مطورين آخرين واحصل على المساعدة وشارك تجاربك مع CrewAI.
</Card>
</CardGroup>

View File

@@ -0,0 +1,152 @@
---
title: مقدمة
description: ابنِ فرق Agents ذكاء اصطناعي تعمل معًا لمعالجة المهام المعقدة
icon: handshake
mode: "wide"
---
# ما هو CrewAI؟
**CrewAI هو إطار العمل مفتوح المصدر الرائد لتنسيق Agents الذكاء الاصطناعي المستقلة وبناء سير العمل المعقدة.**
يمكّن المطورين من بناء أنظمة متعددة الـ Agents جاهزة للإنتاج من خلال الجمع بين الذكاء التعاوني لـ **Crews** والتحكم الدقيق لـ **Flows**.
- **[CrewAI Flows](/ar/guides/flows/first-flow)**: العمود الفقري لتطبيق الذكاء الاصطناعي. تتيح لك Flows إنشاء سير عمل منظمة قائمة على الأحداث تدير الحالة وتتحكم في التنفيذ. وهي توفر البنية الأساسية التي تعمل ضمنها Agents الذكاء الاصطناعي.
- **[CrewAI Crews](/ar/guides/crews/first-crew)**: وحدات العمل ضمن Flow. الـ Crews هي فرق من Agents مستقلة تتعاون لحل مهام محددة يفوضها إليها Flow.
مع أكثر من 100,000 مطور معتمد عبر دوراتنا المجتمعية، يُعد CrewAI المعيار لأتمتة الذكاء الاصطناعي الجاهزة للمؤسسات.
### شاهد: بناء Agents و Flows في CrewAI باستخدام Coding Agent Skills
قم بتثبيت مهارات وكيل البرمجة الخاصة بنا (Claude Code، Codex، ...) لتشغيل وكلاء البرمجة بسرعة مع CrewAI.
يمكنك تثبيتها باستخدام `npx skills add crewaiinc/skills`
<iframe src="https://www.loom.com/embed/befb9f68b81f42ad8112bfdd95a780af" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style={{width: "100%", height: "400px"}}></iframe>
## بنية CrewAI المعمارية
صُممت بنية CrewAI لتحقيق التوازن بين الاستقلالية والتحكم.
### 1. Flows: العمود الفقري
<Note>
فكّر في Flow كـ "المدير" أو "تعريف العملية" لتطبيقك. يحدد الخطوات والمنطق وكيفية تدفق البيانات عبر نظامك.
</Note>
<Frame caption="نظرة عامة على إطار عمل CrewAI">
<img src="/images/flows.png" alt="نظرة عامة على إطار عمل CrewAI" />
</Frame>
توفر Flows:
- **إدارة الحالة**: حفظ البيانات عبر الخطوات والتنفيذات.
- **تنفيذ قائم على الأحداث**: تشغيل إجراءات بناءً على أحداث أو مدخلات خارجية.
- **التحكم في التدفق**: استخدام المنطق الشرطي والحلقات والتفرع.
### 2. Crews: الذكاء
<Note>
الـ Crews هي "الفرق" التي تقوم بالعمل الثقيل. ضمن Flow، يمكنك تشغيل Crew لمعالجة مشكلة معقدة تتطلب إبداعًا وتعاونًا.
</Note>
<Frame caption="نظرة عامة على إطار عمل CrewAI">
<img src="/images/crews.png" alt="نظرة عامة على إطار عمل CrewAI" />
</Frame>
توفر Crews:
- **Agents بأدوار محددة**: Agents متخصصة بأهداف وأدوات محددة.
- **تعاون مستقل**: تعمل الـ Agents معًا لحل المهام.
- **تفويض المهام**: يتم تعيين المهام وتنفيذها بناءً على قدرات الـ Agent.
## كيف يعمل الكل معًا
1. يبدأ **Flow** حدثًا أو يشغّل عملية.
2. يدير **Flow** الحالة ويقرر ما يجب فعله بعد ذلك.
3. يفوّض **Flow** مهمة معقدة إلى **Crew**.
4. تتعاون Agents الـ **Crew** لإكمال المهمة.
5. يعيد **Crew** النتيجة إلى **Flow**.
6. يستمر **Flow** في التنفيذ بناءً على النتيجة.
## الميزات الرئيسية
<CardGroup cols={2}>
<Card title="Flows بمستوى الإنتاج" icon="arrow-progress">
ابنِ سير عمل موثوقة وذات حالة يمكنها التعامل مع العمليات طويلة التشغيل والمنطق المعقد.
</Card>
<Card title="Crews مستقلة" icon="users">
انشر فرقًا من الـ Agents يمكنها التخطيط والتنفيذ والتعاون لتحقيق أهداف عالية المستوى.
</Card>
<Card title="أدوات مرنة" icon="screwdriver-wrench">
اربط Agents بأي API أو قاعدة بيانات أو أداة محلية.
</Card>
<Card title="أمان المؤسسات" icon="lock">
مصمم مع مراعاة الأمان والامتثال لعمليات نشر المؤسسات.
</Card>
</CardGroup>
## متى تستخدم Crews مقابل Flows
**الإجابة المختصرة: استخدم كليهما.**
لأي تطبيق جاهز للإنتاج، **ابدأ بـ Flow**.
- **استخدم Flow** لتعريف الهيكل العام والحالة والمنطق لتطبيقك.
- **استخدم Crew** ضمن خطوة Flow عندما تحتاج فريقًا من الـ Agents لأداء مهمة معقدة محددة تتطلب استقلالية.
| حالة الاستخدام | البنية المعمارية |
| :--- | :--- |
| **أتمتة بسيطة** | Flow واحد مع مهام Python |
| **بحث معقد** | Flow يدير الحالة -> Crew يجري البحث |
| **واجهة تطبيق خلفية** | Flow يعالج طلبات API -> Crew ينشئ المحتوى -> Flow يحفظ في قاعدة البيانات |
## لماذا تختار CrewAI؟
- **تشغيل مستقل**: تتخذ الـ Agents قرارات ذكية بناءً على أدوارها وأدواتها المتاحة
- **تفاعل طبيعي**: تتواصل الـ Agents وتتعاون كأعضاء فريق بشري
- **تصميم قابل للتوسيع**: سهولة إضافة أدوات وأدوار وقدرات جديدة
- **جاهز للإنتاج**: مبني للموثوقية والتوسع في التطبيقات الواقعية
- **موجّه نحو الأمان**: مصمم مع مراعاة متطلبات أمان المؤسسات
- **كفاءة التكلفة**: محسّن لتقليل استخدام الرموز المميزة واستدعاءات API
## هل أنت مستعد للبدء في البناء؟
<CardGroup cols={2}>
<Card
title="ابنِ أول Flow لك"
icon="diagram-project"
href="/ar/guides/flows/first-flow"
>
تعلم كيفية إنشاء سير عمل منظمة قائمة على الأحداث مع تحكم دقيق في التنفيذ.
</Card>
<Card
title="ابنِ أول Crew لك"
icon="users-gear"
href="/ar/guides/crews/first-crew"
>
دليل تفصيلي لإنشاء فريق AI تعاوني يعمل معًا لحل المشكلات المعقدة.
</Card>
</CardGroup>
<CardGroup cols={3}>
<Card
title="تثبيت CrewAI"
icon="wrench"
href="/ar/installation"
>
ابدأ مع CrewAI في بيئة التطوير الخاصة بك.
</Card>
<Card
title="البداية السريعة"
icon="bolt"
href="/ar/quickstart"
>
أنشئ Flow وشغّل طاقمًا بوكيل واحد وأنشئ تقريرًا من البداية للنهاية.
</Card>
<Card
title="انضم إلى المجتمع"
icon="comments"
href="https://community.crewai.com"
>
تواصل مع مطورين آخرين واحصل على المساعدة وشارك تجاربك مع CrewAI.
</Card>
</CardGroup>

View File

@@ -0,0 +1,87 @@
---
title: بروتوكول Agent-to-Agent (A2A)
description: الـ Agents تفوّض المهام إلى Agents A2A بعيدة و/أو تعمل كـ Agents خادم متوافقة مع A2A.
icon: network-wired
mode: "wide"
---
## تفويض Agent A2A
يعامل CrewAI [بروتوكول A2A](https://a2a-protocol.org/latest/) كبنية تفويض أساسية، مما يمكّن الـ Agents من تفويض المهام وطلب المعلومات والتعاون مع Agents بعيدة، وكذلك العمل كـ Agents خادم متوافقة مع A2A. في وضع العميل، تختار الـ Agents تلقائيًا بين التنفيذ المحلي والتفويض البعيد بناءً على متطلبات المهمة.
## كيف يعمل
عندما يُهيَّأ Agent بقدرات A2A:
1. يحلل الـ Agent كل مهمة
2. يقرر إما:
- معالجة المهمة مباشرة باستخدام قدراته الخاصة
- التفويض إلى Agent A2A بعيد للمعالجة المتخصصة
3. إذا فوّض، يتواصل الـ Agent مع Agent A2A البعيد عبر البروتوكول
4. تُعاد النتائج إلى سير عمل CrewAI
<Note>
تفويض A2A يتطلب حزمة `a2a-sdk`. ثبّتها بـ: `uv add 'crewai[a2a]'` أو `pip install 'crewai[a2a]'`
</Note>
## التهيئة الأساسية
<Warning>
`crewai.a2a.config.A2AConfig` مهمل وسيُزال في v2.0.0. استخدم `A2AClientConfig` للاتصال بـ Agents بعيدة و/أو `A2AServerConfig` لعرض الـ Agents كخوادم.
</Warning>
```python Code
from crewai import Agent, Crew, Task
from crewai.a2a import A2AClientConfig
agent = Agent(
role="Research Coordinator",
goal="Coordinate research tasks efficiently",
backstory="Expert at delegating to specialized research agents",
llm="gpt-4o",
a2a=A2AClientConfig(
endpoint="https://example.com/.well-known/agent-card.json",
timeout=120,
max_turns=10
)
)
task = Task(
description="Research the latest developments in quantum computing",
expected_output="A comprehensive research report",
agent=agent
)
crew = Crew(agents=[agent], tasks=[task], verbose=True)
result = crew.kickoff()
```
## خيارات تهيئة العميل
راجع الملف الإنجليزي الأصلي للحصول على القائمة الكاملة لمعاملات `A2AClientConfig` وخيارات المصادقة وآليات التحديث وتهيئة الخادم.
## أفضل الممارسات
<CardGroup cols={2}>
<Card title="عيّن مهلات مناسبة" icon="clock">
هيّئ المهلات بناءً على أوقات استجابة Agent A2A المتوقعة.
</Card>
<Card title="حدّ جولات المحادثة" icon="comments">
استخدم `max_turns` لمنع التبادل المفرط.
</Card>
<Card title="استخدم معالجة أخطاء مرنة" icon="shield-check">
عيّن `fail_fast=False` لبيئات الإنتاج مع عدة Agents.
</Card>
<Card title="أمّن بيانات الاعتماد" icon="lock">
خزّن رموز المصادقة وبيانات الاعتماد كمتغيرات بيئة، ليس في الكود.
</Card>
</CardGroup>
## تعلم المزيد
- [توثيق بروتوكول A2A](https://a2a-protocol.org)
- [تطبيقات A2A النموذجية](https://github.com/a2aproject/a2a-samples)
- [A2A Python SDK](https://github.com/a2aproject/a2a-python)

View File

@@ -0,0 +1,47 @@
---
title: خطافات قبل وبعد الانطلاق
description: تعلم كيفية استخدام خطافات قبل وبعد الانطلاق في CrewAI
mode: "wide"
---
يوفر CrewAI خطافات تتيح لك تنفيذ كود قبل وبعد انطلاق Crew. هذه الخطافات مفيدة لمعالجة المدخلات مسبقًا أو معالجة النتائج لاحقًا.
## خطاف قبل الانطلاق
يُنفَّذ خطاف قبل الانطلاق قبل أن يبدأ Crew مهامه. يتلقى قاموس المدخلات ويمكنه تعديله قبل تمريره إلى Crew. يمكنك استخدام هذا الخطاف لإعداد بيئتك أو تحميل البيانات اللازمة أو معالجة المدخلات مسبقًا.
```python
from crewai import CrewBase
from crewai.project import before_kickoff
@CrewBase
class MyCrew:
@before_kickoff
def prepare_data(self, inputs):
inputs['processed'] = True
return inputs
```
## خطاف بعد الانطلاق
يُنفَّذ خطاف بعد الانطلاق بعد إتمام Crew مهامه. يتلقى كائن النتيجة الذي يحتوي على مخرجات تنفيذ Crew. هذا الخطاف مثالي لمعالجة النتائج لاحقًا مثل التسجيل أو تحويل البيانات أو التحليل الإضافي.
```python
from crewai import CrewBase
from crewai.project import after_kickoff
@CrewBase
class MyCrew:
@after_kickoff
def log_results(self, result):
print("Crew execution completed with result:", result)
return result
```
## استخدام كلا الخطافين
يمكن استخدام كلا الخطافين معًا لتوفير عملية إعداد وتفكيك شاملة لتنفيذ Crew. وهما مفيدان بشكل خاص في الحفاظ على بنية كود نظيفة من خلال فصل المسؤوليات وتعزيز نمطية تنفيذات CrewAI.
## الخلاصة
توفر خطافات قبل وبعد الانطلاق في CrewAI طرقًا قوية للتفاعل مع دورة حياة تنفيذ Crew. من خلال فهم واستخدام هذه الخطافات، يمكنك تعزيز متانة ومرونة Agents الذكاء الاصطناعي بشكل كبير.

View File

@@ -0,0 +1,41 @@
---
title: أحضر Agent الخاص بك
description: تعلم كيفية إحضار Agents خاصة بك تعمل ضمن Crew.
icon: robots
mode: "wide"
---
قابلية التشغيل البيني مفهوم أساسي في CrewAI. يوضح هذا الدليل كيفية إحضار Agents خاصة بك تعمل ضمن Crew.
## دليل المحوّلات لإحضار Agents الخاصة (Agents من LangGraph وOpenAI وغيرها...)
نتطلب 3 محوّلات لتحويل أي Agent من أطر عمل مختلفة للعمل ضمن Crew.
1. BaseAgentAdapter
2. BaseToolAdapter
3. BaseConverter
## BaseAgentAdapter
تعرّف هذه الفئة المجردة الواجهة المشتركة والوظائف التي يجب أن تنفذها جميع محوّلات الـ Agent. تمتد BaseAgent للحفاظ على التوافق مع إطار عمل CrewAI مع إضافة متطلبات خاصة بالمحوّل.
الطرق المطلوبة:
1. `def configure_tools`
2. `def configure_structured_output`
## إنشاء محوّل خاص بك
لدمج Agent من إطار عمل مختلف في CrewAI، تحتاج لإنشاء محوّل مخصص بوراثة `BaseAgentAdapter`. يعمل هذا المحوّل كطبقة توافق تترجم بين واجهات CrewAI والمتطلبات المحددة للـ Agent الخارجي.
راجع الملف الإنجليزي الأصلي لأمثلة الكود التفصيلية لتنفيذ BaseAgentAdapter وBaseToolAdapter وBaseConverter.
## محوّلات جاهزة للاستخدام
نوفر محوّلات جاهزة للأطر التالية:
1. LangGraph
2. OpenAI Agents
## تشغيل Crew مع Agents محوّلة:
راجع الملف الإنجليزي الأصلي للحصول على مثال الكود الكامل الذي يوضح استخدام CrewAI Agent وOpenAI Agent Adapter وLangGraph Agent Adapter معًا في Crew واحد.

View File

@@ -0,0 +1,80 @@
---
title: Agents البرمجة
description: تعلم كيفية تمكين Agents CrewAI من كتابة وتنفيذ الكود، واستكشف الميزات المتقدمة لوظائف محسّنة.
icon: rectangle-code
mode: "wide"
---
## مقدمة
أصبح لدى CrewAI Agents القدرة القوية على كتابة وتنفيذ الكود، مما يعزز قدراتها في حل المشكلات بشكل كبير. هذه الميزة مفيدة بشكل خاص للمهام التي تتطلب حلولاً حسابية أو برمجية.
## تمكين تنفيذ الكود
لتمكين تنفيذ الكود لـ Agent، عيّن معامل `allow_code_execution` إلى `True` عند إنشاء الـ Agent.
```python Code
from crewai import Agent
coding_agent = Agent(
role="Senior Python Developer",
goal="Craft well-designed and thought-out code",
backstory="You are a senior Python developer with extensive experience in software architecture and best practices.",
allow_code_execution=True
)
```
<Note>
لاحظ أن معامل `allow_code_execution` يكون `False` افتراضيًا.
</Note>
## اعتبارات مهمة
1. **اختيار النموذج**: يُوصى بشدة باستخدام نماذج أكثر قدرة مثل Claude 3.5 Sonnet وGPT-4 عند تمكين تنفيذ الكود.
2. **معالجة الأخطاء**: تتضمن ميزة تنفيذ الكود معالجة أخطاء. إذا أثار الكود المُنفَّذ استثناءً، سيتلقى الـ Agent رسالة الخطأ ويمكنه محاولة تصحيح الكود. يتحكم معامل `max_retry_limit` (الافتراضي 2) في الحد الأقصى لعدد المحاولات.
3. **التبعيات**: لاستخدام ميزة تنفيذ الكود، تحتاج لتثبيت حزمة `crewai_tools`.
## عملية تنفيذ الكود
<Steps>
<Step title="تحليل المهمة">
يحلل الـ Agent المهمة ويحدد أن تنفيذ الكود ضروري.
</Step>
<Step title="صياغة الكود">
يصيغ كود Python اللازم لحل المشكلة.
</Step>
<Step title="تنفيذ الكود">
يُرسَل الكود إلى أداة تنفيذ الكود الداخلية (`CodeInterpreterTool`).
</Step>
<Step title="تفسير النتيجة">
يفسر الـ Agent النتيجة ويدمجها في استجابته أو يستخدمها لمزيد من حل المشكلات.
</Step>
</Steps>
## مثال استخدام
```python Code
from crewai import Agent, Task, Crew
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants.",
agent=coding_agent
)
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
result = analysis_crew.kickoff()
print(result)
```

View File

@@ -0,0 +1,14 @@
---
title: المهام الشرطية
description: تعلم كيفية استخدام المهام الشرطية في انطلاق crewAI
icon: diagram-subtask
mode: "wide"
---
## مقدمة
تتيح المهام الشرطية في crewAI التكيف الديناميكي لسير العمل بناءً على نتائج المهام السابقة. تمكّن هذه الميزة القوية الـ Crews من اتخاذ قرارات وتنفيذ المهام بشكل انتقائي، مما يعزز مرونة وكفاءة عملياتك المدفوعة بالذكاء الاصطناعي.
## مثال استخدام
راجع الملف الإنجليزي الأصلي للحصول على مثال الكود الكامل الذي يوضح استخدام `ConditionalTask` مع دالة شرط `is_data_missing` للتحكم في تنفيذ المهام بناءً على مخرجات المهام السابقة.

