Compare commits

...

59 Commits

Author SHA1 Message Date
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
Vulnerability Scan / pip-audit (push) Has been cancelled
Mark stale issues and pull requests / stale (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
218 changed files with 15477 additions and 3823 deletions

View File

@@ -6,7 +6,24 @@ permissions:
contents: read
jobs:
lint:
changes:
name: Detect changes
runs-on: ubuntu-latest
outputs:
code: ${{ steps.filter.outputs.code }}
steps:
- uses: actions/checkout@v4
- uses: dorny/paths-filter@v3
id: filter
with:
filters: |
code:
- '!docs/**'
- '!**/*.md'
lint-run:
needs: changes
if: needs.changes.outputs.code == 'true'
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
@@ -48,3 +65,23 @@ jobs:
~/.local/share/uv
.venv
key: uv-main-py3.11-${{ 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

View File

@@ -6,8 +6,25 @@ permissions:
contents: read
jobs:
tests:
changes:
name: Detect changes
runs-on: ubuntu-latest
outputs:
code: ${{ steps.filter.outputs.code }}
steps:
- uses: actions/checkout@v4
- uses: dorny/paths-filter@v3
id: filter
with:
filters: |
code:
- '!docs/**'
- '!**/*.md'
tests-matrix:
name: tests (${{ matrix.python-version }})
needs: changes
if: needs.changes.outputs.code == 'true'
runs-on: ubuntu-latest
timeout-minutes: 15
strategy:
@@ -98,3 +115,23 @@ jobs:
~/.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: ${{ steps.filter.outputs.code }}
steps:
- uses: actions/checkout@v4
- uses: dorny/paths-filter@v3
id: filter
with:
filters: |
code:
- '!docs/**'
- '!**/*.md'
type-checker-matrix:
name: type-checker (${{ matrix.python-version }})
needs: changes
if: needs.changes.outputs.code == 'true'
runs-on: ubuntu-latest
strategy:
fail-fast: false
@@ -57,14 +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

@@ -24,6 +24,14 @@ repos:
rev: 0.11.3
hooks:
- id: uv-lock
- repo: local
hooks:
- id: pip-audit
name: pip-audit
entry: bash -c 'source .venv/bin/activate && uv run pip-audit --skip-editable --ignore-vuln CVE-2025-69872 --ignore-vuln CVE-2026-25645 --ignore-vuln CVE-2026-27448 --ignore-vuln CVE-2026-27459 --ignore-vuln PYSEC-2023-235' --
language: system
pass_filenames: false
stages: [pre-push, manual]
- repo: https://github.com/commitizen-tools/commitizen
rev: v4.10.1
hooks:

View File

@@ -4,6 +4,224 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
icon: "clock"
mode: "wide"
---
<Update label="13 أبريل 2026">
## v1.14.2a3
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a3)
## ما الذي تغير
### الميزات
- إضافة واجهة سطر الأوامر للتحقق من النشر
- تحسين سهولة استخدام تهيئة LLM
### إصلاحات الأخطاء
- تجاوز pypdf و uv إلى إصدارات مصححة لـ CVE-2026-40260 و GHSA-pjjw-68hj-v9mw
- ترقية requests إلى >=2.33.0 لمعالجة ثغرة ملف مؤقت CVE
- الحفاظ على معلمات استدعاء أداة Bedrock من خلال إزالة القيمة الافتراضية الصحيحة
- تنظيف مخططات الأدوات لوضع صارم
- إصلاح اختبار تسلسل تضمين MemoryRecord
### الوثائق
- تنظيف لغة A2A الخاصة بالمؤسسات
- إضافة وثائق ميزات A2A الخاصة بالمؤسسات
- تحديث وثائق A2A الخاصة بالمصادر المفتوحة
- تحديث سجل التغييرات والإصدار لـ v1.14.2a2
## المساهمون
@Yanhu007, @greysonlalonde
</Update>
<Update label="10 أبريل 2026">
## v1.14.2a2
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a2)
## ما الذي تغير
### الميزات
- إضافة واجهة مستخدم نصية لنقطة التحقق مع عرض شجري، ودعم التفرع، ومدخلات/مخرجات قابلة للتعديل
- إثراء تتبع رموز LLM مع رموز الاستدلال ورموز إنشاء التخزين المؤقت
- إضافة معلمة `from_checkpoint` إلى طرق الانطلاق
- تضمين `crewai_version` في نقاط التحقق مع إطار عمل الهجرة
- إضافة تفرع نقاط التحقق مع تتبع السلالة
### إصلاحات الأخطاء
- إصلاح توجيه الوضع الصارم إلى مزودي Anthropic وBedrock
- تعزيز NL2SQLTool مع وضع القراءة فقط الافتراضي، والتحقق من الاستعلامات، والاستعلامات المعلمة
### الوثائق
- تحديث سجل التغييرات والإصدار لـ v1.14.2a1
## المساهمون
@alex-clawd, @github-actions[bot], @greysonlalonde, @lucasgomide
</Update>
<Update label="9 أبريل 2026">
## v1.14.2a1
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a1)
## ما الذي تغير
### إصلاحات الأخطاء
- إصلاح إصدار حدث flow_finished بعد استئناف HITL
- إصلاح إصدار التشفير إلى 46.0.7 لمعالجة CVE-2026-39892
### إعادة هيكلة
- إعادة هيكلة لاستخدام I18N_DEFAULT المشترك
### الوثائق
- تحديث سجل التغييرات والإصدار لـ v1.14.1
## المساهمون
@greysonlalonde
</Update>
<Update label="9 أبريل 2026">
## v1.14.1
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.1)
## ما الذي تغير
### الميزات
- إضافة متصفح TUI لنقاط التفتيش غير المتزامنة
- إضافة دالة aclose()/close() ومدير سياق غير متزامن لمخرجات البث
### إصلاحات الأخطاء
- إصلاح التعبير النمطي لزيادة إصدار pyproject.toml
- تنظيف أسماء الأدوات في مرشحات زخرفة الخطاف
- إصلاح تسجيل معالجات نقاط التفتيش عند إنشاء CheckpointConfig
- رفع إصدار transformers إلى 5.5.0 لحل CVE-2026-1839
- إزالة غلاف FilteredStream لـ stdout/stderr
### الوثائق
- تحديث سجل التغييرات والإصدار لـ v1.14.1rc1
### إعادة الهيكلة
- استبدال القائمة المحظورة الثابتة باستبعاد حقل BaseTool الديناميكي في توليد المواصفات
- استبدال التعبير النمطي بـ tomlkit في واجهة سطر أوامر أدوات التطوير
- استخدام كائن PRINTER المشترك
- جعل BaseProvider نموذجاً أساسياً مع مميز نوع المزود
## المساهمون
@greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay
</Update>
<Update label="9 أبريل 2026">
## v1.14.1rc1
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.1rc1)
## ما الذي تغير
### الميزات
- إضافة متصفح TUI لنقطة التحقق غير المتزامنة
- إضافة aclose()/close() ومدير سياق غير متزامن لمخرجات البث
### إصلاحات الأخطاء
- إصلاح زيادة إصدارات pyproject.toml باستخدام التعبيرات العادية
- تنظيف أسماء الأدوات في مرشحات ديكور المكونات
- زيادة إصدار transformers إلى 5.5.0 لحل CVE-2026-1839
- تسجيل معالجات نقطة التحقق عند إنشاء CheckpointConfig
### إعادة الهيكلة
- استبدال القائمة المحظورة الثابتة باستبعاد حقل BaseTool الديناميكي في توليد المواصفات
- استبدال التعبيرات العادية بـ tomlkit في واجهة سطر الأوامر devtools
- استخدام كائن PRINTER المشترك
- جعل BaseProvider نموذجًا أساسيًا مع مميز نوع المزود
- إزالة غلاف stdout/stderr لـ FilteredStream
- إزالة flow/config.py غير المستخدمة
### الوثائق
- تحديث سجل التغييرات والإصدار لـ v1.14.0
## المساهمون
@greysonlalonde, @iris-clawd, @joaomdmoura
</Update>
<Update label="7 أبريل 2026">
## v1.14.0
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.0)
## ما الذي تغير
### الميزات
- إضافة أوامر CLI لقائمة/معلومات نقاط التحقق
- إضافة guardrail_type و name لتمييز التتبع
- إضافة SqliteProvider لتخزين نقاط التحقق
- إضافة CheckpointConfig للتسجيل التلقائي لنقاط التحقق
- تنفيذ تسجيل حالة وقت التشغيل، نظام الأحداث، وإعادة هيكلة المنفذ
### إصلاحات الأخطاء
- إضافة حماية من SSRF وتجاوز المسار
- إضافة التحقق من المسار وعنوان URL لأدوات RAG
- استبعاد متجهات التضمين من تسلسل الذاكرة لتوفير الرموز
- التأكد من وجود دليل الإخراج قبل الكتابة في قالب التدفق
- رفع litellm إلى >=1.83.0 لمعالجة CVE-2026-35030
- إزالة حقل فهرسة SEO الذي يتسبب في عرض الصفحة العربية بشكل غير صحيح
### الوثائق
- تحديث سجل التغييرات والإصدار لـ v1.14.0
- تحديث أدلة البدء السريع والتثبيت لتحسين الوضوح
- إضافة قسم مزودي التخزين، تصدير JsonProvider
- إضافة دليل علامة AMP التدريبية
### إعادة الهيكلة
- تنظيف واجهة برمجة تطبيقات نقاط التحقق
- إزالة CodeInterpreterTool وإهمال معلمات تنفيذ الكود
## المساهمون
@alex-clawd, @github-actions[bot], @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide
</Update>
<Update label="7 أبريل 2026">
## v1.14.0a4
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.0a4)
## ما الذي تغير
### الميزات
- إضافة guardrail_type و name لتمييز الآثار
- إضافة SqliteProvider لتخزين نقاط التحقق
- إضافة CheckpointConfig للتخزين التلقائي لنقاط التحقق
- تنفيذ نقاط التحقق لحالة التشغيل، نظام الأحداث، وإعادة هيكلة المنفذ
### إصلاحات الأخطاء
- استبعاد متجهات التضمين من تسلسل الذاكرة لتوفير الرموز
- رفع litellm إلى >=1.83.0 لمعالجة CVE-2026-35030
### الوثائق
- تحديث أدلة البدء السريع والتثبيت لتحسين الوضوح
- إضافة قسم مقدمي التخزين وتصدير JsonProvider
### الأداء
- استخدام JSONB لعمود بيانات نقاط التحقق
### إعادة الهيكلة
- إزالة CodeInterpreterTool وإهمال معلمات تنفيذ الكود
## المساهمون
@alex-clawd, @github-actions[bot], @greysonlalonde, @joaomdmoura, @lorenzejay, @lucasgomide
</Update>
<Update label="6 أبريل 2026">
## v1.14.0a3

View File

@@ -250,16 +250,12 @@ analysis_agent = Agent(
#### تنفيذ الكود
- `allow_code_execution`: يجب أن يكون True لتشغيل الكود
- `code_execution_mode`:
- `"safe"`: يستخدم Docker (موصى به للإنتاج)
- `"unsafe"`: تنفيذ مباشر (استخدم فقط في بيئات موثوقة)
<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>
<Note>
يشغّل هذا صورة Docker افتراضية. إذا أردت تهيئة صورة Docker،
راجع أداة Code Interpreter في قسم الأدوات. أضف أداة
مفسر الكود كأداة في معامل أداة الوكيل.
</Note>
- `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
@@ -332,9 +328,9 @@ print(result.raw)
### الأمان وتنفيذ الكود
- عند استخدام `allow_code_execution`، كن حذرًا مع مدخلات المستخدم وتحقق منها دائمًا
- استخدم `code_execution_mode: "safe"` (Docker) في بيئات الإنتاج
- فكّر في تعيين حدود `max_execution_time` مناسبة لمنع الحلقات اللانهائية
<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

View File

@@ -39,7 +39,7 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./my_checkpoints",
location="./my_checkpoints",
on_events=["task_completed", "crew_kickoff_completed"],
max_checkpoints=5,
),
@@ -50,7 +50,7 @@ crew = Crew(
| الحقل | النوع | الافتراضي | الوصف |
|:------|:------|:----------|:------|
| `directory` | `str` | `"./.checkpoints"` | مسار ملفات نقاط الحفظ |
| `location` | `str` | `"./.checkpoints"` | مسار ملفات نقاط الحفظ |
| `on_events` | `list[str]` | `["task_completed"]` | انواع الاحداث التي تطلق نقطة حفظ |
| `provider` | `BaseProvider` | `JsonProvider()` | واجهة التخزين |
| `max_checkpoints` | `int \| None` | `None` | الحد الاقصى للملفات؛ يتم حذف الاقدم اولا |
@@ -95,7 +95,7 @@ result = crew.kickoff() # يستأنف من اخر مهمة مكتملة
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, write_task, review_task],
checkpoint=CheckpointConfig(directory="./crew_cp"),
checkpoint=CheckpointConfig(location="./crew_cp"),
)
```
@@ -118,7 +118,7 @@ class MyFlow(Flow):
flow = MyFlow(
checkpoint=CheckpointConfig(
directory="./flow_cp",
location="./flow_cp",
on_events=["method_execution_finished"],
),
)
@@ -137,7 +137,7 @@ agent = Agent(
goal="Research topics",
backstory="Expert researcher",
checkpoint=CheckpointConfig(
directory="./agent_cp",
location="./agent_cp",
on_events=["lite_agent_execution_completed"],
),
)
@@ -160,7 +160,7 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./my_checkpoints",
location="./my_checkpoints",
provider=JsonProvider(),
max_checkpoints=5,
),
@@ -179,15 +179,12 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./.checkpoints.db",
provider=SqliteProvider(max_checkpoints=50),
location="./.checkpoints.db",
provider=SqliteProvider(),
),
)
```
<Note>
عند استخدام `SqliteProvider`، حقل `directory` هو مسار ملف قاعدة البيانات، وليس مجلدا.
</Note>
## انواع الاحداث

View File

@@ -325,6 +325,34 @@ asyncio.run(interactive_research())
- **تجربة المستخدم**: تقليل زمن الاستجابة المتصور بعرض نتائج تدريجية
- **لوحات المعلومات الحية**: بناء واجهات مراقبة تعرض حالة تنفيذ الطاقم
## الإلغاء وتنظيف الموارد
يدعم `CrewStreamingOutput` الإلغاء السلس بحيث يتوقف العمل الجاري فوراً عند انقطاع اتصال المستهلك.
### مدير السياق غير المتزامن
```python Code
streaming = await crew.akickoff(inputs={"topic": "AI"})
async with streaming:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
```
### الإلغاء الصريح
```python Code
streaming = await crew.akickoff(inputs={"topic": "AI"})
try:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
finally:
await streaming.aclose() # غير متزامن
# streaming.close() # المكافئ المتزامن
```
بعد الإلغاء، يكون كل من `streaming.is_cancelled` و `streaming.is_completed` بقيمة `True`. كل من `aclose()` و `close()` متساويان القوة.
## ملاحظات مهمة
- يفعّل البث تلقائياً بث LLM لجميع الوكلاء في الطاقم

View File

@@ -420,6 +420,34 @@ except Exception as e:
print("Streaming completed but flow encountered an error")
```
## الإلغاء وتنظيف الموارد
يدعم `FlowStreamingOutput` الإلغاء السلس بحيث يتوقف العمل الجاري فوراً عند انقطاع اتصال المستهلك.
### مدير السياق غير المتزامن
```python Code
streaming = await flow.kickoff_async()
async with streaming:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
```
### الإلغاء الصريح
```python Code
streaming = await flow.kickoff_async()
try:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
finally:
await streaming.aclose() # غير متزامن
# streaming.close() # المكافئ المتزامن
```
بعد الإلغاء، يكون كل من `streaming.is_cancelled` و `streaming.is_completed` بقيمة `True`. كل من `aclose()` و `close()` متساويان القوة.
## ملاحظات مهمة
- يفعّل البث تلقائياً بث LLM لأي أطقم مستخدمة داخل التدفق

50
docs/ar/skills.mdx Normal file
View File

@@ -0,0 +1,50 @@
---
title: Skills
description: ثبّت crewaiinc/skills من السجل الرسمي على skills.sh—Flows وCrews ووكلاء مرتبطون بالوثائق لـ Claude Code وCursor وCodex وغيرها.
icon: wand-magic-sparkles
mode: "wide"
---
# Skills
**امنح وكيل البرمجة سياق CrewAI في أمر واحد.**
تُنشر **Skills** الخاصة بـ CrewAI على **[skills.sh/crewaiinc/skills](https://skills.sh/crewaiinc/skills)**—السجل الرسمي لـ `crewaiinc/skills`، بما في ذلك كل مهارة (مثل **design-agent** و**getting-started** و**design-task** و**ask-docs**) وإحصاءات التثبيت والتدقيقات. تعلّم وكلاء البرمجة—مثل Claude Code وCursor وCodex—هيكلة Flows وضبط Crews واستخدام الأدوات واتباع أنماط CrewAI. نفّذ الأمر أدناه (أو الصقه في الوكيل).
```shell Terminal
npx skills add crewaiinc/skills
```
يضيف ذلك حزمة المهارات إلى سير عمل الوكيل لتطبيق اتفاقيات CrewAI دون إعادة شرح الإطار في كل جلسة. المصدر والقضايا على [GitHub](https://github.com/crewAIInc/skills).
## ما يحصل عليه الوكيل
- **Flows** — تطبيقات ذات حالة وخطوات وkickoffs للـ crew على نمط CrewAI
- **Crews والوكلاء** — أنماط YAML أولاً، أدوار، مهام، وتفويض
- **الأدوات والتكاملات** — ربط الوكلاء بالبحث وواجهات API وأدوات CrewAI الشائعة
- **هيكل المشروع** — مواءمة مع قوالب CLI واتفاقيات المستودع
- **أنماط محدثة** — تتبع المهارات وثائق CrewAI والممارسات الموصى بها
## تعرّف أكثر على هذا الموقع
<CardGroup cols={2}>
<Card title="أدوات البرمجة و AGENTS.md" icon="terminal" href="/ar/guides/coding-tools/agents-md">
استخدام `AGENTS.md` وسير عمل وكلاء البرمجة مع CrewAI.
</Card>
<Card title="البداية السريعة" icon="rocket" href="/ar/quickstart">
ابنِ أول Flow وcrew من البداية للنهاية.
</Card>
<Card title="التثبيت" icon="download" href="/ar/installation">
ثبّت CrewAI CLI وحزمة Python.
</Card>
<Card title="سجل Skills (skills.sh)" icon="globe" href="https://skills.sh/crewaiinc/skills">
القائمة الرسمية لـ `crewaiinc/skills`—المهارات والتثبيتات والتدقيقات.
</Card>
<Card title="المصدر على GitHub" icon="code-branch" href="https://github.com/crewAIInc/skills">
مصدر الحزمة والتحديثات والقضايا.
</Card>
</CardGroup>
### فيديو: CrewAI مع مهارات وكلاء البرمجة
<iframe src="https://www.loom.com/embed/befb9f68b81f42ad8112bfdd95a780af" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style={{ width: "100%", height: "400px" }} />

View File

@@ -7,6 +7,10 @@ mode: "wide"
# `CodeInterpreterTool`
<Warning>
**مهجور:** تمت إزالة `CodeInterpreterTool` من `crewai-tools`. كما أن معاملَي `allow_code_execution` و`code_execution_mode` على `Agent` أصبحا مهجورَين. استخدم خدمة بيئة معزولة مخصصة — [E2B](https://e2b.dev) أو [Modal](https://modal.com) — لتنفيذ الكود بشكل آمن ومعزول.
</Warning>
## الوصف
تمكّن `CodeInterpreterTool` وكلاء CrewAI من تنفيذ كود Python 3 الذي يولّدونه بشكل مستقل. هذه الوظيفة ذات قيمة خاصة لأنها تتيح للوكلاء إنشاء الكود وتنفيذه والحصول على النتائج واستخدام تلك المعلومات لاتخاذ القرارات والإجراءات اللاحقة.

View File

@@ -11,7 +11,7 @@ mode: "wide"
يتيح ذلك سير عمل متعددة مثل أن يقوم وكيل بالوصول إلى قاعدة البيانات واسترجاع المعلومات بناءً على الهدف ثم استخدام تلك المعلومات لتوليد استجابة أو تقرير أو أي مخرجات أخرى. بالإضافة إلى ذلك، يوفر القدرة للوكيل على تحديث قاعدة البيانات بناءً على هدفه.
**تنبيه**: تأكد من أن الوكيل لديه وصول إلى نسخة قراءة فقط أو أنه من المقبول أن يقوم الوكيل بتنفيذ استعلامات إدراج/تحديث على قاعدة البيانات.
**تنبيه**: الأداة للقراءة فقط بشكل افتراضي (SELECT/SHOW/DESCRIBE/EXPLAIN فقط). تتطلب عمليات الكتابة تمرير `allow_dml=True` أو ضبط متغير البيئة `CREWAI_NL2SQL_ALLOW_DML=true`. عند تفعيل الكتابة، تأكد من أن الوكيل يستخدم مستخدم قاعدة بيانات محدود الصلاحيات أو نسخة قراءة كلما أمكن.
## نموذج الأمان
@@ -36,6 +36,74 @@ mode: "wide"
- أضف خطافات `before_tool_call` لفرض أنماط الاستعلام المسموح بها
- فعّل تسجيل الاستعلامات والتنبيهات للعبارات التدميرية
## وضع القراءة فقط وتهيئة DML
تعمل `NL2SQLTool` في **وضع القراءة فقط بشكل افتراضي**. لا يُسمح إلا بأنواع العبارات التالية دون تهيئة إضافية:
- `SELECT`
- `SHOW`
- `DESCRIBE`
- `EXPLAIN`
أي محاولة لتنفيذ عملية كتابة (`INSERT`، `UPDATE`، `DELETE`، `DROP`، `CREATE`، `ALTER`، `TRUNCATE`، إلخ) ستُسبب خطأً ما لم يتم تفعيل DML صراحةً.
كما تُحظر الاستعلامات متعددة العبارات التي تحتوي على فاصلة منقوطة (مثل `SELECT 1; DROP TABLE users`) في وضع القراءة فقط لمنع هجمات الحقن.
### تفعيل عمليات الكتابة
يمكنك تفعيل DML (لغة معالجة البيانات) بطريقتين:
**الخيار الأول — معامل المُنشئ:**
```python
from crewai_tools import NL2SQLTool
nl2sql = NL2SQLTool(
db_uri="postgresql://example@localhost:5432/test_db",
allow_dml=True,
)
```
**الخيار الثاني — متغير البيئة:**
```bash
CREWAI_NL2SQL_ALLOW_DML=true
```
```python
from crewai_tools import NL2SQLTool
# DML مفعّل عبر متغير البيئة
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
```
### أمثلة الاستخدام
**القراءة فقط (الافتراضي) — آمن للتحليلات والتقارير:**
```python
from crewai_tools import NL2SQLTool
# يُسمح فقط بـ SELECT/SHOW/DESCRIBE/EXPLAIN
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
```
**مع تفعيل DML — مطلوب لأعباء عمل الكتابة:**
```python
from crewai_tools import NL2SQLTool
# يُسمح بـ INSERT وUPDATE وDELETE وDROP وغيرها
nl2sql = NL2SQLTool(
db_uri="postgresql://example@localhost:5432/test_db",
allow_dml=True,
)
```
<Warning>
يمنح تفعيل DML للوكيل القدرة على تعديل البيانات أو حذفها. لا تفعّله إلا عندما يتطلب حالة الاستخدام صراحةً وصولاً للكتابة، وتأكد من أن بيانات اعتماد قاعدة البيانات محدودة بالحد الأدنى من الصلاحيات المطلوبة.
</Warning>
## المتطلبات
- SqlAlchemy

View File

@@ -74,3 +74,19 @@ tool = CSVSearchTool(
}
)
```
## الأمان
### التحقق من صحة المسارات
يتم التحقق من مسارات الملفات المقدمة لهذه الأداة مقابل مجلد العمل الحالي. يتم رفض المسارات التي تحل خارج مجلد العمل وإطلاق `ValueError`.
للسماح بالمسارات خارج مجلد العمل (مثلاً في الاختبارات أو خطوط الأنابيب الموثوقة)، عيّن متغير البيئة التالي:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### التحقق من صحة الروابط
يتم التحقق من مدخلات الروابط: يتم حظر مخطط `file://` والطلبات التي تستهدف نطاقات IP الخاصة أو المحجوزة لمنع هجمات تزوير الطلبات من جانب الخادم (SSRF).

