- 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
* 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.
* 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>
* 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
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>
* 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>
* 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>
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>
- 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.
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.
* 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>
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.
* 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
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.
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.
* 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>
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.
- 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
* 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>
* 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>
- 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>