View File

@@ -0,0 +1,77 @@
---
title: إنشاء أدوات مخصصة
description: دليل شامل لصياغة واستخدام وإدارة الأدوات المخصصة ضمن إطار عمل CrewAI، بما في ذلك الوظائف الجديدة ومعالجة الأخطاء.
icon: hammer
mode: "wide"
---
## إنشاء واستخدام الأدوات في CrewAI
يقدم هذا الدليل تعليمات مفصلة لإنشاء أدوات مخصصة لإطار عمل CrewAI وكيفية إدارة واستخدام هذه الأدوات بكفاءة، مع دمج أحدث الوظائف مثل تفويض الأدوات ومعالجة الأخطاء واستدعاء الأدوات الديناميكي.
<Tip>
**هل تريد نشر أداتك للمجتمع؟** إذا كنت تبني أداة يمكن أن تفيد الآخرين، اطلع على دليل [نشر أدوات مخصصة](/ar/guides/tools/publish-custom-tools) لتعلم كيفية تعبئة وتوزيع أداتك على PyPI.
</Tip>
### وراثة `BaseTool`
لإنشاء أداة مخصصة، ورث من `BaseTool` وعرّف السمات الضرورية بما في ذلك `args_schema` للتحقق من المدخلات وطريقة `_run`.
```python Code
from typing import Type
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
class MyToolInput(BaseModel):
"""Input schema for MyCustomTool."""
argument: str = Field(..., description="Description of the argument.")
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "What this tool does. It's vital for effective utilization."
args_schema: Type[BaseModel] = MyToolInput
def _run(self, argument: str) -> str:
return "Tool's result"
```
### استخدام مزخرف `tool`
```python Code
from crewai.tools import tool
@tool("Tool Name")
def my_simple_tool(question: str) -> str:
"""Tool description for clarity."""
return "Tool output"
```
### تعريف دالة تخزين مؤقت للأداة
```python Code
@tool("Tool with Caching")
def cached_tool(argument: str) -> str:
"""Tool functionality description."""
return "Cacheable result"
def my_cache_strategy(arguments: dict, result: str) -> bool:
return True if some_condition else False
cached_tool.cache_function = my_cache_strategy
```
### إنشاء أدوات غير متزامنة
يدعم CrewAI الأدوات غير المتزامنة لعمليات I/O غير المحجوبة.
```python Code
import aiohttp
from crewai.tools import tool
@tool("Async Web Fetcher")
async def fetch_webpage(url: str) -> str:
"""Fetch content from a webpage asynchronously."""
async with aiohttp.ClientSession() as session:
async with session.get(url) as response:
return await response.text()
```

View File

@@ -0,0 +1,55 @@
---
title: تنفيذ LLM مخصص
description: تعلم كيفية إنشاء تنفيذات LLM مخصصة في CrewAI.
icon: code
mode: "wide"
---
## نظرة عامة
يدعم CrewAI تنفيذات LLM المخصصة من خلال فئة `BaseLLM` المجردة. يتيح لك ذلك دمج أي مزود LLM لا يحظى بدعم مدمج في LiteLLM، أو تنفيذ آليات مصادقة مخصصة.
## بداية سريعة
راجع الملف الإنجليزي الأصلي للحصول على تنفيذ LLM مخصص كامل يوضح طريقة `call()` المطلوبة والطرق الاختيارية مثل `supports_function_calling()` و`get_context_window_size()`.
## استخدام LLM المخصص
```python
from crewai import Agent, Task, Crew
custom_llm = CustomLLM(
model="my-custom-model",
api_key="your-api-key",
endpoint="https://api.example.com/v1/chat/completions",
temperature=0.7
)
agent = Agent(
role="Research Assistant",
goal="Find and analyze information",
backstory="You are a research assistant.",
llm=custom_llm
)
task = Task(
description="Research the latest developments in AI",
expected_output="A comprehensive summary",
agent=agent
)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
```
## الطرق المطلوبة
### البنّاء: `__init__()`
**مهم**: يجب استدعاء `super().__init__(model, temperature)` مع المعاملات المطلوبة.
### الطريقة المجردة: `call()`
طريقة `call()` هي قلب تنفيذ LLM. يجب أن تقبل الرسائل وتعيد استجابة نصية وتعالج الأدوات واستدعاء الدوال إذا كانت مدعومة.
يغطي هذا الدليل أساسيات تنفيذ LLM مخصصة في CrewAI.

View File

@@ -0,0 +1,81 @@
---
title: Agent مدير مخصص
description: تعلم كيفية تعيين Agent مخصص كمدير في CrewAI، مما يوفر مزيدًا من التحكم في إدارة المهام والتنسيق.
icon: user-shield
mode: "wide"
---
# تعيين Agent محدد كمدير في CrewAI
يتيح CrewAI للمستخدمين تعيين Agent محدد كمدير للـ Crew، مما يوفر مزيدًا من التحكم في إدارة المهام وتنسيقها.
## استخدام سمة `manager_agent`
تتيح لك سمة `manager_agent` تعريف Agent مخصص لإدارة الـ Crew. سيشرف هذا الـ Agent على العملية بأكملها لضمان إتمام المهام بكفاءة وبأعلى المعايير.
```python Code
import os
from crewai import Agent, Task, Crew, Process
researcher = Agent(
role="Researcher",
goal="Conduct thorough research and analysis on AI and AI agents",
backstory="You're an expert researcher...",
allow_delegation=False,
)
writer = Agent(
role="Senior Writer",
goal="Create compelling content about AI and AI agents",
backstory="You're a senior writer...",
allow_delegation=False,
)
task = Task(
description="Generate a list of 5 interesting ideas for an article...",
expected_output="5 bullet points, each with a paragraph and accompanying notes.",
)
manager = Agent(
role="Project Manager",
goal="Efficiently manage the crew and ensure high-quality task completion",
backstory="You're an experienced project manager...",
allow_delegation=True,
)
crew = Crew(
agents=[researcher, writer],
tasks=[task],
manager_agent=manager,
process=Process.hierarchical,
)
result = crew.kickoff()
```
## فوائد Agent المدير المخصص
- **تحكم محسّن**: تخصيص نهج الإدارة ليناسب الاحتياجات المحددة لمشروعك.
- **تنسيق محسّن**: ضمان تنسيق المهام وإدارتها بكفاءة من قبل Agent ذي خبرة.
- **إدارة قابلة للتخصيص**: تعريف أدوار ومسؤوليات إدارية تتماشى مع أهداف مشروعك.
## تعيين LLM للمدير
إذا كنت تستخدم العملية الهرمية ولا تريد تعيين Agent مدير مخصص، يمكنك تحديد نموذج اللغة للمدير:
```python Code
from crewai import LLM
manager_llm = LLM(model="gpt-4o")
crew = Crew(
agents=[researcher, writer],
tasks=[task],
process=Process.hierarchical,
manager_llm=manager_llm
)
```
<Note>
يجب تعيين إما `manager_agent` أو `manager_llm` عند استخدام العملية الهرمية.
</Note>

View File

@@ -0,0 +1,67 @@
---
title: تخصيص الـ Agents
description: دليل شامل لتخصيص الـ Agents لأدوار ومهام محددة وتخصيصات متقدمة ضمن إطار عمل CrewAI.
icon: user-pen
mode: "wide"
---
## السمات القابلة للتخصيص
يعتمد بناء فريق CrewAI فعّال على القدرة على تخصيص Agents الذكاء الاصطناعي ديناميكيًا لتلبية المتطلبات الفريدة لأي مشروع. يغطي هذا القسم السمات الأساسية التي يمكنك تخصيصها.
### السمات الرئيسية للتخصيص
| السمة | الوصف |
|:-----------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------|
| **Role** | يحدد وظيفة الـ Agent ضمن Crew، مثل 'محلل' أو 'ممثل خدمة عملاء'. |
| **Goal** | يعرّف أهداف الـ Agent، متوافقة مع دوره ومهمة Crew الشاملة. |
| **Backstory** | يوفر عمقًا لشخصية الـ Agent، معززًا الدوافع والتفاعلات ضمن Crew. |
| **Tools** *(اختياري)* | يمثل القدرات أو الطرق التي يستخدمها الـ Agent للمهام. |
| **Cache** *(اختياري)* | يحدد ما إذا كان الـ Agent يجب أن يستخدم ذاكرة مؤقتة لاستخدام الأدوات. |
| **Max RPM** | يعيّن الحد الأقصى للطلبات في الدقيقة (`max_rpm`). |
| **Verbose** *(اختياري)* | يمكّن التسجيل التفصيلي للتصحيح والتحسين. |
| **Allow Delegation** *(اختياري)* | يتحكم في تفويض المهام لـ Agents أخرى، الافتراضي `False`. |
| **Max Iter** *(اختياري)* | يحد الحد الأقصى لعدد التكرارات (`max_iter`) لمهمة، الافتراضي 25. |
## خيارات تخصيص متقدمة
### تخصيص نموذج اللغة
يمكن تخصيص الـ Agents بنماذج لغة محددة (`llm`) ونماذج لغة لاستدعاء الدوال (`function_calling_llm`)، مما يوفر تحكمًا متقدمًا في قدرات المعالجة وصنع القرار.
## إعدادات الأداء والتصحيح
- **وضع التفصيل**: يمكّن التسجيل التفصيلي لإجراءات الـ Agent.
- **حد RPM**: يعيّن الحد الأقصى للطلبات في الدقيقة.
### مثال: تعيين أدوات لـ Agent
```python Code
import os
from crewai import Agent
from crewai_tools import SerperDevTool
os.environ["OPENAI_API_KEY"] = "Your Key"
os.environ["SERPER_API_KEY"] = "Your Key"
search_tool = SerperDevTool()
agent = Agent(
role='Research Analyst',
goal='Provide up-to-date market analysis',
backstory='An expert analyst with a keen eye for market trends.',
tools=[search_tool],
memory=True,
verbose=True,
max_rpm=None,
max_iter=25,
)
```
## التفويض والاستقلالية
التحكم في قدرة الـ Agent على تفويض المهام أو طرح الأسئلة أمر حيوي لتخصيص استقلاليته وديناميكيات التعاون. افتراضيًا، سمة `allow_delegation` معيّنة على `False`.
## الخلاصة
تخصيص الـ Agents في CrewAI من خلال تعيين أدوارهم وأهدافهم وخلفياتهم وأدواتهم، إلى جانب خيارات متقدمة مثل تخصيص نموذج اللغة والذاكرة وإعدادات الأداء وتفضيلات التفويض، يجهّز فريق AI دقيق وقادر جاهز للتحديات المعقدة.

View File

@@ -0,0 +1,52 @@
---
title: "إنشاء الصور باستخدام DALL-E"
description: "تعلم كيفية استخدام DALL-E لإنشاء صور مدعومة بالذكاء الاصطناعي في مشاريع CrewAI"
icon: "image"
mode: "wide"
---
يدعم CrewAI التكامل مع DALL-E من OpenAI، مما يتيح لـ Agents الذكاء الاصطناعي إنشاء صور كجزء من مهامهم. سيرشدك هذا الدليل عبر كيفية إعداد واستخدام أداة DALL-E في مشاريع CrewAI.
## المتطلبات المسبقة
- crewAI مثبّت (أحدث إصدار)
- مفتاح OpenAI API مع وصول إلى DALL-E
## إعداد أداة DALL-E
<Steps>
<Step title="استيراد أداة DALL-E">
```python
from crewai_tools import DallETool
```
</Step>
<Step title="إضافة أداة DALL-E إلى تهيئة Agent">
```python
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config['researcher'],
tools=[SerperDevTool(), DallETool()],
allow_delegation=False,
verbose=True
)
```
</Step>
</Steps>
## استخدام أداة DALL-E
بمجرد إضافة أداة DALL-E إلى Agent، يمكنه إنشاء صور بناءً على مطالبات نصية. ستعيد الأداة رابط URL للصورة المُنشأة.
## أفضل الممارسات
1. **كن محددًا في مطالبات إنشاء الصور** للحصول على أفضل النتائج.
2. **ضع في اعتبارك وقت الإنشاء** - قد يستغرق إنشاء الصور بعض الوقت.
3. **اتبع سياسات الاستخدام** - التزم دائمًا بسياسات استخدام OpenAI عند إنشاء الصور.
## استكشاف الأخطاء
1. **تحقق من وصول API** - تأكد من أن مفتاح OpenAI API لديه وصول إلى DALL-E.
2. **توافق الإصدارات** - تأكد من استخدام أحدث إصدار من crewAI وcrewai-tools.
3. **تهيئة الأداة** - تحقق من إضافة أداة DALL-E بشكل صحيح لقائمة أدوات الـ Agent.

View File

@@ -0,0 +1,86 @@
---
title: نظرة عامة على خطافات التنفيذ
description: فهم واستخدام خطافات التنفيذ في CrewAI للتحكم الدقيق في عمليات الـ Agent
mode: "wide"
---
توفر خطافات التنفيذ تحكمًا دقيقًا في سلوك وقت تشغيل Agents CrewAI. على عكس خطافات الانطلاق التي تعمل قبل وبعد تنفيذ Crew، تعترض خطافات التنفيذ عمليات محددة أثناء تنفيذ الـ Agent، مما يتيح لك تعديل السلوك وتنفيذ فحوصات أمان وإضافة مراقبة شاملة.
## أنواع خطافات التنفيذ
### 1. [خطافات استدعاء LLM](/learn/llm-hooks)
التحكم ومراقبة تفاعلات نموذج اللغة:
- **قبل استدعاء LLM**: تعديل المطالبات، التحقق من المدخلات، بوابات الموافقة
- **بعد استدعاء LLM**: تحويل الاستجابات، تنقية المخرجات، تحديث سجل المحادثة
### 2. [خطافات استدعاء الأدوات](/learn/tool-hooks)
التحكم ومراقبة تنفيذ الأدوات:
- **قبل استدعاء الأداة**: تعديل المدخلات، التحقق من المعاملات، حظر العمليات الخطرة
- **بعد استدعاء الأداة**: تحويل النتائج، تنقية المخرجات، تسجيل تفاصيل التنفيذ
## طرق تسجيل الخطافات
### 1. خطافات بالمزخرفات (مُوصى بها)
```python
from crewai.hooks import before_llm_call, after_llm_call, before_tool_call, after_tool_call
@before_llm_call
def limit_iterations(context):
if context.iterations > 10:
return False
return None
@after_llm_call
def sanitize_response(context):
if "API_KEY" in context.response:
return context.response.replace("API_KEY", "[REDACTED]")
return None
@before_tool_call
def block_dangerous_tools(context):
if context.tool_name == "delete_database":
return False
return None
```
### 2. خطافات نطاق Crew
```python
from crewai import CrewBase
from crewai.project import crew
from crewai.hooks import before_llm_call_crew, after_tool_call_crew
@CrewBase
class MyProjCrew:
@before_llm_call_crew
def validate_inputs(self, context):
print(f"LLM call in {self.__class__.__name__}")
return None
@after_tool_call_crew
def log_results(self, context):
print(f"Tool result: {context.tool_result[:50]}...")
return None
```
## أفضل الممارسات
1. **اجعل الخطافات مركّزة** - كل خطاف يجب أن يكون له مسؤولية واحدة واضحة
2. **عالج الأخطاء بلطف**
3. **عدّل السياق في مكانه**
4. **استخدم تلميحات الأنواع**
5. **نظّف في الاختبارات**
## التوثيق ذو الصلة
- [خطافات استدعاء LLM](/learn/llm-hooks)
- [خطافات استدعاء الأدوات](/learn/tool-hooks)
- [خطافات قبل وبعد الانطلاق](/learn/before-and-after-kickoff-hooks)
- [التدخل البشري](/learn/human-in-the-loop)
## الخلاصة
توفر خطافات التنفيذ تحكمًا قويًا في سلوك وقت تشغيل الـ Agent. استخدمها لتنفيذ حواجز أمان وسير عمل موافقة ومراقبة شاملة ومنطق أعمال مخصص.

View File

@@ -0,0 +1,45 @@
---
title: فرض مخرجات الأداة كنتيجة
description: تعلم كيفية فرض مخرجات الأداة كنتيجة لمهمة Agent في CrewAI.
icon: wrench-simple
mode: "wide"
---
## مقدمة
في CrewAI، يمكنك فرض مخرجات أداة كنتيجة لمهمة Agent. هذه الميزة مفيدة عندما تريد التأكد من التقاط مخرجات الأداة وإعادتها كنتيجة للمهمة، متجنبًا أي تعديل من قبل الـ Agent أثناء تنفيذ المهمة.
## فرض مخرجات الأداة كنتيجة
لفرض مخرجات الأداة كنتيجة لمهمة Agent، تحتاج لتعيين معامل `result_as_answer` إلى `True` عند إضافة أداة إلى الـ Agent.
```python Code
from crewai.agent import Agent
from my_tool import MyCustomTool
coding_agent = Agent(
role="Data Scientist",
goal="Produce amazing reports on AI",
backstory="You work with data and AI",
tools=[MyCustomTool(result_as_answer=True)],
)
task_result = coding_agent.execute_task(task)
```
## سير العمل أثناء التنفيذ
<Steps>
<Step title="تنفيذ المهمة">
ينفذ الـ Agent المهمة باستخدام الأداة المقدمة.
</Step>
<Step title="مخرجات الأداة">
تولّد الأداة المخرجات التي تُلتقط كنتيجة للمهمة.
</Step>
<Step title="تفاعل الـ Agent">
قد يتأمل الـ Agent ويستخلص دروسًا من الأداة لكن لا يعدّل المخرجات.
</Step>
<Step title="إعادة النتيجة">
تُعاد مخرجات الأداة كنتيجة للمهمة دون أي تعديلات.
</Step>
</Steps>

View File

@@ -0,0 +1,76 @@
---
title: العملية الهرمية
description: دليل شامل لفهم وتطبيق العملية الهرمية ضمن مشاريع CrewAI.
icon: sitemap
mode: "wide"
---
## مقدمة
تقدم العملية الهرمية في CrewAI نهجًا منظمًا لإدارة المهام، محاكاةً للتسلسلات الهرمية التنظيمية التقليدية للتفويض والتنفيذ الفعّال للمهام.
<Tip>
صُممت العملية الهرمية للاستفادة من نماذج متقدمة مثل GPT-4، مما يحسّن استخدام الرموز المميزة مع التعامل مع المهام المعقدة بكفاءة أكبر.
</Tip>
## نظرة عامة على العملية الهرمية
افتراضيًا، تُدار المهام في CrewAI من خلال عملية متسلسلة. لكن اعتماد نهج هرمي يتيح تسلسلاً واضحًا في إدارة المهام، حيث يقوم Agent 'مدير' بتنسيق سير العمل وتفويض المهام والتحقق من النتائج.
### الميزات الرئيسية
- **تفويض المهام**: Agent مدير يوزّع المهام بين أعضاء Crew بناءً على أدوارهم وقدراتهم.
- **التحقق من النتائج**: يقيّم المدير النتائج لضمان استيفائها للمعايير المطلوبة.
- **سير عمل فعّال**: يحاكي الهياكل المؤسسية مقدمًا نهجًا منظمًا لإدارة المهام.
## تنفيذ العملية الهرمية
```python Code
from crewai import Crew, Process, Agent
researcher = Agent(
role='Researcher',
goal='Conduct in-depth analysis',
backstory='Experienced data analyst with a knack for uncovering hidden trends.',
)
writer = Agent(
role='Writer',
goal='Create engaging content',
backstory='Creative writer passionate about storytelling in technical domains.',
)
project_crew = Crew(
tasks=[...],
agents=[researcher, writer],
manager_llm="gpt-4o",
process=Process.hierarchical,
planning=True,
)
```
### استخدام Agent مدير مخصص
```python
manager = Agent(
role="Project Manager",
goal="Efficiently manage the crew and ensure high-quality task completion",
backstory="You're an experienced project manager...",
allow_delegation=True,
)
project_crew = Crew(
tasks=[...],
agents=[researcher, writer],
manager_agent=manager,
process=Process.hierarchical,
planning=True,
)
```
<Tip>
لمزيد من التفاصيل حول إنشاء وتخصيص Agent مدير، اطلع على [توثيق Agent المدير المخصص](/ar/learn/custom-manager-agent).
</Tip>
## الخلاصة
اعتماد العملية الهرمية في CrewAI مع التهيئات الصحيحة وفهم قدرات النظام يسهّل نهجًا منظمًا وفعّالاً لإدارة المشاريع. استفد من الميزات المتقدمة والتخصيصات لتكييف سير العمل لاحتياجاتك المحددة.