View File

@@ -68,3 +68,15 @@ tool = DirectorySearchTool(
}
)
```
## الأمان
### التحقق من صحة المسارات
يتم التحقق من مسارات المجلدات المقدمة لهذه الأداة مقابل مجلد العمل الحالي. يتم رفض المسارات التي تحل خارج مجلد العمل وإطلاق `ValueError`.
للسماح بالمسارات خارج مجلد العمل (مثلاً في الاختبارات أو خطوط الأنابيب الموثوقة)، عيّن متغير البيئة التالي:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```

View File

@@ -73,3 +73,19 @@ tool = JSONSearchTool(
}
)
```
## الأمان
### التحقق من صحة المسارات
يتم التحقق من مسارات الملفات المقدمة لهذه الأداة مقابل مجلد العمل الحالي. يتم رفض المسارات التي تحل خارج مجلد العمل وإطلاق `ValueError`.
للسماح بالمسارات خارج مجلد العمل (مثلاً في الاختبارات أو خطوط الأنابيب الموثوقة)، عيّن متغير البيئة التالي:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### التحقق من صحة الروابط
يتم التحقق من مدخلات الروابط: يتم حظر مخطط `file://` والطلبات التي تستهدف نطاقات IP الخاصة أو المحجوزة لمنع هجمات تزوير الطلبات من جانب الخادم (SSRF).

View File

@@ -105,3 +105,19 @@ tool = PDFSearchTool(
}
)
```
## الأمان
### التحقق من صحة المسارات
يتم التحقق من مسارات الملفات المقدمة لهذه الأداة مقابل مجلد العمل الحالي. يتم رفض المسارات التي تحل خارج مجلد العمل وإطلاق `ValueError`.
للسماح بالمسارات خارج مجلد العمل (مثلاً في الاختبارات أو خطوط الأنابيب الموثوقة)، عيّن متغير البيئة التالي:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### التحقق من صحة الروابط
يتم التحقق من مدخلات الروابط: يتم حظر مخطط `file://` والطلبات التي تستهدف نطاقات IP الخاصة أو المحجوزة لمنع هجمات تزوير الطلبات من جانب الخادم (SSRF).

File diff suppressed because it is too large Load Diff

View File

@@ -4,6 +4,224 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
icon: "clock"
mode: "wide"
---
<Update label="Apr 13, 2026">
## v1.14.2a3
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a3)
## What's Changed
### Features
- Add deploy validation CLI
- Improve LLM initialization ergonomics
### Bug Fixes
- Override pypdf and uv to patched versions for CVE-2026-40260 and GHSA-pjjw-68hj-v9mw
- Upgrade requests to >=2.33.0 for CVE temp file vulnerability
- Preserve Bedrock tool call arguments by removing truthy default
- Sanitize tool schemas for strict mode
- Deflake MemoryRecord embedding serialization test
### Documentation
- Clean up enterprise A2A language
- Add enterprise A2A feature documentation
- Update OSS A2A documentation
- Update changelog and version for v1.14.2a2
## Contributors
@Yanhu007, @greysonlalonde
</Update>
<Update label="Apr 10, 2026">
## v1.14.2a2
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a2)
## What's Changed
### Features
- Add checkpoint TUI with tree view, fork support, and editable inputs/outputs
- Enrich LLM token tracking with reasoning tokens and cache creation tokens
- Add `from_checkpoint` parameter to kickoff methods
- Embed `crewai_version` in checkpoints with migration framework
- Add checkpoint forking with lineage tracking
### Bug Fixes
- Fix strict mode forwarding to Anthropic and Bedrock providers
- Harden NL2SQLTool with read-only default, query validation, and parameterized queries
### Documentation
- Update changelog and version for v1.14.2a1
## Contributors
@alex-clawd, @github-actions[bot], @greysonlalonde, @lucasgomide
</Update>
<Update label="Apr 09, 2026">
## v1.14.2a1
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a1)
## What's Changed
### Bug Fixes
- Fix emission of flow_finished event after HITL resume
- Fix cryptography version to 46.0.7 to address CVE-2026-39892
### Refactoring
- Refactor to use shared I18N_DEFAULT singleton
### Documentation
- Update changelog and version for v1.14.1
## Contributors
@greysonlalonde
</Update>
<Update label="Apr 09, 2026">
## v1.14.1
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.1)
## What's Changed
### Features
- Add async checkpoint TUI browser
- Add aclose()/close() and async context manager to streaming outputs
### Bug Fixes
- Fix regex for template pyproject.toml version bumps
- Sanitize tool names in hook decorator filters
- Fix checkpoint handlers registration when CheckpointConfig is created
- Bump transformers to 5.5.0 to resolve CVE-2026-1839
- Remove FilteredStream stdout/stderr wrapper
### Documentation
- Update changelog and version for v1.14.1rc1
### Refactoring
- Replace hardcoded denylist with dynamic BaseTool field exclusion in spec gen
- Replace regex with tomlkit in devtools CLI
- Use shared PRINTER singleton
- Make BaseProvider a BaseModel with provider_type discriminator
## Contributors
@greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay
</Update>
<Update label="Apr 09, 2026">
## v1.14.1rc1
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.1rc1)
## What's Changed
### Features
- Add async checkpoint TUI browser
- Add aclose()/close() and async context manager to streaming outputs
### Bug Fixes
- Fix template pyproject.toml version bumps using regex
- Sanitize tool names in hook decorator filters
- Bump transformers to 5.5.0 to resolve CVE-2026-1839
- Register checkpoint handlers when CheckpointConfig is created
### Refactoring
- Replace hardcoded denylist with dynamic BaseTool field exclusion in spec gen
- Replace regex with tomlkit in devtools CLI
- Use shared PRINTER singleton
- Make BaseProvider a BaseModel with provider_type discriminator
- Remove FilteredStream stdout/stderr wrapper
- Remove unused flow/config.py
### Documentation
- Update changelog and version for v1.14.0
## Contributors
@greysonlalonde, @iris-clawd, @joaomdmoura
</Update>
<Update label="Apr 07, 2026">
## v1.14.0
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.0)
## What's Changed
### Features
- Add checkpoint list/info CLI commands
- Add guardrail_type and name to distinguish traces
- Add SqliteProvider for checkpoint storage
- Add CheckpointConfig for automatic checkpointing
- Implement runtime state checkpointing, event system, and executor refactor
### Bug Fixes
- Add SSRF and path traversal protections
- Add path and URL validation to RAG tools
- Exclude embedding vectors from memory serialization to save tokens
- Ensure output directory exists before writing in flow template
- Bump litellm to >=1.83.0 to address CVE-2026-35030
- Remove SEO indexing field causing Arabic page rendering
### Documentation
- Update changelog and version for v1.14.0
- Update quickstart and installation guides for improved clarity
- Add storage providers section, export JsonProvider
- Add AMP Training Tab guide
### Refactoring
- Clean up checkpoint API
- Remove CodeInterpreterTool and deprecate code execution parameters
## Contributors
@alex-clawd, @github-actions[bot], @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide
</Update>
<Update label="Apr 07, 2026">
## v1.14.0a4
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.0a4)
## What's Changed
### Features
- Add guardrail_type and name to distinguish traces
- Add SqliteProvider for checkpoint storage
- Add CheckpointConfig for automatic checkpointing
- Implement runtime state checkpointing, event system, and executor refactor
### Bug Fixes
- Exclude embedding vectors from memory serialization to save tokens
- Bump litellm to >=1.83.0 to address CVE-2026-35030
### Documentation
- Update quickstart and installation guides for improved clarity
- Add storage providers section and export JsonProvider
### Performance
- Use JSONB for checkpoint data column
### Refactoring
- Remove CodeInterpreterTool and deprecate code execution params
## Contributors
@alex-clawd, @github-actions[bot], @greysonlalonde, @joaomdmoura, @lorenzejay, @lucasgomide
</Update>
<Update label="Apr 06, 2026">
## v1.14.0a3

View File

@@ -308,16 +308,12 @@ multimodal_agent = Agent(
#### Code Execution
- `allow_code_execution`: Must be True to run code
- `code_execution_mode`:
- `"safe"`: Uses Docker (recommended for production)
- `"unsafe"`: Direct execution (use only in trusted environments)
<Warning>
`allow_code_execution` and `code_execution_mode` are deprecated. `CodeInterpreterTool` has been removed from `crewai-tools`. Use a dedicated sandbox service such as [E2B](https://e2b.dev) or [Modal](https://modal.com) for secure code execution.
</Warning>
<Note>
This runs a default Docker image. If you want to configure the docker image,
the checkout the Code Interpreter Tool in the tools section. Add the code
interpreter tool as a tool in the agent as a tool parameter.
</Note>
- `allow_code_execution` _(deprecated)_: Previously enabled built-in code execution via `CodeInterpreterTool`.
- `code_execution_mode` _(deprecated)_: Previously controlled execution mode (`"safe"` for Docker, `"unsafe"` for direct execution).
#### Advanced Features
@@ -667,9 +663,9 @@ asyncio.run(main())
### Security and Code Execution
- When using `allow_code_execution`, be cautious with user input and always validate it
- Use `code_execution_mode: "safe"` (Docker) in production environments
- Consider setting appropriate `max_execution_time` limits to prevent infinite loops
<Warning>
`allow_code_execution` and `code_execution_mode` are deprecated and `CodeInterpreterTool` has been removed. Use a dedicated sandbox service such as [E2B](https://e2b.dev) or [Modal](https://modal.com) for secure code execution.
</Warning>
### Performance Optimization

View File

@@ -39,7 +39,7 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./my_checkpoints",
location="./my_checkpoints",
on_events=["task_completed", "crew_kickoff_completed"],
max_checkpoints=5,
),
@@ -50,10 +50,11 @@ crew = Crew(
| Field | Type | Default | Description |
|:------|:-----|:--------|:------------|
| `directory` | `str` | `"./.checkpoints"` | Filesystem path for checkpoint files |
| `location` | `str` | `"./.checkpoints"` | Storage destination — a directory for `JsonProvider`, a database file path for `SqliteProvider` |
| `on_events` | `list[str]` | `["task_completed"]` | Event types that trigger a checkpoint |
| `provider` | `BaseProvider` | `JsonProvider()` | Storage backend |
| `max_checkpoints` | `int \| None` | `None` | Max files to keep; oldest pruned first |
| `max_checkpoints` | `int \| None` | `None` | Max checkpoints to keep. Oldest are pruned after each write. Pruning is handled by the provider. |
| `restore_from` | `Path \| str \| None` | `None` | Path to a checkpoint to restore from. Used when passing config via a kickoff method's `from_checkpoint` parameter. |
### Inheritance and Opt-Out
@@ -79,13 +80,42 @@ crew = Crew(
## Resuming from a Checkpoint
Pass a `CheckpointConfig` with `restore_from` to any kickoff method. The crew restores from that checkpoint, skips completed tasks, and resumes.
```python
# Restore and resume
crew = Crew.from_checkpoint("./my_checkpoints/20260407T120000_abc123.json")
result = crew.kickoff() # picks up from last completed task
from crewai import Crew, CheckpointConfig
crew = Crew(agents=[...], tasks=[...])
result = crew.kickoff(
from_checkpoint=CheckpointConfig(
restore_from="./my_checkpoints/20260407T120000_abc123.json",
),
)
```
The restored crew skips already-completed tasks and resumes from the first incomplete one.
Remaining `CheckpointConfig` fields apply to the new run, so checkpointing continues after the restore.
You can also use the classmethod directly:
```python
config = CheckpointConfig(restore_from="./my_checkpoints/20260407T120000_abc123.json")
crew = Crew.from_checkpoint(config)
result = crew.kickoff()
```
## Forking from a Checkpoint
`fork()` restores a checkpoint and starts a new execution branch. Useful for exploring alternative paths from the same point.
```python
from crewai import Crew, CheckpointConfig
config = CheckpointConfig(restore_from="./my_checkpoints/20260407T120000_abc123.json")
crew = Crew.fork(config, branch="experiment-a")
result = crew.kickoff(inputs={"strategy": "aggressive"})
```
Each fork gets a unique lineage ID so checkpoints from different branches don't collide. The `branch` label is optional and auto-generated if omitted.
## Works on Crew, Flow, and Agent
@@ -95,7 +125,7 @@ The restored crew skips already-completed tasks and resumes from the first incom
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, write_task, review_task],
checkpoint=CheckpointConfig(directory="./crew_cp"),
checkpoint=CheckpointConfig(location="./crew_cp"),
)
```
@@ -118,14 +148,15 @@ class MyFlow(Flow):
flow = MyFlow(
checkpoint=CheckpointConfig(
directory="./flow_cp",
location="./flow_cp",
on_events=["method_execution_finished"],
),
)
result = flow.kickoff()
# Resume
flow = MyFlow.from_checkpoint("./flow_cp/20260407T120000_abc123.json")
config = CheckpointConfig(restore_from="./flow_cp/20260407T120000_abc123.json")
flow = MyFlow.from_checkpoint(config)
result = flow.kickoff()
```
@@ -137,7 +168,7 @@ agent = Agent(
goal="Research topics",
backstory="Expert researcher",
checkpoint=CheckpointConfig(
directory="./agent_cp",
location="./agent_cp",
on_events=["lite_agent_execution_completed"],
),
)
@@ -160,14 +191,14 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./my_checkpoints",
location="./my_checkpoints",
provider=JsonProvider(), # this is the default
max_checkpoints=5, # prunes oldest files
),
)
```
Files are named `<timestamp>_<uuid>.json` inside the directory.
Files are named `<timestamp>_<uuid>.json` inside the location directory.
### SqliteProvider
@@ -181,17 +212,14 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./.checkpoints.db",
provider=SqliteProvider(max_checkpoints=50),
location="./.checkpoints.db",
provider=SqliteProvider(),
max_checkpoints=50,
),
)
```
`SqliteProvider` accepts its own `max_checkpoints` parameter that prunes old rows via SQL. WAL journal mode is enabled for concurrent read access.
<Note>
When using `SqliteProvider`, the `directory` field is the database file path, not a directory. The `max_checkpoints` on `CheckpointConfig` controls filesystem pruning (for `JsonProvider`), while `SqliteProvider.max_checkpoints` controls row pruning in the database.
</Note>
WAL journal mode is enabled for concurrent read access.
## Event Types
@@ -234,3 +262,44 @@ async def on_llm_done_async(source, event, state):
The `state` argument is the `RuntimeState` passed automatically by the event bus when your handler accepts 3 parameters. You can register handlers on any event type listed in the [Event Listeners](/en/concepts/event-listener) documentation.
Checkpointing is best-effort: if a checkpoint write fails, the error is logged but execution continues uninterrupted.
## CLI
The `crewai checkpoint` command gives you a TUI for browsing, inspecting, resuming, and forking checkpoints. It auto-detects whether your checkpoints are JSON files or a SQLite database.
```bash
# Launch the TUI — auto-detects .checkpoints/ or .checkpoints.db
crewai checkpoint
# Point at a specific location
crewai checkpoint --location ./my_checkpoints
crewai checkpoint --location ./.checkpoints.db
```
<Frame>
<img src="/images/checkpointing.png" alt="Checkpoint TUI" />
</Frame>
The left panel is a tree view. Checkpoints are grouped by branch, and forks nest under the checkpoint they diverged from. Select a checkpoint to see its metadata, entity state, and task progress in the detail panel. Hit **Resume** to pick up where it left off, or **Fork** to start a new branch from that point.
### Editing inputs and task outputs
When a checkpoint is selected, the detail panel shows:
- **Inputs** — if the original kickoff had inputs (e.g. `{topic}`), they appear as editable fields pre-filled with the original values. Change them before resuming or forking.
- **Task outputs** — completed tasks show their output in editable text areas. Edit a task's output to change the context that downstream tasks receive. When you modify a task output and hit Fork, all subsequent tasks are invalidated and re-run with the new context.
This is useful for "what if" exploration — fork from a checkpoint, tweak a task's result, and see how it changes downstream behavior.
### Subcommands
```bash
# List all checkpoints
crewai checkpoint list ./my_checkpoints
# Inspect a specific checkpoint
crewai checkpoint info ./my_checkpoints/20260407T120000_abc123.json
# Inspect latest in a SQLite database
crewai checkpoint info ./.checkpoints.db
```

View File

@@ -0,0 +1,227 @@
---
title: A2A on AMP
description: Production-grade Agent-to-Agent communication with distributed state and multi-scheme authentication
icon: "network-wired"
mode: "wide"
---
<Warning>
A2A server agents on AMP are in early release. APIs may change in future versions.
</Warning>
## Overview
CrewAI AMP extends the open-source [A2A protocol implementation](/en/learn/a2a-agent-delegation) with production infrastructure for deploying distributed agents at scale. AMP supports A2A protocol versions 0.2 and 0.3. When you deploy a crew or agent with A2A server configuration to AMP, the platform automatically provisions distributed state management, authentication, multi-transport endpoints, and lifecycle management.
<Note>
For A2A protocol fundamentals, client/server configuration, and authentication schemes, see the [A2A Agent Delegation](/en/learn/a2a-agent-delegation) documentation. This page covers what AMP adds on top of the open-source implementation.
</Note>
### Usage
Add `A2AServerConfig` to any agent in your crew and deploy to AMP. The platform detects agents with server configuration and automatically registers A2A endpoints, generates agent cards, and provisions the infrastructure described below.
```python
from crewai import Agent, Crew, Task
from crewai.a2a import A2AServerConfig
from crewai.a2a.auth import EnterpriseTokenAuth
agent = Agent(
role="Data Analyst",
goal="Analyze datasets and provide insights",
backstory="Expert data scientist with statistical analysis skills",
llm="gpt-4o",
a2a=A2AServerConfig(
auth=EnterpriseTokenAuth()
)
)
task = Task(
description="Analyze the provided dataset",
expected_output="Statistical summary with key insights",
agent=agent
)
crew = Crew(agents=[agent], tasks=[task])
```
After [deploying to AMP](/en/enterprise/guides/deploy-to-amp), the platform registers two levels of A2A endpoints:
- **Crew-level**: an aggregate agent card at `/.well-known/agent-card.json` where each agent with `A2AServerConfig` is listed as a skill, with a JSON-RPC endpoint at `/a2a`
- **Per-agent**: isolated agent cards and JSON-RPC endpoints mounted at `/a2a/agents/{role}/`, each with its own tenancy
Clients can interact with the crew as a whole or target a specific agent directly. To route a request to a specific agent through the crew-level endpoint, include `"target_agent"` in the message metadata with the agent's slugified role name (e.g., `"data-analyst"` for an agent with role `"Data Analyst"`). If no `target_agent` is provided, the request is handled by the first agent in the crew.
See [A2A Agent Delegation](/en/learn/a2a-agent-delegation#server-configuration-options) for the full list of `A2AServerConfig` options.
<Warning>
Per the A2A protocol, agent cards are publicly accessible to enable discovery. This includes both the crew-level card at `/.well-known/agent-card.json` and per-agent cards at `/a2a/agents/{role}/.well-known/agent-card.json`. Do not include sensitive information in agent names, descriptions, or skill definitions.
</Warning>
### File Inputs and Structured Output
A2A on AMP supports passing files and requesting structured output in both directions. Clients can send files as `FilePart`s and request structured responses by embedding a JSON schema in the message. Server agents receive files as `input_files` on the task, and return structured data as `DataPart`s when a schema is provided. See [File Inputs and Structured Output](/en/learn/a2a-agent-delegation#file-inputs-and-structured-output) for details.
### What AMP Adds
<CardGroup cols={2}>
<Card title="Distributed State" icon="database">
Persistent task, context, and result storage
</Card>
<Card title="Enterprise Authentication" icon="shield-halved">
OIDC, OAuth2, mTLS, and Enterprise token validation beyond simple bearer tokens
</Card>
<Card title="gRPC Transport" icon="bolt">
Full gRPC server with TLS and authentication
</Card>
<Card title="Context Lifecycle" icon="clock-rotate-left">
Automatic idle detection, expiration, and cleanup of long-running conversations
</Card>
<Card title="Signed Webhooks" icon="signature">
HMAC-SHA256 signed push notifications with replay protection
</Card>
<Card title="Multi-Transport" icon="arrows-split-up-and-left">
REST, JSON-RPC, and gRPC endpoints served simultaneously from a single deployment
</Card>
</CardGroup>
---
## Distributed State Management
In the open-source implementation, task and context state lives in memory on a single process. AMP replaces this with persistent, distributed stores.
### Storage Layers
| Store | Purpose |
|---|---|
| **Task Store** | Persists A2A task state and metadata |
| **Context Store** | Tracks conversation context, creation time, last activity, and associated tasks |
| **Result Store** | Caches task results for retrieval |
| **Push Config Store** | Manages webhook subscriptions per task |
Multiple A2A deployments are automatically isolated from each other, preventing data collisions when sharing infrastructure.
---
## Enterprise Authentication
AMP supports six authentication schemes for incoming A2A requests, configurable per deployment. Authentication works across both HTTP and gRPC transports.
| Scheme | Description | Use Case |
|---|---|---|
| **SimpleTokenAuth** | Static bearer token from `AUTH_TOKEN` env var | Development, simple deployments |
| **EnterpriseTokenAuth** | Token verification via CrewAI PlusAPI with integration token claims | AMP-to-AMP agent communication |
| **OIDCAuth** | OpenID Connect JWT validation with JWKS endpoint caching | Enterprise SSO integration |
| **OAuth2ServerAuth** | OAuth2 with configurable scopes | Fine-grained access control |
| **APIKeyServerAuth** | API key validation via header or query parameter | Third-party integrations |
| **MTLSServerAuth** | Mutual TLS certificate-based authentication | Zero-trust environments |
The configured auth scheme automatically populates the agent card's `securitySchemes` and `security` fields. Clients discover authentication requirements by fetching the agent card before making requests.
---
## Extended Agent Cards
AMP supports role-based skill visibility through extended agent cards. Unauthenticated users see the standard agent card with public skills. Authenticated users receive an extended card with additional capabilities.
This enables patterns like:
- Public agents that expose basic skills to anyone, with advanced skills available to authenticated clients
- Internal agents that advertise different capabilities based on the caller's identity
---
## gRPC Transport
If enabled, AMP provides full gRPC support alongside the default JSON-RPC transport.
- **TLS termination** with configurable certificate and key paths
- **gRPC reflection** for debugging with tools like `grpcurl`
- **Authentication** using the same schemes available for HTTP
- **Extension validation** ensuring clients support required protocol extensions
- **Version negotiation** across A2A protocol versions 0.2 and 0.3
For deployments exposing multiple agents, AMP automatically allocates per-agent gRPC ports and coordinates TLS, startup, and shutdown across all servers.
---
## Context Lifecycle Management
AMP tracks the lifecycle of A2A conversation contexts and automatically manages cleanup.
### Lifecycle States
| State | Condition | Action |
|---|---|---|
| **Active** | Context has recent activity | None |
| **Idle** | No activity for a configured period | Marked idle, event emitted |
| **Expired** | Context exceeds its maximum lifetime | Marked expired, associated tasks cleaned up, event emitted |
A background cleanup task runs hourly to scan for idle and expired contexts. All state transitions emit CrewAI events that integrate with the platform's observability features.
---
## Signed Push Notifications
When an A2A agent sends push notifications to a client webhook, AMP signs each request with HMAC-SHA256 to ensure integrity and prevent tampering.
### Signature Headers
| Header | Purpose |
|---|---|
| `X-A2A-Signature` | HMAC-SHA256 signature in `sha256={hex_digest}` format |
| `X-A2A-Signature-Timestamp` | Unix timestamp bound to the signature |
| `X-A2A-Notification-Token` | Optional notification auth token |
### Security Properties
- **Integrity**: payload cannot be modified without invalidating the signature
- **Replay protection**: signatures are timestamp-bound with a configurable tolerance window
- **Retry with backoff**: failed deliveries retry with exponential backoff
---
## Distributed Event Streaming
In the open-source implementation, SSE streaming works within a single process. AMP propagates SSE events across instances so that clients receive updates even when the instance holding the streaming connection differs from the instance executing the task.
---
## Multi-Transport Endpoints
AMP serves REST and JSON-RPC by default. gRPC is available as an additional transport if enabled.
| Transport | Path Convention | Description |
|---|---|---|
| **REST** | `/v1/message:send`, `/v1/message:stream`, `/v1/tasks` | Google API conventions |
| **JSON-RPC** | Standard A2A JSON-RPC endpoint | Default A2A protocol transport |
| **gRPC** | Per-agent port allocation | Optional, high-performance binary protocol |
All active transports share the same authentication, version negotiation, and extension validation. Agent cards are generated from agent and crew metadata — roles, goals, and tools become skills and descriptions — and automatically include interfaces for each active transport. They can also be manually configured via `A2AServerConfig`.
---
## Version and Extension Negotiation
AMP validates A2A protocol versions and extensions at the transport layer.
### Version Negotiation
- Clients send the `A2A-Version` header with their preferred version
- AMP validates against supported versions (0.2, 0.3) and falls back to 0.3 if unspecified
- The negotiated version is returned in the response headers
### Extension Validation
- Clients declare supported extensions via the `X-A2A-Extensions` header
- AMP validates that clients support all extensions the agent requires
- Requests from clients missing required extensions receive an `UnsupportedExtensionError`
---
## Next Steps
- [A2A Agent Delegation](/en/learn/a2a-agent-delegation) — A2A protocol fundamentals and configuration
- [A2UI](/en/learn/a2ui) — Interactive UI rendering over A2A
- [Deploy to AMP](/en/enterprise/guides/deploy-to-amp) — General deployment guide
- [Webhook Streaming](/en/enterprise/features/webhook-streaming) — Event streaming for deployed automations

View File

@@ -7,6 +7,10 @@ mode: "wide"
## A2A Agent Delegation
<Info>
Deploying A2A agents to production? See [A2A on AMP](/en/enterprise/features/a2a) for distributed state, enterprise authentication, gRPC transport, and horizontal scaling.
</Info>
CrewAI treats [A2A protocol](https://a2a-protocol.org/latest/) as a first-class delegation primitive, enabling agents to delegate tasks, request information, and collaborate with remote agents, as well as act as A2A-compliant server agents.
In client mode, agents autonomously choose between local execution and remote delegation based on task requirements.
@@ -96,24 +100,28 @@ The `A2AClientConfig` class accepts the following parameters:
Update mechanism for receiving task status. Options: `StreamingConfig`, `PollingConfig`, or `PushNotificationConfig`.
</ParamField>
<ParamField path="transport_protocol" type="Literal['JSONRPC', 'GRPC', 'HTTP+JSON']" default="JSONRPC">
Transport protocol for A2A communication. Options: `JSONRPC` (default), `GRPC`, or `HTTP+JSON`.
</ParamField>
<ParamField path="accepted_output_modes" type="list[str]" default='["application/json"]'>
Media types the client can accept in responses.
</ParamField>
<ParamField path="supported_transports" type="list[str]" default='["JSONRPC"]'>
Ordered list of transport protocols the client supports.
</ParamField>
<ParamField path="use_client_preference" type="bool" default="False">
Whether to prioritize client transport preferences over server.
</ParamField>
<ParamField path="extensions" type="list[str]" default="[]">
Extension URIs the client supports.
A2A protocol extension URIs the client supports.
</ParamField>
<ParamField path="client_extensions" type="list[A2AExtension]" default="[]">
Client-side processing hooks for tool injection, prompt augmentation, and response modification.
</ParamField>
<ParamField path="transport" type="ClientTransportConfig" default="ClientTransportConfig()">
Transport configuration including preferred transport, supported transports for negotiation, and protocol-specific settings (gRPC message sizes, keepalive, etc.).
</ParamField>
<ParamField path="transport_protocol" type="Literal['JSONRPC', 'GRPC', 'HTTP+JSON']" default="None">
**Deprecated**: Use `transport=ClientTransportConfig(preferred=...)` instead.
</ParamField>
<ParamField path="supported_transports" type="list[str]" default="None">
**Deprecated**: Use `transport=ClientTransportConfig(supported=...)` instead.
</ParamField>
## Authentication
@@ -405,11 +413,7 @@ agent = Agent(
Preferred endpoint URL. If set, overrides the URL passed to `to_agent_card()`.
</ParamField>
<ParamField path="preferred_transport" type="Literal['JSONRPC', 'GRPC', 'HTTP+JSON']" default="JSONRPC">
Transport protocol for the preferred endpoint.
</ParamField>
<ParamField path="protocol_version" type="str" default="0.3">
<ParamField path="protocol_version" type="str" default="0.3.0">
A2A protocol version this agent supports.
</ParamField>
@@ -441,8 +445,36 @@ agent = Agent(
Whether agent provides extended card to authenticated users.
</ParamField>
<ParamField path="signatures" type="list[AgentCardSignature]" default="[]">
JSON Web Signatures for the AgentCard.
<ParamField path="extended_skills" type="list[AgentSkill]" default="[]">
Additional skills visible only to authenticated users in the extended agent card.
</ParamField>
<ParamField path="signing_config" type="AgentCardSigningConfig" default="None">
Configuration for signing the AgentCard with JWS. Supports RS256, ES256, PS256, and related algorithms.
</ParamField>
<ParamField path="server_extensions" type="list[ServerExtension]" default="[]">
Server-side A2A protocol extensions with `on_request`/`on_response` hooks that modify agent behavior.
</ParamField>
<ParamField path="push_notifications" type="ServerPushNotificationConfig" default="None">
Configuration for outgoing push notifications, including HMAC-SHA256 signing secret.
</ParamField>
<ParamField path="transport" type="ServerTransportConfig" default="ServerTransportConfig()">
Transport configuration including preferred transport, gRPC server settings, JSON-RPC paths, and HTTP+JSON settings.
</ParamField>
<ParamField path="auth" type="ServerAuthScheme" default="None">
Authentication scheme for incoming A2A requests. Defaults to `SimpleTokenAuth` using the `AUTH_TOKEN` environment variable.
</ParamField>
<ParamField path="preferred_transport" type="Literal['JSONRPC', 'GRPC', 'HTTP+JSON']" default="None">
**Deprecated**: Use `transport=ServerTransportConfig(preferred=...)` instead.
</ParamField>
<ParamField path="signatures" type="list[AgentCardSignature]" default="None">
**Deprecated**: Use `signing_config=AgentCardSigningConfig(...)` instead.
</ParamField>
### Combined Client and Server
@@ -468,6 +500,14 @@ agent = Agent(
)
```
### File Inputs and Structured Output
A2A supports passing files and requesting structured output in both directions.
**Client side**: When delegating to a remote A2A agent, files from the task's `input_files` are sent as `FilePart`s in the outgoing message. If `response_model` is set on the `A2AClientConfig`, the Pydantic model's JSON schema is embedded in the message metadata, requesting structured output from the remote agent.
**Server side**: Incoming `FilePart`s are extracted and passed to the agent's task as `input_files`. If the client included a JSON schema, the server creates a response model from it and applies it to the task. When the agent returns structured data, the response is sent back as a `DataPart` rather than plain text.
## Best Practices
<CardGroup cols={2}>