View File

@@ -0,0 +1,98 @@
---
title: التغذية الراجعة البشرية في Flows
description: تعلم كيفية دمج التغذية الراجعة البشرية مباشرة في CrewAI Flows باستخدام مزخرف @human_feedback
icon: user-check
mode: "wide"
---
## نظرة عامة
<Note>
يتطلب مزخرف `@human_feedback` إصدار **CrewAI 1.8.0 أو أحدث**. تأكد من تحديث تثبيتك قبل استخدام هذه الميزة.
</Note>
يمكّن مزخرف `@human_feedback` سير العمل البشري في الحلقة (HITL) مباشرة ضمن CrewAI Flows. يتيح لك إيقاف تنفيذ Flow مؤقتًا وعرض المخرجات لإنسان للمراجعة وجمع تعليقاته واختياريًا التوجيه إلى مستمعين مختلفين بناءً على نتيجة التعليقات.
هذا مفيد بشكل خاص لـ:
- **ضمان الجودة**: مراجعة المحتوى المُنشأ بالذكاء الاصطناعي قبل استخدامه
- **بوابات القرار**: السماح للبشر باتخاذ قرارات حرجة في سير العمل الآلي
- **سير عمل الموافقة**: تنفيذ أنماط الموافقة/الرفض/المراجعة
- **التحسين التفاعلي**: جمع التعليقات لتحسين المخرجات تكراريًا
## بداية سريعة
```python Code
from crewai.flow.flow import Flow, start, listen
from crewai.flow.human_feedback import human_feedback
class SimpleReviewFlow(Flow):
@start()
@human_feedback(message="Please review this content:")
def generate_content(self):
return "This is AI-generated content that needs review."
@listen(generate_content)
def process_feedback(self, result):
print(f"Content: {result.output}")
print(f"Human said: {result.feedback}")
flow = SimpleReviewFlow()
flow.kickoff()
```
## التوجيه مع emit
عند تحديد `emit`، يصبح المزخرف موجّهًا. يُفسَّر التعليق البشري الحر بواسطة LLM ويُختزل إلى إحدى النتائج المحددة:
```python Code
from crewai.flow.flow import Flow, start, listen, or_
from crewai.flow.human_feedback import human_feedback
class ReviewFlow(Flow):
@start()
def generate_content(self):
return "Draft blog post content here..."
@human_feedback(
message="Do you approve this content for publication?",
emit=["approved", "rejected", "needs_revision"],
llm="gpt-4o-mini",
default_outcome="needs_revision",
)
@listen(or_("generate_content", "needs_revision"))
def review_content(self):
return "Draft blog post content here..."
@listen("approved")
def publish(self, result):
print(f"Publishing! User said: {result.feedback}")
@listen("rejected")
def discard(self, result):
print(f"Discarding. Reason: {result.feedback}")
```
## التعلم من التغذية الراجعة
معامل `learn=True` يمكّن حلقة تغذية راجعة بين المراجعين البشريين ونظام الذاكرة. عند تمكينه، يحسّن النظام مخرجاته تدريجيًا بالتعلم من التصحيحات البشرية السابقة.
## أفضل الممارسات
1. **اكتب رسائل طلب واضحة**
2. **اختر نتائج ذات معنى**
3. **وفّر دائمًا نتيجة افتراضية**
4. **استخدم سجل التعليقات لمسارات التدقيق**
## التغذية الراجعة البشرية غير المتزامنة (غير محجوبة)
استخدم معامل `provider` لتحديد استراتيجية جمع تعليقات مخصصة تتكامل مع أنظمة خارجية مثل Slack والبريد الإلكتروني وWebhooks وواجهات API.
## التوثيق ذو الصلة
- [نظرة عامة على Flows](/ar/concepts/flows)
- [إدارة حالة Flow](/ar/guides/flows/mastering-flow-state)
- [حفظ Flow](/ar/concepts/flows#persistence)
- [التوجيه مع @router](/ar/concepts/flows#router)
- [إدخال بشري عند التنفيذ](/ar/learn/human-input-on-execution)
- [الذاكرة](/ar/concepts/memory)

View File

@@ -0,0 +1,80 @@
---
title: "سير عمل التدخل البشري (HITL)"
description: "تعلم كيفية تنفيذ سير عمل التدخل البشري في CrewAI لتعزيز صنع القرار"
icon: "user-check"
mode: "wide"
---
التدخل البشري (HITL) هو نهج قوي يجمع بين الذكاء الاصطناعي والخبرة البشرية لتعزيز صنع القرار وتحسين نتائج المهام. يوفر CrewAI طرقًا متعددة لتنفيذ HITL حسب احتياجاتك.
## اختيار نهج HITL
يوفر CrewAI نهجين رئيسيين لتنفيذ سير عمل التدخل البشري:
| النهج | الأنسب لـ | التكامل | الإصدار |
|----------|----------|-------------|---------|
| **قائم على Flow** (مزخرف `@human_feedback`) | التطوير المحلي، المراجعة عبر وحدة التحكم، سير العمل المتزامن | [التغذية الراجعة البشرية في Flows](/ar/learn/human-feedback-in-flows) | **1.8.0+** |
| **قائم على Webhook** (المؤسسات) | نشر الإنتاج، سير العمل غير المتزامن، التكاملات الخارجية (Slack، Teams، إلخ) | هذا الدليل | - |
<Tip>
إذا كنت تبني Flows وتريد إضافة خطوات مراجعة بشرية مع توجيه بناءً على التعليقات، اطلع على دليل [التغذية الراجعة البشرية في Flows](/ar/learn/human-feedback-in-flows) لمزخرف `@human_feedback`.
</Tip>
## إعداد سير عمل HITL القائم على Webhook
<Steps>
<Step title="تهيئة المهمة">
أعدّ مهمتك مع تمكين إدخال بشري.
</Step>
<Step title="توفير عنوان Webhook URL">
عند تشغيل Crew، أدرج عنوان Webhook URL لإدخال بشري.
</Step>
<Step title="تلقي إشعار Webhook">
بمجرد إتمام Crew المهمة التي تتطلب إدخالاً بشريًا، ستتلقى إشعار Webhook.
</Step>
<Step title="مراجعة مخرجات المهمة">
سيتوقف النظام في حالة `Pending Human Input`. راجع مخرجات المهمة بعناية.
</Step>
<Step title="إرسال التغذية الراجعة البشرية">
استدعِ نقطة نهاية الاستئناف لـ Crew.
<Warning>
**مهم: يجب توفير عناوين Webhook URL مرة أخرى**:
يجب توفير نفس عناوين Webhook URL في استدعاء الاستئناف التي استخدمتها في استدعاء الانطلاق.
</Warning>
</Step>
<Step title="معالجة التعليقات السلبية">
إذا قدمت تعليقات سلبية، سيعيد Crew محاولة المهمة مع سياق إضافي من تعليقاتك.
</Step>
<Step title="استمرار التنفيذ">
عند إرسال تعليقات إيجابية، سيستمر التنفيذ إلى الخطوات التالية.
</Step>
</Steps>
## أفضل الممارسات
- **كن محددًا**: قدم تعليقات واضحة وقابلة للتنفيذ
- **ابقَ ذا صلة**: أدرج فقط معلومات تساعد في تحسين تنفيذ المهمة
- **كن في الوقت المناسب**: استجب لمطالبات HITL بسرعة لتجنب تأخير سير العمل
- **راجع بعناية**: تحقق من تعليقاتك قبل الإرسال لضمان الدقة
## حالات الاستخدام الشائعة
سير عمل HITL مفيدة بشكل خاص لـ:
- ضمان الجودة والتحقق
- سيناريوهات صنع القرار المعقدة
- العمليات الحساسة أو عالية المخاطر
- المهام الإبداعية التي تتطلب حكمًا بشريًا
- مراجعات الامتثال والتنظيم
## ميزات المؤسسات
<Card title="منصة إدارة HITL للـ Flow" icon="users-gear" href="https://docs-platform.crewai.com/platform/ar/features/flow-hitl-management">
يوفر CrewAI Enterprise نظام إدارة HITL شامل لـ Flows مع مراجعة داخل المنصة وتعيين المستجيبين والأذونات وسياسات التصعيد وإدارة SLA والتوجيه الديناميكي والتحليلات الكاملة. [تعلم المزيد](https://docs-platform.crewai.com/platform/ar/features/flow-hitl-management)
</Card>

View File

@@ -0,0 +1,99 @@
---
title: الإدخال البشري أثناء التنفيذ
description: دمج CrewAI مع الإدخال البشري أثناء التنفيذ في عمليات اتخاذ القرارات المعقدة والاستفادة الكاملة من إمكانيات خصائص وأدوات الوكيل.
icon: user-plus
mode: "wide"
---
## الإدخال البشري في تنفيذ الوكيل
يُعد الإدخال البشري أمراً بالغ الأهمية في العديد من سيناريوهات تنفيذ الوكلاء، حيث يسمح للوكلاء بطلب معلومات إضافية أو توضيحات عند الضرورة.
هذه الميزة مفيدة بشكل خاص في عمليات اتخاذ القرارات المعقدة أو عندما يحتاج الوكلاء إلى مزيد من التفاصيل لإكمال مهمة بفعالية.
## استخدام الإدخال البشري مع CrewAI
لدمج الإدخال البشري في تنفيذ الوكيل، قم بتعيين علامة `human_input` في تعريف المهمة. عند تفعيلها، يطلب الوكيل من المستخدم إدخالاً قبل تقديم إجابته النهائية.
يمكن أن يوفر هذا الإدخال سياقاً إضافياً، أو يوضح الغموض، أو يتحقق من مخرجات الوكيل.
### مثال:
```shell
pip install crewai
```
```python Code
import os
from crewai import Agent, Task, Crew
from crewai_tools import SerperDevTool
os.environ["SERPER_API_KEY"] = "Your Key" # serper.dev API key
os.environ["OPENAI_API_KEY"] = "Your Key"
# Loading Tools
search_tool = SerperDevTool()
# Define your agents with roles, goals, tools, and additional attributes
researcher = Agent(
role='Senior Research Analyst',
goal='Uncover cutting-edge developments in AI and data science',
backstory=(
"You are a Senior Research Analyst at a leading tech think tank. "
"Your expertise lies in identifying emerging trends and technologies in AI and data science. "
"You have a knack for dissecting complex data and presenting actionable insights."
),
verbose=True,
allow_delegation=False,
tools=[search_tool]
)
writer = Agent(
role='Tech Content Strategist',
goal='Craft compelling content on tech advancements',
backstory=(
"You are a renowned Tech Content Strategist, known for your insightful and engaging articles on technology and innovation. "
"With a deep understanding of the tech industry, you transform complex concepts into compelling narratives."
),
verbose=True,
allow_delegation=True,
tools=[search_tool],
cache=False, # Disable cache for this agent
)
# Create tasks for your agents
task1 = Task(
description=(
"Conduct a comprehensive analysis of the latest advancements in AI in 2025. "
"Identify key trends, breakthrough technologies, and potential industry impacts. "
"Compile your findings in a detailed report. "
"Make sure to check with a human if the draft is good before finalizing your answer."
),
expected_output='A comprehensive full report on the latest AI advancements in 2025, leave nothing out',
agent=researcher,
human_input=True
)
task2 = Task(
description=(
"Using the insights from the researcher\'s report, develop an engaging blog post that highlights the most significant AI advancements. "
"Your post should be informative yet accessible, catering to a tech-savvy audience. "
"Aim for a narrative that captures the essence of these breakthroughs and their implications for the future."
),
expected_output='A compelling 3 paragraphs blog post formatted as markdown about the latest AI advancements in 2025',
agent=writer,
human_input=True
)
# Instantiate your crew with a sequential process
crew = Crew(
agents=[researcher, writer],
tasks=[task1, task2],
verbose=True,
memory=True,
planning=True # Enable planning feature for the crew
)
# Get your crew to work!
result = crew.kickoff()
print("######################")
print(result)
```

View File

@@ -0,0 +1,306 @@
---
title: تشغيل الطاقم بشكل غير متزامن
description: تشغيل الطاقم بشكل غير متزامن
icon: rocket-launch
mode: "wide"
---
## مقدمة
يوفر CrewAI القدرة على تشغيل طاقم بشكل غير متزامن، مما يتيح لك بدء تنفيذ الطاقم بطريقة غير حاجبة.
هذه الميزة مفيدة بشكل خاص عندما تريد تشغيل عدة أطقم بشكل متزامن أو عندما تحتاج إلى أداء مهام أخرى أثناء تنفيذ الطاقم.
يقدم CrewAI نهجين للتنفيذ غير المتزامن:
| الطريقة | النوع | الوصف |
|--------|------|-------------|
| `akickoff()` | غير متزامن أصلي | async/await أصلي عبر سلسلة التنفيذ بالكامل |
| `kickoff_async()` | قائم على الخيوط | يغلف التنفيذ المتزامن في `asyncio.to_thread` |
<Note>
لأحمال العمل عالية التزامن، يُوصى باستخدام `akickoff()` لأنه يستخدم async أصلي لتنفيذ المهام وعمليات الذاكرة واسترجاع المعرفة.
</Note>
## التنفيذ غير المتزامن الأصلي مع `akickoff()`
توفر طريقة `akickoff()` تنفيذاً غير متزامن أصلياً حقيقياً، باستخدام async/await عبر سلسلة التنفيذ بالكامل بما في ذلك تنفيذ المهام وعمليات الذاكرة واستعلامات المعرفة.
### توقيع الطريقة
```python Code
async def akickoff(self, inputs: dict) -> CrewOutput:
```
### المعاملات
- `inputs` (dict): قاموس يحتوي على بيانات الإدخال المطلوبة للمهام.
### القيمة المُرجعة
- `CrewOutput`: كائن يمثل نتيجة تنفيذ الطاقم.
### مثال: تنفيذ طاقم غير متزامن أصلي
```python Code
import asyncio
from crewai import Crew, Agent, Task
# Create an agent
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
# Create a task
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
# Create a crew
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
# Native async execution
async def main():
result = await analysis_crew.akickoff(inputs={"ages": [25, 30, 35, 40, 45]})
print("Crew Result:", result)
asyncio.run(main())
```
### مثال: عدة أطقم غير متزامنة أصلية
تشغيل عدة أطقم بشكل متزامن باستخدام `asyncio.gather()` مع async أصلي:
```python Code
import asyncio
from crewai import Crew, Agent, Task
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
task_1 = Task(
description="Analyze the first dataset and calculate the average age. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
task_2 = Task(
description="Analyze the second dataset and calculate the average age. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
crew_1 = Crew(agents=[coding_agent], tasks=[task_1])
crew_2 = Crew(agents=[coding_agent], tasks=[task_2])
async def main():
results = await asyncio.gather(
crew_1.akickoff(inputs={"ages": [25, 30, 35, 40, 45]}),
crew_2.akickoff(inputs={"ages": [20, 22, 24, 28, 30]})
)
for i, result in enumerate(results, 1):
print(f"Crew {i} Result:", result)
asyncio.run(main())
```
### مثال: async أصلي لمدخلات متعددة
استخدم `akickoff_for_each()` لتنفيذ طاقمك على مدخلات متعددة بشكل متزامن مع async أصلي:
```python Code
import asyncio
from crewai import Crew, Agent, Task
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
data_analysis_task = Task(
description="Analyze the dataset and calculate the average age. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
async def main():
datasets = [
{"ages": [25, 30, 35, 40, 45]},
{"ages": [20, 22, 24, 28, 30]},
{"ages": [30, 35, 40, 45, 50]}
]
results = await analysis_crew.akickoff_for_each(datasets)
for i, result in enumerate(results, 1):
print(f"Dataset {i} Result:", result)
asyncio.run(main())
```
## التنفيذ غير المتزامن القائم على الخيوط مع `kickoff_async()`
توفر طريقة `kickoff_async()` تنفيذاً غير متزامن عن طريق تغليف `kickoff()` المتزامن في خيط. هذا مفيد للتكامل البسيط مع async أو للتوافق مع الإصدارات السابقة.
### توقيع الطريقة
```python Code
async def kickoff_async(self, inputs: dict) -> CrewOutput:
```
### المعاملات
- `inputs` (dict): قاموس يحتوي على بيانات الإدخال المطلوبة للمهام.
### القيمة المُرجعة
- `CrewOutput`: كائن يمثل نتيجة تنفيذ الطاقم.
### مثال: تنفيذ غير متزامن قائم على الخيوط
```python Code
import asyncio
from crewai import Crew, Agent, Task
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
async def async_crew_execution():
result = await analysis_crew.kickoff_async(inputs={"ages": [25, 30, 35, 40, 45]})
print("Crew Result:", result)
asyncio.run(async_crew_execution())
```
### مثال: عدة أطقم غير متزامنة قائمة على الخيوط
```python Code
import asyncio
from crewai import Crew, Agent, Task
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
task_1 = Task(
description="Analyze the first dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
task_2 = Task(
description="Analyze the second dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
crew_1 = Crew(agents=[coding_agent], tasks=[task_1])
crew_2 = Crew(agents=[coding_agent], tasks=[task_2])
async def async_multiple_crews():
result_1 = crew_1.kickoff_async(inputs={"ages": [25, 30, 35, 40, 45]})
result_2 = crew_2.kickoff_async(inputs={"ages": [20, 22, 24, 28, 30]})
results = await asyncio.gather(result_1, result_2)
for i, result in enumerate(results, 1):
print(f"Crew {i} Result:", result)
asyncio.run(async_multiple_crews())
```
## البث غير المتزامن
تدعم كلتا الطريقتين غير المتزامنتين البث عند تعيين `stream=True` على الطاقم:
```python Code
import asyncio
from crewai import Crew, Agent, Task
agent = Agent(
role="Researcher",
goal="Research and summarize topics",
backstory="You are an expert researcher."
)
task = Task(
description="Research the topic: {topic}",
agent=agent,
expected_output="A comprehensive summary of the topic."
)
crew = Crew(
agents=[agent],
tasks=[task],
stream=True # Enable streaming
)
async def main():
streaming_output = await crew.akickoff(inputs={"topic": "AI trends in 2024"})
# Async iteration over streaming chunks
async for chunk in streaming_output:
print(f"Chunk: {chunk.content}")
# Access final result after streaming completes
result = streaming_output.result
print(f"Final result: {result.raw}")
asyncio.run(main())
```
## حالات الاستخدام المحتملة
- **توليد المحتوى بالتوازي**: تشغيل عدة أطقم مستقلة بشكل غير متزامن، كل منها مسؤول عن توليد محتوى حول مواضيع مختلفة. على سبيل المثال، قد يبحث طاقم ويصوغ مقالاً عن اتجاهات الذكاء الاصطناعي، بينما يولد طاقم آخر منشورات وسائل التواصل الاجتماعي حول إطلاق منتج جديد.
- **مهام أبحاث السوق المتزامنة**: إطلاق عدة أطقم بشكل غير متزامن لإجراء أبحاث السوق بالتوازي. قد يحلل طاقم اتجاهات الصناعة، بينما يفحص آخر استراتيجيات المنافسين، ويقيّم ثالث مشاعر المستهلكين.
- **وحدات تخطيط السفر المستقلة**: تنفيذ أطقم منفصلة للتخطيط المستقل لجوانب مختلفة من رحلة. قد يتعامل طاقم مع خيارات الرحلات الجوية، وآخر مع الإقامة، وثالث يخطط للأنشطة.
## الاختيار بين `akickoff()` و `kickoff_async()`
| الميزة | `akickoff()` | `kickoff_async()` |
|---------|--------------|-------------------|
| نموذج التنفيذ | async/await أصلي | غلاف قائم على الخيوط |
| تنفيذ المهام | غير متزامن مع `aexecute_sync()` | متزامن في مجمع الخيوط |
| عمليات الذاكرة | غير متزامنة | متزامنة في مجمع الخيوط |
| استرجاع المعرفة | غير متزامن | متزامن في مجمع الخيوط |
| الأفضل لـ | أحمال العمل عالية التزامن والمرتبطة بالإدخال/الإخراج | التكامل البسيط مع async |
| دعم البث | نعم | نعم |

View File

@@ -0,0 +1,54 @@
---
title: تشغيل الطاقم لكل عنصر
description: تشغيل الطاقم لكل عنصر في قائمة
icon: at
mode: "wide"
---
## مقدمة
يوفر CrewAI القدرة على تشغيل طاقم لكل عنصر في قائمة، مما يتيح لك تنفيذ الطاقم لكل عنصر في القائمة.
هذه الميزة مفيدة بشكل خاص عندما تحتاج إلى تنفيذ نفس مجموعة المهام لعناصر متعددة.
## تشغيل طاقم لكل عنصر
لتشغيل طاقم لكل عنصر في قائمة، استخدم طريقة `kickoff_for_each()`.
تنفذ هذه الطريقة الطاقم لكل عنصر في القائمة، مما يتيح لك معالجة عناصر متعددة بكفاءة.
إليك مثالاً على كيفية تشغيل طاقم لكل عنصر في قائمة:
```python Code
from crewai import Crew, Agent, Task
# Create an agent with code execution enabled
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
# Create a task that requires code execution
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age calculated from the dataset"
)
# Create a crew and add the task
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task],
verbose=True,
memory=False
)
datasets = [
{ "ages": [25, 30, 35, 40, 45] },
{ "ages": [20, 25, 30, 35, 40] },
{ "ages": [30, 35, 40, 45, 50] }
]
# Execute the crew
result = analysis_crew.kickoff_for_each(inputs=datasets)
```

View File

@@ -0,0 +1,358 @@
---
title: استخدام CrewAI بدون LiteLLM
description: كيفية استخدام CrewAI مع التكاملات الأصلية للمزودين وإزالة اعتمادية LiteLLM من مشروعك.
icon: shield-check
mode: "wide"
---
## نظرة عامة
يدعم CrewAI مسارين للاتصال بمزودي LLM:
1. **التكاملات الأصلية** — اتصالات SDK مباشرة مع OpenAI وAnthropic وGoogle Gemini وAzure OpenAI وAWS Bedrock
2. **LiteLLM كاحتياط** — طبقة ترجمة تدعم أكثر من 100 مزود إضافي
يشرح هذا الدليل كيفية استخدام CrewAI حصرياً مع التكاملات الأصلية للمزودين، مع إزالة أي اعتمادية على LiteLLM.
<Warning>
تم عزل حزمة `litellm` على PyPI بسبب حادث أمني/موثوقية. إذا كنت تعتمد على مزودين يحتاجون LiteLLM، يجب عليك الانتقال إلى التكاملات الأصلية. توفر لك تكاملات CrewAI الأصلية الوظائف الكاملة بدون LiteLLM.
</Warning>
## لماذا إزالة LiteLLM؟
- **تقليل سطح الاعتماديات** — حزم أقل تعني مخاطر أقل محتملة في سلسلة التوريد
- **أداء أفضل** — تتواصل حزم SDK الأصلية مباشرة مع واجهات برمجة تطبيقات المزودين، مما يلغي طبقة الترجمة
- **تصحيح أخطاء أبسط** — طبقة تجريد واحدة أقل بين كودك والمزود
- **حجم تثبيت أصغر** — يجلب LiteLLM العديد من الاعتماديات العابرة
## المزودون الأصليون (لا يحتاجون LiteLLM)
هؤلاء المزودون يستخدمون حزم SDK الخاصة بهم ويعملون بدون تثبيت LiteLLM:
<CardGroup cols={2}>
<Card title="OpenAI" icon="bolt">
GPT-4o، GPT-4o-mini، o1، o3-mini، والمزيد.
```bash
uv add "crewai[openai]"
```
</Card>
<Card title="Anthropic" icon="a">
Claude Sonnet، Claude Haiku، والمزيد.
```bash
uv add "crewai[anthropic]"
```
</Card>
<Card title="Google Gemini" icon="google">
Gemini 2.0 Flash، Gemini 2.0 Pro، والمزيد.
```bash
uv add "crewai[gemini]"
```
</Card>
<Card title="Azure OpenAI" icon="microsoft">
نماذج OpenAI المستضافة على Azure.
```bash
uv add "crewai[azure]"
```
</Card>
<Card title="AWS Bedrock" icon="aws">
Claude، Llama، Titan، والمزيد عبر AWS.
```bash
uv add "crewai[bedrock]"
```
</Card>
</CardGroup>
<Info>
إذا كنت تستخدم المزودين الأصليين فقط، فلن تحتاج **أبداً** لتثبيت `crewai[litellm]`. حزمة `crewai` الأساسية بالإضافة إلى الإضافة الخاصة بالمزود الذي اخترته هي كل ما تحتاجه.
</Info>
## كيفية التحقق مما إذا كنت تستخدم LiteLLM
### تحقق من سلاسل النماذج الخاصة بك
إذا كان كودك يستخدم بادئات النماذج هذه، فأنت تمرر عبر LiteLLM:
| البادئة | المزود | يستخدم LiteLLM؟ |
|--------|----------|---------------|
| `ollama/` | Ollama | ✅ نعم |
| `groq/` | Groq | ✅ نعم |
| `together_ai/` | Together AI | ✅ نعم |
| `mistral/` | Mistral | ✅ نعم |
| `cohere/` | Cohere | ✅ نعم |
| `huggingface/` | Hugging Face | ✅ نعم |
| `openai/` | OpenAI | ❌ أصلي |
| `anthropic/` | Anthropic | ❌ أصلي |
| `gemini/` | Google Gemini | ❌ أصلي |
| `azure/` | Azure OpenAI | ❌ أصلي |
| `bedrock/` | AWS Bedrock | ❌ أصلي |
### تحقق مما إذا كان LiteLLM مثبتاً
```bash
# Using pip
pip show litellm
# Using uv
uv pip show litellm
```
إذا أرجع الأمر معلومات الحزمة، فإن LiteLLM مثبت في بيئتك.
### تحقق من اعتمادياتك
انظر إلى ملف `pyproject.toml` الخاص بك بحثاً عن `crewai[litellm]`:
```toml
# If you see this, you have LiteLLM as a dependency
dependencies = [
"crewai[litellm]>=0.100.0", # ← Uses LiteLLM
]
# Change to a native provider extra instead
dependencies = [
"crewai[openai]>=0.100.0", # ← Native, no LiteLLM
]
```
## دليل الانتقال
### الخطوة 1: حدد مزودك الحالي
ابحث عن جميع استدعاءات `LLM()` وسلاسل النماذج في كودك:
```bash
# Search your codebase for LLM model strings
grep -r "LLM(" --include="*.py" .
grep -r "llm=" --include="*.yaml" .
grep -r "llm:" --include="*.yaml" .
```
### الخطوة 2: انتقل إلى مزود أصلي
<Tabs>
<Tab title="الانتقال إلى OpenAI">
```python
from crewai import LLM
# Before (LiteLLM):
# llm = LLM(model="groq/llama-3.1-70b")
# After (Native):
llm = LLM(model="openai/gpt-4o")
```
```bash
# Install
uv add "crewai[openai]"
# Set your API key
export OPENAI_API_KEY="sk-..."
```
</Tab>
<Tab title="الانتقال إلى Anthropic">
```python
from crewai import LLM
# Before (LiteLLM):
# llm = LLM(model="together_ai/meta-llama/Meta-Llama-3.1-70B")
# After (Native):
llm = LLM(model="anthropic/claude-sonnet-4-20250514")
```
```bash
# Install
uv add "crewai[anthropic]"
# Set your API key
export ANTHROPIC_API_KEY="sk-ant-..."
```
</Tab>
<Tab title="الانتقال إلى Gemini">
```python
from crewai import LLM
# Before (LiteLLM):
# llm = LLM(model="mistral/mistral-large-latest")
# After (Native):
llm = LLM(model="gemini/gemini-2.0-flash")
```
```bash
# Install
uv add "crewai[gemini]"
# Set your API key
export GEMINI_API_KEY="..."
```
</Tab>
<Tab title="الانتقال إلى Azure OpenAI">
```python
from crewai import LLM
# After (Native):
llm = LLM(
model="azure/your-deployment-name",
api_key="your-azure-api-key",
base_url="https://your-resource.openai.azure.com",
api_version="2024-06-01"
)
```
```bash
# Install
uv add "crewai[azure]"
```
</Tab>
<Tab title="الانتقال إلى AWS Bedrock">
```python
from crewai import LLM
# After (Native):
llm = LLM(
model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0",
aws_region_name="us-east-1"
)
```
```bash
# Install
uv add "crewai[bedrock]"
# Configure AWS credentials
export AWS_ACCESS_KEY_ID="..."
export AWS_SECRET_ACCESS_KEY="..."
export AWS_DEFAULT_REGION="us-east-1"
```
</Tab>
</Tabs>
### الخطوة 3: الاحتفاظ بـ Ollama بدون LiteLLM
إذا كنت تستخدم Ollama وتريد الاستمرار في استخدامه، يمكنك الاتصال عبر واجهة برمجة تطبيقات Ollama المتوافقة مع OpenAI:
```python
from crewai import LLM
# Before (LiteLLM):
# llm = LLM(model="ollama/llama3")
# After (OpenAI-compatible mode, no LiteLLM needed):
llm = LLM(
model="openai/llama3",
base_url="http://localhost:11434/v1",
api_key="ollama" # Ollama doesn't require a real API key
)
```
<Tip>
العديد من خوادم الاستدلال المحلية (Ollama، vLLM، LM Studio، llama.cpp) توفر واجهة برمجة تطبيقات متوافقة مع OpenAI. يمكنك استخدام بادئة `openai/` مع `base_url` مخصص للاتصال بأي منها بشكل أصلي.
</Tip>
### الخطوة 4: تحديث إعدادات YAML
```yaml
# Before (LiteLLM providers):
researcher:
role: Research Specialist
goal: Conduct research
backstory: A dedicated researcher
llm: groq/llama-3.1-70b # ← LiteLLM
# After (Native provider):
researcher:
role: Research Specialist
goal: Conduct research
backstory: A dedicated researcher
llm: openai/gpt-4o # ← Native
```
### الخطوة 5: إزالة LiteLLM
بمجرد انتقال جميع مراجع النماذج الخاصة بك:
```bash
# Remove litellm from your project
uv remove litellm
# Or if using pip
pip uninstall litellm
# Update your pyproject.toml: change crewai[litellm] to your provider extra
# e.g., crewai[openai], crewai[anthropic], crewai[gemini]
```
### الخطوة 6: التحقق
شغّل مشروعك وتأكد من أن كل شيء يعمل:
```bash
# Run your crew
crewai run
# Or run your tests
uv run pytest
```
## مرجع سريع: خريطة سلاسل النماذج
فيما يلي مسارات الانتقال الشائعة من المزودين المعتمدين على LiteLLM إلى المزودين الأصليين:
```python
from crewai import LLM
# ─── LiteLLM providers → Native alternatives ────────────────────
# Groq → OpenAI or Anthropic
# llm = LLM(model="groq/llama-3.1-70b")
llm = LLM(model="openai/gpt-4o-mini") # Fast & affordable
llm = LLM(model="anthropic/claude-haiku-3-5") # Fast & affordable
# Together AI → OpenAI or Gemini
# llm = LLM(model="together_ai/meta-llama/Meta-Llama-3.1-70B")
llm = LLM(model="openai/gpt-4o") # High quality
llm = LLM(model="gemini/gemini-2.0-flash") # Fast & capable
# Mistral → Anthropic or OpenAI
# llm = LLM(model="mistral/mistral-large-latest")
llm = LLM(model="anthropic/claude-sonnet-4-20250514") # High quality
# Ollama → OpenAI-compatible (keep using local models)
# llm = LLM(model="ollama/llama3")
llm = LLM(
model="openai/llama3",
base_url="http://localhost:11434/v1",
api_key="ollama"
)
```
## الأسئلة الشائعة
<AccordionGroup>
<Accordion title="هل أفقد أي وظائف بإزالة LiteLLM؟">
لا، إذا كنت تستخدم أحد المزودين الخمسة المدعومين أصلياً (OpenAI، Anthropic، Gemini، Azure، Bedrock). تدعم هذه التكاملات الأصلية جميع ميزات CrewAI بما في ذلك البث واستدعاء الأدوات والمخرجات المنظمة والمزيد. ستفقد فقط الوصول إلى المزودين المتاحين حصرياً عبر LiteLLM (مثل Groq وTogether AI وMistral كمزودين من الدرجة الأولى).
</Accordion>
<Accordion title="هل يمكنني استخدام عدة مزودين أصليين في نفس الوقت؟">
نعم. ثبّت إضافات متعددة واستخدم مزودين مختلفين لوكلاء مختلفين:
```bash
uv add "crewai[openai,anthropic,gemini]"
```
```python
researcher = Agent(llm="openai/gpt-4o", ...)
writer = Agent(llm="anthropic/claude-sonnet-4-20250514", ...)
```
</Accordion>
<Accordion title="هل LiteLLM آمن للاستخدام الآن؟">
بغض النظر عن حالة العزل، فإن تقليل سطح اعتمادياتك يُعد ممارسة أمنية جيدة. إذا كنت تحتاج فقط مزودين يدعمهم CrewAI أصلياً، فلا يوجد سبب لإبقاء LiteLLM مثبتاً.
</Accordion>
<Accordion title="ماذا عن متغيرات البيئة مثل OPENAI_API_KEY؟">
يستخدم المزودون الأصليون نفس متغيرات البيئة التي اعتدت عليها. لا حاجة لتغييرات على `OPENAI_API_KEY` أو `ANTHROPIC_API_KEY` أو `GEMINI_API_KEY` وغيرها.
</Accordion>
</AccordionGroup>
## موارد ذات صلة
- [اتصالات LLM](/ar/learn/llm-connections) — الدليل الكامل لربط CrewAI مع أي LLM
- [مفاهيم LLM](/ar/concepts/llms) — فهم نماذج اللغة الكبيرة في CrewAI
- [دليل اختيار LLM](/ar/learn/llm-selection-guide) — اختيار النموذج المناسب لحالة استخدامك

View File

@@ -0,0 +1,214 @@
---
title: الاتصال بأي LLM
description: دليل شامل لدمج CrewAI مع نماذج اللغة الكبيرة المختلفة (LLMs) باستخدام LiteLLM، بما في ذلك المزودون المدعومون وخيارات الإعداد.
icon: brain-circuit
mode: "wide"
---
## ربط CrewAI بنماذج اللغة الكبيرة
يتصل CrewAI بنماذج اللغة الكبيرة من خلال تكاملات SDK الأصلية لأكثر المزودين شيوعاً (OpenAI وAnthropic وGoogle Gemini وAzure وAWS Bedrock)، ويستخدم LiteLLM كاحتياط مرن لجميع المزودين الآخرين.
<Note>
افتراضياً، يستخدم CrewAI نموذج `gpt-4o-mini`. يتم تحديد ذلك بواسطة متغير البيئة `OPENAI_MODEL_NAME`، الذي يكون قيمته الافتراضية "gpt-4o-mini" إذا لم يتم تعيينه.
يمكنك بسهولة إعداد وكلائك لاستخدام نموذج أو مزود مختلف كما هو موضح في هذا الدليل.
</Note>
## المزودون المدعومون
يدعم LiteLLM مجموعة واسعة من المزودين، بما في ذلك على سبيل المثال لا الحصر:
- OpenAI
- Anthropic
- Google (Vertex AI, Gemini)
- Azure OpenAI
- AWS (Bedrock, SageMaker)
- Cohere
- VoyageAI
- Hugging Face
- Ollama
- Mistral AI
- Replicate
- Together AI
- AI21
- Cloudflare Workers AI
- DeepInfra
- Groq
- SambaNova
- Nebius AI Studio
- [NVIDIA NIMs](https://docs.api.nvidia.com/nim/reference/models-1)
- والمزيد!
للحصول على قائمة كاملة ومحدثة بالمزودين المدعومين، يرجى الرجوع إلى [وثائق مزودي LiteLLM](https://docs.litellm.ai/docs/providers).
<Info>
لاستخدام أي مزود غير مغطى بتكامل أصلي، أضف LiteLLM كاعتمادية لمشروعك:
```bash
uv add 'crewai[litellm]'
```
يستخدم المزودون الأصليون (OpenAI، Anthropic، Google Gemini، Azure، AWS Bedrock) إضافات SDK الخاصة بهم — راجع [أمثلة إعداد المزودين](/ar/concepts/llms#provider-configuration-examples).
</Info>
## تغيير نموذج اللغة الكبير
لاستخدام LLM مختلف مع وكلاء CrewAI، لديك عدة خيارات:
<Tabs>
<Tab title="باستخدام معرف نصي">
مرر اسم النموذج كسلسلة نصية عند تهيئة الوكيل:
<CodeGroup>
```python Code
from crewai import Agent
# Using OpenAI's GPT-4
openai_agent = Agent(
role='OpenAI Expert',
goal='Provide insights using GPT-4',
backstory="An AI assistant powered by OpenAI's latest model.",
llm='gpt-4'
)
# Using Anthropic's Claude
claude_agent = Agent(
role='Anthropic Expert',
goal='Analyze data using Claude',
backstory="An AI assistant leveraging Anthropic's language model.",
llm='claude-2'
)
```
</CodeGroup>
</Tab>
<Tab title="باستخدام فئة LLM">
لمزيد من الإعداد التفصيلي، استخدم فئة LLM:
<CodeGroup>
```python Code
from crewai import Agent, LLM
llm = LLM(
model="gpt-4",
temperature=0.7,
base_url="https://api.openai.com/v1",
api_key="your-api-key-here"
)
agent = Agent(
role='Customized LLM Expert',
goal='Provide tailored responses',
backstory="An AI assistant with custom LLM settings.",
llm=llm
)
```
</CodeGroup>
</Tab>
</Tabs>
## خيارات الإعداد
عند إعداد LLM لوكيلك، يمكنك الوصول إلى مجموعة واسعة من المعاملات:
| المعامل | النوع | الوصف |
|:----------|:-----:|:-------------|
| **model** | `str` | اسم النموذج المراد استخدامه (مثل "gpt-4"، "claude-2") |
| **temperature** | `float` | يتحكم في العشوائية في المخرجات (0.0 إلى 1.0) |
| **max_tokens** | `int` | الحد الأقصى لعدد الرموز المولدة |
| **top_p** | `float` | يتحكم في تنوع المخرجات (0.0 إلى 1.0) |
| **frequency_penalty** | `float` | يعاقب الرموز الجديدة بناءً على تكرارها في النص حتى الآن |
| **presence_penalty** | `float` | يعاقب الرموز الجديدة بناءً على وجودها في النص حتى الآن |
| **stop** | `str`, `List[str]` | تسلسل(ات) لإيقاف التوليد |
| **base_url** | `str` | عنوان URL الأساسي لنقطة نهاية API |
| **api_key** | `str` | مفتاح API الخاص بك للمصادقة |
للحصول على قائمة كاملة بالمعاملات وأوصافها، راجع وثائق فئة LLM.
## الاتصال بنماذج LLM المتوافقة مع OpenAI
يمكنك الاتصال بنماذج LLM المتوافقة مع OpenAI باستخدام متغيرات البيئة أو عن طريق تعيين خصائص محددة في فئة LLM:
<Tabs>
<Tab title="باستخدام متغيرات البيئة">
<CodeGroup>
```python Generic
import os
os.environ["OPENAI_API_KEY"] = "your-api-key"
os.environ["OPENAI_API_BASE"] = "https://api.your-provider.com/v1"
os.environ["OPENAI_MODEL_NAME"] = "your-model-name"
```
```python Google
import os
# Example using Gemini's OpenAI-compatible API.
os.environ["OPENAI_API_KEY"] = "your-gemini-key" # Should start with AIza...
os.environ["OPENAI_API_BASE"] = "https://generativelanguage.googleapis.com/v1beta/openai/"
os.environ["OPENAI_MODEL_NAME"] = "openai/gemini-2.0-flash" # Add your Gemini model here, under openai/
```
</CodeGroup>
</Tab>
<Tab title="باستخدام خصائص فئة LLM">
<CodeGroup>
```python Generic
llm = LLM(
model="custom-model-name",
api_key="your-api-key",
base_url="https://api.your-provider.com/v1"
)
agent = Agent(llm=llm, ...)
```
```python Google
# Example using Gemini's OpenAI-compatible API
llm = LLM(
model="openai/gemini-2.0-flash",
base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
api_key="your-gemini-key", # Should start with AIza...
)
agent = Agent(llm=llm, ...)
```
</CodeGroup>
</Tab>
</Tabs>
## استخدام النماذج المحلية مع Ollama
للنماذج المحلية مثل تلك التي يوفرها Ollama:
<Steps>
<Step title="تحميل وتثبيت Ollama">
[انقر هنا لتحميل وتثبيت Ollama](https://ollama.com/download)
</Step>
<Step title="سحب النموذج المطلوب">
على سبيل المثال، شغّل `ollama pull llama3.2` لتحميل النموذج.
</Step>
<Step title="إعداد وكيلك">
<CodeGroup>
```python Code
agent = Agent(
role='Local AI Expert',
goal='Process information using a local model',
backstory="An AI assistant running on local hardware.",
llm=LLM(model="ollama/llama3.2", base_url="http://localhost:11434")
)
```
</CodeGroup>
</Step>
</Steps>
## تغيير عنوان URL الأساسي لـ API
يمكنك تغيير عنوان URL الأساسي لـ API لأي مزود LLM عن طريق تعيين معامل `base_url`:
```python Code
llm = LLM(
model="custom-model-name",
base_url="https://api.your-provider.com/v1",
api_key="your-api-key"
)
agent = Agent(llm=llm, ...)
```
هذا مفيد بشكل خاص عند العمل مع واجهات برمجة تطبيقات متوافقة مع OpenAI أو عندما تحتاج إلى تحديد نقطة نهاية مختلفة للمزود الذي اخترته.
## الخاتمة
من خلال الاستفادة من LiteLLM، يوفر CrewAI تكاملاً سلساً مع مجموعة واسعة من نماذج اللغة الكبيرة. تتيح لك هذه المرونة اختيار النموذج الأنسب لاحتياجاتك المحددة، سواء كنت تعطي الأولوية للأداء أو كفاءة التكلفة أو النشر المحلي. تذكر الرجوع إلى [وثائق LiteLLM](https://docs.litellm.ai/docs/) للحصول على أحدث المعلومات حول النماذج المدعومة وخيارات الإعداد.