View File

@@ -325,6 +325,34 @@ Streaming is particularly valuable for:
- **User Experience**: Reduce perceived latency by showing incremental results
- **Live Dashboards**: Build monitoring interfaces that display crew execution status
## Cancellation and Resource Cleanup
`CrewStreamingOutput` supports graceful cancellation so that in-flight work stops promptly when the consumer disconnects.
### Async Context Manager
```python Code
streaming = await crew.akickoff(inputs={"topic": "AI"})
async with streaming:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
```
### Explicit Cancellation
```python Code
streaming = await crew.akickoff(inputs={"topic": "AI"})
try:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
finally:
await streaming.aclose() # async
# streaming.close() # sync equivalent
```
After cancellation, `streaming.is_cancelled` and `streaming.is_completed` are both `True`. Both `aclose()` and `close()` are idempotent.
## Important Notes
- Streaming automatically enables LLM streaming for all agents in the crew

View File

@@ -420,6 +420,34 @@ except Exception as e:
print("Streaming completed but flow encountered an error")
```
## Cancellation and Resource Cleanup
`FlowStreamingOutput` supports graceful cancellation so that in-flight work stops promptly when the consumer disconnects.
### Async Context Manager
```python Code
streaming = await flow.kickoff_async()
async with streaming:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
```
### Explicit Cancellation
```python Code
streaming = await flow.kickoff_async()
try:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
finally:
await streaming.aclose() # async
# streaming.close() # sync equivalent
```
After cancellation, `streaming.is_cancelled` and `streaming.is_completed` are both `True`. Both `aclose()` and `close()` are idempotent.
## Important Notes
- Streaming automatically enables LLM streaming for any crews used within the flow

50
docs/en/skills.mdx Normal file
View File

@@ -0,0 +1,50 @@
---
title: Skills
description: Install crewaiinc/skills from the official registry at skills.sh—Flows, Crews, and docs-aware agents for Claude Code, Cursor, Codex, and more.
icon: wand-magic-sparkles
mode: "wide"
---
# Skills
**Give your AI coding agent CrewAI context in one command.**
CrewAI **Skills** are published on **[skills.sh/crewaiinc/skills](https://skills.sh/crewaiinc/skills)**—the official registry for `crewaiinc/skills`, including individual skills (for example **design-agent**, **getting-started**, **design-task**, and **ask-docs**), install stats, and audits. They teach coding agents—like Claude Code, Cursor, and Codex—how to scaffold Flows, configure Crews, use tools, and follow CrewAI patterns. Run the install below (or paste it into your agent).
```shell Terminal
npx skills add crewaiinc/skills
```
That pulls the official skill pack into your agent workflow so it can apply CrewAI conventions without you re-explaining the framework each session. Source code and issues live on [GitHub](https://github.com/crewAIInc/skills).
## What your agent gets
- **Flows** — structure stateful apps, steps, and crew kickoffs the CrewAI way
- **Crews & agents** — YAML-first patterns, roles, tasks, and delegation
- **Tools & integrations** — hook agents to search, APIs, and common CrewAI tools
- **Project layout** — align with CLI scaffolds and repo conventions
- **Up-to-date patterns** — skills track current CrewAI docs and recommended practices
## Learn more on this site
<CardGroup cols={2}>
<Card title="Coding tools & AGENTS.md" icon="terminal" href="/en/guides/coding-tools/agents-md">
How to use `AGENTS.md` and coding-agent workflows with CrewAI.
</Card>
<Card title="Quickstart" icon="rocket" href="/en/quickstart">
Build your first Flow and crew end-to-end.
</Card>
<Card title="Installation" icon="download" href="/en/installation">
Install the CrewAI CLI and Python package.
</Card>
<Card title="Skills registry (skills.sh)" icon="globe" href="https://skills.sh/crewaiinc/skills">
Official listing for `crewaiinc/skills`—skills, installs, and audits.
</Card>
<Card title="GitHub source" icon="code-branch" href="https://github.com/crewAIInc/skills">
Source, updates, and issues for the skill pack.
</Card>
</CardGroup>
### Video: CrewAI with coding agent skills
<iframe src="https://www.loom.com/embed/befb9f68b81f42ad8112bfdd95a780af" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style={{ width: "100%", height: "400px" }} />

View File

@@ -7,6 +7,10 @@ mode: "wide"
# `CodeInterpreterTool`
<Warning>
**Deprecated:** `CodeInterpreterTool` has been removed from `crewai-tools`. The `allow_code_execution` and `code_execution_mode` parameters on `Agent` are also deprecated. Use a dedicated sandbox service — [E2B](https://e2b.dev) or [Modal](https://modal.com) — for secure, isolated code execution.
</Warning>
## Description
The `CodeInterpreterTool` enables CrewAI agents to execute Python 3 code that they generate autonomously. This functionality is particularly valuable as it allows agents to create code, execute it, obtain the results, and utilize that information to inform subsequent decisions and actions.

View File

@@ -13,7 +13,7 @@ This tool is used to convert natural language to SQL queries. When passed to the
This enables multiple workflows like having an Agent to access the database fetch information based on the goal and then use the information to generate a response, report or any other output.
Along with that provides the ability for the Agent to update the database based on its goal.
**Attention**: Make sure that the Agent has access to a Read-Replica or that is okay for the Agent to run insert/update queries on the database.
**Attention**: By default the tool is read-only (SELECT/SHOW/DESCRIBE/EXPLAIN only). Write operations require `allow_dml=True` or the `CREWAI_NL2SQL_ALLOW_DML=true` environment variable. When write access is enabled, make sure the Agent uses a scoped database user or a read replica where possible.
## Security Model
@@ -38,6 +38,74 @@ Use all of the following in production:
- Add `before_tool_call` hooks to enforce allowed query patterns
- Enable query logging and alerting for destructive statements
## Read-Only Mode & DML Configuration
`NL2SQLTool` operates in **read-only mode by default**. Only the following statement types are permitted without additional configuration:
- `SELECT`
- `SHOW`
- `DESCRIBE`
- `EXPLAIN`
Any attempt to execute a write operation (`INSERT`, `UPDATE`, `DELETE`, `DROP`, `CREATE`, `ALTER`, `TRUNCATE`, etc.) will raise an error unless DML is explicitly enabled.
Multi-statement queries containing semicolons (e.g. `SELECT 1; DROP TABLE users`) are also blocked in read-only mode to prevent injection attacks.
### Enabling Write Operations
You can enable DML (Data Manipulation Language) in two ways:
**Option 1 — constructor parameter:**
```python
from crewai_tools import NL2SQLTool
nl2sql = NL2SQLTool(
db_uri="postgresql://example@localhost:5432/test_db",
allow_dml=True,
)
```
**Option 2 — environment variable:**
```bash
CREWAI_NL2SQL_ALLOW_DML=true
```
```python
from crewai_tools import NL2SQLTool
# DML enabled via environment variable
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
```
### Usage Examples
**Read-only (default) — safe for analytics and reporting:**
```python
from crewai_tools import NL2SQLTool
# Only SELECT/SHOW/DESCRIBE/EXPLAIN are permitted
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
```
**DML enabled — required for write workloads:**
```python
from crewai_tools import NL2SQLTool
# INSERT, UPDATE, DELETE, DROP, etc. are permitted
nl2sql = NL2SQLTool(
db_uri="postgresql://example@localhost:5432/test_db",
allow_dml=True,
)
```
<Warning>
Enabling DML gives the agent the ability to modify or destroy data. Only enable this when your use case explicitly requires write access, and ensure the database credentials are scoped to the minimum required privileges.
</Warning>
## Requirements
- SqlAlchemy

View File

@@ -75,4 +75,20 @@ tool = CSVSearchTool(
},
}
)
## Security
### Path Validation
File paths provided to this tool are validated against the current working directory. Paths that resolve outside the working directory are rejected with a `ValueError`.
To allow paths outside the working directory (for example, in tests or trusted pipelines), set the environment variable:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### URL Validation
URL inputs are validated: `file://` URIs and requests targeting private or reserved IP ranges are blocked to prevent server-side request forgery (SSRF) attacks.
```

View File

@@ -67,4 +67,16 @@ tool = DirectorySearchTool(
},
}
)
## Security
### Path Validation
Directory paths provided to this tool are validated against the current working directory. Paths that resolve outside the working directory are rejected with a `ValueError`.
To allow paths outside the working directory (for example, in tests or trusted pipelines), set the environment variable:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
```

View File

@@ -74,3 +74,19 @@ tool = JSONSearchTool(
}
)
```
## Security
### Path Validation
File paths provided to this tool are validated against the current working directory. Paths that resolve outside the working directory are rejected with a `ValueError`.
To allow paths outside the working directory (for example, in tests or trusted pipelines), set the environment variable:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### URL Validation
URL inputs are validated: `file://` URIs and requests targeting private or reserved IP ranges are blocked to prevent server-side request forgery (SSRF) attacks.