View File

@@ -0,0 +1,427 @@
---
title: خطافات استدعاء LLM
description: تعلم كيفية استخدام خطافات استدعاء LLM لاعتراض وتعديل والتحكم في تفاعلات نماذج اللغة في CrewAI
mode: "wide"
---
توفر خطافات استدعاء LLM تحكماً دقيقاً في تفاعلات نماذج اللغة أثناء تنفيذ الوكيل. تتيح لك هذه الخطافات اعتراض استدعاءات LLM وتعديل المطالبات وتحويل الاستجابات وتنفيذ بوابات الموافقة وإضافة تسجيل أو مراقبة مخصصة.
## نظرة عامة
تُنفذ خطافات LLM في نقطتين حرجتين:
- **قبل استدعاء LLM**: تعديل الرسائل، التحقق من المدخلات، أو حظر التنفيذ
- **بعد استدعاء LLM**: تحويل الاستجابات، تنقية المخرجات، أو تعديل سجل المحادثة
## أنواع الخطافات
### خطافات ما قبل استدعاء LLM
تُنفذ قبل كل استدعاء LLM، ويمكن لهذه الخطافات:
- فحص وتعديل الرسائل المرسلة إلى LLM
- حظر تنفيذ LLM بناءً على شروط
- تنفيذ تحديد معدل أو بوابات موافقة
- إضافة سياق أو رسائل نظام
- تسجيل تفاصيل الطلب
**التوقيع:**
```python
def before_hook(context: LLMCallHookContext) -> bool | None:
# Return False to block execution
# Return True or None to allow execution
...
```
### خطافات ما بعد استدعاء LLM
تُنفذ بعد كل استدعاء LLM، ويمكن لهذه الخطافات:
- تعديل أو تنقية استجابات LLM
- إضافة بيانات وصفية أو تنسيق
- تسجيل تفاصيل الاستجابة
- تحديث سجل المحادثة
- تنفيذ تصفية المحتوى
**التوقيع:**
```python
def after_hook(context: LLMCallHookContext) -> str | None:
# Return modified response string
# Return None to keep original response
...
```
## سياق خطاف LLM
يوفر كائن `LLMCallHookContext` وصولاً شاملاً لحالة التنفيذ:
```python
class LLMCallHookContext:
executor: CrewAgentExecutor # Full executor reference
messages: list # Mutable message list
agent: Agent # Current agent
task: Task # Current task
crew: Crew # Crew instance
llm: BaseLLM # LLM instance
iterations: int # Current iteration count
response: str | None # LLM response (after hooks only)
```
### تعديل الرسائل
**مهم:** قم دائماً بتعديل الرسائل في مكانها:
```python
# ✅ Correct - modify in-place
def add_context(context: LLMCallHookContext) -> None:
context.messages.append({"role": "system", "content": "Be concise"})
# ❌ Wrong - replaces list reference
def wrong_approach(context: LLMCallHookContext) -> None:
context.messages = [{"role": "system", "content": "Be concise"}]
```
## طرق التسجيل
### 1. تسجيل الخطافات العامة
تسجيل خطافات تنطبق على جميع استدعاءات LLM عبر جميع الأطقم:
```python
from crewai.hooks import register_before_llm_call_hook, register_after_llm_call_hook
def log_llm_call(context):
print(f"LLM call by {context.agent.role} at iteration {context.iterations}")
return None # Allow execution
register_before_llm_call_hook(log_llm_call)
```
### 2. التسجيل باستخدام المزخرفات
استخدم المزخرفات لصياغة أنظف:
```python
from crewai.hooks import before_llm_call, after_llm_call
@before_llm_call
def validate_iteration_count(context):
if context.iterations > 10:
print("⚠️ Exceeded maximum iterations")
return False # Block execution
return None
@after_llm_call
def sanitize_response(context):
if context.response and "API_KEY" in context.response:
return context.response.replace("API_KEY", "[REDACTED]")
return None
```
### 3. خطافات نطاق الطاقم
تسجيل خطافات لمثيل طاقم محدد:
```python
@CrewBase
class MyProjCrew:
@before_llm_call_crew
def validate_inputs(self, context):
# Only applies to this crew
if context.iterations == 0:
print(f"Starting task: {context.task.description}")
return None
@after_llm_call_crew
def log_responses(self, context):
# Crew-specific response logging
print(f"Response length: {len(context.response)}")
return None
@crew
def crew(self) -> Crew:
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True
)
```
## حالات الاستخدام الشائعة
### 1. تحديد التكرارات
```python
@before_llm_call
def limit_iterations(context: LLMCallHookContext) -> bool | None:
max_iterations = 15
if context.iterations > max_iterations:
print(f"⛔ Blocked: Exceeded {max_iterations} iterations")
return False # Block execution
return None
```
### 2. بوابة الموافقة البشرية
```python
@before_llm_call
def require_approval(context: LLMCallHookContext) -> bool | None:
if context.iterations > 5:
response = context.request_human_input(
prompt=f"Iteration {context.iterations}: Approve LLM call?",
default_message="Press Enter to approve, or type 'no' to block:"
)
if response.lower() == "no":
print("🚫 LLM call blocked by user")
return False
return None
```
### 3. إضافة سياق النظام
```python
@before_llm_call
def add_guardrails(context: LLMCallHookContext) -> None:
# Add safety guidelines to every LLM call
context.messages.append({
"role": "system",
"content": "Ensure responses are factual and cite sources when possible."
})
return None
```
### 4. تنقية الاستجابات
```python
@after_llm_call
def sanitize_sensitive_data(context: LLMCallHookContext) -> str | None:
if not context.response:
return None
# Remove sensitive patterns
import re
sanitized = context.response
sanitized = re.sub(r'\b\d{3}-\d{2}-\d{4}\b', '[SSN-REDACTED]', sanitized)
sanitized = re.sub(r'\b\d{4}[- ]?\d{4}[- ]?\d{4}[- ]?\d{4}\b', '[CARD-REDACTED]', sanitized)
return sanitized
```
### 5. تتبع التكاليف
```python
import tiktoken
@before_llm_call
def track_token_usage(context: LLMCallHookContext) -> None:
encoding = tiktoken.get_encoding("cl100k_base")
total_tokens = sum(
len(encoding.encode(msg.get("content", "")))
for msg in context.messages
)
print(f"📊 Input tokens: ~{total_tokens}")
return None
@after_llm_call
def track_response_tokens(context: LLMCallHookContext) -> None:
if context.response:
encoding = tiktoken.get_encoding("cl100k_base")
tokens = len(encoding.encode(context.response))
print(f"📊 Response tokens: ~{tokens}")
return None
```
### 6. تسجيل التصحيح
```python
@before_llm_call
def debug_request(context: LLMCallHookContext) -> None:
print(f"""
🔍 LLM Call Debug:
- Agent: {context.agent.role}
- Task: {context.task.description[:50]}...
- Iteration: {context.iterations}
- Message Count: {len(context.messages)}
- Last Message: {context.messages[-1] if context.messages else 'None'}
""")
return None
@after_llm_call
def debug_response(context: LLMCallHookContext) -> None:
if context.response:
print(f"✅ Response Preview: {context.response[:100]}...")
return None
```
## إدارة الخطافات
### إلغاء تسجيل الخطافات
```python
from crewai.hooks import (
unregister_before_llm_call_hook,
unregister_after_llm_call_hook
)
# Unregister specific hook
def my_hook(context):
...
register_before_llm_call_hook(my_hook)
# Later...
unregister_before_llm_call_hook(my_hook) # Returns True if found
```
### مسح الخطافات
```python
from crewai.hooks import (
clear_before_llm_call_hooks,
clear_after_llm_call_hooks,
clear_all_llm_call_hooks
)
# Clear specific hook type
count = clear_before_llm_call_hooks()
print(f"Cleared {count} before hooks")
# Clear all LLM hooks
before_count, after_count = clear_all_llm_call_hooks()
print(f"Cleared {before_count} before and {after_count} after hooks")
```
### عرض الخطافات المسجلة
```python
from crewai.hooks import (
get_before_llm_call_hooks,
get_after_llm_call_hooks
)
# Get current hooks
before_hooks = get_before_llm_call_hooks()
after_hooks = get_after_llm_call_hooks()
print(f"Registered: {len(before_hooks)} before, {len(after_hooks)} after")
```
## أنماط متقدمة
### تنفيذ خطاف مشروط
```python
@before_llm_call
def conditional_blocking(context: LLMCallHookContext) -> bool | None:
# Only block for specific agents
if context.agent.role == "researcher" and context.iterations > 10:
return False
# Only block for specific tasks
if "sensitive" in context.task.description.lower() and context.iterations > 5:
return False
return None
```
### تعديلات واعية بالسياق
```python
@before_llm_call
def adaptive_prompting(context: LLMCallHookContext) -> None:
# Add different context based on iteration
if context.iterations == 0:
context.messages.append({
"role": "system",
"content": "Start with a high-level overview."
})
elif context.iterations > 3:
context.messages.append({
"role": "system",
"content": "Focus on specific details and provide examples."
})
return None
```
### ربط الخطافات
```python
# Multiple hooks execute in registration order
@before_llm_call
def first_hook(context):
print("1. First hook executed")
return None
@before_llm_call
def second_hook(context):
print("2. Second hook executed")
return None
@before_llm_call
def blocking_hook(context):
if context.iterations > 10:
print("3. Blocking hook - execution stopped")
return False # Subsequent hooks won't execute
print("3. Blocking hook - execution allowed")
return None
```
## أفضل الممارسات
1. **اجعل الخطافات مركزة**: يجب أن يكون لكل خطاف مسؤولية واحدة
2. **تجنب الحسابات الثقيلة**: تُنفذ الخطافات في كل استدعاء LLM
3. **تعامل مع الأخطاء بأناقة**: استخدم try-except لمنع فشل الخطافات من كسر التنفيذ
4. **استخدم تلميحات الأنواع**: استفد من `LLMCallHookContext` لدعم أفضل في بيئة التطوير
5. **وثّق سلوك الخطاف**: خاصة لشروط الحظر
6. **اختبر الخطافات بشكل مستقل**: اختبر الخطافات وحدوياً قبل الاستخدام في الإنتاج
7. **امسح الخطافات في الاختبارات**: استخدم `clear_all_llm_call_hooks()` بين تشغيلات الاختبار
8. **عدّل في المكان**: قم دائماً بتعديل `context.messages` في مكانها، ولا تستبدلها
## معالجة الأخطاء
```python
@before_llm_call
def safe_hook(context: LLMCallHookContext) -> bool | None:
try:
# Your hook logic
if some_condition:
return False
except Exception as e:
print(f"⚠️ Hook error: {e}")
# Decide: allow or block on error
return None # Allow execution despite error
```
## أمان الأنواع
```python
from crewai.hooks import LLMCallHookContext, BeforeLLMCallHookType, AfterLLMCallHookType
# Explicit type annotations
def my_before_hook(context: LLMCallHookContext) -> bool | None:
return None
def my_after_hook(context: LLMCallHookContext) -> str | None:
return None
# Type-safe registration
register_before_llm_call_hook(my_before_hook)
register_after_llm_call_hook(my_after_hook)
```
## استكشاف الأخطاء وإصلاحها
### الخطاف لا يُنفذ
- تحقق من أن الخطاف مسجل قبل تنفيذ الطاقم
- تحقق مما إذا كان خطاف سابق أرجع `False` (يحظر الخطافات اللاحقة)
- تأكد من أن توقيع الخطاف يطابق النوع المتوقع
### تعديلات الرسائل لا تستمر
- استخدم التعديلات في المكان: `context.messages.append()`
- لا تستبدل القائمة: `context.messages = []`
### تعديلات الاستجابة لا تعمل
- أرجع السلسلة النصية المعدلة من خطافات ما بعد
- إرجاع `None` يحتفظ بالاستجابة الأصلية
## الخاتمة
توفر خطافات استدعاء LLM إمكانيات قوية للتحكم في تفاعلات نماذج اللغة ومراقبتها في CrewAI. استخدمها لتنفيذ حواجز الأمان وبوابات الموافقة والتسجيل وتتبع التكاليف وتنقية الاستجابات. مع معالجة الأخطاء المناسبة وأمان الأنواع، تُمكّن الخطافات أنظمة وكلاء قوية وجاهزة للإنتاج.

View File

@@ -0,0 +1,821 @@
---
title: "دليل اختيار LLM الاستراتيجي"
description: "إطار عمل استراتيجي لاختيار نموذج اللغة الكبير المناسب لوكلاء الذكاء الاصطناعي في CrewAI وكتابة تعريفات فعالة للمهام والوكلاء"
icon: "brain-circuit"
mode: "wide"
---
## نهج CrewAI في اختيار LLM
بدلاً من توصيات نماذج محددة، ندعو إلى **إطار تفكير** يساعدك على اتخاذ قرارات مستنيرة بناءً على حالة استخدامك المحددة وقيودك ومتطلباتك. يتطور مشهد LLM بسرعة، مع ظهور نماذج جديدة بانتظام وتحديث النماذج الحالية بشكل متكرر. الأهم هو تطوير نهج منظم للتقييم يبقى ذا صلة بغض النظر عن النماذج المتاحة تحديداً.
<Note>
يركز هذا الدليل على التفكير الاستراتيجي بدلاً من توصيات نماذج محددة،
حيث يتطور مشهد LLM بسرعة.
</Note>
## إطار القرار السريع
<Steps>
<Step title="حلل مهامك">
ابدأ بفهم عميق لما تتطلبه مهامك فعلاً. ضع في الاعتبار التعقيد المعرفي
المطلوب وعمق الاستدلال اللازم وتنسيق المخرجات المتوقعة وحجم السياق الذي
سيحتاج النموذج لمعالجته. سيوجه هذا التحليل الأساسي كل قرار لاحق.
</Step>
<Step title="خريطة قدرات النماذج">
بمجرد فهم متطلباتك، اربطها بنقاط قوة النماذج. تتفوق عائلات النماذج
المختلفة في أنواع مختلفة من العمل؛ بعضها محسّن للاستدلال والتحليل وبعضها
للإبداع وتوليد المحتوى وبعضها للسرعة والكفاءة.
</Step>
<Step title="ضع في الاعتبار القيود">
ضع في حسبانك قيودك التشغيلية الواقعية بما في ذلك قيود الميزانية ومتطلبات
زمن الاستجابة واحتياجات خصوصية البيانات وقدرات البنية التحتية. قد لا يكون
النموذج الأفضل نظرياً هو الخيار الأفضل عملياً لوضعك.
</Step>
<Step title="اختبر وكرر">
ابدأ بنماذج موثوقة ومفهومة جيداً وحسّن بناءً على الأداء الفعلي في حالة
استخدامك المحددة. غالباً ما تختلف النتائج الواقعية عن المعايير النظرية، لذا
فإن الاختبار التجريبي ضروري.
</Step>
</Steps>
## Core Selection Framework
### a. Task-First Thinking
The most critical step in LLM selection is understanding what your task actually demands. Too often, teams select models based on general reputation or benchmark scores without carefully analyzing their specific requirements. This approach leads to either over-engineering simple tasks with expensive, complex models, or under-powering sophisticated work with models that lack the necessary capabilities.
<Tabs>
<Tab title="Reasoning Complexity">
- **Simple Tasks** represent the majority of everyday AI work and include basic instruction following, straightforward data processing, and simple formatting operations. These tasks typically have clear inputs and outputs with minimal ambiguity. The cognitive load is low, and the model primarily needs to follow explicit instructions rather than engage in complex reasoning.
- **Complex Tasks** require multi-step reasoning, strategic thinking, and the ability to handle ambiguous or incomplete information. These might involve analyzing multiple data sources, developing comprehensive strategies, or solving problems that require breaking down into smaller components. The model needs to maintain context across multiple reasoning steps and often must make inferences that aren't explicitly stated.
- **Creative Tasks** demand a different type of cognitive capability focused on generating novel, engaging, and contextually appropriate content. This includes storytelling, marketing copy creation, and creative problem-solving. The model needs to understand nuance, tone, and audience while producing content that feels authentic and engaging rather than formulaic.
</Tab>
<Tab title="Output Requirements">
- **Structured Data** tasks require precision and consistency in format adherence. When working with JSON, XML, or database formats, the model must reliably produce syntactically correct output that can be programmatically processed. These tasks often have strict validation requirements and little tolerance for format errors, making reliability more important than creativity.
- **Creative Content** outputs demand a balance of technical competence and creative flair. The model needs to understand audience, tone, and brand voice while producing content that engages readers and achieves specific communication goals. Quality here is often subjective and requires models that can adapt their writing style to different contexts and purposes.
- **Technical Content** sits between structured data and creative content, requiring both precision and clarity. Documentation, code generation, and technical analysis need to be accurate and comprehensive while remaining accessible to the intended audience. The model must understand complex technical concepts and communicate them effectively.
</Tab>
<Tab title="Context Needs">
- **Short Context** scenarios involve focused, immediate tasks where the model needs to process limited information quickly. These are often transactional interactions where speed and efficiency matter more than deep understanding. The model doesn't need to maintain extensive conversation history or process large documents.
- **Long Context** requirements emerge when working with substantial documents, extended conversations, or complex multi-part tasks. The model needs to maintain coherence across thousands of tokens while referencing earlier information accurately. This capability becomes crucial for document analysis, comprehensive research, and sophisticated dialogue systems.
- **Very Long Context** scenarios push the boundaries of what's currently possible, involving massive document processing, extensive research synthesis, or complex multi-session interactions. These use cases require models specifically designed for extended context handling and often involve trade-offs between context length and processing speed.
</Tab>
</Tabs>
### b. Model Capability Mapping
Understanding model capabilities requires looking beyond marketing claims and benchmark scores to understand the fundamental strengths and limitations of different model architectures and training approaches.
<AccordionGroup>
<Accordion title="Reasoning Models" icon="brain">
Reasoning models represent a specialized category designed specifically for complex, multi-step thinking tasks. These models excel when problems require careful analysis, strategic planning, or systematic problem decomposition. They typically employ techniques like chain-of-thought reasoning or tree-of-thought processing to work through complex problems step by step.
The strength of reasoning models lies in their ability to maintain logical consistency across extended reasoning chains and to break down complex problems into manageable components. They're particularly valuable for strategic planning, complex analysis, and situations where the quality of reasoning matters more than speed of response.
However, reasoning models often come with trade-offs in terms of speed and cost. They may also be less suitable for creative tasks or simple operations where their sophisticated reasoning capabilities aren't needed. Consider these models when your tasks involve genuine complexity that benefits from systematic, step-by-step analysis.
</Accordion>
<Accordion title="General Purpose Models" icon="microchip">
General purpose models offer the most balanced approach to LLM selection, providing solid performance across a wide range of tasks without extreme specialization in any particular area. These models are trained on diverse datasets and optimized for versatility rather than peak performance in specific domains.
The primary advantage of general purpose models is their reliability and predictability across different types of work. They handle most standard business tasks competently, from research and analysis to content creation and data processing. This makes them excellent choices for teams that need consistent performance across varied workflows.
While general purpose models may not achieve the peak performance of specialized alternatives in specific domains, they offer operational simplicity and reduced complexity in model management. They're often the best starting point for new projects, allowing teams to understand their specific needs before potentially optimizing with more specialized models.
</Accordion>
<Accordion title="Fast & Efficient Models" icon="bolt">
Fast and efficient models prioritize speed, cost-effectiveness, and resource efficiency over sophisticated reasoning capabilities. These models are optimized for high-throughput scenarios where quick responses and low operational costs are more important than nuanced understanding or complex reasoning.
These models excel in scenarios involving routine operations, simple data processing, function calling, and high-volume tasks where the cognitive requirements are relatively straightforward. They're particularly valuable for applications that need to process many requests quickly or operate within tight budget constraints.
The key consideration with efficient models is ensuring that their capabilities align with your task requirements. While they can handle many routine operations effectively, they may struggle with tasks requiring nuanced understanding, complex reasoning, or sophisticated content generation. They're best used for well-defined, routine operations where speed and cost matter more than sophistication.
</Accordion>
<Accordion title="Creative Models" icon="pen">
Creative models are specifically optimized for content generation, writing quality, and creative thinking tasks. These models typically excel at understanding nuance, tone, and style while producing engaging, contextually appropriate content that feels natural and authentic.
The strength of creative models lies in their ability to adapt writing style to different audiences, maintain consistent voice and tone, and generate content that engages readers effectively. They often perform better on tasks involving storytelling, marketing copy, brand communications, and other content where creativity and engagement are primary goals.
When selecting creative models, consider not just their ability to generate text, but their understanding of audience, context, and purpose. The best creative models can adapt their output to match specific brand voices, target different audience segments, and maintain consistency across extended content pieces.
</Accordion>
<Accordion title="Open Source Models" icon="code">
Open source models offer unique advantages in terms of cost control, customization potential, data privacy, and deployment flexibility. These models can be run locally or on private infrastructure, providing complete control over data handling and model behavior.
The primary benefits of open source models include elimination of per-token costs, ability to fine-tune for specific use cases, complete data privacy, and independence from external API providers. They're particularly valuable for organizations with strict data privacy requirements, budget constraints, or specific customization needs.
However, open source models require more technical expertise to deploy and maintain effectively. Teams need to consider infrastructure costs, model management complexity, and the ongoing effort required to keep models updated and optimized. The total cost of ownership may be higher than cloud-based alternatives when factoring in technical overhead.
</Accordion>
</AccordionGroup>
## Strategic Configuration Patterns
### a. Multi-Model Approach
<Tip>
Use different models for different purposes within the same crew to optimize
both performance and cost.
</Tip>
The most sophisticated CrewAI implementations often employ multiple models strategically, assigning different models to different agents based on their specific roles and requirements. This approach allows teams to optimize for both performance and cost by using the most appropriate model for each type of work.
Planning agents benefit from reasoning models that can handle complex strategic thinking and multi-step analysis. These agents often serve as the "brain" of the operation, developing strategies and coordinating other agents' work. Content agents, on the other hand, perform best with creative models that excel at writing quality and audience engagement. Processing agents handling routine operations can use efficient models that prioritize speed and cost-effectiveness.
**Example: Research and Analysis Crew**
```python
from crewai import Agent, Task, Crew, LLM
# High-capability reasoning model for strategic planning
manager_llm = LLM(model="gemini-2.5-flash-preview-05-20", temperature=0.1)
# Creative model for content generation
content_llm = LLM(model="claude-3-5-sonnet-20241022", temperature=0.7)
# Efficient model for data processing
processing_llm = LLM(model="gpt-4o-mini", temperature=0)
research_manager = Agent(
role="Research Strategy Manager",
goal="Develop comprehensive research strategies and coordinate team efforts",
backstory="Expert research strategist with deep analytical capabilities",
llm=manager_llm, # High-capability model for complex reasoning
verbose=True
)
content_writer = Agent(
role="Research Content Writer",
goal="Transform research findings into compelling, well-structured reports",
backstory="Skilled writer who excels at making complex topics accessible",
llm=content_llm, # Creative model for engaging content
verbose=True
)
data_processor = Agent(
role="Data Analysis Specialist",
goal="Extract and organize key data points from research sources",
backstory="Detail-oriented analyst focused on accuracy and efficiency",
llm=processing_llm, # Fast, cost-effective model for routine tasks
verbose=True
)
crew = Crew(
agents=[research_manager, content_writer, data_processor],
tasks=[...], # Your specific tasks
manager_llm=manager_llm, # Manager uses the reasoning model
verbose=True
)
```
The key to successful multi-model implementation is understanding how different agents interact and ensuring that model capabilities align with agent responsibilities. This requires careful planning but can result in significant improvements in both output quality and operational efficiency.
### b. Component-Specific Selection
<Tabs>
<Tab title="Manager LLM">
The manager LLM plays a crucial role in hierarchical CrewAI processes, serving as the coordination point for multiple agents and tasks. This model needs to excel at delegation, task prioritization, and maintaining context across multiple concurrent operations.
Effective manager LLMs require strong reasoning capabilities to make good delegation decisions, consistent performance to ensure predictable coordination, and excellent context management to track the state of multiple agents simultaneously. The model needs to understand the capabilities and limitations of different agents while optimizing task allocation for efficiency and quality.
Cost considerations are particularly important for manager LLMs since they're involved in every operation. The model needs to provide sufficient capability for effective coordination while remaining cost-effective for frequent use. This often means finding models that offer good reasoning capabilities without the premium pricing of the most sophisticated options.
</Tab>
<Tab title="Function Calling LLM">
Function calling LLMs handle tool usage across all agents, making them critical for crews that rely heavily on external tools and APIs. These models need to excel at understanding tool capabilities, extracting parameters accurately, and handling tool responses effectively.
The most important characteristics for function calling LLMs are precision and reliability rather than creativity or sophisticated reasoning. The model needs to consistently extract the correct parameters from natural language requests and handle tool responses appropriately. Speed is also important since tool usage often involves multiple round trips that can impact overall performance.
Many teams find that specialized function calling models or general purpose models with strong tool support work better than creative or reasoning-focused models for this role. The key is ensuring that the model can reliably bridge the gap between natural language instructions and structured tool calls.
</Tab>
<Tab title="Agent-Specific Overrides">
Individual agents can override crew-level LLM settings when their specific needs differ significantly from the general crew requirements. This capability allows for fine-tuned optimization while maintaining operational simplicity for most agents.
Consider agent-specific overrides when an agent's role requires capabilities that differ substantially from other crew members. For example, a creative writing agent might benefit from a model optimized for content generation, while a data analysis agent might perform better with a reasoning-focused model.
The challenge with agent-specific overrides is balancing optimization with operational complexity. Each additional model adds complexity to deployment, monitoring, and cost management. Teams should focus overrides on agents where the performance improvement justifies the additional complexity.
</Tab>
</Tabs>
## Task Definition Framework
### a. Focus on Clarity Over Complexity
Effective task definition is often more important than model selection in determining the quality of CrewAI outputs. Well-defined tasks provide clear direction and context that enable even modest models to perform well, while poorly defined tasks can cause even sophisticated models to produce unsatisfactory results.
<AccordionGroup>
<Accordion title="Effective Task Descriptions" icon="list-check">
The best task descriptions strike a balance between providing sufficient detail and maintaining clarity. They should define the specific objective clearly enough that there's no ambiguity about what success looks like, while explaining the approach or methodology in enough detail that the agent understands how to proceed.
Effective task descriptions include relevant context and constraints that help the agent understand the broader purpose and any limitations they need to work within. They break complex work into focused steps that can be executed systematically, rather than presenting overwhelming, multi-faceted objectives that are difficult to approach systematically.
Common mistakes include being too vague about objectives, failing to provide necessary context, setting unclear success criteria, or combining multiple unrelated tasks into a single description. The goal is to provide enough information for the agent to succeed while maintaining focus on a single, clear objective.
</Accordion>
<Accordion title="Expected Output Guidelines" icon="bullseye">
Expected output guidelines serve as a contract between the task definition and the agent, clearly specifying what the deliverable should look like and how it will be evaluated. These guidelines should describe both the format and structure needed, as well as the key elements that must be included for the output to be considered complete.
The best output guidelines provide concrete examples of quality indicators and define completion criteria clearly enough that both the agent and human reviewers can assess whether the task has been completed successfully. This reduces ambiguity and helps ensure consistent results across multiple task executions.
Avoid generic output descriptions that could apply to any task, missing format specifications that leave agents guessing about structure, unclear quality standards that make evaluation difficult, or failing to provide examples or templates that help agents understand expectations.
</Accordion>
</AccordionGroup>
### b. Task Sequencing Strategy
<Tabs>
<Tab title="Sequential Dependencies">
Sequential task dependencies are essential when tasks build upon previous outputs, information flows from one task to another, or quality depends on the completion of prerequisite work. This approach ensures that each task has access to the information and context it needs to succeed.
Implementing sequential dependencies effectively requires using the context parameter to chain related tasks, building complexity gradually through task progression, and ensuring that each task produces outputs that serve as meaningful inputs for subsequent tasks. The goal is to maintain logical flow between dependent tasks while avoiding unnecessary bottlenecks.
Sequential dependencies work best when there's a clear logical progression from one task to another and when the output of one task genuinely improves the quality or feasibility of subsequent tasks. However, they can create bottlenecks if not managed carefully, so it's important to identify which dependencies are truly necessary versus those that are merely convenient.
</Tab>
<Tab title="Parallel Execution">
Parallel execution becomes valuable when tasks are independent of each other, time efficiency is important, or different expertise areas are involved that don't require coordination. This approach can significantly reduce overall execution time while allowing specialized agents to work on their areas of strength simultaneously.
Successful parallel execution requires identifying tasks that can truly run independently, grouping related but separate work streams effectively, and planning for result integration when parallel tasks need to be combined into a final deliverable. The key is ensuring that parallel tasks don't create conflicts or redundancies that reduce overall quality.
Consider parallel execution when you have multiple independent research streams, different types of analysis that don't depend on each other, or content creation tasks that can be developed simultaneously. However, be mindful of resource allocation and ensure that parallel execution doesn't overwhelm your available model capacity or budget.
</Tab>
</Tabs>
## Optimizing Agent Configuration for LLM Performance
### a. Role-Driven LLM Selection
<Warning>
Generic agent roles make it impossible to select the right LLM. Specific roles
enable targeted model optimization.
</Warning>
The specificity of your agent roles directly determines which LLM capabilities matter most for optimal performance. This creates a strategic opportunity to match precise model strengths with agent responsibilities.
**Generic vs. Specific Role Impact on LLM Choice:**
When defining roles, think about the specific domain knowledge, working style, and decision-making frameworks that would be most valuable for the tasks the agent will handle. The more specific and contextual the role definition, the better the model can embody that role effectively.
```python
# ✅ Specific role - clear LLM requirements
specific_agent = Agent(
role="SaaS Revenue Operations Analyst", # Clear domain expertise needed
goal="Analyze recurring revenue metrics and identify growth opportunities",
backstory="Specialist in SaaS business models with deep understanding of ARR, churn, and expansion revenue",
llm=LLM(model="gpt-4o") # Reasoning model justified for complex analysis
)
```
**Role-to-Model Mapping Strategy:**
- **"Research Analyst"** → Reasoning model (GPT-4o, Claude Sonnet) for complex analysis
- **"Content Editor"** → Creative model (Claude, GPT-4o) for writing quality
- **"Data Processor"** → Efficient model (GPT-4o-mini, Gemini Flash) for structured tasks
- **"API Coordinator"** → Function-calling optimized model (GPT-4o, Claude) for tool usage
### b. Backstory as Model Context Amplifier
<Info>
Strategic backstories multiply your chosen LLM's effectiveness by providing
domain-specific context that generic prompting cannot achieve.
</Info>
A well-crafted backstory transforms your LLM choice from generic capability to specialized expertise. This is especially crucial for cost optimization - a well-contextualized efficient model can outperform a premium model without proper context.
**Context-Driven Performance Example:**
```python
# Context amplifies model effectiveness
domain_expert = Agent(
role="B2B SaaS Marketing Strategist",
goal="Develop comprehensive go-to-market strategies for enterprise software",
backstory="""
You have 10+ years of experience scaling B2B SaaS companies from Series A to IPO.
You understand the nuances of enterprise sales cycles, the importance of product-market
fit in different verticals, and how to balance growth metrics with unit economics.
You've worked with companies like Salesforce, HubSpot, and emerging unicorns, giving
you perspective on both established and disruptive go-to-market strategies.
""",
llm=LLM(model="claude-3-5-sonnet", temperature=0.3) # Balanced creativity with domain knowledge
)
# This context enables Claude to perform like a domain expert
# Without it, even it would produce generic marketing advice
```
**Backstory Elements That Enhance LLM Performance:**
- **Domain Experience**: "10+ years in enterprise SaaS sales"
- **Specific Expertise**: "Specializes in technical due diligence for Series B+ rounds"
- **Working Style**: "Prefers data-driven decisions with clear documentation"
- **Quality Standards**: "Insists on citing sources and showing analytical work"
### c. Holistic Agent-LLM Optimization
The most effective agent configurations create synergy between role specificity, backstory depth, and LLM selection. Each element reinforces the others to maximize model performance.
**Optimization Framework:**
```python
# Example: Technical Documentation Agent
tech_writer = Agent(
role="API Documentation Specialist", # Specific role for clear LLM requirements
goal="Create comprehensive, developer-friendly API documentation",
backstory="""
You're a technical writer with 8+ years documenting REST APIs, GraphQL endpoints,
and SDK integration guides. You've worked with developer tools companies and
understand what developers need: clear examples, comprehensive error handling,
and practical use cases. You prioritize accuracy and usability over marketing fluff.
""",
llm=LLM(
model="claude-3-5-sonnet", # Excellent for technical writing
temperature=0.1 # Low temperature for accuracy
),
tools=[code_analyzer_tool, api_scanner_tool],
verbose=True
)
```
**Alignment Checklist:**
- ✅ **Role Specificity**: Clear domain and responsibilities
- ✅ **LLM Match**: Model strengths align with role requirements
- ✅ **Backstory Depth**: Provides domain context the LLM can leverage
- ✅ **Tool Integration**: Tools support the agent's specialized function
- ✅ **Parameter Tuning**: Temperature and settings optimize for role needs
The key is creating agents where every configuration choice reinforces your LLM selection strategy, maximizing performance while optimizing costs.
## Practical Implementation Checklist
Rather than repeating the strategic framework, here's a tactical checklist for implementing your LLM selection decisions in CrewAI:
<Steps>
<Step title="Audit Your Current Setup" icon="clipboard-check">
**What to Review:**
- Are all agents using the same LLM by default?
- Which agents handle the most complex reasoning tasks?
- Which agents primarily do data processing or formatting?
- Are any agents heavily tool-dependent?
**Action**: Document current agent roles and identify optimization opportunities.
</Step>
<Step title="Implement Crew-Level Strategy" icon="users-gear">
**Set Your Baseline:**
```python
# Start with a reliable default for the crew
default_crew_llm = LLM(model="gpt-4o-mini") # Cost-effective baseline
crew = Crew(
agents=[...],
tasks=[...],
memory=True
)
```
**Action**: Establish your crew's default LLM before optimizing individual agents.
</Step>
<Step title="Optimize High-Impact Agents" icon="star">
**Identify and Upgrade Key Agents:**
```python
# Manager or coordination agents
manager_agent = Agent(
role="Project Manager",
llm=LLM(model="gemini-2.5-flash-preview-05-20"), # Premium for coordination
# ... rest of config
)
# Creative or customer-facing agents
content_agent = Agent(
role="Content Creator",
llm=LLM(model="claude-3-5-sonnet"), # Best for writing
# ... rest of config
)
```
**Action**: Upgrade 20% of your agents that handle 80% of the complexity.
</Step>
<Step title="Validate with Enterprise Testing" icon="test-tube">
**Once you deploy your agents to production:**
- Use [CrewAI AMP platform](https://app.crewai.com) to A/B test your model selections
- Run multiple iterations with real inputs to measure consistency and performance
- Compare cost vs. performance across your optimized setup
- Share results with your team for collaborative decision-making
**Action**: Replace guesswork with data-driven validation using the testing platform.
</Step>
</Steps>
### When to Use Different Model Types
<Tabs>
<Tab title="Reasoning Models">
Reasoning models become essential when tasks require genuine multi-step logical thinking, strategic planning, or high-level decision making that benefits from systematic analysis. These models excel when problems need to be broken down into components and analyzed systematically rather than handled through pattern matching or simple instruction following.
Consider reasoning models for business strategy development, complex data analysis that requires drawing insights from multiple sources, multi-step problem solving where each step depends on previous analysis, and strategic planning tasks that require considering multiple variables and their interactions.
However, reasoning models often come with higher costs and slower response times, so they're best reserved for tasks where their sophisticated capabilities provide genuine value rather than being used for simple operations that don't require complex reasoning.
</Tab>
<Tab title="Creative Models">
Creative models become valuable when content generation is the primary output and the quality, style, and engagement level of that content directly impact success. These models excel when writing quality and style matter significantly, creative ideation or brainstorming is needed, or brand voice and tone are important considerations.
Use creative models for blog post writing and article creation, marketing copy that needs to engage and persuade, creative storytelling and narrative development, and brand communications where voice and tone are crucial. These models often understand nuance and context better than general purpose alternatives.
Creative models may be less suitable for technical or analytical tasks where precision and factual accuracy are more important than engagement and style. They're best used when the creative and communicative aspects of the output are primary success factors.
</Tab>
<Tab title="Efficient Models">
Efficient models are ideal for high-frequency, routine operations where speed and cost optimization are priorities. These models work best when tasks have clear, well-defined parameters and don't require sophisticated reasoning or creative capabilities.
Consider efficient models for data processing and transformation tasks, simple formatting and organization operations, function calling and tool usage where precision matters more than sophistication, and high-volume operations where cost per operation is a significant factor.
The key with efficient models is ensuring that their capabilities align with task requirements. They can handle many routine operations effectively but may struggle with tasks requiring nuanced understanding, complex reasoning, or sophisticated content generation.
</Tab>
<Tab title="Open Source Models">
Open source models become attractive when budget constraints are significant, data privacy requirements exist, customization needs are important, or local deployment is required for operational or compliance reasons.
Consider open source models for internal company tools where data privacy is paramount, privacy-sensitive applications that can't use external APIs, cost-optimized deployments where per-token pricing is prohibitive, and situations requiring custom model modifications or fine-tuning.
However, open source models require more technical expertise to deploy and maintain effectively. Consider the total cost of ownership including infrastructure, technical overhead, and ongoing maintenance when evaluating open source options.
</Tab>
</Tabs>
## Common CrewAI Model Selection Pitfalls
<AccordionGroup>
<Accordion title="The 'One Model Fits All' Trap" icon="triangle-exclamation">
**The Problem**: Using the same LLM for all agents in a crew, regardless of their specific roles and responsibilities. This is often the default approach but rarely optimal.
**Real Example**: Using GPT-4o for both a strategic planning manager and a data extraction agent. The manager needs reasoning capabilities worth the premium cost, but the data extractor could perform just as well with GPT-4o-mini at a fraction of the price.
**CrewAI Solution**: Leverage agent-specific LLM configuration to match model capabilities with agent roles:
```python
# Strategic agent gets premium model
manager = Agent(role="Strategy Manager", llm=LLM(model="gpt-4o"))
# Processing agent gets efficient model
processor = Agent(role="Data Processor", llm=LLM(model="gpt-4o-mini"))
```
</Accordion>
<Accordion title="Ignoring Crew-Level vs Agent-Level LLM Hierarchy" icon="shuffle">
**The Problem**: Not understanding how CrewAI's LLM hierarchy works - crew LLM, manager LLM, and agent LLM settings can conflict or be poorly coordinated.
**Real Example**: Setting a crew to use Claude, but having agents configured with GPT models, creating inconsistent behavior and unnecessary model switching overhead.
**CrewAI Solution**: Plan your LLM hierarchy strategically:
```python
crew = Crew(
agents=[agent1, agent2],
tasks=[task1, task2],
manager_llm=LLM(model="gpt-4o"), # For crew coordination
process=Process.hierarchical # When using manager_llm
)
# Agents inherit crew LLM unless specifically overridden
agent1 = Agent(llm=LLM(model="claude-3-5-sonnet")) # Override for specific needs
```
</Accordion>
<Accordion title="Function Calling Model Mismatch" icon="screwdriver-wrench">
**The Problem**: Choosing models based on general capabilities while ignoring function calling performance for tool-heavy CrewAI workflows.
**Real Example**: Selecting a creative-focused model for an agent that primarily needs to call APIs, search tools, or process structured data. The agent struggles with tool parameter extraction and reliable function calls.
**CrewAI Solution**: Prioritize function calling capabilities for tool-heavy agents:
```python
# For agents that use many tools
tool_agent = Agent(
role="API Integration Specialist",
tools=[search_tool, api_tool, data_tool],
llm=LLM(model="gpt-4o"), # Excellent function calling
# OR
llm=LLM(model="claude-3-5-sonnet") # Also strong with tools
)
```
</Accordion>
<Accordion title="Premature Optimization Without Testing" icon="gear">
**The Problem**: Making complex model selection decisions based on theoretical performance without validating with actual CrewAI workflows and tasks.
**Real Example**: Implementing elaborate model switching logic based on task types without testing if the performance gains justify the operational complexity.
**CrewAI Solution**: Start simple, then optimize based on real performance data:
```python
# Start with this
crew = Crew(agents=[...], tasks=[...], llm=LLM(model="gpt-4o-mini"))
# Test performance, then optimize specific agents as needed
# Use Enterprise platform testing to validate improvements
```
</Accordion>
<Accordion title="Overlooking Context and Memory Limitations" icon="brain">
**The Problem**: Not considering how model context windows interact with CrewAI's memory and context sharing between agents.
**Real Example**: Using a short-context model for agents that need to maintain conversation history across multiple task iterations, or in crews with extensive agent-to-agent communication.
**CrewAI Solution**: Match context capabilities to crew communication patterns.
</Accordion>
</AccordionGroup>
## Testing and Iteration Strategy
<Steps>
<Step title="Start Simple" icon="play">
Begin with reliable, general-purpose models that are well-understood and
widely supported. This provides a stable foundation for understanding your
specific requirements and performance expectations before optimizing for
specialized needs.
</Step>
<Step title="Measure What Matters" icon="chart-line">
Develop metrics that align with your specific use case and business
requirements rather than relying solely on general benchmarks. Focus on
measuring outcomes that directly impact your success rather than theoretical
performance indicators.
</Step>
<Step title="Iterate Based on Results" icon="arrows-rotate">
Make model changes based on observed performance in your specific context
rather than theoretical considerations or general recommendations.
Real-world performance often differs significantly from benchmark results or
general reputation.
</Step>
<Step title="Consider Total Cost" icon="calculator">
Evaluate the complete cost of ownership including model costs, development
time, maintenance overhead, and operational complexity. The cheapest model
per token may not be the most cost-effective choice when considering all
factors.
</Step>
</Steps>
<Tip>
Focus on understanding your requirements first, then select models that best
match those needs. The best LLM choice is the one that consistently delivers
the results you need within your operational constraints.
</Tip>
### Enterprise-Grade Model Validation
For teams serious about optimizing their LLM selection, the **CrewAI AMP platform** provides sophisticated testing capabilities that go far beyond basic CLI testing. The platform enables comprehensive model evaluation that helps you make data-driven decisions about your LLM strategy.
<Frame>
![Enterprise Testing Interface](/images/enterprise/enterprise-testing.png)
</Frame>
**Advanced Testing Features:**
- **Multi-Model Comparison**: Test multiple LLMs simultaneously across the same tasks and inputs. Compare performance between GPT-4o, Claude, Llama, Groq, Cerebras, and other leading models in parallel to identify the best fit for your specific use case.
- **Statistical Rigor**: Configure multiple iterations with consistent inputs to measure reliability and performance variance. This helps identify models that not only perform well but do so consistently across runs.
- **Real-World Validation**: Use your actual crew inputs and scenarios rather than synthetic benchmarks. The platform allows you to test with your specific industry context, company information, and real use cases for more accurate evaluation.
- **Comprehensive Analytics**: Access detailed performance metrics, execution times, and cost analysis across all tested models. This enables data-driven decision making rather than relying on general model reputation or theoretical capabilities.
- **Team Collaboration**: Share testing results and model performance data across your team, enabling collaborative decision-making and consistent model selection strategies across projects.
Go to [app.crewai.com](https://app.crewai.com) to get started!
<Info>
The Enterprise platform transforms model selection from guesswork into a
data-driven process, enabling you to validate the principles in this guide
with your actual use cases and requirements.
</Info>
## Key Principles Summary
<CardGroup cols={2}>
<Card title="Task-Driven Selection" icon="bullseye">
Choose models based on what the task actually requires, not theoretical capabilities or general reputation.
</Card>
{" "}
<Card title="Capability Matching" icon="puzzle-piece">
Align model strengths with agent roles and responsibilities for optimal
performance.
</Card>
{" "}
<Card title="Strategic Consistency" icon="link">
Maintain coherent model selection strategy across related components and
workflows.
</Card>
{" "}
<Card title="Practical Testing" icon="flask">
Validate choices through real-world usage rather than benchmarks alone.
</Card>
{" "}
<Card title="Iterative Improvement" icon="arrow-up">
Start simple and optimize based on actual performance and needs.
</Card>
<Card title="Operational Balance" icon="scale-balanced">
Balance performance requirements with cost and complexity constraints.
</Card>
</CardGroup>
<Check>
Remember: The best LLM choice is the one that consistently delivers the
results you need within your operational constraints. Focus on understanding
your requirements first, then select models that best match those needs.
</Check>
## Current Model Landscape (June 2025)
<Warning>
**Snapshot in Time**: The following model rankings represent current
leaderboard standings as of June 2025, compiled from [LMSys
Arena](https://arena.lmsys.org/), [Artificial
Analysis](https://artificialanalysis.ai/), and other leading benchmarks. LLM
performance, availability, and pricing change rapidly. Always conduct your own
evaluations with your specific use cases and data.
</Warning>
### Leading Models by Category
The tables below show a representative sample of current top-performing models across different categories, with guidance on their suitability for CrewAI agents:
<Note>
These tables/metrics showcase selected leading models in each category and are
not exhaustive. Many excellent models exist beyond those listed here. The goal
is to illustrate the types of capabilities to look for rather than provide a
complete catalog.
</Note>
<Tabs>
<Tab title="Reasoning & Planning">
**Best for Manager LLMs and Complex Analysis**
| Model | Intelligence Score | Cost ($/M tokens) | Speed | Best Use in CrewAI |
|:------|:------------------|:------------------|:------|:------------------|
| **o3** | 70 | $17.50 | Fast | Manager LLM for complex multi-agent coordination |
| **Gemini 2.5 Pro** | 69 | $3.44 | Fast | Strategic planning agents, research coordination |
| **DeepSeek R1** | 68 | $0.96 | Moderate | Cost-effective reasoning for budget-conscious crews |
| **Claude 4 Sonnet** | 53 | $6.00 | Fast | Analysis agents requiring nuanced understanding |
| **Qwen3 235B (Reasoning)** | 62 | $2.63 | Moderate | Open-source alternative for reasoning tasks |
These models excel at multi-step reasoning and are ideal for agents that need to develop strategies, coordinate other agents, or analyze complex information.
</Tab>
<Tab title="Coding & Technical">
**Best for Development and Tool-Heavy Workflows**
| Model | Coding Performance | Tool Use Score | Cost ($/M tokens) | Best Use in CrewAI |
|:------|:------------------|:---------------|:------------------|:------------------|
| **Claude 4 Sonnet** | Excellent | 72.7% | $6.00 | Primary coding agent, technical documentation |
| **Claude 4 Opus** | Excellent | 72.5% | $30.00 | Complex software architecture, code review |
| **DeepSeek V3** | Very Good | High | $0.48 | Cost-effective coding for routine development |
| **Qwen2.5 Coder 32B** | Very Good | Medium | $0.15 | Budget-friendly coding agent |
| **Llama 3.1 405B** | Good | 81.1% | $3.50 | Function calling LLM for tool-heavy workflows |
These models are optimized for code generation, debugging, and technical problem-solving, making them ideal for development-focused crews.
</Tab>
<Tab title="Speed & Efficiency">
**Best for High-Throughput and Real-Time Applications**
| Model | Speed (tokens/s) | Latency (TTFT) | Cost ($/M tokens) | Best Use in CrewAI |
|:------|:-----------------|:---------------|:------------------|:------------------|
| **Llama 4 Scout** | 2,600 | 0.33s | $0.27 | High-volume processing agents |
| **Gemini 2.5 Flash** | 376 | 0.30s | $0.26 | Real-time response agents |
| **DeepSeek R1 Distill** | 383 | Variable | $0.04 | Cost-optimized high-speed processing |
| **Llama 3.3 70B** | 2,500 | 0.52s | $0.60 | Balanced speed and capability |
| **Nova Micro** | High | 0.30s | $0.04 | Simple, fast task execution |
These models prioritize speed and efficiency, perfect for agents handling routine operations or requiring quick responses. **Pro tip**: Pairing these models with fast inference providers like Groq can achieve even better performance, especially for open-source models like Llama.
</Tab>
<Tab title="Balanced Performance">
**Best All-Around Models for General Crews**
| Model | Overall Score | Versatility | Cost ($/M tokens) | Best Use in CrewAI |
|:------|:--------------|:------------|:------------------|:------------------|
| **GPT-4.1** | 53 | Excellent | $3.50 | General-purpose crew LLM |
| **Claude 3.7 Sonnet** | 48 | Very Good | $6.00 | Balanced reasoning and creativity |
| **Gemini 2.0 Flash** | 48 | Good | $0.17 | Cost-effective general use |
| **Llama 4 Maverick** | 51 | Good | $0.37 | Open-source general purpose |
| **Qwen3 32B** | 44 | Good | $1.23 | Budget-friendly versatility |
These models offer good performance across multiple dimensions, suitable for crews with diverse task requirements.
</Tab>
</Tabs>
### Selection Framework for Current Models
<AccordionGroup>
<Accordion title="High-Performance Crews" icon="rocket">
**When performance is the priority**: Use top-tier models like **o3**, **Gemini 2.5 Pro**, or **Claude 4 Sonnet** for manager LLMs and critical agents. These models excel at complex reasoning and coordination but come with higher costs.
**Strategy**: Implement a multi-model approach where premium models handle strategic thinking while efficient models handle routine operations.
</Accordion>
<Accordion title="Cost-Conscious Crews" icon="dollar-sign">
**When budget is a primary constraint**: Focus on models like **DeepSeek R1**, **Llama 4 Scout**, or **Gemini 2.0 Flash**. These provide strong performance at significantly lower costs.
**Strategy**: Use cost-effective models for most agents, reserving premium models only for the most critical decision-making roles.
</Accordion>
<Accordion title="Specialized Workflows" icon="screwdriver-wrench">
**For specific domain expertise**: Choose models optimized for your primary use case. **Claude 4** series for coding, **Gemini 2.5 Pro** for research, **Llama 405B** for function calling.
**Strategy**: Select models based on your crew's primary function, ensuring the core capability aligns with model strengths.
</Accordion>
<Accordion title="Enterprise & Privacy" icon="shield">
**For data-sensitive operations**: Consider open-source models like **Llama 4** series, **DeepSeek V3**, or **Qwen3** that can be deployed locally while maintaining competitive performance.
**Strategy**: Deploy open-source models on private infrastructure, accepting potential performance trade-offs for data control.
</Accordion>
</AccordionGroup>
### Key Considerations for Model Selection
- **Performance Trends**: The current landscape shows strong competition between reasoning-focused models (o3, Gemini 2.5 Pro) and balanced models (Claude 4, GPT-4.1). Specialized models like DeepSeek R1 offer excellent cost-performance ratios.
- **Speed vs. Intelligence Trade-offs**: Models like Llama 4 Scout prioritize speed (2,600 tokens/s) while maintaining reasonable intelligence, whereas models like o3 maximize reasoning capability at the cost of speed and price.
- **Open Source Viability**: The gap between open-source and proprietary models continues to narrow, with models like Llama 4 Maverick and DeepSeek V3 offering competitive performance at attractive price points. Fast inference providers particularly shine with open-source models, often delivering better speed-to-cost ratios than proprietary alternatives.
<Info>
**Testing is Essential**: Leaderboard rankings provide general guidance, but
your specific use case, prompting style, and evaluation criteria may produce
different results. Always test candidate models with your actual tasks and
data before making final decisions.
</Info>
### Practical Implementation Strategy
<Steps>
<Step title="Start with Proven Models">
Begin with well-established models like **GPT-4.1**, **Claude 3.7 Sonnet**, or **Gemini 2.0 Flash** that offer good performance across multiple dimensions and have extensive real-world validation.
</Step>
<Step title="Identify Specialized Needs">
Determine if your crew has specific requirements (coding, reasoning, speed)
that would benefit from specialized models like **Claude 4 Sonnet** for
development or **o3** for complex analysis. For speed-critical applications,
consider fast inference providers like **Groq** alongside model selection.
</Step>
<Step title="Implement Multi-Model Strategy">
Use different models for different agents based on their roles.
High-capability models for managers and complex tasks, efficient models for
routine operations.
</Step>
<Step title="Monitor and Optimize">
Track performance metrics relevant to your use case and be prepared to adjust model selections as new models are released or pricing changes.
</Step>
</Steps>