View File

@@ -105,4 +105,20 @@ tool = PDFSearchTool(
},
}
)
## Security
### Path Validation
File paths provided to this tool are validated against the current working directory. Paths that resolve outside the working directory are rejected with a `ValueError`.
To allow paths outside the working directory (for example, in tests or trusted pipelines), set the environment variable:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### URL Validation
URL inputs are validated: `file://` URIs and requests targeting private or reserved IP ranges are blocked to prevent server-side request forgery (SSRF) attacks.
```

Binary file not shown.

After

Width:  |  Height:  |  Size: 315 KiB

View File

@@ -4,6 +4,224 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
icon: "clock"
mode: "wide"
---
<Update label="2026년 4월 13일">
## v1.14.2a3
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a3)
## 변경 사항
### 기능
- 배포 검증 CLI 추가
- LLM 초기화 사용성 개선
### 버그 수정
- CVE-2026-40260 및 GHSA-pjjw-68hj-v9mw에 대한 패치된 버전으로 pypdf 및 uv 재정의
- CVE 임시 파일 취약점에 대해 requests를 >=2.33.0으로 업그레이드
- 진리값 기본값을 제거하여 Bedrock 도구 호출 인수 보존
- 엄격 모드를 위한 도구 스키마 정리
- MemoryRecord 임베딩 직렬화 테스트의 불안정성 제거
### 문서
- 기업 A2A 언어 정리
- 기업 A2A 기능 문서 추가
- OSS A2A 문서 업데이트
- v1.14.2a2에 대한 변경 로그 및 버전 업데이트
## 기여자
@Yanhu007, @greysonlalonde
</Update>
<Update label="2026년 4월 10일">
## v1.14.2a2
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a2)
## 변경 사항
### 기능
- 트리 뷰, 포크 지원 및 편집 가능한 입력/출력을 갖춘 체크포인트 TUI 추가
- 추론 토큰 및 캐시 생성 토큰으로 LLM 토큰 추적 강화
- 킥오프 메서드에 `from_checkpoint` 매개변수 추가
- 마이그레이션 프레임워크와 함께 체크포인트에 `crewai_version` 포함
- 계보 추적이 가능한 체크포인트 포킹 추가
### 버그 수정
- Anthropic 및 Bedrock 공급자로의 엄격 모드 포워딩 수정
- 읽기 전용 기본값, 쿼리 검증 및 매개변수화된 쿼리로 NL2SQLTool 강화
### 문서
- v1.14.2a1에 대한 변경 로그 및 버전 업데이트
## 기여자
@alex-clawd, @github-actions[bot], @greysonlalonde, @lucasgomide
</Update>
<Update label="2026년 4월 9일">
## v1.14.2a1
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a1)
## 변경 사항
### 버그 수정
- HITL 재개 후 flow_finished 이벤트 방출 수정
- CVE-2026-39892 문제를 해결하기 위해 암호화 버전을 46.0.7로 수정
### 리팩토링
- 공유 I18N_DEFAULT 싱글톤을 사용하도록 리팩토링
### 문서
- v1.14.1에 대한 변경 로그 및 버전 업데이트
## 기여자
@greysonlalonde
</Update>
<Update label="2026년 4월 9일">
## v1.14.1
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.1)
## 변경 사항
### 기능
- 비동기 체크포인트 TUI 브라우저 추가
- 스트리밍 출력에 aclose()/close() 및 비동기 컨텍스트 관리자 추가
### 버그 수정
- 템플릿 pyproject.toml 버전 증가를 위한 정규 표현식 수정
- 훅 데코레이터 필터에서 도구 이름 정리
- CheckpointConfig 생성 시 체크포인트 핸들러 등록 수정
- CVE-2026-1839 해결을 위해 transformers를 5.5.0으로 업데이트
- FilteredStream stdout/stderr 래퍼 제거
### 문서
- v1.14.1rc1에 대한 변경 로그 및 버전 업데이트
### 리팩토링
- 하드코딩된 거부 목록을 동적 BaseTool 필드 제외로 교체
- devtools CLI에서 정규 표현식을 tomlkit으로 교체
- 공유 PRINTER 싱글톤 사용
- BaseProvider를 provider_type 식별자가 있는 BaseModel로 변경
## 기여자
@greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay
</Update>
<Update label="2026년 4월 9일">
## v1.14.1rc1
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.1rc1)
## 변경 사항
### 기능
- 비동기 체크포인트 TUI 브라우저 추가
- 스트리밍 출력에 aclose()/close() 및 비동기 컨텍스트 관리자 추가
### 버그 수정
- 정규 표현식을 사용하여 템플릿 pyproject.toml 버전 증가 수정
- 후크 데코레이터 필터에서 도구 이름 정리
- CVE-2026-1839 해결을 위해 transformers를 5.5.0으로 업데이트
- CheckpointConfig가 생성될 때 체크포인트 핸들러 등록
### 리팩토링
- 하드코딩된 거부 목록을 동적 BaseTool 필드 제외로 교체
- devtools CLI에서 정규 표현식을 tomlkit으로 교체
- 공유 PRINTER 싱글톤 사용
- BaseProvider를 provider_type 구분자가 있는 BaseModel로 변경
- FilteredStream stdout/stderr 래퍼 제거
- 사용되지 않는 flow/config.py 제거
### 문서
- v1.14.0에 대한 변경 로그 및 버전 업데이트
## 기여자
@greysonlalonde, @iris-clawd, @joaomdmoura
</Update>
<Update label="2026년 4월 7일">
## v1.14.0
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.0)
## 변경 사항
### 기능
- 체크포인트 목록/정보 CLI 명령 추가
- 추적을 구분하기 위한 guardrail_type 및 이름 추가
- 체크포인트 저장을 위한 SqliteProvider 추가
- 자동 체크포인트 생성을 위한 CheckpointConfig 추가
- 런타임 상태 체크포인트, 이벤트 시스템 및 실행기 리팩토링 구현
### 버그 수정
- SSRF 및 경로 탐색 보호 추가
- RAG 도구에 경로 및 URL 유효성 검사 추가
- 토큰 절약을 위해 메모리 직렬화에서 임베딩 벡터 제외
- 흐름 템플릿에 쓰기 전에 출력 디렉토리가 존재하는지 확인
- CVE-2026-35030 문제를 해결하기 위해 litellm을 >=1.83.0으로 업데이트
- 아랍어 페이지 렌더링을 유발하는 SEO 인덱싱 필드 제거
### 문서
- v1.14.0에 대한 변경 로그 및 버전 업데이트
- 명확성을 개선하기 위해 빠른 시작 및 설치 가이드 업데이트
- 저장소 제공자 섹션 추가, JsonProvider 내보내기
- AMP 교육 탭 가이드 추가
### 리팩토링
- 체크포인트 API 정리
- CodeInterpreterTool 제거 및 코드 실행 매개변수 사용 중단
## 기여자
@alex-clawd, @github-actions[bot], @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide
</Update>
<Update label="2026년 4월 7일">
## v1.14.0a4
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.0a4)
## 변경 사항
### 기능
- 추적을 구분하기 위해 guardrail_type 및 이름 추가
- 체크포인트 저장을 위한 SqliteProvider 추가
- 자동 체크포인트 생성을 위한 CheckpointConfig 추가
- 런타임 상태 체크포인트, 이벤트 시스템 및 실행기 리팩토링 구현
### 버그 수정
- 토큰 절약을 위해 메모리 직렬화에서 임베딩 벡터 제외
- CVE-2026-35030 문제를 해결하기 위해 litellm을 >=1.83.0으로 업데이트
### 문서
- 명확성을 개선하기 위해 빠른 시작 및 설치 가이드 업데이트
- 저장소 제공자 섹션 추가 및 JsonProvider 내보내기
### 성능
- 체크포인트 데이터 열에 JSONB 사용
### 리팩토링
- CodeInterpreterTool 제거 및 코드 실행 매개변수 사용 중단
## 기여자
@alex-clawd, @github-actions[bot], @greysonlalonde, @joaomdmoura, @lorenzejay, @lucasgomide
</Update>
<Update label="2026년 4월 6일">
## v1.14.0a3

View File

@@ -291,15 +291,13 @@ multimodal_agent = Agent(
- `max_retry_limit`: 오류 발생 시 재시도 횟수
#### 코드 실행
- `allow_code_execution`: 코드를 실행하려면 True여야 합니다
- `code_execution_mode`:
- `"safe"`: Docker를 사용합니다 (프로덕션에 권장)
- `"unsafe"`: 직접 실행 (신뢰할 수 있는 환경에서만 사용)
<Note>
이 옵션은 기본 Docker 이미지를 실행합니다. Docker 이미지를 구성하려면 도구 섹션에 있는 Code Interpreter Tool을 확인하십시오.
Code Interpreter Tool을 에이전트의 도구 파라미터로 추가하십시오.
</Note>
<Warning>
`allow_code_execution` 및 `code_execution_mode`는 더 이상 사용되지 않습니다. `CodeInterpreterTool`이 `crewai-tools`에서 제거되었습니다. 안전한 코드 실행을 위해 [E2B](https://e2b.dev) 또는 [Modal](https://modal.com)과 같은 전용 샌드박스 서비스를 사용하세요.
</Warning>
- `allow_code_execution` _(지원 중단)_: 이전에 `CodeInterpreterTool`을 통한 내장 코드 실행을 활성화했습니다.
- `code_execution_mode` _(지원 중단)_: 이전에 실행 모드를 제어했습니다 (Docker의 경우 `"safe"`, 직접 실행의 경우 `"unsafe"`).
#### 고급 기능
- `multimodal`: 텍스트와 시각적 콘텐츠 처리를 위한 멀티모달 기능 활성화
@@ -627,9 +625,10 @@ asyncio.run(main())
## 중요한 고려사항 및 모범 사례
### 보안 및 코드 실행
- `allow_code_execution`을 사용할 때는 사용자 입력에 주의하고 항상 입력 값을 검증하세요
- 운영 환경에서는 `code_execution_mode: "safe"`(Docker)를 사용하세요
- 무한 루프를 방지하기 위해 적절한 `max_execution_time` 제한을 설정하는 것을 고려하세요
<Warning>
`allow_code_execution` 및 `code_execution_mode`는 더 이상 사용되지 않으며 `CodeInterpreterTool`이 제거되었습니다. 안전한 코드 실행을 위해 [E2B](https://e2b.dev) 또는 [Modal](https://modal.com)과 같은 전용 샌드박스 서비스를 사용하세요.
</Warning>
### 성능 최적화
- `respect_context_window: true`를 사용하여 토큰 제한 문제를 방지하세요.

View File

@@ -39,7 +39,7 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./my_checkpoints",
location="./my_checkpoints",
on_events=["task_completed", "crew_kickoff_completed"],
max_checkpoints=5,
),
@@ -50,7 +50,7 @@ crew = Crew(
| 필드 | 타입 | 기본값 | 설명 |
|:-----|:-----|:-------|:-----|
| `directory` | `str` | `"./.checkpoints"` | 체크포인트 파일 경로 |
| `location` | `str` | `"./.checkpoints"` | 체크포인트 파일 경로 |
| `on_events` | `list[str]` | `["task_completed"]` | 체크포인트를 트리거하는 이벤트 타입 |
| `provider` | `BaseProvider` | `JsonProvider()` | 스토리지 백엔드 |
| `max_checkpoints` | `int \| None` | `None` | 보관할 최대 파일 수; 오래된 것부터 삭제 |
@@ -95,7 +95,7 @@ result = crew.kickoff() # 마지막으로 완료된 태스크부터 재개
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, write_task, review_task],
checkpoint=CheckpointConfig(directory="./crew_cp"),
checkpoint=CheckpointConfig(location="./crew_cp"),
)
```
@@ -118,7 +118,7 @@ class MyFlow(Flow):
flow = MyFlow(
checkpoint=CheckpointConfig(
directory="./flow_cp",
location="./flow_cp",
on_events=["method_execution_finished"],
),
)
@@ -137,7 +137,7 @@ agent = Agent(
goal="Research topics",
backstory="Expert researcher",
checkpoint=CheckpointConfig(
directory="./agent_cp",
location="./agent_cp",
on_events=["lite_agent_execution_completed"],
),
)
@@ -160,7 +160,7 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./my_checkpoints",
location="./my_checkpoints",
provider=JsonProvider(),
max_checkpoints=5,
),
@@ -179,15 +179,12 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./.checkpoints.db",
provider=SqliteProvider(max_checkpoints=50),
location="./.checkpoints.db",
provider=SqliteProvider(),
),
)
```
<Note>
`SqliteProvider`를 사용할 때 `directory` 필드는 디렉토리가 아닌 데이터베이스 파일 경로입니다.
</Note>
## 이벤트 타입

View File

@@ -325,6 +325,34 @@ asyncio.run(interactive_research())
- **사용자 경험**: 점진적인 결과를 표시하여 체감 지연 시간 감소
- **라이브 대시보드**: crew 실행 상태를 표시하는 모니터링 인터페이스 구축
## 취소 및 리소스 정리
`CrewStreamingOutput`은 소비자가 연결을 끊을 때 진행 중인 작업을 즉시 중단하는 정상적인 취소를 지원합니다.
### 비동기 컨텍스트 매니저
```python Code
streaming = await crew.akickoff(inputs={"topic": "AI"})
async with streaming:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
```
### 명시적 취소
```python Code
streaming = await crew.akickoff(inputs={"topic": "AI"})
try:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
finally:
await streaming.aclose() # 비동기
# streaming.close() # 동기 버전
```
취소 후 `streaming.is_cancelled`와 `streaming.is_completed`는 모두 `True`입니다. `aclose()`와 `close()` 모두 멱등성을 가집니다.
## 중요 사항
- 스트리밍은 crew의 모든 에이전트에 대해 자동으로 LLM 스트리밍을 활성화합니다

50
docs/ko/skills.mdx Normal file
View File

@@ -0,0 +1,50 @@
---
title: Skills
description: skills.sh의 공식 레지스트리에서 crewaiinc/skills를 설치하세요. Claude Code, Cursor, Codex 등을 위한 Flow, Crew, 문서 연동 스킬.
icon: wand-magic-sparkles
mode: "wide"
---
# Skills
**한 번의 명령으로 코딩 에이전트에 CrewAI 컨텍스트를 제공하세요.**
CrewAI **Skills**는 **[skills.sh/crewaiinc/skills](https://skills.sh/crewaiinc/skills)**에 게시됩니다. `crewaiinc/skills`의 공식 레지스트리로, 개별 스킬(예: **design-agent**, **getting-started**, **design-task**, **ask-docs**), 설치 수, 감사 정보를 확인할 수 있습니다. Claude Code, Cursor, Codex 같은 코딩 에이전트에게 Flow 구성, Crew 설정, 도구 사용, CrewAI 패턴을 가르칩니다. 아래를 실행하거나 에이전트에 붙여 넣으세요.
```shell Terminal
npx skills add crewaiinc/skills
```
에이전트 워크플로에 스킬 팩이 추가되어 세션마다 프레임워크를 다시 설명하지 않아도 CrewAI 관례를 적용할 수 있습니다. 소스와 이슈는 [GitHub](https://github.com/crewAIInc/skills)에서 관리합니다.
## 에이전트가 얻는 것
- **Flows** — CrewAI 방식의 상태ful 앱, 단계, crew kickoff
- **Crew & 에이전트** — YAML 우선 패턴, 역할, 작업, 위임
- **도구 & 통합** — 검색, API, 일반적인 CrewAI 도구 연결
- **프로젝트 구조** — CLI 스캐폴드 및 저장소 관례와 정렬
- **최신 패턴** — 스킬이 현재 CrewAI 문서 및 권장 사항을 반영
## 이 사이트에서 더 알아보기
<CardGroup cols={2}>
<Card title="코딩 도구 & AGENTS.md" icon="terminal" href="/ko/guides/coding-tools/agents-md">
CrewAI와 `AGENTS.md`, 코딩 에이전트 워크플로 사용법.
</Card>
<Card title="빠른 시작" icon="rocket" href="/ko/quickstart">
첫 Flow와 crew를 처음부터 끝까지 구축합니다.
</Card>
<Card title="설치" icon="download" href="/ko/installation">
CrewAI CLI와 Python 패키지를 설치합니다.
</Card>
<Card title="Skills 레지스트리 (skills.sh)" icon="globe" href="https://skills.sh/crewaiinc/skills">
`crewaiinc/skills` 공식 목록—스킬, 설치 수, 감사.
</Card>
<Card title="GitHub 소스" icon="code-branch" href="https://github.com/crewAIInc/skills">
스킬 팩 소스, 업데이트, 이슈.
</Card>
</CardGroup>
### 영상: 코딩 에이전트 스킬과 CrewAI
<iframe src="https://www.loom.com/embed/befb9f68b81f42ad8112bfdd95a780af" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style={{ width: "100%", height: "400px" }} />

View File

@@ -7,6 +7,10 @@ mode: "wide"
# `CodeInterpreterTool`
<Warning>
**지원 중단:** `CodeInterpreterTool`이 `crewai-tools`에서 제거되었습니다. `Agent`의 `allow_code_execution` 및 `code_execution_mode` 파라미터도 더 이상 사용되지 않습니다. 안전하고 격리된 코드 실행을 위해 전용 샌드박스 서비스 — [E2B](https://e2b.dev) 또는 [Modal](https://modal.com) — 을 사용하세요.
</Warning>
## 설명
`CodeInterpreterTool`은 CrewAI 에이전트가 자율적으로 생성한 Python 3 코드를 실행할 수 있도록 합니다. 이 기능은 에이전트가 코드를 생성하고, 실행하며, 결과를 얻고, 그 정보를 활용하여 이후의 결정과 행동에 반영할 수 있다는 점에서 특히 유용합니다.

View File

@@ -11,7 +11,75 @@ mode: "wide"
이를 통해 에이전트가 데이터베이스에 접근하여 목표에 따라 정보를 가져오고, 해당 정보를 사용해 응답, 보고서 또는 기타 출력물을 생성하는 다양한 워크플로우가 가능해집니다. 또한 에이전트가 자신의 목표에 맞춰 데이터베이스를 업데이트할 수 있는 기능도 제공합니다.
**주의**: 에이전트가 Read-Replica에 접근할 수 있거나, 에이전트가 데이터베이스에 insert/update 쿼리를 실행해도 괜찮은지 반드시 확인하십시오.
**주의**: 도구는 기본적으로 읽기 전용(SELECT/SHOW/DESCRIBE/EXPLAIN만 허용)으로 동작합니다. 쓰기 작업을 수행하려면 `allow_dml=True` 매개변수 또는 `CREWAI_NL2SQL_ALLOW_DML=true` 환경 변수가 필요합니다. 쓰기 접근이 활성화된 경우, 가능하면 권한이 제한된 데이터베이스 사용자나 읽기 복제본을 사용하십시오.
## 읽기 전용 모드 및 DML 구성
`NL2SQLTool`은 기본적으로 **읽기 전용 모드**로 동작합니다. 추가 구성 없이 허용되는 구문 유형은 다음과 같습니다:
- `SELECT`
- `SHOW`
- `DESCRIBE`
- `EXPLAIN`
DML을 명시적으로 활성화하지 않으면 쓰기 작업(`INSERT`, `UPDATE`, `DELETE`, `DROP`, `CREATE`, `ALTER`, `TRUNCATE` 등)을 실행하려고 할 때 오류가 발생합니다.
읽기 전용 모드에서는 세미콜론이 포함된 다중 구문 쿼리(예: `SELECT 1; DROP TABLE users`)도 인젝션 공격을 방지하기 위해 차단됩니다.
### 쓰기 작업 활성화
DML(데이터 조작 언어)을 활성화하는 방법은 두 가지입니다:
**옵션 1 — 생성자 매개변수:**
```python
from crewai_tools import NL2SQLTool
nl2sql = NL2SQLTool(
db_uri="postgresql://example@localhost:5432/test_db",
allow_dml=True,
)
```
**옵션 2 — 환경 변수:**
```bash
CREWAI_NL2SQL_ALLOW_DML=true
```
```python
from crewai_tools import NL2SQLTool
# 환경 변수를 통해 DML 활성화
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
```
### 사용 예시
**읽기 전용(기본값) — 분석 및 보고 워크로드에 안전:**
```python
from crewai_tools import NL2SQLTool
# SELECT/SHOW/DESCRIBE/EXPLAIN만 허용
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
```
**DML 활성화 — 쓰기 워크로드에 필요:**
```python
from crewai_tools import NL2SQLTool
# INSERT, UPDATE, DELETE, DROP 등이 허용됨
nl2sql = NL2SQLTool(
db_uri="postgresql://example@localhost:5432/test_db",
allow_dml=True,
)
```
<Warning>
DML을 활성화하면 에이전트가 데이터를 수정하거나 삭제할 수 있습니다. 사용 사례에서 명시적으로 쓰기 접근이 필요한 경우에만 활성화하고, 데이터베이스 자격 증명이 최소 필요 권한으로 제한되어 있는지 확인하십시오.
</Warning>
## 요구 사항

View File

@@ -76,3 +76,19 @@ tool = CSVSearchTool(
}
)
```
## 보안
### 경로 유효성 검사
이 도구에 제공되는 파일 경로는 현재 작업 디렉터리에 대해 검증됩니다. 작업 디렉터리 외부로 확인되는 경로는 `ValueError`로 거부됩니다.
작업 디렉터리 외부의 경로를 허용하려면 (예: 테스트 또는 신뢰할 수 있는 파이프라인), 다음 환경 변수를 설정하세요:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### URL 유효성 검사
URL 입력도 검증됩니다: `file://` URI와 사설 또는 예약된 IP 범위를 대상으로 하는 요청은 서버 측 요청 위조(SSRF) 공격을 방지하기 위해 차단됩니다.

View File

@@ -68,3 +68,15 @@ tool = DirectorySearchTool(
}
)
```
## 보안
### 경로 유효성 검사
이 도구에 제공되는 디렉터리 경로는 현재 작업 디렉터리에 대해 검증됩니다. 작업 디렉터리 외부로 확인되는 경로는 `ValueError`로 거부됩니다.
작업 디렉터리 외부의 경로를 허용하려면 (예: 테스트 또는 신뢰할 수 있는 파이프라인), 다음 환경 변수를 설정하세요:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```

View File

@@ -71,3 +71,19 @@ tool = JSONSearchTool(
}
)
```
## 보안
### 경로 유효성 검사
이 도구에 제공되는 파일 경로는 현재 작업 디렉터리에 대해 검증됩니다. 작업 디렉터리 외부로 확인되는 경로는 `ValueError`로 거부됩니다.
작업 디렉터리 외부의 경로를 허용하려면 (예: 테스트 또는 신뢰할 수 있는 파이프라인), 다음 환경 변수를 설정하세요:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### URL 유효성 검사
URL 입력도 검증됩니다: `file://` URI와 사설 또는 예약된 IP 범위를 대상으로 하는 요청은 서버 측 요청 위조(SSRF) 공격을 방지하기 위해 차단됩니다.