View File

@@ -0,0 +1,141 @@
---
title: استخدام الوكلاء متعددي الوسائط
description: تعلم كيفية تفعيل واستخدام القدرات متعددة الوسائط في وكلائك لمعالجة الصور والمحتوى غير النصي ضمن إطار عمل CrewAI.
icon: video
mode: "wide"
---
## استخدام الوكلاء متعددي الوسائط
يدعم CrewAI الوكلاء متعددي الوسائط القادرين على معالجة المحتوى النصي وغير النصي مثل الصور. سيوضح لك هذا الدليل كيفية تفعيل واستخدام القدرات متعددة الوسائط في وكلائك.
### تفعيل القدرات متعددة الوسائط
لإنشاء وكيل متعدد الوسائط، ما عليك سوى تعيين معامل `multimodal` إلى `True` عند تهيئة وكيلك:
```python
from crewai import Agent
agent = Agent(
role="Image Analyst",
goal="Analyze and extract insights from images",
backstory="An expert in visual content interpretation with years of experience in image analysis",
multimodal=True # This enables multimodal capabilities
)
```
عند تعيين `multimodal=True`، يتم إعداد الوكيل تلقائياً بالأدوات اللازمة للتعامل مع المحتوى غير النصي، بما في ذلك `AddImageTool`.
### العمل مع الصور
يأتي الوكيل متعدد الوسائط مُعداً مسبقاً بأداة `AddImageTool`، التي تتيح له معالجة الصور. لا تحتاج إلى إضافة هذه الأداة يدوياً — فهي مضمنة تلقائياً عند تفعيل القدرات متعددة الوسائط.
إليك مثالاً كاملاً يوضح كيفية استخدام وكيل متعدد الوسائط لتحليل صورة:
```python
from crewai import Agent, Task, Crew
# Create a multimodal agent
image_analyst = Agent(
role="Product Analyst",
goal="Analyze product images and provide detailed descriptions",
backstory="Expert in visual product analysis with deep knowledge of design and features",
multimodal=True
)
# Create a task for image analysis
task = Task(
description="Analyze the product image at https://example.com/product.jpg and provide a detailed description",
expected_output="A detailed description of the product image",
agent=image_analyst
)
# Create and run the crew
crew = Crew(
agents=[image_analyst],
tasks=[task]
)
result = crew.kickoff()
```
### الاستخدام المتقدم مع السياق
يمكنك تقديم سياق إضافي أو أسئلة محددة حول الصورة عند إنشاء مهام للوكلاء متعددي الوسائط. يمكن أن يتضمن وصف المهمة جوانب محددة تريد أن يركز عليها الوكيل:
```python
from crewai import Agent, Task, Crew
# Create a multimodal agent for detailed analysis
expert_analyst = Agent(
role="Visual Quality Inspector",
goal="Perform detailed quality analysis of product images",
backstory="Senior quality control expert with expertise in visual inspection",
multimodal=True # AddImageTool is automatically included
)
# Create a task with specific analysis requirements
inspection_task = Task(
description="""
Analyze the product image at https://example.com/product.jpg with focus on:
1. Quality of materials
2. Manufacturing defects
3. Compliance with standards
Provide a detailed report highlighting any issues found.
""",
expected_output="A detailed report highlighting any issues found",
agent=expert_analyst
)
# Create and run the crew
crew = Crew(
agents=[expert_analyst],
tasks=[inspection_task]
)
result = crew.kickoff()
```
### تفاصيل الأداة
عند العمل مع الوكلاء متعددي الوسائط، يتم إعداد `AddImageTool` تلقائياً بالمخطط التالي:
```python
class AddImageToolSchema:
image_url: str # Required: The URL or path of the image to process
action: Optional[str] = None # Optional: Additional context or specific questions about the image
```
سيتعامل الوكيل متعدد الوسائط تلقائياً مع معالجة الصور من خلال أدواته المدمجة، مما يتيح له:
- الوصول إلى الصور عبر عناوين URL أو مسارات الملفات المحلية
- معالجة محتوى الصورة مع سياق اختياري أو أسئلة محددة
- تقديم تحليلات ورؤى بناءً على المعلومات البصرية ومتطلبات المهمة
### أفضل الممارسات
عند العمل مع الوكلاء متعددي الوسائط، ضع هذه الممارسات في الاعتبار:
1. **الوصول إلى الصور**
- تأكد من أن صورك قابلة للوصول عبر عناوين URL التي يمكن للوكيل الوصول إليها
- للصور المحلية، فكر في استضافتها مؤقتاً أو استخدام مسارات ملفات مطلقة
- تحقق من أن عناوين URL للصور صالحة وقابلة للوصول قبل تشغيل المهام
2. **وصف المهمة**
- كن محدداً حول الجوانب التي تريد من الوكيل تحليلها في الصورة
- قم بتضمين أسئلة أو متطلبات واضحة في وصف المهمة
- فكر في استخدام معامل `action` الاختياري للتحليل المركز
3. **إدارة الموارد**
- قد تتطلب معالجة الصور موارد حسابية أكثر من المهام النصية فقط
- قد تتطلب بعض نماذج اللغة ترميز base64 لبيانات الصورة
- فكر في المعالجة الدفعية لصور متعددة لتحسين الأداء
4. **إعداد البيئة**
- تحقق من أن بيئتك تحتوي على الاعتماديات اللازمة لمعالجة الصور
- تأكد من أن نموذج اللغة الخاص بك يدعم القدرات متعددة الوسائط
- اختبر بصور صغيرة أولاً للتحقق من إعدادك
5. **معالجة الأخطاء**
- نفّذ معالجة أخطاء مناسبة لحالات فشل تحميل الصور
- ضع استراتيجيات احتياطية لحالات فشل معالجة الصور
- راقب وسجل عمليات معالجة الصور لأغراض التصحيح