View File

@@ -102,3 +102,19 @@ tool = PDFSearchTool(
}
)
```
## 보안
### 경로 유효성 검사
이 도구에 제공되는 파일 경로는 현재 작업 디렉터리에 대해 검증됩니다. 작업 디렉터리 외부로 확인되는 경로는 `ValueError`로 거부됩니다.
작업 디렉터리 외부의 경로를 허용하려면 (예: 테스트 또는 신뢰할 수 있는 파이프라인), 다음 환경 변수를 설정하세요:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### URL 유효성 검사
URL 입력도 검증됩니다: `file://` URI와 사설 또는 예약된 IP 범위를 대상으로 하는 요청은 서버 측 요청 위조(SSRF) 공격을 방지하기 위해 차단됩니다.

View File

@@ -4,6 +4,224 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
icon: "clock"
mode: "wide"
---
<Update label="13 abr 2026">
## v1.14.2a3
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a3)
## O que Mudou
### Recursos
- Adicionar CLI de validação de deploy
- Melhorar a ergonomia de inicialização do LLM
### Correções de Bugs
- Substituir pypdf e uv por versões corrigidas para CVE-2026-40260 e GHSA-pjjw-68hj-v9mw
- Atualizar requests para >=2.33.0 devido à vulnerabilidade de arquivo temporário CVE
- Preservar os argumentos de chamada da ferramenta Bedrock removendo o padrão truthy
- Sanitizar esquemas de ferramentas para modo estrito
- Remover flakiness do teste de serialização de embedding MemoryRecord
### Documentação
- Limpar a linguagem do A2A empresarial
- Adicionar documentação de recursos do A2A empresarial
- Atualizar documentação do A2A OSS
- Atualizar changelog e versão para v1.14.2a2
## Contribuidores
@Yanhu007, @greysonlalonde
</Update>
<Update label="10 abr 2026">
## v1.14.2a2
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a2)
## O que Mudou
### Funcionalidades
- Adicionar TUI de ponto de verificação com visualização em árvore, suporte a bifurcações e entradas/saídas editáveis
- Enriquecer o rastreamento de tokens LLM com tokens de raciocínio e tokens de criação de cache
- Adicionar parâmetro `from_checkpoint` aos métodos de inicialização
- Incorporar `crewai_version` em pontos de verificação com o framework de migração
- Adicionar bifurcação de ponto de verificação com rastreamento de linhagem
### Correções de Bugs
- Corrigir o encaminhamento em modo estrito para os provedores Anthropic e Bedrock
- Fortalecer NL2SQLTool com padrão somente leitura, validação de consultas e consultas parametrizadas
### Documentação
- Atualizar changelog e versão para v1.14.2a1
## Contributors
@alex-clawd, @github-actions[bot], @greysonlalonde, @lucasgomide
</Update>
<Update label="09 abr 2026">
## v1.14.2a1
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a1)
## O que Mudou
### Correções de Bugs
- Corrigir a emissão do evento flow_finished após a retomada do HITL
- Corrigir a versão da criptografia para 46.0.7 para resolver o CVE-2026-39892
### Refatoração
- Refatorar para usar o singleton I18N_DEFAULT compartilhado
### Documentação
- Atualizar o changelog e a versão para v1.14.1
## Contribuidores
@greysonlalonde
</Update>
<Update label="09 abr 2026">
## v1.14.1
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.1)
## O que Mudou
### Funcionalidades
- Adicionar navegador TUI de ponto de verificação assíncrono
- Adicionar aclose()/close() e gerenciador de contexto assíncrono para saídas de streaming
### Correções de Bugs
- Corrigir regex para aumentos de versão do template pyproject.toml
- Sanitizar nomes de ferramentas nos filtros do decorador de hook
- Corrigir registro de manipuladores de ponto de verificação quando CheckpointConfig é criado
- Atualizar transformers para 5.5.0 para resolver CVE-2026-1839
- Remover wrapper stdout/stderr de FilteredStream
### Documentação
- Atualizar changelog e versão para v1.14.1rc1
### Refatoração
- Substituir lista de negação codificada por exclusão dinâmica de campo BaseTool na geração de especificações
- Substituir regex por tomlkit na CLI do devtools
- Usar singleton PRINTER compartilhado
- Fazer BaseProvider um BaseModel com discriminador provider_type
## Contribuidores
@greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay
</Update>
<Update label="09 abr 2026">
## v1.14.1rc1
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.1rc1)
## O que Mudou
### Recursos
- Adicionar navegador TUI de ponto de verificação assíncrono
- Adicionar aclose()/close() e gerenciador de contexto assíncrono para saídas de streaming
### Correções de Bugs
- Corrigir aumentos de versão do template pyproject.toml usando regex
- Sanitizar nomes de ferramentas nos filtros do decorador de hook
- Atualizar transformers para 5.5.0 para resolver CVE-2026-1839
- Registrar manipuladores de ponto de verificação quando CheckpointConfig é criado
### Refatoração
- Substituir lista de negação codificada por exclusão dinâmica de campo BaseTool na geração de especificações
- Substituir regex por tomlkit na CLI do devtools
- Usar singleton PRINTER compartilhado
- Tornar BaseProvider um BaseModel com discriminador de tipo de provedor
- Remover wrapper stdout/stderr de FilteredStream
- Remover flow/config.py não utilizado
### Documentação
- Atualizar changelog e versão para v1.14.0
## Contribuidores
@greysonlalonde, @iris-clawd, @joaomdmoura
</Update>
<Update label="07 abr 2026">
## v1.14.0
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.0)
## O que Mudou
### Recursos
- Adicionar comandos CLI de lista/informações de checkpoint
- Adicionar guardrail_type e nome para distinguir rastros
- Adicionar SqliteProvider para armazenamento de checkpoints
- Adicionar CheckpointConfig para checkpointing automático
- Implementar checkpointing de estado em tempo de execução, sistema de eventos e refatoração do executor
### Correções de Bugs
- Adicionar proteções contra SSRF e travessia de caminho
- Adicionar validação de caminho e URL às ferramentas RAG
- Excluir vetores de incorporação da serialização de memória para economizar tokens
- Garantir que o diretório de saída exista antes de escrever no modelo de fluxo
- Atualizar litellm para >=1.83.0 para resolver CVE-2026-35030
- Remover campo de indexação SEO que causava renderização de página em árabe
### Documentação
- Atualizar changelog e versão para v1.14.0
- Atualizar guias de início rápido e instalação para maior clareza
- Adicionar seção de provedores de armazenamento, exportar JsonProvider
- Adicionar guia da aba de Treinamento AMP
### Refatoração
- Limpar API de checkpoint
- Remover CodeInterpreterTool e descontinuar parâmetros de execução de código
## Contribuidores
@alex-clawd, @github-actions[bot], @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide
</Update>
<Update label="07 abr 2026">
## v1.14.0a4
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.0a4)
## O que Mudou
### Recursos
- Adicionar guardrail_type e nome para distinguir rastros
- Adicionar SqliteProvider para armazenamento de checkpoints
- Adicionar CheckpointConfig para checkpointing automático
- Implementar checkpointing de estado em tempo de execução, sistema de eventos e refatoração do executor
### Correções de Bugs
- Excluir vetores de incorporação da serialização de memória para economizar tokens
- Atualizar litellm para >=1.83.0 para resolver CVE-2026-35030
### Documentação
- Atualizar guias de início rápido e instalação para melhor clareza
- Adicionar seção de provedores de armazenamento e exportar JsonProvider
### Desempenho
- Usar JSONB para a coluna de dados de checkpoint
### Refatoração
- Remover CodeInterpreterTool e descontinuar parâmetros de execução de código
## Contribuidores
@alex-clawd, @github-actions[bot], @greysonlalonde, @joaomdmoura, @lorenzejay, @lucasgomide
</Update>
<Update label="06 abr 2026">
## v1.14.0a3

View File

@@ -304,17 +304,12 @@ multimodal_agent = Agent(
#### Execução de Código
- `allow_code_execution`: Deve ser True para permitir execução de código
- `code_execution_mode`:
- `"safe"`: Usa Docker (recomendado para produção)
- `"unsafe"`: Execução direta (apenas em ambientes confiáveis)
<Warning>
`allow_code_execution` e `code_execution_mode` estão depreciados. O `CodeInterpreterTool` foi removido do `crewai-tools`. Use um serviço de sandbox dedicado como [E2B](https://e2b.dev) ou [Modal](https://modal.com) para execução segura de código.
</Warning>
<Note>
Isso executa uma imagem Docker padrão. Se você deseja configurar a imagem
Docker, veja a ferramenta Code Interpreter na seção de ferramentas. Adicione a
ferramenta de interpretação de código como um parâmetro em ferramentas no
agente.
</Note>
- `allow_code_execution` _(depreciado)_: Anteriormente habilitava a execução de código embutida via `CodeInterpreterTool`.
- `code_execution_mode` _(depreciado)_: Anteriormente controlava o modo de execução (`"safe"` para Docker, `"unsafe"` para execução direta).
#### Funcionalidades Avançadas
@@ -565,9 +560,9 @@ agent = Agent(
### Segurança e Execução de Código
- Ao usar `allow_code_execution`, seja cauteloso com entradas do usuário e sempre as valide
- Use `code_execution_mode: "safe"` (Docker) em ambientes de produção
- Considere definir limites adequados de `max_execution_time` para evitar loops infinitos
<Warning>
`allow_code_execution` e `code_execution_mode` estão depreciados e o `CodeInterpreterTool` foi removido. Use um serviço de sandbox dedicado como [E2B](https://e2b.dev) ou [Modal](https://modal.com) para execução segura de código.
</Warning>
### Otimização de Performance

View File

@@ -39,7 +39,7 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./my_checkpoints",
location="./my_checkpoints",
on_events=["task_completed", "crew_kickoff_completed"],
max_checkpoints=5,
),
@@ -50,7 +50,7 @@ crew = Crew(
| Campo | Tipo | Padrao | Descricao |
|:------|:-----|:-------|:----------|
| `directory` | `str` | `"./.checkpoints"` | Caminho para os arquivos de checkpoint |
| `location` | `str` | `"./.checkpoints"` | Caminho para os arquivos de checkpoint |
| `on_events` | `list[str]` | `["task_completed"]` | Tipos de evento que acionam um checkpoint |
| `provider` | `BaseProvider` | `JsonProvider()` | Backend de armazenamento |
| `max_checkpoints` | `int \| None` | `None` | Maximo de arquivos a manter; os mais antigos sao removidos primeiro |
@@ -95,7 +95,7 @@ A crew restaurada pula tarefas ja concluidas e retoma a partir da primeira incom
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, write_task, review_task],
checkpoint=CheckpointConfig(directory="./crew_cp"),
checkpoint=CheckpointConfig(location="./crew_cp"),
)
```
@@ -118,7 +118,7 @@ class MyFlow(Flow):
flow = MyFlow(
checkpoint=CheckpointConfig(
directory="./flow_cp",
location="./flow_cp",
on_events=["method_execution_finished"],
),
)
@@ -137,7 +137,7 @@ agent = Agent(
goal="Research topics",
backstory="Expert researcher",
checkpoint=CheckpointConfig(
directory="./agent_cp",
location="./agent_cp",
on_events=["lite_agent_execution_completed"],
),
)
@@ -160,7 +160,7 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./my_checkpoints",
location="./my_checkpoints",
provider=JsonProvider(),
max_checkpoints=5,
),
@@ -179,15 +179,12 @@ crew = Crew(
agents=[...],
tasks=[...],
checkpoint=CheckpointConfig(
directory="./.checkpoints.db",
provider=SqliteProvider(max_checkpoints=50),
location="./.checkpoints.db",
provider=SqliteProvider(),
),
)
```
<Note>
Ao usar `SqliteProvider`, o campo `directory` e o caminho do arquivo de banco de dados, nao um diretorio.
</Note>
## Tipos de Evento

View File

@@ -325,6 +325,34 @@ O streaming é particularmente valioso para:
- **Experiência do Usuário**: Reduzir latência percebida mostrando resultados incrementais
- **Dashboards ao Vivo**: Construir interfaces de monitoramento que exibem status de execução da crew
## Cancelamento e Limpeza de Recursos
`CrewStreamingOutput` suporta cancelamento gracioso para que o trabalho em andamento pare imediatamente quando o consumidor desconecta.
### Gerenciador de Contexto Assíncrono
```python Code
streaming = await crew.akickoff(inputs={"topic": "AI"})
async with streaming:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
```
### Cancelamento Explícito
```python Code
streaming = await crew.akickoff(inputs={"topic": "AI"})
try:
async for chunk in streaming:
print(chunk.content, end="", flush=True)
finally:
await streaming.aclose() # assíncrono
# streaming.close() # equivalente síncrono
```
Após o cancelamento, `streaming.is_cancelled` e `streaming.is_completed` são ambos `True`. Tanto `aclose()` quanto `close()` são idempotentes.
## Notas Importantes
- O streaming ativa automaticamente o streaming do LLM para todos os agentes na crew

50
docs/pt-BR/skills.mdx Normal file
View File

@@ -0,0 +1,50 @@
---
title: Skills
description: Instale crewaiinc/skills pelo registro oficial em skills.sh—Flows, Crews e agentes alinhados à documentação para Claude Code, Cursor, Codex e outros.
icon: wand-magic-sparkles
mode: "wide"
---
# Skills
**Dê ao seu agente de código o contexto do CrewAI em um comando.**
As **Skills** do CrewAI são publicadas em **[skills.sh/crewaiinc/skills](https://skills.sh/crewaiinc/skills)**—o registro oficial de `crewaiinc/skills`, com cada skill (por exemplo **design-agent**, **getting-started**, **design-task** e **ask-docs**), estatísticas de instalação e auditorias. Ensinam agentes de código—como Claude Code, Cursor e Codex—a estruturar Flows, configurar Crews, usar ferramentas e seguir os padrões do CrewAI. Execute o comando abaixo (ou cole no seu agente).
```shell Terminal
npx skills add crewaiinc/skills
```
Isso adiciona o pacote de skills ao fluxo do seu agente para aplicar convenções do CrewAI sem precisar reexplicar o framework a cada sessão. Código-fonte e issues ficam no [GitHub](https://github.com/crewAIInc/skills).
## O que seu agente ganha
- **Flows** — apps com estado, passos e kickoffs de crew no estilo CrewAI
- **Crews e agentes** — padrões YAML-first, papéis, tarefas e delegação
- **Ferramentas e integrações** — conectar agentes a busca, APIs e ferramentas comuns
- **Layout de projeto** — alinhar com scaffolds da CLI e convenções do repositório
- **Padrões atualizados** — skills acompanham a documentação e as práticas recomendadas
## Saiba mais neste site
<CardGroup cols={2}>
<Card title="Ferramentas de codificação e AGENTS.md" icon="terminal" href="/pt-BR/guides/coding-tools/agents-md">
Como usar `AGENTS.md` e fluxos de agente de código com o CrewAI.
</Card>
<Card title="Início rápido" icon="rocket" href="/pt-BR/quickstart">
Construa seu primeiro Flow e crew ponta a ponta.
</Card>
<Card title="Instalação" icon="download" href="/pt-BR/installation">
Instale a CLI e o pacote Python do CrewAI.
</Card>
<Card title="Registro de skills (skills.sh)" icon="globe" href="https://skills.sh/crewaiinc/skills">
Listagem oficial de `crewaiinc/skills`—skills, instalações e auditorias.
</Card>
<Card title="Código no GitHub" icon="code-branch" href="https://github.com/crewAIInc/skills">
Fonte, atualizações e issues do pacote de skills.
</Card>
</CardGroup>
### Vídeo: CrewAI com coding agent skills
<iframe src="https://www.loom.com/embed/befb9f68b81f42ad8112bfdd95a780af" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style={{ width: "100%", height: "400px" }} />

View File

@@ -7,6 +7,10 @@ mode: "wide"
# `CodeInterpreterTool`
<Warning>
**Depreciado:** O `CodeInterpreterTool` foi removido do `crewai-tools`. Os parâmetros `allow_code_execution` e `code_execution_mode` do `Agent` também estão depreciados. Use um serviço de sandbox dedicado — [E2B](https://e2b.dev) ou [Modal](https://modal.com) — para execução de código segura e isolada.
</Warning>
## Descrição
O `CodeInterpreterTool` permite que agentes CrewAI executem códigos Python 3 gerados autonomamente. Essa funcionalidade é particularmente valiosa, pois permite que os agentes criem códigos, os executem, obtenham os resultados e usem essas informações para orientar decisões e ações subsequentes.

View File

@@ -11,7 +11,75 @@ Esta ferramenta é utilizada para converter linguagem natural em consultas SQL.
Isso possibilita múltiplos fluxos de trabalho, como por exemplo ter um Agente acessando o banco de dados para buscar informações com base em um objetivo e, então, usar essas informações para gerar uma resposta, relatório ou qualquer outro tipo de saída. Além disso, permite que o Agente atualize o banco de dados de acordo com seu objetivo.
**Atenção**: Certifique-se de que o Agente tenha acesso a um Read-Replica ou que seja permitido que o Agente execute consultas de inserção/atualização no banco de dados.
**Atenção**: Por padrão, a ferramenta opera em modo somente leitura (apenas SELECT/SHOW/DESCRIBE/EXPLAIN). Operações de escrita exigem `allow_dml=True` ou a variável de ambiente `CREWAI_NL2SQL_ALLOW_DML=true`. Quando o acesso de escrita estiver habilitado, certifique-se de que o Agente use um usuário de banco de dados com privilégios mínimos ou um Read-Replica sempre que possível.
## Modo Somente Leitura e Configuração de DML
O `NL2SQLTool` opera em **modo somente leitura por padrão**. Apenas os seguintes tipos de instrução são permitidos sem configuração adicional:
- `SELECT`
- `SHOW`
- `DESCRIBE`
- `EXPLAIN`
Qualquer tentativa de executar uma operação de escrita (`INSERT`, `UPDATE`, `DELETE`, `DROP`, `CREATE`, `ALTER`, `TRUNCATE`, etc.) resultará em erro, a menos que o DML seja habilitado explicitamente.
Consultas com múltiplas instruções contendo ponto e vírgula (ex.: `SELECT 1; DROP TABLE users`) também são bloqueadas no modo somente leitura para prevenir ataques de injeção.
### Habilitando Operações de Escrita
Você pode habilitar DML (Linguagem de Manipulação de Dados) de duas formas:
**Opção 1 — parâmetro do construtor:**
```python
from crewai_tools import NL2SQLTool
nl2sql = NL2SQLTool(
db_uri="postgresql://example@localhost:5432/test_db",
allow_dml=True,
)
```
**Opção 2 — variável de ambiente:**
```bash
CREWAI_NL2SQL_ALLOW_DML=true
```
```python
from crewai_tools import NL2SQLTool
# DML habilitado via variável de ambiente
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
```
### Exemplos de Uso
**Somente leitura (padrão) — seguro para análise e relatórios:**
```python
from crewai_tools import NL2SQLTool
# Apenas SELECT/SHOW/DESCRIBE/EXPLAIN são permitidos
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
```
**Com DML habilitado — necessário para workloads de escrita:**
```python
from crewai_tools import NL2SQLTool
# INSERT, UPDATE, DELETE, DROP, etc. são permitidos
nl2sql = NL2SQLTool(
db_uri="postgresql://example@localhost:5432/test_db",
allow_dml=True,
)
```
<Warning>
Habilitar DML concede ao agente a capacidade de modificar ou destruir dados. Ative apenas quando o seu caso de uso exigir explicitamente acesso de escrita e certifique-se de que as credenciais do banco de dados estejam limitadas aos privilégios mínimos necessários.
</Warning>
## Requisitos

View File

@@ -75,4 +75,20 @@ tool = CSVSearchTool(
),
)
)
## Segurança
### Validação de Caminhos
Os caminhos de arquivo fornecidos a esta ferramenta são validados em relação ao diretório de trabalho atual. Caminhos que resolvem fora do diretório de trabalho são rejeitados com um `ValueError`.
Para permitir caminhos fora do diretório de trabalho (por exemplo, em testes ou pipelines confiáveis), defina a variável de ambiente:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### Validação de URLs
Entradas de URL também são validadas: URIs `file://` e requisições direcionadas a faixas de IP privadas ou reservadas são bloqueadas para prevenir ataques de falsificação de requisições do lado do servidor (SSRF).
```

View File

@@ -67,4 +67,16 @@ tool = DirectorySearchTool(
},
}
)
```
## Segurança
### Validação de Caminhos
Os caminhos de diretório fornecidos a esta ferramenta são validados em relação ao diretório de trabalho atual. Caminhos que resolvem fora do diretório de trabalho são rejeitados com um `ValueError`.
Para permitir caminhos fora do diretório de trabalho (por exemplo, em testes ou pipelines confiáveis), defina a variável de ambiente:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```

View File

@@ -73,4 +73,20 @@ tool = JSONSearchTool(
},
}
)
## Segurança
### Validação de Caminhos
Os caminhos de arquivo fornecidos a esta ferramenta são validados em relação ao diretório de trabalho atual. Caminhos que resolvem fora do diretório de trabalho são rejeitados com um `ValueError`.
Para permitir caminhos fora do diretório de trabalho (por exemplo, em testes ou pipelines confiáveis), defina a variável de ambiente:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### Validação de URLs
Entradas de URL também são validadas: URIs `file://` e requisições direcionadas a faixas de IP privadas ou reservadas são bloqueadas para prevenir ataques de falsificação de requisições do lado do servidor (SSRF).
```

View File

@@ -101,4 +101,20 @@ tool = PDFSearchTool(
},
}
)
```
```
## Segurança
### Validação de Caminhos
Os caminhos de arquivo fornecidos a esta ferramenta são validados em relação ao diretório de trabalho atual. Caminhos que resolvem fora do diretório de trabalho são rejeitados com um `ValueError`.
Para permitir caminhos fora do diretório de trabalho (por exemplo, em testes ou pipelines confiáveis), defina a variável de ambiente:
```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true
```
### Validação de URLs
Entradas de URL também são validadas: URIs `file://` e requisições direcionadas a faixas de IP privadas ou reservadas são bloqueadas para prevenir ataques de falsificação de requisições do lado do servidor (SSRF).

View File

@@ -9,7 +9,7 @@ authors = [
requires-python = ">=3.10, <3.14"
dependencies = [
"Pillow~=12.1.1",
"pypdf~=6.9.1",
"pypdf~=6.10.0",
"python-magic>=0.4.27",
"aiocache~=0.12.3",
"aiofiles~=24.1.0",

View File

@@ -152,4 +152,4 @@ __all__ = [
"wrap_file_source",
]
__version__ = "1.14.0a3"
__version__ = "1.14.2a3"

View File

@@ -9,8 +9,8 @@ authors = [
requires-python = ">=3.10, <3.14"
dependencies = [
"pytube~=15.0.0",
"requests~=2.32.5",
"crewai==1.14.0a3",
"requests>=2.33.0,<3",
"crewai==1.14.2a3",
"tiktoken~=0.8.0",
"beautifulsoup4~=4.13.4",
"python-docx~=1.2.0",

View File

@@ -305,4 +305,4 @@ __all__ = [
"ZapierActionTools",
]
__version__ = "1.14.0a3"
__version__ = "1.14.2a3"

View File

@@ -154,21 +154,19 @@ class ToolSpecExtractor:
return default_value
# Dynamically computed from BaseTool so that any future fields or
# computed_fields added to BaseTool are automatically excluded from
# the generated spec — no hardcoded denylist to maintain.
# ``package_dependencies`` is not a BaseTool field but is extracted
# into its own top-level key, so it's also excluded from init_params.
_BASE_TOOL_FIELDS: set[str] = (
set(BaseTool.model_fields)
| set(BaseTool.model_computed_fields)
| {"package_dependencies"}
)
@staticmethod
def _extract_init_params(tool_class: type[BaseTool]) -> dict[str, Any]:
ignored_init_params = [
"name",
"description",
"env_vars",
"args_schema",
"description_updated",
"cache_function",
"result_as_answer",
"max_usage_count",
"current_usage_count",
"package_dependencies",
]
json_schema = tool_class.model_json_schema(
schema_generator=SchemaGenerator, mode="serialization"
)
@@ -176,8 +174,14 @@ class ToolSpecExtractor:
json_schema["properties"] = {
key: value
for key, value in json_schema["properties"].items()
if key not in ignored_init_params
if key not in ToolSpecExtractor._BASE_TOOL_FIELDS
}
if "required" in json_schema:
json_schema["required"] = [
key
for key in json_schema["required"]
if key not in ToolSpecExtractor._BASE_TOOL_FIELDS
]
return json_schema
def save_to_json(self, output_path: str) -> None:

View File

@@ -109,7 +109,7 @@ class DataTypes:
if isinstance(content, str):
try:
url = urlparse(content)
is_url = bool(url.scheme and url.netloc) or url.scheme == "file"
is_url = bool(url.scheme in ("http", "https") and url.netloc)
except Exception: # noqa: S110
pass

View File

@@ -0,0 +1,205 @@
"""Path and URL validation utilities for crewai-tools.
Provides validation for file paths and URLs to prevent unauthorized
file access and server-side request forgery (SSRF) when tools accept
user-controlled or LLM-controlled inputs at runtime.
Set CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true to bypass validation (not
recommended for production).
"""
from __future__ import annotations
import ipaddress
import logging
import os
import socket
from urllib.parse import urlparse
logger = logging.getLogger(__name__)
_UNSAFE_PATHS_ENV = "CREWAI_TOOLS_ALLOW_UNSAFE_PATHS"
def _is_escape_hatch_enabled() -> bool:
"""Check if the unsafe paths escape hatch is enabled."""
return os.environ.get(_UNSAFE_PATHS_ENV, "").lower() in ("true", "1", "yes")
# ---------------------------------------------------------------------------
# File path validation
# ---------------------------------------------------------------------------
def validate_file_path(path: str, base_dir: str | None = None) -> str:
"""Validate that a file path is safe to read.
Resolves symlinks and ``..`` components, then checks that the resolved
path falls within *base_dir* (defaults to the current working directory).
Args:
path: The file path to validate.
base_dir: Allowed root directory. Defaults to ``os.getcwd()``.
Returns:
The resolved, validated absolute path.
Raises:
ValueError: If the path escapes the allowed directory.
"""
if _is_escape_hatch_enabled():
logger.warning(
"%s is enabled — skipping file path validation for: %s",
_UNSAFE_PATHS_ENV,
path,
)
return os.path.realpath(path)
if base_dir is None:
base_dir = os.getcwd()
resolved_base = os.path.realpath(base_dir)
resolved_path = os.path.realpath(
os.path.join(resolved_base, path) if not os.path.isabs(path) else path
)
# Ensure the resolved path is within the base directory.
# When resolved_base already ends with a separator (e.g. the filesystem
# root "/"), appending os.sep would double it ("//"), so use the base
# as-is in that case.
prefix = resolved_base if resolved_base.endswith(os.sep) else resolved_base + os.sep
if not resolved_path.startswith(prefix) and resolved_path != resolved_base:
raise ValueError(
f"Path '{path}' resolves to '{resolved_path}' which is outside "
f"the allowed directory '{resolved_base}'. "
f"Set {_UNSAFE_PATHS_ENV}=true to bypass this check."
)
return resolved_path
def validate_directory_path(path: str, base_dir: str | None = None) -> str:
"""Validate that a directory path is safe to read.
Same as :func:`validate_file_path` but also checks that the path
is an existing directory.
Args:
path: The directory path to validate.
base_dir: Allowed root directory. Defaults to ``os.getcwd()``.
Returns:
The resolved, validated absolute path.
Raises:
ValueError: If the path escapes the allowed directory or is not a directory.
"""
validated = validate_file_path(path, base_dir)
if not os.path.isdir(validated):
raise ValueError(f"Path '{validated}' is not a directory.")
return validated
# ---------------------------------------------------------------------------
# URL validation
# ---------------------------------------------------------------------------
# Private and reserved IP ranges that should not be accessed
_BLOCKED_IPV4_NETWORKS = [
ipaddress.ip_network("10.0.0.0/8"),
ipaddress.ip_network("172.16.0.0/12"),
ipaddress.ip_network("192.168.0.0/16"),
ipaddress.ip_network("127.0.0.0/8"),
ipaddress.ip_network("169.254.0.0/16"), # Link-local / cloud metadata
ipaddress.ip_network("0.0.0.0/32"),
]
_BLOCKED_IPV6_NETWORKS = [
ipaddress.ip_network("::1/128"),
ipaddress.ip_network("::/128"),
ipaddress.ip_network("fc00::/7"), # Unique local addresses
ipaddress.ip_network("fe80::/10"), # Link-local IPv6
]
def _is_private_or_reserved(ip_str: str) -> bool:
"""Check if an IP address is private, reserved, or otherwise unsafe."""
try:
addr = ipaddress.ip_address(ip_str)
# Unwrap IPv4-mapped IPv6 addresses (e.g., ::ffff:127.0.0.1) to IPv4
# so they are only checked against IPv4 networks (avoids TypeError when
# an IPv4Address is compared against an IPv6Network).
if isinstance(addr, ipaddress.IPv6Address) and addr.ipv4_mapped:
addr = addr.ipv4_mapped
networks = (
_BLOCKED_IPV4_NETWORKS
if isinstance(addr, ipaddress.IPv4Address)
else _BLOCKED_IPV6_NETWORKS
)
return any(addr in network for network in networks)
except ValueError:
return True # If we can't parse, block it
def validate_url(url: str) -> str:
"""Validate that a URL is safe to fetch.
Blocks ``file://`` scheme entirely. For ``http``/``https``, resolves
DNS and checks that the target IP is not private or reserved (prevents
SSRF to internal services and cloud metadata endpoints).
Args:
url: The URL to validate.
Returns:
The validated URL string.
Raises:
ValueError: If the URL uses a blocked scheme or resolves to a
private/reserved IP address.
"""
if _is_escape_hatch_enabled():
logger.warning(
"%s is enabled — skipping URL validation for: %s",
_UNSAFE_PATHS_ENV,
url,
)
return url
parsed = urlparse(url)
# Block file:// scheme
if parsed.scheme == "file":
raise ValueError(
f"file:// URLs are not allowed: '{url}'. "
f"Use a file path instead, or set {_UNSAFE_PATHS_ENV}=true to bypass."
)
# Only allow http and https
if parsed.scheme not in ("http", "https"):
raise ValueError(
f"URL scheme '{parsed.scheme}' is not allowed. Only http and https are supported."
)
if not parsed.hostname:
raise ValueError(f"URL has no hostname: '{url}'")
# Resolve DNS and check IPs
try:
addrinfos = socket.getaddrinfo(
parsed.hostname, parsed.port or (443 if parsed.scheme == "https" else 80)
)
except socket.gaierror as exc:
raise ValueError(f"Could not resolve hostname: '{parsed.hostname}'") from exc
for _family, _, _, _, sockaddr in addrinfos:
ip_str = str(sockaddr[0])
if _is_private_or_reserved(ip_str):
raise ValueError(
f"URL '{url}' resolves to private/reserved IP {ip_str}. "
f"Access to internal networks is not allowed. "
f"Set {_UNSAFE_PATHS_ENV}=true to bypass."
)
return url