View File

@@ -0,0 +1,159 @@
---
title: "نظرة عامة"
description: "تعلم كيفية بناء وتخصيص وتحسين تطبيقات CrewAI الخاصة بك مع أدلة وبرامج تعليمية شاملة"
icon: "face-smile"
mode: "wide"
---
## تعلم CrewAI
يوفر هذا القسم أدلة وبرامج تعليمية شاملة لمساعدتك في إتقان CrewAI، من المفاهيم الأساسية إلى التقنيات المتقدمة. سواء كنت قد بدأت للتو أو تبحث عن تحسين تطبيقاتك الحالية، ستوجهك هذه الموارد عبر كل جانب من جوانب بناء سير عمل وكلاء الذكاء الاصطناعي القوية.
## أدلة البدء
### المفاهيم الأساسية
<CardGroup cols={2}>
<Card title="العملية التسلسلية" icon="list-ol" href="/ar/learn/sequential-process">
تعلم كيفية تنفيذ المهام بترتيب تسلسلي لسير عمل منظم.
</Card>
<Card title="العملية الهرمية" icon="sitemap" href="/ar/learn/hierarchical-process">
تنفيذ تنفيذ المهام الهرمي مع وكلاء مديرين يشرفون على سير العمل.
</Card>
<Card title="المهام الشرطية" icon="code-branch" href="/ar/learn/conditional-tasks">
إنشاء سير عمل ديناميكي مع تنفيذ مهام شرطي بناءً على النتائج.
</Card>
<Card title="التشغيل غير المتزامن" icon="bolt" href="/ar/learn/kickoff-async">
تنفيذ الأطقم بشكل غير متزامن لأداء وتزامن محسّن.
</Card>
</CardGroup>
### تطوير الوكلاء
<CardGroup cols={2}>
<Card title="تخصيص الوكلاء" icon="user-gear" href="/ar/learn/customizing-agents">
تعلم كيفية تخصيص سلوك الوكلاء وأدوارهم وقدراتهم.
</Card>
<Card title="وكلاء البرمجة" icon="code" href="/ar/learn/coding-agents">
بناء وكلاء يمكنهم كتابة وتنفيذ وتصحيح الكود تلقائياً.
</Card>
<Card title="الوكلاء متعددو الوسائط" icon="images" href="/ar/learn/multimodal-agents">
إنشاء وكلاء يمكنهم معالجة النصوص والصور وأنواع الوسائط الأخرى.
</Card>
<Card title="وكيل المدير المخصص" icon="user-tie" href="/ar/learn/custom-manager-agent">
تنفيذ وكلاء مديرين مخصصين لسير العمل الهرمي المعقد.
</Card>
</CardGroup>
## الميزات المتقدمة
### التحكم في سير العمل
<CardGroup cols={2}>
<Card title="الإنسان في الحلقة" icon="user-check" href="/ar/learn/human-in-the-loop">
دمج الإشراف البشري والتدخل في سير عمل الوكلاء.
</Card>
<Card title="الإدخال البشري أثناء التنفيذ" icon="hand-paper" href="/ar/learn/human-input-on-execution">
السماح بالإدخال البشري أثناء تنفيذ المهام لاتخاذ قرارات ديناميكية.
</Card>
<Card title="إعادة تشغيل المهام" icon="rotate-left" href="/ar/learn/replay-tasks-from-latest-crew-kickoff">
إعادة تشغيل واستئناف المهام من عمليات تنفيذ الطاقم السابقة.
</Card>
<Card title="التشغيل لكل عنصر" icon="repeat" href="/ar/learn/kickoff-for-each">
تنفيذ الأطقم عدة مرات بمدخلات مختلفة بكفاءة.
</Card>
</CardGroup>
### التخصيص والتكامل
<CardGroup cols={2}>
<Card title="LLM مخصص" icon="brain" href="/ar/learn/custom-llm">
دمج نماذج لغة ومزودين مخصصين مع CrewAI.
</Card>
<Card title="اتصالات LLM" icon="link" href="/ar/learn/llm-connections">
إعداد وإدارة الاتصالات بمزودي LLM المختلفين.
</Card>
<Card title="إنشاء أدوات مخصصة" icon="wrench" href="/ar/learn/create-custom-tools">
بناء أدوات مخصصة لتوسيع قدرات الوكلاء.
</Card>
<Card title="استخدام التعليقات التوضيحية" icon="at" href="/ar/learn/using-annotations">
استخدام تعليقات Python التوضيحية لكود أنظف وأسهل في الصيانة.
</Card>
</CardGroup>
## التطبيقات المتخصصة
### المحتوى والوسائط
<CardGroup cols={2}>
<Card title="توليد صور DALL-E" icon="image" href="/ar/learn/dalle-image-generation">
توليد الصور باستخدام تكامل DALL-E مع وكلائك.
</Card>
<Card title="أحضر وكيلك الخاص" icon="user-plus" href="/ar/learn/bring-your-own-agent">
دمج الوكلاء والنماذج الموجودة في سير عمل CrewAI.
</Card>
</CardGroup>
### إدارة الأدوات
<CardGroup cols={2}>
<Card title="فرض مخرجات الأداة كنتيجة" icon="hammer" href="/ar/learn/force-tool-output-as-result">
إعداد الأدوات لإرجاع مخرجاتها مباشرة كنتائج للمهام.
</Card>
</CardGroup>
## توصيات مسار التعلم
### للمبتدئين
1. ابدأ بـ **العملية التسلسلية** لفهم تنفيذ سير العمل الأساسي
2. تعلم **تخصيص الوكلاء** لإنشاء إعدادات وكلاء فعالة
3. استكشف **إنشاء أدوات مخصصة** لتوسيع الوظائف
4. جرب **الإنسان في الحلقة** لسير العمل التفاعلي
### للمستخدمين المتوسطين
1. أتقن **العملية الهرمية** لأنظمة الوكلاء المتعددة المعقدة
2. نفّذ **المهام الشرطية** لسير العمل الديناميكي
3. استخدم **التشغيل غير المتزامن** لتحسين الأداء
4. ادمج **LLM مخصص** للنماذج المتخصصة
### للمستخدمين المتقدمين
1. ابنِ **وكلاء متعددي الوسائط** لمعالجة الوسائط المعقدة
2. أنشئ **وكلاء مديرين مخصصين** للتنسيق المتطور
3. نفّذ **أحضر وكيلك الخاص** للأنظمة الهجينة
4. استخدم **إعادة تشغيل المهام** لاسترداد الأخطاء بشكل متين
## أفضل الممارسات
### التطوير
- **ابدأ بالبساطة**: ابدأ بسير العمل التسلسلي الأساسي قبل إضافة التعقيد
- **اختبر تدريجياً**: اختبر كل مكون قبل دمجه في أنظمة أكبر
- **استخدم التعليقات التوضيحية**: استفد من تعليقات Python التوضيحية لكود أنظف وأسهل في الصيانة
- **أدوات مخصصة**: ابنِ أدوات قابلة لإعادة الاستخدام يمكن مشاركتها عبر وكلاء مختلفين
### الإنتاج
- **معالجة الأخطاء**: نفّذ معالجة أخطاء وآليات استرداد قوية
- **الأداء**: استخدم التنفيذ غير المتزامن وحسّن استدعاءات LLM لأداء أفضل
- **المراقبة**: ادمج أدوات المراقبة لتتبع أداء الوكلاء
- **الإشراف البشري**: ضمّن نقاط تفتيش بشرية للقرارات الحرجة
### التحسين
- **إدارة الموارد**: راقب وحسّن استخدام الرموز وتكاليف API
- **تصميم سير العمل**: صمم سير عمل يقلل من استدعاءات LLM غير الضرورية
- **كفاءة الأدوات**: أنشئ أدوات فعالة توفر أقصى قيمة بأقل حمل
- **التحسين التكراري**: استخدم التغذية الراجعة والمقاييس لتحسين أداء الوكلاء باستمرار
## الحصول على المساعدة
- **التوثيق**: يتضمن كل دليل أمثلة وشروحات مفصلة
- **المجتمع**: انضم إلى [منتدى CrewAI](https://community.crewai.com) للمناقشات والدعم
- **الأمثلة**: تحقق من قسم الأمثلة للتطبيقات العاملة الكاملة
- **الدعم**: تواصل مع [support@crewai.com](mailto:support@crewai.com) للمساعدة التقنية
ابدأ بالأدلة التي تتوافق مع احتياجاتك الحالية واستكشف تدريجياً المواضيع الأكثر تقدماً مع إتقانك للأساسيات.

View File

@@ -0,0 +1,79 @@
---
title: إعادة تشغيل المهام من آخر تنفيذ للطاقم
description: إعادة تشغيل المهام من آخر crew.kickoff(...)
icon: arrow-right
mode: "wide"
---
## مقدمة
يوفر CrewAI القدرة على إعادة التشغيل من مهمة محددة من آخر تشغيل للطاقم. هذه الميزة مفيدة بشكل خاص عندما تكون قد أنهيت تشغيلاً وقد ترغب في إعادة محاولة مهام معينة أو لا تحتاج إلى إعادة جلب البيانات ووكلاؤك لديهم بالفعل السياق المحفوظ من تنفيذ التشغيل، لذا تحتاج فقط إلى إعادة تشغيل المهام التي تريدها.
<Note>
يجب عليك تشغيل `crew.kickoff()` قبل أن تتمكن من إعادة تشغيل مهمة.
حالياً، يُدعم فقط آخر تشغيل، لذا إذا استخدمت `kickoff_for_each`، فسيسمح لك فقط بإعادة التشغيل من أحدث تشغيل للطاقم.
</Note>
إليك مثالاً على كيفية إعادة التشغيل من مهمة:
### إعادة التشغيل من مهمة محددة باستخدام CLI
لاستخدام ميزة إعادة التشغيل، اتبع هذه الخطوات:
<Steps>
<Step title="افتح الطرفية أو موجه الأوامر."></Step>
<Step title="انتقل إلى المجلد الذي يقع فيه مشروع CrewAI الخاص بك."></Step>
<Step title="شغّل الأوامر التالية:">
لعرض معرفات المهام من آخر تشغيل، استخدم:
```shell
crewai log-tasks-outputs
```
بمجرد حصولك على `task_id` لإعادة التشغيل، استخدم:
```shell
crewai replay -t <task_id>
```
</Step>
</Steps>
<Note>
تأكد من أن `crewai` مثبت ومُعد بشكل صحيح في بيئة التطوير الخاصة بك.
</Note>
### إعادة التشغيل من مهمة برمجياً
لإعادة التشغيل من مهمة برمجياً، استخدم الخطوات التالية:
<Steps>
<Step title="حدد معرف المهمة ومعاملات الإدخال لعملية إعادة التشغيل.">
حدد `task_id` ومعاملات الإدخال لعملية إعادة التشغيل.
</Step>
<Step title="نفّذ أمر إعادة التشغيل ضمن كتلة try-except للتعامل مع الأخطاء المحتملة.">
نفّذ أمر إعادة التشغيل ضمن كتلة try-except للتعامل مع الأخطاء المحتملة.
<CodeGroup>
```python Code
def replay():
"""
Replay the crew execution from a specific task.
"""
task_id = '<task_id>'
inputs = {"topic": "CrewAI Training"} # This is optional; you can pass in the inputs you want to replay; otherwise, it uses the previous kickoff's inputs.
try:
YourCrewName_Crew().crew().replay(task_id=task_id, inputs=inputs)
except subprocess.CalledProcessError as e:
raise Exception(f"An error occurred while replaying the crew: {e}")
except Exception as e:
raise Exception(f"An unexpected error occurred: {e}")
```
</CodeGroup>
</Step>
</Steps>
## الخاتمة
مع التحسينات المذكورة أعلاه والوظائف المفصلة، أصبحت إعادة تشغيل مهام محددة في CrewAI أكثر كفاءة ومتانة.
تأكد من اتباع الأوامر والخطوات بدقة لتحقيق أقصى استفادة من هذه الميزات.

View File

@@ -0,0 +1,128 @@
---
title: العمليات التسلسلية
description: دليل شامل لاستخدام العمليات التسلسلية لتنفيذ المهام في مشاريع CrewAI.
icon: forward
mode: "wide"
---
## مقدمة
يقدم CrewAI إطار عمل مرن لتنفيذ المهام بطريقة منظمة، يدعم كلاً من العمليات التسلسلية والهرمية.
يوضح هذا الدليل كيفية تنفيذ هذه العمليات بفعالية لضمان تنفيذ المهام بكفاءة وإكمال المشروع.
## نظرة عامة على العملية التسلسلية
تضمن العملية التسلسلية تنفيذ المهام واحدة تلو الأخرى، باتباع تقدم خطي.
هذا النهج مثالي للمشاريع التي تتطلب إكمال المهام بترتيب محدد.
### الميزات الرئيسية
- **تدفق مهام خطي**: يضمن تقدماً منظماً من خلال التعامل مع المهام بتسلسل محدد مسبقاً.
- **البساطة**: الأنسب للمشاريع ذات المهام الواضحة خطوة بخطوة.
- **سهولة المراقبة**: يسهل التتبع السهل لإكمال المهام وتقدم المشروع.
## تنفيذ العملية التسلسلية
لاستخدام العملية التسلسلية، قم بتجميع طاقمك وتعريف المهام بالترتيب الذي تحتاج إلى تنفيذها به.
```python Code
from crewai import Crew, Process, Agent, Task, TaskOutput, CrewOutput
# Define your agents
researcher = Agent(
role='Researcher',
goal='Conduct foundational research',
backstory='An experienced researcher with a passion for uncovering insights'
)
analyst = Agent(
role='Data Analyst',
goal='Analyze research findings',
backstory='A meticulous analyst with a knack for uncovering patterns'
)
writer = Agent(
role='Writer',
goal='Draft the final report',
backstory='A skilled writer with a talent for crafting compelling narratives'
)
# Define your tasks
research_task = Task(
description='Gather relevant data...',
agent=researcher,
expected_output='Raw Data'
)
analysis_task = Task(
description='Analyze the data...',
agent=analyst,
expected_output='Data Insights'
)
writing_task = Task(
description='Compose the report...',
agent=writer,
expected_output='Final Report'
)
# Form the crew with a sequential process
report_crew = Crew(
agents=[researcher, analyst, writer],
tasks=[research_task, analysis_task, writing_task],
process=Process.sequential
)
# Execute the crew
result = report_crew.kickoff()
# Accessing the type-safe output
task_output: TaskOutput = result.tasks[0].output
crew_output: CrewOutput = result.output
```
### ملاحظة:
يجب أن يكون لكل مهمة في عملية تسلسلية وكيل مُعيّن. تأكد من أن كل `Task` تتضمن معامل `agent`.
### سير العمل أثناء التنفيذ
1. **المهمة الأولى**: في العملية التسلسلية، يكمل الوكيل الأول مهمته ويشير إلى الإكمال.
2. **المهام اللاحقة**: يلتقط الوكلاء مهامهم بناءً على نوع العملية، مع نتائج المهام السابقة أو التوجيهات التي تقود تنفيذهم.
3. **الإكمال**: تنتهي العملية بمجرد تنفيذ المهمة النهائية، مما يؤدي إلى إكمال المشروع.
## الميزات المتقدمة
### تفويض المهام
في العمليات التسلسلية، إذا كان الوكيل لديه `allow_delegation` مُعيّن إلى `True`، يمكنه تفويض المهام إلى وكلاء آخرين في الطاقم.
يتم إعداد هذه الميزة تلقائياً عندما يكون هناك عدة وكلاء في الطاقم.
### التنفيذ غير المتزامن
يمكن تنفيذ المهام بشكل غير متزامن، مما يسمح بالمعالجة المتوازية عند الاقتضاء.
لإنشاء مهمة غير متزامنة، عيّن `async_execution=True` عند تعريف المهمة.
### الذاكرة والتخزين المؤقت
يدعم CrewAI كلاً من ميزتي الذاكرة والتخزين المؤقت:
- **الذاكرة**: فعّلها بتعيين `memory=True` عند إنشاء الطاقم. يتيح هذا للوكلاء الاحتفاظ بالمعلومات عبر المهام.
- **التخزين المؤقت**: افتراضياً، التخزين المؤقت مفعّل. عيّن `cache=False` لتعطيله.
### دوال الاستدعاء الراجع
يمكنك تعيين دوال استدعاء راجع على مستوى المهمة والخطوة:
- `task_callback`: يُنفذ بعد إكمال كل مهمة.
- `step_callback`: يُنفذ بعد كل خطوة في تنفيذ الوكيل.
### مقاييس الاستخدام
يتتبع CrewAI استخدام الرموز عبر جميع المهام والوكلاء. يمكنك الوصول إلى هذه المقاييس بعد التنفيذ.
## أفضل الممارسات للعمليات التسلسلية
1. **الترتيب مهم**: رتّب المهام بتسلسل منطقي حيث تبني كل مهمة على سابقتها.
2. **أوصاف مهام واضحة**: قدم أوصافاً مفصلة لكل مهمة لتوجيه الوكلاء بفعالية.
3. **اختيار الوكيل المناسب**: طابق مهارات وأدوار الوكلاء مع متطلبات كل مهمة.
4. **استخدم السياق**: استفد من سياق المهام السابقة لإبلاغ المهام اللاحقة.
يضمن هذا التوثيق المحدث أن التفاصيل تعكس بدقة أحدث التغييرات في قاعدة الكود وتصف بوضوح كيفية الاستفادة من الميزات والإعدادات الجديدة.
تم الحفاظ على بساطة المحتوى ومباشرته لضمان سهولة الفهم.

Some files were not shown because too many files have changed in this diff Show More