View File

@@ -7,6 +7,8 @@ from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, Field
import requests
from crewai_tools.security.safe_path import validate_url
class BrightDataConfig(BaseModel):
API_URL: str = "https://api.brightdata.com/request"
@@ -134,6 +136,7 @@ class BrightDataWebUnlockerTool(BaseTool):
"Content-Type": "application/json",
}
validate_url(url)
try:
response = requests.post(
self.base_url, json=payload, headers=headers, timeout=30

View File

@@ -3,6 +3,8 @@ from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class ContextualAICreateAgentSchema(BaseModel):
"""Schema for contextual create agent tool."""
@@ -47,6 +49,7 @@ class ContextualAICreateAgentTool(BaseTool):
document_paths: list[str],
) -> str:
"""Create a complete RAG pipeline with documents."""
resolved_paths = [validate_file_path(doc_path) for doc_path in document_paths]
try:
import os
@@ -56,7 +59,7 @@ class ContextualAICreateAgentTool(BaseTool):
# Upload documents
document_ids = []
for doc_path in document_paths:
for doc_path in resolved_paths:
if not os.path.exists(doc_path):
raise FileNotFoundError(f"Document not found: {doc_path}")

View File

@@ -1,6 +1,8 @@
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class ContextualAIParseSchema(BaseModel):
"""Schema for contextual parse tool."""
@@ -45,6 +47,7 @@ class ContextualAIParseTool(BaseTool):
"""Parse a document using Contextual AI's parser."""
if output_types is None:
output_types = ["markdown-per-page"]
file_path = validate_file_path(file_path)
try:
import json
import os

View File

@@ -4,6 +4,8 @@ from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_directory_path
class FixedDirectoryReadToolSchema(BaseModel):
"""Input for DirectoryReadTool."""
@@ -39,6 +41,7 @@ class DirectoryReadTool(BaseTool):
if directory is None:
raise ValueError("Directory must be provided.")
directory = validate_directory_path(directory)
if directory[-1] == "/":
directory = directory[:-1]
files_list = [

View File

@@ -3,6 +3,7 @@ from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.rag.data_types import DataType
from crewai_tools.security.safe_path import validate_directory_path
from crewai_tools.tools.rag.rag_tool import RagTool
@@ -37,6 +38,7 @@ class DirectorySearchTool(RagTool):
self._generate_description()
def add(self, directory: str) -> None: # type: ignore[override]
directory = validate_directory_path(directory)
super().add(directory, data_type=DataType.DIRECTORY)
def _run( # type: ignore[override]

View File

@@ -3,6 +3,8 @@ from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class FileReadToolSchema(BaseModel):
"""Input for FileReadTool."""
@@ -76,6 +78,7 @@ class FileReadTool(BaseTool):
if file_path is None:
return "Error: No file path provided. Please provide a file path either in the constructor or as an argument."
file_path = validate_file_path(file_path)
try:
with open(file_path, "r") as file:
if start_line == 1 and line_count is None:

View File

@@ -5,6 +5,8 @@ import zipfile
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class FileCompressorToolInput(BaseModel):
"""Input schema for FileCompressorTool."""
@@ -40,12 +42,15 @@ class FileCompressorTool(BaseTool):
overwrite: bool = False,
format: str = "zip",
) -> str:
input_path = validate_file_path(input_path)
if not os.path.exists(input_path):
return f"Input path '{input_path}' does not exist."
if not output_path:
output_path = self._generate_output_path(input_path, format)
output_path = validate_file_path(output_path)
format_extension = {
"zip": ".zip",
"tar": ".tar",

View File

@@ -5,6 +5,8 @@ from typing import Any
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, ConfigDict, Field, PrivateAttr
from crewai_tools.security.safe_path import validate_url
try:
from firecrawl import FirecrawlApp # type: ignore[import-untyped]
@@ -106,6 +108,7 @@ class FirecrawlCrawlWebsiteTool(BaseTool):
if not self._firecrawl:
raise RuntimeError("FirecrawlApp not properly initialized")
url = validate_url(url)
return self._firecrawl.crawl(url=url, poll_interval=2, **self.config)

View File

@@ -5,6 +5,8 @@ from typing import Any
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, ConfigDict, Field, PrivateAttr
from crewai_tools.security.safe_path import validate_url
try:
from firecrawl import FirecrawlApp # type: ignore[import-untyped]
@@ -106,6 +108,7 @@ class FirecrawlScrapeWebsiteTool(BaseTool):
if not self._firecrawl:
raise RuntimeError("FirecrawlApp not properly initialized")
url = validate_url(url)
return self._firecrawl.scrape(url=url, **self.config)

View File

@@ -4,6 +4,8 @@ from typing import Any, Literal
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_url
class HyperbrowserLoadToolSchema(BaseModel):
url: str = Field(description="Website URL")
@@ -119,6 +121,7 @@ class HyperbrowserLoadTool(BaseTool):
) from e
params = self._prepare_params(params)
url = validate_url(url)
if operation == "scrape":
scrape_params = StartScrapeJobParams(url=url, **params)

View File

@@ -4,6 +4,8 @@ from crewai.tools import BaseTool
from pydantic import BaseModel, Field
import requests
from crewai_tools.security.safe_path import validate_url
class JinaScrapeWebsiteToolInput(BaseModel):
"""Input schema for JinaScrapeWebsiteTool."""
@@ -45,6 +47,7 @@ class JinaScrapeWebsiteTool(BaseTool):
"Website URL must be provided either during initialization or execution"
)
url = validate_url(url)
response = requests.get(
f"https://r.jina.ai/{url}", headers=self.headers, timeout=15
)

View File

@@ -1,7 +1,17 @@
from collections.abc import Iterator
import logging
import os
import re
from typing import Any
try:
from typing import Self
except ImportError:
from typing_extensions import Self
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, model_validator
try:
@@ -12,6 +22,186 @@ try:
except ImportError:
SQLALCHEMY_AVAILABLE = False
logger = logging.getLogger(__name__)
# Commands allowed in read-only mode
# NOTE: WITH is intentionally excluded — writable CTEs start with WITH, so the
# CTE body must be inspected separately (see _validate_statement).
_READ_ONLY_COMMANDS = {"SELECT", "SHOW", "DESCRIBE", "DESC", "EXPLAIN"}
# Commands that mutate state and are blocked by default
_WRITE_COMMANDS = {
"INSERT",
"UPDATE",
"DELETE",
"DROP",
"ALTER",
"CREATE",
"TRUNCATE",
"GRANT",
"REVOKE",
"EXEC",
"EXECUTE",
"CALL",
"MERGE",
"REPLACE",
"UPSERT",
"LOAD",
"COPY",
"VACUUM",
"ANALYZE",
"ANALYSE",
"REINDEX",
"CLUSTER",
"REFRESH",
"COMMENT",
"SET",
"RESET",
}
# Subset of write commands that can realistically appear *inside* a CTE body.
# Narrower than _WRITE_COMMANDS to avoid false positives on identifiers like
# ``comment``, ``set``, or ``reset`` which are common column/table names.
_CTE_WRITE_INDICATORS = {
"INSERT",
"UPDATE",
"DELETE",
"DROP",
"ALTER",
"CREATE",
"TRUNCATE",
"MERGE",
}
_AS_PAREN_RE = re.compile(r"\bAS\s*\(", re.IGNORECASE)
def _iter_as_paren_matches(stmt: str) -> Iterator[re.Match[str]]:
"""Yield regex matches for ``AS\\s*(`` outside of string literals."""
# Build a set of character positions that are inside string literals.
in_string: set[int] = set()
i = 0
while i < len(stmt):
if stmt[i] == "'":
start = i
end = _skip_string_literal(stmt, i)
in_string.update(range(start, end))
i = end
else:
i += 1
for m in _AS_PAREN_RE.finditer(stmt):
if m.start() not in in_string:
yield m
def _detect_writable_cte(stmt: str) -> str | None:
"""Return the first write command inside a CTE body, or None.
Instead of tokenizing the whole statement (which falsely matches column
names like ``comment``), this walks through parenthesized CTE bodies and
checks only the *first keyword after* an opening ``AS (`` for a write
command. Uses a regex to handle any whitespace (spaces, tabs, newlines)
between ``AS`` and ``(``. Skips matches inside string literals.
"""
for m in _iter_as_paren_matches(stmt):
body = stmt[m.end() :].lstrip()
first_word = body.split()[0].upper().strip("()") if body.split() else ""
if first_word in _CTE_WRITE_INDICATORS:
return first_word
return None
def _skip_string_literal(stmt: str, pos: int) -> int:
"""Skip past a string literal starting at pos (single-quoted).
Handles escaped quotes ('') inside the literal.
Returns the index after the closing quote.
"""
quote_char = stmt[pos]
i = pos + 1
while i < len(stmt):
if stmt[i] == quote_char:
# Check for escaped quote ('')
if i + 1 < len(stmt) and stmt[i + 1] == quote_char:
i += 2
continue
return i + 1
i += 1
return i # Unterminated literal — return end
def _find_matching_close_paren(stmt: str, start: int) -> int:
"""Find the matching close paren, skipping string literals."""
depth = 1
i = start
while i < len(stmt) and depth > 0:
ch = stmt[i]
if ch == "'":
i = _skip_string_literal(stmt, i)
continue
if ch == "(":
depth += 1
elif ch == ")":
depth -= 1
i += 1
return i
def _extract_main_query_after_cte(stmt: str) -> str | None:
"""Extract the main (outer) query that follows all CTE definitions.
For ``WITH cte AS (SELECT 1) DELETE FROM users``, returns ``DELETE FROM users``.
Returns None if no main query is found after the last CTE body.
Handles parentheses inside string literals (e.g., ``SELECT '(' FROM t``).
"""
last_cte_end = 0
for m in _iter_as_paren_matches(stmt):
last_cte_end = _find_matching_close_paren(stmt, m.end())
if last_cte_end > 0:
remainder = stmt[last_cte_end:].strip().lstrip(",").strip()
if remainder:
return remainder
return None
def _resolve_explain_command(stmt: str) -> str | None:
"""Resolve the underlying command from an EXPLAIN [ANALYZE] [VERBOSE] statement.
Returns the real command (e.g., 'DELETE') if ANALYZE is present, else None.
Handles both space-separated and parenthesized syntax.
"""
rest = stmt.strip()[len("EXPLAIN") :].strip()
if not rest:
return None
analyze_found = False
explain_opts = {"ANALYZE", "ANALYSE", "VERBOSE"}
if rest.startswith("("):
close = rest.find(")")
if close != -1:
options_str = rest[1:close].upper()
analyze_found = any(
opt.strip() in ("ANALYZE", "ANALYSE") for opt in options_str.split(",")
)
rest = rest[close + 1 :].strip()
else:
while rest:
first_opt = rest.split()[0].upper().rstrip(";") if rest.split() else ""
if first_opt in ("ANALYZE", "ANALYSE"):
analyze_found = True
if first_opt not in explain_opts:
break
rest = rest[len(first_opt) :].strip()
if analyze_found and rest:
return rest.split()[0].upper().rstrip(";")
return None
class NL2SQLToolInput(BaseModel):
sql_query: str = Field(
@@ -21,20 +211,70 @@ class NL2SQLToolInput(BaseModel):
class NL2SQLTool(BaseTool):
"""Tool that converts natural language to SQL and executes it against a database.
By default the tool operates in **read-only mode**: only SELECT, SHOW,
DESCRIBE, EXPLAIN, and read-only CTEs (WITH … SELECT) are permitted. Write
operations (INSERT, UPDATE, DELETE, DROP, ALTER, CREATE, TRUNCATE, …) are
blocked unless ``allow_dml=True`` is set explicitly or the environment
variable ``CREWAI_NL2SQL_ALLOW_DML=true`` is present.
Writable CTEs (``WITH d AS (DELETE …) SELECT …``) and
``EXPLAIN ANALYZE <write-stmt>`` are treated as write operations and are
blocked in read-only mode.
The ``_fetch_all_available_columns`` helper uses parameterised queries so
that table names coming from the database catalogue cannot be used as an
injection vector.
"""
name: str = "NL2SQLTool"
description: str = "Converts natural language to SQL queries and executes them."
description: str = (
"Converts natural language to SQL queries and executes them against a "
"database. Read-only by default — only SELECT/SHOW/DESCRIBE/EXPLAIN "
"queries (and read-only CTEs) are allowed unless configured with "
"allow_dml=True."
)
db_uri: str = Field(
title="Database URI",
description="The URI of the database to connect to.",
)
allow_dml: bool = Field(
default=False,
title="Allow DML",
description=(
"When False (default) only read statements are permitted. "
"Set to True to allow INSERT/UPDATE/DELETE/DROP and other "
"write operations."
),
)
tables: list[dict[str, Any]] = Field(default_factory=list)
columns: dict[str, list[dict[str, Any]] | str] = Field(default_factory=dict)
args_schema: type[BaseModel] = NL2SQLToolInput
@model_validator(mode="after")
def _apply_env_override(self) -> Self:
"""Allow CREWAI_NL2SQL_ALLOW_DML=true to override allow_dml at runtime."""
if os.environ.get("CREWAI_NL2SQL_ALLOW_DML", "").strip().lower() == "true":
if not self.allow_dml:
logger.warning(
"NL2SQLTool: CREWAI_NL2SQL_ALLOW_DML env var is set — "
"DML/DDL operations are enabled. Ensure this is intentional."
)
self.allow_dml = True
return self
def model_post_init(self, __context: Any) -> None:
if not SQLALCHEMY_AVAILABLE:
raise ImportError(
"sqlalchemy is not installed. Please install it with `pip install crewai-tools[sqlalchemy]`"
"sqlalchemy is not installed. Please install it with "
"`pip install crewai-tools[sqlalchemy]`"
)
if self.allow_dml:
logger.warning(
"NL2SQLTool: allow_dml=True — write operations (INSERT/UPDATE/"
"DELETE/DROP/…) are permitted. Use with caution."
)
data: dict[str, list[dict[str, Any]] | str] = {}
@@ -50,42 +290,216 @@ class NL2SQLTool(BaseTool):
self.tables = tables
self.columns = data
# ------------------------------------------------------------------
# Query validation
# ------------------------------------------------------------------
def _validate_query(self, sql_query: str) -> None:
"""Raise ValueError if *sql_query* is not permitted under the current config.
Splits the query on semicolons and validates each statement
independently. When ``allow_dml=False`` (the default), multi-statement
queries are rejected outright to prevent ``SELECT 1; DROP TABLE users``
style bypasses. When ``allow_dml=True`` every statement is checked and
a warning is emitted for write operations.
"""
statements = [s.strip() for s in sql_query.split(";") if s.strip()]
if not statements:
raise ValueError("NL2SQLTool received an empty SQL query.")
if not self.allow_dml and len(statements) > 1:
raise ValueError(
"NL2SQLTool blocked a multi-statement query in read-only mode. "
"Semicolons are not permitted when allow_dml=False."
)
for stmt in statements:
self._validate_statement(stmt)
def _validate_statement(self, stmt: str) -> None:
"""Validate a single SQL statement (no semicolons)."""
command = self._extract_command(stmt)
# EXPLAIN ANALYZE / EXPLAIN ANALYSE actually *executes* the underlying
# query. Resolve the real command so write operations are caught.
# Handles both space-separated ("EXPLAIN ANALYZE DELETE …") and
# parenthesized ("EXPLAIN (ANALYZE) DELETE …", "EXPLAIN (ANALYZE, VERBOSE) DELETE …").
# EXPLAIN ANALYZE actually executes the underlying query — resolve the
# real command so write operations are caught.
if command == "EXPLAIN":
resolved = _resolve_explain_command(stmt)
if resolved:
command = resolved
# WITH starts a CTE. Read-only CTEs are fine; writable CTEs
# (e.g. WITH d AS (DELETE …) SELECT …) must be blocked in read-only mode.
if command == "WITH":
# Check for write commands inside CTE bodies.
write_found = _detect_writable_cte(stmt)
if write_found:
found = write_found
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool is configured in read-only mode and blocked a "
f"writable CTE containing a '{found}' statement. To allow "
f"write operations set allow_dml=True or "
f"CREWAI_NL2SQL_ALLOW_DML=true."
)
logger.warning(
"NL2SQLTool: executing writable CTE with '%s' because allow_dml=True.",
found,
)
return
# Check the main query after the CTE definitions.
main_query = _extract_main_query_after_cte(stmt)
if main_query:
main_cmd = main_query.split()[0].upper().rstrip(";")
if main_cmd in _WRITE_COMMANDS:
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool is configured in read-only mode and blocked a "
f"'{main_cmd}' statement after a CTE. To allow write "
f"operations set allow_dml=True or "
f"CREWAI_NL2SQL_ALLOW_DML=true."
)
logger.warning(
"NL2SQLTool: executing '%s' after CTE because allow_dml=True.",
main_cmd,
)
elif main_cmd not in _READ_ONLY_COMMANDS:
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool blocked an unrecognised SQL command '{main_cmd}' "
f"after a CTE. Only {sorted(_READ_ONLY_COMMANDS)} are allowed "
f"in read-only mode."
)
return
if command in _WRITE_COMMANDS:
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool is configured in read-only mode and blocked a "
f"'{command}' statement. To allow write operations set "
f"allow_dml=True or CREWAI_NL2SQL_ALLOW_DML=true."
)
logger.warning(
"NL2SQLTool: executing write statement '%s' because allow_dml=True.",
command,
)
elif command not in _READ_ONLY_COMMANDS:
# Unknown command — block by default unless DML is explicitly enabled
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool blocked an unrecognised SQL command '{command}'. "
f"Only {sorted(_READ_ONLY_COMMANDS)} are allowed in read-only "
f"mode."
)
@staticmethod
def _extract_command(sql_query: str) -> str:
"""Return the uppercased first keyword of *sql_query*."""
stripped = sql_query.strip().lstrip("(")
first_token = stripped.split()[0] if stripped.split() else ""
return first_token.upper().rstrip(";")
# ------------------------------------------------------------------
# Schema introspection helpers
# ------------------------------------------------------------------
def _fetch_available_tables(self) -> list[dict[str, Any]] | str:
return self.execute_sql(
"SELECT table_name FROM information_schema.tables WHERE table_schema = 'public';"
"SELECT table_name FROM information_schema.tables "
"WHERE table_schema = 'public';"
)
def _fetch_all_available_columns(
self, table_name: str
) -> list[dict[str, Any]] | str:
"""Fetch columns for *table_name* using a parameterised query.
The table name is bound via SQLAlchemy's ``:param`` syntax to prevent
SQL injection from catalogue values.
"""
return self.execute_sql(
f"SELECT column_name, data_type FROM information_schema.columns WHERE table_name = '{table_name}';" # noqa: S608
"SELECT column_name, data_type FROM information_schema.columns "
"WHERE table_name = :table_name",
params={"table_name": table_name},
)
# ------------------------------------------------------------------
# Core execution
# ------------------------------------------------------------------
def _run(self, sql_query: str) -> list[dict[str, Any]] | str:
try:
self._validate_query(sql_query)
data = self.execute_sql(sql_query)
except ValueError:
raise
except Exception as exc:
data = (
f"Based on these tables {self.tables} and columns {self.columns}, "
"you can create SQL queries to retrieve data from the database."
f"Get the original request {sql_query} and the error {exc} and create the correct SQL query."
"you can create SQL queries to retrieve data from the database. "
f"Get the original request {sql_query} and the error {exc} and "
"create the correct SQL query."
)
return data
def execute_sql(self, sql_query: str) -> list[dict[str, Any]] | str:
def execute_sql(
self,
sql_query: str,
params: dict[str, Any] | None = None,
) -> list[dict[str, Any]] | str:
"""Execute *sql_query* and return the results as a list of dicts.
Parameters
----------
sql_query:
The SQL statement to run.
params:
Optional mapping of bind parameters (e.g. ``{"table_name": "users"}``).
"""
if not SQLALCHEMY_AVAILABLE:
raise ImportError(
"sqlalchemy is not installed. Please install it with `pip install crewai-tools[sqlalchemy]`"
"sqlalchemy is not installed. Please install it with "
"`pip install crewai-tools[sqlalchemy]`"
)
# Check ALL statements so that e.g. "SELECT 1; DROP TABLE t" triggers a
# commit when allow_dml=True, regardless of statement order.
_stmts = [s.strip() for s in sql_query.split(";") if s.strip()]
def _is_write_stmt(s: str) -> bool:
cmd = self._extract_command(s)
if cmd in _WRITE_COMMANDS:
return True
if cmd == "EXPLAIN":
# Resolve the underlying command for EXPLAIN ANALYZE
resolved = _resolve_explain_command(s)
if resolved and resolved in _WRITE_COMMANDS:
return True
if cmd == "WITH":
if _detect_writable_cte(s):
return True
main_q = _extract_main_query_after_cte(s)
if main_q:
return main_q.split()[0].upper().rstrip(";") in _WRITE_COMMANDS
return False
is_write = any(_is_write_stmt(s) for s in _stmts)
engine = create_engine(self.db_uri)
Session = sessionmaker(bind=engine) # noqa: N806
session = Session()
try:
result = session.execute(text(sql_query))
session.commit()
result = session.execute(text(sql_query), params or {})
# Only commit when the operation actually mutates state
if self.allow_dml and is_write:
session.commit()
if result.returns_rows: # type: ignore[attr-defined]
columns = result.keys()

View File

@@ -11,6 +11,8 @@ from crewai.tools.base_tool import BaseTool
from crewai.utilities.types import LLMMessage
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class OCRToolSchema(BaseModel):
"""Input schema for Optical Character Recognition Tool.
@@ -98,5 +100,6 @@ class OCRTool(BaseTool):
Returns:
str: Base64-encoded image data as a UTF-8 string.
"""
image_path = validate_file_path(image_path)
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode()

View File

@@ -1,4 +1,5 @@
from abc import ABC, abstractmethod
import os
from typing import Any, Literal, cast
from crewai.rag.core.base_embeddings_callable import EmbeddingFunction
@@ -246,7 +247,94 @@ class RagTool(BaseTool):
# Auto-detect type from extension
rag_tool.add("path/to/document.pdf") # auto-detects PDF
"""
self.adapter.add(*args, **kwargs)
# Validate file paths and URLs before adding to prevent
# unauthorized file reads and SSRF.
from urllib.parse import urlparse
from crewai_tools.security.safe_path import validate_file_path, validate_url
def _check_url(value: str, label: str) -> None:
try:
validate_url(value)
except ValueError as e:
raise ValueError(f"Blocked unsafe {label}: {e}") from e
def _check_path(value: str, label: str) -> str:
try:
return validate_file_path(value)
except ValueError as e:
raise ValueError(f"Blocked unsafe {label}: {e}") from e
validated_args: list[ContentItem] = []
for arg in args:
source_ref = (
str(arg.get("source", arg.get("content", "")))
if isinstance(arg, dict)
else str(arg)
)
# Check if it's a URL — only catch urlparse-specific errors here;
# validate_url's ValueError must propagate so it is never silently bypassed.
try:
parsed = urlparse(source_ref)
except (ValueError, AttributeError):
parsed = None
if parsed is not None and parsed.scheme in ("http", "https", "file"):
try:
validate_url(source_ref)
except ValueError as e:
raise ValueError(f"Blocked unsafe URL: {e}") from e
validated_args.append(arg)
continue
# Check if it looks like a file path (not a plain text string).
# Check both os.sep (backslash on Windows) and "/" so that
# forward-slash paths like "sub/file.txt" are caught on all platforms.
if (
os.path.sep in source_ref
or "/" in source_ref
or source_ref.startswith(".")
or os.path.isabs(source_ref)
):
try:
resolved_ref = validate_file_path(source_ref)
except ValueError as e:
raise ValueError(f"Blocked unsafe file path: {e}") from e
# Use the resolved path to prevent symlink TOCTOU
if isinstance(arg, dict):
arg = {**arg}
if "source" in arg:
arg["source"] = resolved_ref
elif "content" in arg:
arg["content"] = resolved_ref
else:
arg = resolved_ref
validated_args.append(arg)
# Validate keyword path/URL arguments — these are equally user-controlled
# and must not bypass the checks applied to positional args.
if "path" in kwargs and kwargs.get("path") is not None:
kwargs["path"] = _check_path(str(kwargs["path"]), "path")
if "file_path" in kwargs and kwargs.get("file_path") is not None:
kwargs["file_path"] = _check_path(str(kwargs["file_path"]), "file_path")
if "directory_path" in kwargs and kwargs.get("directory_path") is not None:
kwargs["directory_path"] = _check_path(
str(kwargs["directory_path"]), "directory_path"
)
if "url" in kwargs and kwargs.get("url") is not None:
_check_url(str(kwargs["url"]), "url")
if "website" in kwargs and kwargs.get("website") is not None:
_check_url(str(kwargs["website"]), "website")
if "github_url" in kwargs and kwargs.get("github_url") is not None:
_check_url(str(kwargs["github_url"]), "github_url")
if "youtube_url" in kwargs and kwargs.get("youtube_url") is not None:
_check_url(str(kwargs["youtube_url"]), "youtube_url")
self.adapter.add(*validated_args, **kwargs)
def _run(
self,

View File

@@ -5,6 +5,8 @@ from crewai.tools import BaseTool
from pydantic import BaseModel, Field
import requests
from crewai_tools.security.safe_path import validate_url
try:
from bs4 import BeautifulSoup
@@ -81,6 +83,7 @@ class ScrapeElementFromWebsiteTool(BaseTool):
if website_url is None or css_element is None:
raise ValueError("Both website_url and css_element must be provided.")
website_url = validate_url(website_url)
page = requests.get(
website_url,
headers=self.headers,

View File

@@ -5,6 +5,8 @@ from typing import Any
from pydantic import Field
import requests
from crewai_tools.security.safe_path import validate_url
try:
from bs4 import BeautifulSoup
@@ -73,6 +75,7 @@ class ScrapeWebsiteTool(BaseTool):
if website_url is None:
raise ValueError("Website URL must be provided.")
website_url = validate_url(website_url)
page = requests.get(
website_url,
timeout=15,

View File

@@ -5,6 +5,8 @@ from typing import Any, Literal
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_url
logger = logging.getLogger(__file__)
@@ -72,6 +74,7 @@ class ScrapflyScrapeWebsiteTool(BaseTool):
) -> str | None:
from scrapfly import ScrapeConfig
url = validate_url(url)
scrape_config = scrape_config if scrape_config is not None else {}
try:
response = self.scrapfly.scrape( # type: ignore[union-attr]

View File

@@ -5,6 +5,8 @@ from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, Field
import requests
from crewai_tools.security.safe_path import validate_url
class SerperScrapeWebsiteInput(BaseModel):
"""Input schema for SerperScrapeWebsite."""
@@ -42,6 +44,7 @@ class SerperScrapeWebsiteTool(BaseTool):
Returns:
Scraped website content as a string
"""
validate_url(url)
try:
# Serper API endpoint
api_url = "https://scrape.serper.dev"

View File

@@ -5,6 +5,7 @@ from crewai.tools import EnvVar
from pydantic import BaseModel, Field
import requests
from crewai_tools.security.safe_path import validate_url
from crewai_tools.tools.rag.rag_tool import RagTool
@@ -48,6 +49,7 @@ class SerplyWebpageToMarkdownTool(RagTool):
if self.proxy_location and not self.headers.get("X-Proxy-Location"):
self.headers["X-Proxy-Location"] = self.proxy_location
validate_url(url)
data = {"url": url, "method": "GET", "response_type": "markdown"}
response = requests.request(
"POST",

View File

@@ -7,6 +7,8 @@ from crewai.tools import BaseTool, EnvVar
from crewai.utilities.types import LLMMessage
from pydantic import BaseModel, Field, PrivateAttr, field_validator
from crewai_tools.security.safe_path import validate_file_path
class ImagePromptSchema(BaseModel):
"""Input for Vision Tool."""
@@ -135,5 +137,6 @@ class VisionTool(BaseTool):
Returns:
Base64-encoded image data
"""
image_path = validate_file_path(image_path)
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode()

View File

@@ -3,6 +3,7 @@ from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.rag.data_types import DataType
from crewai_tools.security.safe_path import validate_url
from crewai_tools.tools.rag.rag_tool import RagTool
@@ -37,6 +38,7 @@ class WebsiteSearchTool(RagTool):
self._generate_description()
def add(self, website: str) -> None: # type: ignore[override]
website = validate_url(website)
super().add(website, data_type=DataType.WEBSITE)
def _run( # type: ignore[override]

View File

@@ -0,0 +1,10 @@
"""Backward-compatible re-export from crewai_tools.security.safe_path."""
from crewai_tools.security.safe_path import (
validate_directory_path,
validate_file_path,
validate_url,
)
__all__ = ["validate_directory_path", "validate_file_path", "validate_url"]

View File

@@ -45,6 +45,26 @@ class MockTool(BaseTool):
)
# --- Intermediate base class (like RagTool, BraveSearchToolBase) ---
class MockIntermediateBase(BaseTool):
"""Simulates an intermediate tool base class (e.g. RagTool, BraveSearchToolBase)."""
name: str = "Intermediate Base"
description: str = "An intermediate tool base"
shared_config: str = Field("default_config", description="Config from intermediate base")
def _run(self, query: str) -> str:
return query
class MockDerivedTool(MockIntermediateBase):
"""A tool inheriting from an intermediate base, like CodeDocsSearchTool(RagTool)."""
name: str = "Derived Tool"
description: str = "A tool that inherits from intermediate base"
derived_param: str = Field("derived_default", description="Param specific to derived tool")
@pytest.fixture
def extractor():
ext = ToolSpecExtractor()
@@ -169,6 +189,87 @@ def test_extract_package_dependencies(mock_tool_extractor):
]
def test_base_tool_fields_excluded_from_init_params(mock_tool_extractor):
"""BaseTool internal fields (including computed_field like tool_type) must
never appear in init_params_schema. Studio reads this schema to render
the tool config UI — internal fields confuse users."""
init_schema = mock_tool_extractor["init_params_schema"]
props = set(init_schema.get("properties", {}).keys())
required = set(init_schema.get("required", []))
# These are all BaseTool's own fields — none should leak
base_fields = {"name", "description", "env_vars", "args_schema",
"description_updated", "cache_function", "result_as_answer",
"max_usage_count", "current_usage_count", "tool_type",
"package_dependencies"}
leaked_props = base_fields & props
assert not leaked_props, (
f"BaseTool fields leaked into init_params_schema properties: {leaked_props}"
)
leaked_required = base_fields & required
assert not leaked_required, (
f"BaseTool fields leaked into init_params_schema required: {leaked_required}"
)
def test_intermediate_base_fields_preserved_for_derived_tool(extractor):
"""When a tool inherits from an intermediate base (e.g. RagTool),
the intermediate's fields should be included — only BaseTool's own
fields are excluded."""
with (
mock.patch(
"crewai_tools.generate_tool_specs.dir",
return_value=["MockDerivedTool"],
),
mock.patch(
"crewai_tools.generate_tool_specs.getattr",
return_value=MockDerivedTool,
),
):
extractor.extract_all_tools()
assert len(extractor.tools_spec) == 1
tool_info = extractor.tools_spec[0]
props = set(tool_info["init_params_schema"].get("properties", {}).keys())
# Intermediate base's field should be preserved
assert "shared_config" in props, (
"Intermediate base class fields should be preserved in init_params_schema"
)
# Derived tool's own field should be preserved
assert "derived_param" in props, (
"Derived tool's own fields should be preserved in init_params_schema"
)
# BaseTool internals should still be excluded
assert "tool_type" not in props
assert "cache_function" not in props
assert "result_as_answer" not in props
def test_future_base_tool_field_auto_excluded(extractor):
"""If a new field is added to BaseTool in the future, it should be
automatically excluded from spec generation without needing to update
the ignored list. This test verifies the allowlist approach works
by checking that ONLY non-BaseTool fields appear."""
with (
mock.patch("crewai_tools.generate_tool_specs.dir", return_value=["MockTool"]),
mock.patch("crewai_tools.generate_tool_specs.getattr", return_value=MockTool),
):
extractor.extract_all_tools()
tool_info = extractor.tools_spec[0]
props = set(tool_info["init_params_schema"].get("properties", {}).keys())
base_all = set(BaseTool.model_fields) | set(BaseTool.model_computed_fields)
leaked = base_all & props
assert not leaked, (
f"BaseTool fields should be auto-excluded but found: {leaked}. "
"The spec generator should dynamically compute BaseTool's fields "
"instead of using a hardcoded denylist."
)
def test_save_to_json(extractor, tmp_path):
extractor.tools_spec = [
{

View File

@@ -3,10 +3,21 @@ from tempfile import TemporaryDirectory
from typing import cast
from unittest.mock import MagicMock, Mock, patch
import pytest
from crewai_tools.adapters.crewai_rag_adapter import CrewAIRagAdapter
from crewai_tools.tools.rag.rag_tool import RagTool
@pytest.fixture(autouse=True)
def allow_tmp_paths(monkeypatch: pytest.MonkeyPatch) -> None:
"""Allow absolute paths outside CWD (e.g. /tmp/) for these RagTool tests.
Path validation is tested separately in test_rag_tool_path_validation.py.
"""
monkeypatch.setenv("CREWAI_TOOLS_ALLOW_UNSAFE_PATHS", "true")
@patch("crewai_tools.adapters.crewai_rag_adapter.get_rag_client")
@patch("crewai_tools.adapters.crewai_rag_adapter.create_client")
def test_rag_tool_initialization(

View File

@@ -10,6 +10,15 @@ from crewai_tools.rag.data_types import DataType
from crewai_tools.tools.rag.rag_tool import RagTool
@pytest.fixture(autouse=True)
def allow_tmp_paths(monkeypatch: pytest.MonkeyPatch) -> None:
"""Allow absolute paths outside CWD (e.g. /tmp/) for these data-type tests.
Path validation is tested separately in test_rag_tool_path_validation.py.
"""
monkeypatch.setenv("CREWAI_TOOLS_ALLOW_UNSAFE_PATHS", "true")
@pytest.fixture
def mock_rag_client() -> MagicMock:
"""Create a mock RAG client for testing."""

View File

@@ -0,0 +1,80 @@
"""Tests for path and URL validation in RagTool.add() — both positional and keyword args."""
from __future__ import annotations
from unittest.mock import MagicMock, patch
import pytest
from crewai_tools.tools.rag.rag_tool import RagTool
@pytest.fixture()
def mock_rag_client() -> MagicMock:
mock_client = MagicMock()
mock_client.get_or_create_collection = MagicMock(return_value=None)
mock_client.add_documents = MagicMock(return_value=None)
mock_client.search = MagicMock(return_value=[])
return mock_client
@pytest.fixture()
def tool(mock_rag_client: MagicMock) -> RagTool:
with (
patch("crewai_tools.adapters.crewai_rag_adapter.get_rag_client", return_value=mock_rag_client),
patch("crewai_tools.adapters.crewai_rag_adapter.create_client", return_value=mock_rag_client),
):
return RagTool()
# ---------------------------------------------------------------------------
# Positional arg validation (existing behaviour, regression guard)
# ---------------------------------------------------------------------------
class TestPositionalArgValidation:
def test_blocks_traversal_in_positional_arg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe"):
tool.add("../../etc/passwd")
def test_blocks_file_url_in_positional_arg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe"):
tool.add("file:///etc/passwd")
# ---------------------------------------------------------------------------
# Keyword arg validation (the newly fixed gap)
# ---------------------------------------------------------------------------
class TestKwargPathValidation:
def test_blocks_traversal_via_path_kwarg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe path"):
tool.add(path="../../etc/passwd")
def test_blocks_traversal_via_file_path_kwarg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe file_path"):
tool.add(file_path="/etc/passwd")
def test_blocks_traversal_via_directory_path_kwarg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe directory_path"):
tool.add(directory_path="../../sensitive_dir")
def test_blocks_file_url_via_url_kwarg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe url"):
tool.add(url="file:///etc/passwd")
def test_blocks_private_ip_via_url_kwarg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe url"):
tool.add(url="http://169.254.169.254/latest/meta-data/")
def test_blocks_private_ip_via_website_kwarg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe website"):
tool.add(website="http://192.168.1.1/")
def test_blocks_file_url_via_github_url_kwarg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe github_url"):
tool.add(github_url="file:///etc/passwd")
def test_blocks_file_url_via_youtube_url_kwarg(self, tool):
with pytest.raises(ValueError, match="Blocked unsafe youtube_url"):
tool.add(youtube_url="file:///etc/passwd")

View File

@@ -0,0 +1,671 @@
"""Security tests for NL2SQLTool.
Uses an in-memory SQLite database so no external service is needed.
SQLite does not have information_schema, so we patch the schema-introspection
helpers to avoid bootstrap failures and focus purely on the security logic.
"""
import os
from unittest.mock import MagicMock, patch
import pytest
# Skip the entire module if SQLAlchemy is not installed
pytest.importorskip("sqlalchemy")
from sqlalchemy import create_engine, text # noqa: E402
from crewai_tools.tools.nl2sql.nl2sql_tool import NL2SQLTool # noqa: E402
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
SQLITE_URI = "sqlite://" # in-memory
def _make_tool(allow_dml: bool = False, **kwargs) -> NL2SQLTool:
"""Return a NL2SQLTool wired to an in-memory SQLite DB.
Schema-introspection is patched out so we can create the tool without a
real PostgreSQL information_schema.
"""
with (
patch.object(NL2SQLTool, "_fetch_available_tables", return_value=[]),
patch.object(NL2SQLTool, "_fetch_all_available_columns", return_value=[]),
):
return NL2SQLTool(db_uri=SQLITE_URI, allow_dml=allow_dml, **kwargs)
# ---------------------------------------------------------------------------
# Read-only enforcement (allow_dml=False)
# ---------------------------------------------------------------------------
class TestReadOnlyMode:
def test_select_allowed_by_default(self):
tool = _make_tool()
# SQLite supports SELECT without information_schema
result = tool.execute_sql("SELECT 1 AS val")
assert result == [{"val": 1}]
@pytest.mark.parametrize(
"stmt",
[
"INSERT INTO t VALUES (1)",
"UPDATE t SET col = 1",
"DELETE FROM t",
"DROP TABLE t",
"ALTER TABLE t ADD col TEXT",
"CREATE TABLE t (id INTEGER)",
"TRUNCATE TABLE t",
"GRANT SELECT ON t TO user1",
"REVOKE SELECT ON t FROM user1",
"EXEC sp_something",
"EXECUTE sp_something",
"CALL proc()",
],
)
def test_write_statements_blocked_by_default(self, stmt: str):
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(stmt)
def test_explain_allowed(self):
tool = _make_tool()
# Should not raise
tool._validate_query("EXPLAIN SELECT 1")
def test_read_only_cte_allowed(self):
tool = _make_tool()
tool._validate_query("WITH cte AS (SELECT 1) SELECT * FROM cte")
def test_show_allowed(self):
tool = _make_tool()
tool._validate_query("SHOW TABLES")
def test_describe_allowed(self):
tool = _make_tool()
tool._validate_query("DESCRIBE users")
# ---------------------------------------------------------------------------
# DML enabled (allow_dml=True)
# ---------------------------------------------------------------------------
class TestDMLEnabled:
def test_insert_allowed_when_dml_enabled(self):
tool = _make_tool(allow_dml=True)
# Should not raise
tool._validate_query("INSERT INTO t VALUES (1)")
def test_delete_allowed_when_dml_enabled(self):
tool = _make_tool(allow_dml=True)
tool._validate_query("DELETE FROM t WHERE id = 1")
def test_drop_allowed_when_dml_enabled(self):
tool = _make_tool(allow_dml=True)
tool._validate_query("DROP TABLE t")
def test_dml_actually_persists(self):
"""End-to-end: INSERT commits when allow_dml=True."""
# Use a file-based SQLite so we can verify persistence across sessions
import tempfile, os
with tempfile.NamedTemporaryFile(suffix=".db", delete=False) as f:
db_path = f.name
uri = f"sqlite:///{db_path}"
try:
tool = _make_tool(allow_dml=True)
tool.db_uri = uri
engine = create_engine(uri)
with engine.connect() as conn:
conn.execute(text("CREATE TABLE items (id INTEGER PRIMARY KEY)"))
conn.commit()
tool.execute_sql("INSERT INTO items VALUES (42)")
with engine.connect() as conn:
rows = conn.execute(text("SELECT id FROM items")).fetchall()
assert (42,) in rows
finally:
os.unlink(db_path)
# ---------------------------------------------------------------------------
# Parameterised query — SQL injection prevention
# ---------------------------------------------------------------------------
class TestParameterisedQueries:
def test_table_name_is_parameterised(self):
"""_fetch_all_available_columns must not interpolate table_name into SQL."""
tool = _make_tool()
captured_calls = []
def recording_execute_sql(self_inner, sql_query, params=None):
captured_calls.append((sql_query, params))
return []
with patch.object(NL2SQLTool, "execute_sql", recording_execute_sql):
tool._fetch_all_available_columns("users'; DROP TABLE users; --")
assert len(captured_calls) == 1
sql, params = captured_calls[0]
# The raw SQL must NOT contain the injected string
assert "DROP" not in sql
# The table name must be passed as a parameter
assert params is not None
assert params.get("table_name") == "users'; DROP TABLE users; --"
# The SQL template must use the :param syntax
assert ":table_name" in sql
def test_injection_string_not_in_sql_template(self):
"""The f-string vulnerability is gone — table name never lands in the SQL."""
tool = _make_tool()
injection = "'; DROP TABLE users; --"
captured = {}
def spy(self_inner, sql_query, params=None):
captured["sql"] = sql_query
captured["params"] = params
return []
with patch.object(NL2SQLTool, "execute_sql", spy):
tool._fetch_all_available_columns(injection)
assert injection not in captured["sql"]
assert captured["params"]["table_name"] == injection
# ---------------------------------------------------------------------------
# session.commit() not called for read-only queries
# ---------------------------------------------------------------------------
class TestNoCommitForReadOnly:
def test_select_does_not_commit(self):
tool = _make_tool(allow_dml=False)
mock_session = MagicMock()
mock_result = MagicMock()
mock_result.returns_rows = True
mock_result.keys.return_value = ["val"]
mock_result.fetchall.return_value = [(1,)]
mock_session.execute.return_value = mock_result
mock_session_cls = MagicMock(return_value=mock_session)
with (
patch("crewai_tools.tools.nl2sql.nl2sql_tool.create_engine"),
patch(
"crewai_tools.tools.nl2sql.nl2sql_tool.sessionmaker",
return_value=mock_session_cls,
),
):
tool.execute_sql("SELECT 1")
mock_session.commit.assert_not_called()
def test_write_with_dml_enabled_does_commit(self):
tool = _make_tool(allow_dml=True)
mock_session = MagicMock()
mock_result = MagicMock()
mock_result.returns_rows = False
mock_session.execute.return_value = mock_result
mock_session_cls = MagicMock(return_value=mock_session)
with (
patch("crewai_tools.tools.nl2sql.nl2sql_tool.create_engine"),
patch(
"crewai_tools.tools.nl2sql.nl2sql_tool.sessionmaker",
return_value=mock_session_cls,
),
):
tool.execute_sql("INSERT INTO t VALUES (1)")
mock_session.commit.assert_called_once()
# ---------------------------------------------------------------------------
# Environment-variable escape hatch
# ---------------------------------------------------------------------------
class TestEnvVarEscapeHatch:
def test_env_var_enables_dml(self):
with patch.dict(os.environ, {"CREWAI_NL2SQL_ALLOW_DML": "true"}):
tool = _make_tool(allow_dml=False)
assert tool.allow_dml is True
def test_env_var_case_insensitive(self):
with patch.dict(os.environ, {"CREWAI_NL2SQL_ALLOW_DML": "TRUE"}):
tool = _make_tool(allow_dml=False)
assert tool.allow_dml is True
def test_env_var_absent_keeps_default(self):
env = {k: v for k, v in os.environ.items() if k != "CREWAI_NL2SQL_ALLOW_DML"}
with patch.dict(os.environ, env, clear=True):
tool = _make_tool(allow_dml=False)
assert tool.allow_dml is False
def test_env_var_false_does_not_enable_dml(self):
with patch.dict(os.environ, {"CREWAI_NL2SQL_ALLOW_DML": "false"}):
tool = _make_tool(allow_dml=False)
assert tool.allow_dml is False
def test_dml_write_blocked_without_env_var(self):
env = {k: v for k, v in os.environ.items() if k != "CREWAI_NL2SQL_ALLOW_DML"}
with patch.dict(os.environ, env, clear=True):
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query("DROP TABLE sensitive_data")
# ---------------------------------------------------------------------------
# _run() propagates ValueError from _validate_query
# ---------------------------------------------------------------------------
class TestRunValidation:
def test_run_raises_on_blocked_query(self):
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._run("DELETE FROM users")
def test_run_returns_results_for_select(self):
tool = _make_tool(allow_dml=False)
result = tool._run("SELECT 1 AS n")
assert result == [{"n": 1}]
# ---------------------------------------------------------------------------
# Multi-statement / semicolon injection prevention
# ---------------------------------------------------------------------------
class TestSemicolonInjection:
def test_multi_statement_blocked_in_read_only_mode(self):
"""SELECT 1; DROP TABLE users must be rejected when allow_dml=False."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="multi-statement"):
tool._validate_query("SELECT 1; DROP TABLE users")
def test_multi_statement_blocked_even_with_only_selects(self):
"""Two SELECT statements are still rejected in read-only mode."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="multi-statement"):
tool._validate_query("SELECT 1; SELECT 2")
def test_trailing_semicolon_allowed_single_statement(self):
"""A single statement with a trailing semicolon should pass."""
tool = _make_tool(allow_dml=False)
# Should not raise — the part after the semicolon is empty
tool._validate_query("SELECT 1;")
def test_multi_statement_allowed_when_dml_enabled(self):
"""Multiple statements are permitted when allow_dml=True."""
tool = _make_tool(allow_dml=True)
# Should not raise
tool._validate_query("SELECT 1; INSERT INTO t VALUES (1)")
def test_multi_statement_write_still_blocked_individually(self):
"""Even with allow_dml=False, a single write statement is blocked."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query("DROP TABLE users")
# ---------------------------------------------------------------------------
# Writable CTEs (WITH … DELETE/INSERT/UPDATE)
# ---------------------------------------------------------------------------
class TestWritableCTE:
def test_writable_cte_delete_blocked_in_read_only(self):
"""WITH d AS (DELETE FROM users RETURNING *) SELECT * FROM d — blocked."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(
"WITH deleted AS (DELETE FROM users RETURNING *) SELECT * FROM deleted"
)
def test_writable_cte_insert_blocked_in_read_only(self):
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(
"WITH ins AS (INSERT INTO t VALUES (1) RETURNING id) SELECT * FROM ins"
)
def test_writable_cte_update_blocked_in_read_only(self):
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(
"WITH upd AS (UPDATE t SET x=1 RETURNING id) SELECT * FROM upd"
)
def test_writable_cte_allowed_when_dml_enabled(self):
tool = _make_tool(allow_dml=True)
# Should not raise
tool._validate_query(
"WITH deleted AS (DELETE FROM users RETURNING *) SELECT * FROM deleted"
)
def test_plain_read_only_cte_still_allowed(self):
tool = _make_tool(allow_dml=False)
# No write commands in the CTE body — must pass
tool._validate_query("WITH cte AS (SELECT id FROM users) SELECT * FROM cte")
def test_cte_with_comment_column_not_false_positive(self):
"""Column named 'comment' should NOT trigger writable CTE detection."""
tool = _make_tool(allow_dml=False)
# 'comment' is a column name, not a SQL command
tool._validate_query(
"WITH cte AS (SELECT comment FROM posts) SELECT * FROM cte"
)
def test_cte_with_set_column_not_false_positive(self):
"""Column named 'set' should NOT trigger writable CTE detection."""
tool = _make_tool(allow_dml=False)
tool._validate_query(
"WITH cte AS (SELECT set, reset FROM config) SELECT * FROM cte"
)
# ---------------------------------------------------------------------------
# EXPLAIN ANALYZE executes the underlying query
# ---------------------------------------------------------------------------
def test_cte_with_write_main_query_blocked(self):
"""WITH cte AS (SELECT 1) DELETE FROM users — main query must be caught."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(
"WITH cte AS (SELECT 1) DELETE FROM users"
)
def test_cte_with_write_main_query_allowed_with_dml(self):
"""Main query write after CTE should pass when allow_dml=True."""
tool = _make_tool(allow_dml=True)
tool._validate_query(
"WITH cte AS (SELECT id FROM users) INSERT INTO archive SELECT * FROM cte"
)
def test_cte_with_newline_before_paren_blocked(self):
"""AS followed by newline then ( should still detect writable CTE."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(
"WITH cte AS\n(DELETE FROM users RETURNING *) SELECT * FROM cte"
)
def test_cte_with_tab_before_paren_blocked(self):
"""AS followed by tab then ( should still detect writable CTE."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(
"WITH cte AS\t(DELETE FROM users RETURNING *) SELECT * FROM cte"
)
class TestExplainAnalyze:
def test_explain_analyze_delete_blocked_in_read_only(self):
"""EXPLAIN ANALYZE DELETE actually runs the delete — block it."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query("EXPLAIN ANALYZE DELETE FROM users")
def test_explain_analyse_delete_blocked_in_read_only(self):
"""British spelling ANALYSE is also caught."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query("EXPLAIN ANALYSE DELETE FROM users")
def test_explain_analyze_drop_blocked_in_read_only(self):
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query("EXPLAIN ANALYZE DROP TABLE users")
def test_explain_analyze_select_allowed_in_read_only(self):
"""EXPLAIN ANALYZE on a SELECT is safe — must be permitted."""
tool = _make_tool(allow_dml=False)
tool._validate_query("EXPLAIN ANALYZE SELECT * FROM users")
def test_explain_without_analyze_allowed(self):
tool = _make_tool(allow_dml=False)
tool._validate_query("EXPLAIN SELECT * FROM users")
def test_explain_analyze_delete_allowed_when_dml_enabled(self):
tool = _make_tool(allow_dml=True)
tool._validate_query("EXPLAIN ANALYZE DELETE FROM users")
def test_explain_paren_analyze_delete_blocked_in_read_only(self):
"""EXPLAIN (ANALYZE) DELETE actually runs the delete — block it."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query("EXPLAIN (ANALYZE) DELETE FROM users")
def test_explain_paren_analyze_verbose_delete_blocked_in_read_only(self):
"""EXPLAIN (ANALYZE, VERBOSE) DELETE actually runs the delete — block it."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query("EXPLAIN (ANALYZE, VERBOSE) DELETE FROM users")
def test_explain_paren_verbose_select_allowed_in_read_only(self):
"""EXPLAIN (VERBOSE) SELECT is safe — no ANALYZE means no execution."""
tool = _make_tool(allow_dml=False)
tool._validate_query("EXPLAIN (VERBOSE) SELECT * FROM users")
# ---------------------------------------------------------------------------
# Multi-statement commit covers ALL statements (not just the first)
# ---------------------------------------------------------------------------
class TestMultiStatementCommit:
def test_select_then_insert_triggers_commit(self):
"""SELECT 1; INSERT … — commit must happen because INSERT is a write."""
tool = _make_tool(allow_dml=True)
mock_session = MagicMock()
mock_result = MagicMock()
mock_result.returns_rows = False
mock_session.execute.return_value = mock_result
mock_session_cls = MagicMock(return_value=mock_session)
with (
patch("crewai_tools.tools.nl2sql.nl2sql_tool.create_engine"),
patch(
"crewai_tools.tools.nl2sql.nl2sql_tool.sessionmaker",
return_value=mock_session_cls,
),
):
tool.execute_sql("SELECT 1; INSERT INTO t VALUES (1)")
mock_session.commit.assert_called_once()
def test_select_only_multi_statement_does_not_commit(self):
"""Two SELECTs must not trigger a commit even when allow_dml=True."""
tool = _make_tool(allow_dml=True)
mock_session = MagicMock()
mock_result = MagicMock()
mock_result.returns_rows = True
mock_result.keys.return_value = ["v"]
mock_result.fetchall.return_value = [(1,)]
mock_session.execute.return_value = mock_result
mock_session_cls = MagicMock(return_value=mock_session)
with (
patch("crewai_tools.tools.nl2sql.nl2sql_tool.create_engine"),
patch(
"crewai_tools.tools.nl2sql.nl2sql_tool.sessionmaker",
return_value=mock_session_cls,
),
):
tool.execute_sql("SELECT 1; SELECT 2")
def test_writable_cte_triggers_commit(self):
"""WITH d AS (DELETE ...) must trigger commit when allow_dml=True."""
tool = _make_tool(allow_dml=True)
mock_session = MagicMock()
mock_result = MagicMock()
mock_result.returns_rows = True
mock_result.keys.return_value = ["id"]
mock_result.fetchall.return_value = [(1,)]
mock_session.execute.return_value = mock_result
mock_session_cls = MagicMock(return_value=mock_session)
with (
patch("crewai_tools.tools.nl2sql.nl2sql_tool.create_engine"),
patch(
"crewai_tools.tools.nl2sql.nl2sql_tool.sessionmaker",
return_value=mock_session_cls,
),
):
tool.execute_sql(
"WITH d AS (DELETE FROM users RETURNING *) SELECT * FROM d"
)
mock_session.commit.assert_called_once()
# ---------------------------------------------------------------------------
# Extended _WRITE_COMMANDS coverage
# ---------------------------------------------------------------------------
class TestExtendedWriteCommands:
@pytest.mark.parametrize(
"stmt",
[
"UPSERT INTO t VALUES (1)",
"LOAD DATA INFILE 'f.csv' INTO TABLE t",
"COPY t FROM '/tmp/f.csv'",
"VACUUM ANALYZE t",
"ANALYZE t",
"ANALYSE t",
"REINDEX TABLE t",
"CLUSTER t USING idx",
"REFRESH MATERIALIZED VIEW v",
"COMMENT ON TABLE t IS 'desc'",
"SET search_path = myschema",
"RESET search_path",
],
)
def test_extended_write_commands_blocked_by_default(self, stmt: str):
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(stmt)
# ---------------------------------------------------------------------------
# EXPLAIN ANALYZE VERBOSE handling
# ---------------------------------------------------------------------------
class TestExplainAnalyzeVerbose:
def test_explain_analyze_verbose_select_allowed(self):
"""EXPLAIN ANALYZE VERBOSE SELECT should be allowed (read-only)."""
tool = _make_tool(allow_dml=False)
tool._validate_query("EXPLAIN ANALYZE VERBOSE SELECT * FROM users")
def test_explain_analyze_verbose_delete_blocked(self):
"""EXPLAIN ANALYZE VERBOSE DELETE should be blocked."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query("EXPLAIN ANALYZE VERBOSE DELETE FROM users")
def test_explain_verbose_select_allowed(self):
"""EXPLAIN VERBOSE SELECT (no ANALYZE) should be allowed."""
tool = _make_tool(allow_dml=False)
tool._validate_query("EXPLAIN VERBOSE SELECT * FROM users")
# ---------------------------------------------------------------------------
# CTE with string literal parens
# ---------------------------------------------------------------------------
class TestCTEStringLiteralParens:
def test_cte_string_paren_does_not_bypass(self):
"""Parens inside string literals should not confuse the paren walker."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(
"WITH cte AS (SELECT '(' FROM t) DELETE FROM users"
)
def test_cte_string_paren_read_only_allowed(self):
"""Read-only CTE with string literal parens should be allowed."""
tool = _make_tool(allow_dml=False)
tool._validate_query(
"WITH cte AS (SELECT '(' FROM t) SELECT * FROM cte"
)
# ---------------------------------------------------------------------------
# EXPLAIN ANALYZE commit logic
# ---------------------------------------------------------------------------
class TestExplainAnalyzeCommit:
def test_explain_analyze_delete_triggers_commit(self):
"""EXPLAIN ANALYZE DELETE should trigger commit when allow_dml=True."""
tool = _make_tool(allow_dml=True)
mock_session = MagicMock()
mock_result = MagicMock()
mock_result.returns_rows = True
mock_result.keys.return_value = ["QUERY PLAN"]
mock_result.fetchall.return_value = [("Delete on users",)]
mock_session.execute.return_value = mock_result
mock_session_cls = MagicMock(return_value=mock_session)
with (
patch("crewai_tools.tools.nl2sql.nl2sql_tool.create_engine"),
patch(
"crewai_tools.tools.nl2sql.nl2sql_tool.sessionmaker",
return_value=mock_session_cls,
),
):
tool.execute_sql("EXPLAIN ANALYZE DELETE FROM users")
mock_session.commit.assert_called_once()
# ---------------------------------------------------------------------------
# AS( inside string literals must not confuse CTE detection
# ---------------------------------------------------------------------------
class TestCTEStringLiteralAS:
def test_as_paren_inside_string_does_not_bypass(self):
"""'AS (' inside a string literal must not be treated as a CTE body."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="read-only mode"):
tool._validate_query(
"WITH cte AS (SELECT 'AS (' FROM t) DELETE FROM users"
)
def test_as_paren_inside_string_read_only_ok(self):
"""Read-only CTE with 'AS (' in a string should be allowed."""
tool = _make_tool(allow_dml=False)
tool._validate_query(
"WITH cte AS (SELECT 'AS (' FROM t) SELECT * FROM cte"
)
# ---------------------------------------------------------------------------
# Unknown command after CTE should be blocked
# ---------------------------------------------------------------------------
class TestCTEUnknownCommand:
def test_unknown_command_after_cte_blocked(self):
"""WITH cte AS (SELECT 1) FOOBAR should be blocked as unknown."""
tool = _make_tool(allow_dml=False)
with pytest.raises(ValueError, match="unrecognised"):
tool._validate_query("WITH cte AS (SELECT 1) FOOBAR")

View File

@@ -23,6 +23,15 @@ from crewai_tools.tools.rag.rag_tool import Adapter
import pytest
@pytest.fixture(autouse=True)
def allow_tmp_paths(monkeypatch: pytest.MonkeyPatch) -> None:
"""Allow absolute paths outside CWD (e.g. /tmp/) for these search-tool tests.
Path validation is tested separately in test_rag_tool_path_validation.py.
"""
monkeypatch.setenv("CREWAI_TOOLS_ALLOW_UNSAFE_PATHS", "true")
@pytest.fixture
def mock_adapter():
mock_adapter = MagicMock(spec=Adapter)

View File

@@ -0,0 +1,170 @@
"""Tests for path and URL validation utilities."""
from __future__ import annotations
import os
import pytest
from crewai_tools.security.safe_path import (
validate_directory_path,
validate_file_path,
validate_url,
)
# ---------------------------------------------------------------------------
# File path validation
# ---------------------------------------------------------------------------
class TestValidateFilePath:
"""Tests for validate_file_path."""
def test_valid_relative_path(self, tmp_path):
"""Normal relative path within the base directory."""
(tmp_path / "data.json").touch()
result = validate_file_path("data.json", str(tmp_path))
assert result == str(tmp_path / "data.json")
def test_valid_nested_path(self, tmp_path):
"""Nested path within base directory."""
(tmp_path / "sub").mkdir()
(tmp_path / "sub" / "file.txt").touch()
result = validate_file_path("sub/file.txt", str(tmp_path))
assert result == str(tmp_path / "sub" / "file.txt")
def test_rejects_dotdot_traversal(self, tmp_path):
"""Reject ../ traversal that escapes base_dir."""
with pytest.raises(ValueError, match="outside the allowed directory"):
validate_file_path("../../etc/passwd", str(tmp_path))
def test_rejects_absolute_path_outside_base(self, tmp_path):
"""Reject absolute path outside base_dir."""
with pytest.raises(ValueError, match="outside the allowed directory"):
validate_file_path("/etc/passwd", str(tmp_path))
def test_allows_absolute_path_inside_base(self, tmp_path):
"""Allow absolute path that's inside base_dir."""
(tmp_path / "ok.txt").touch()
result = validate_file_path(str(tmp_path / "ok.txt"), str(tmp_path))
assert result == str(tmp_path / "ok.txt")
def test_rejects_symlink_escape(self, tmp_path):
"""Reject symlinks that point outside base_dir."""
link = tmp_path / "sneaky_link"
# Create a symlink pointing to /etc/passwd
os.symlink("/etc/passwd", str(link))
with pytest.raises(ValueError, match="outside the allowed directory"):
validate_file_path("sneaky_link", str(tmp_path))
def test_defaults_to_cwd(self):
"""When no base_dir is given, use cwd."""
cwd = os.getcwd()
# A file in cwd should be valid
result = validate_file_path(".", None)
assert result == os.path.realpath(cwd)
def test_escape_hatch(self, tmp_path, monkeypatch):
"""CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true bypasses validation."""
monkeypatch.setenv("CREWAI_TOOLS_ALLOW_UNSAFE_PATHS", "true")
# This would normally be rejected
result = validate_file_path("/etc/passwd", str(tmp_path))
assert result == os.path.realpath("/etc/passwd")
class TestValidateDirectoryPath:
"""Tests for validate_directory_path."""
def test_valid_directory(self, tmp_path):
(tmp_path / "subdir").mkdir()
result = validate_directory_path("subdir", str(tmp_path))
assert result == str(tmp_path / "subdir")
def test_rejects_file_as_directory(self, tmp_path):
(tmp_path / "file.txt").touch()
with pytest.raises(ValueError, match="not a directory"):
validate_directory_path("file.txt", str(tmp_path))
def test_rejects_traversal(self, tmp_path):
with pytest.raises(ValueError, match="outside the allowed directory"):
validate_directory_path("../../", str(tmp_path))
# ---------------------------------------------------------------------------
# URL validation
# ---------------------------------------------------------------------------
class TestValidateUrl:
"""Tests for validate_url."""
def test_valid_https_url(self):
"""Normal HTTPS URL should pass."""
result = validate_url("https://example.com/data.json")
assert result == "https://example.com/data.json"
def test_valid_http_url(self):
"""Normal HTTP URL should pass."""
result = validate_url("http://example.com/api")
assert result == "http://example.com/api"
def test_blocks_file_scheme(self):
"""file:// URLs must be blocked."""
with pytest.raises(ValueError, match="file:// URLs are not allowed"):
validate_url("file:///etc/passwd")
def test_blocks_file_scheme_with_host(self):
with pytest.raises(ValueError, match="file:// URLs are not allowed"):
validate_url("file://localhost/etc/shadow")
def test_blocks_localhost(self):
"""localhost must be blocked (resolves to 127.0.0.1)."""
with pytest.raises(ValueError, match="private/reserved IP"):
validate_url("http://localhost/admin")
def test_blocks_127_0_0_1(self):
with pytest.raises(ValueError, match="private/reserved IP"):
validate_url("http://127.0.0.1/admin")
def test_blocks_cloud_metadata(self):
"""AWS/GCP/Azure metadata endpoint must be blocked."""
with pytest.raises(ValueError, match="private/reserved IP"):
validate_url("http://169.254.169.254/latest/meta-data/")
def test_blocks_private_10_range(self):
with pytest.raises(ValueError, match="private/reserved IP"):
validate_url("http://10.0.0.1/internal")
def test_blocks_private_172_range(self):
with pytest.raises(ValueError, match="private/reserved IP"):
validate_url("http://172.16.0.1/internal")
def test_blocks_private_192_range(self):
with pytest.raises(ValueError, match="private/reserved IP"):
validate_url("http://192.168.1.1/router")
def test_blocks_zero_address(self):
with pytest.raises(ValueError, match="private/reserved IP"):
validate_url("http://0.0.0.0/")
def test_blocks_ipv6_localhost(self):
with pytest.raises(ValueError, match="private/reserved IP"):
validate_url("http://[::1]/admin")
def test_blocks_ftp_scheme(self):
with pytest.raises(ValueError, match="not allowed"):
validate_url("ftp://example.com/file")
def test_blocks_empty_hostname(self):
with pytest.raises(ValueError, match="no hostname"):
validate_url("http:///path")
def test_blocks_unresolvable_host(self):
with pytest.raises(ValueError, match="Could not resolve"):
validate_url("http://this-host-definitely-does-not-exist-abc123.com/")
def test_escape_hatch(self, monkeypatch):
"""CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true bypasses URL validation."""
monkeypatch.setenv("CREWAI_TOOLS_ALLOW_UNSAFE_PATHS", "true")
# file:// would normally be blocked
result = validate_url("file:///etc/passwd")
assert result == "file:///etc/passwd"

File diff suppressed because it is too large Load Diff

View File

@@ -40,7 +40,7 @@ dependencies = [
"pydantic-settings~=2.10.1",
"httpx~=0.28.1",
"mcp~=1.26.0",
"uv~=0.9.13",
"uv~=0.11.6",
"aiosqlite~=0.21.0",
"pyyaml~=6.0",
"aiofiles~=24.1.0",
@@ -55,7 +55,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
[project.optional-dependencies]
tools = [
"crewai-tools==1.14.0a3",
"crewai-tools==1.14.2a3",
]
embeddings = [
"tiktoken~=0.8.0"
@@ -68,14 +68,14 @@ openpyxl = [
]
mem0 = ["mem0ai~=0.1.94"]
docling = [
"docling~=2.75.0",
"docling~=2.84.0",
]
qdrant = [
"qdrant-client[fastembed]~=1.14.3",
]
aws = [
"boto3~=1.40.38",
"aiobotocore~=2.25.2",
"boto3~=1.42.79",
"aiobotocore~=3.4.0",
]
watson = [
"ibm-watsonx-ai~=1.3.39",
@@ -87,7 +87,7 @@ litellm = [
"litellm~=1.83.0",
]
bedrock = [
"boto3~=1.40.45",
"boto3~=1.42.79",
]
google-genai = [
"google-genai~=1.65.0",

View File

@@ -46,7 +46,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
_suppress_pydantic_deprecation_warnings()
__version__ = "1.14.0a3"
__version__ = "1.14.2a3"
_telemetry_submitted = False

View File

@@ -98,7 +98,6 @@ class A2AErrorCode(IntEnum):
"""The specified artifact was not found."""
# Error code to default message mapping
ERROR_MESSAGES: dict[int, str] = {
A2AErrorCode.JSON_PARSE_ERROR: "Parse error",
A2AErrorCode.INVALID_REQUEST: "Invalid Request",

View File

@@ -63,25 +63,21 @@ class A2AExtension(Protocol):
Example:
class MyExtension:
def inject_tools(self, agent: Agent) -> None:
# Add custom tools to the agent
pass
def extract_state_from_history(
self, conversation_history: Sequence[Message]
) -> ConversationState | None:
# Extract state from conversation
return None
def augment_prompt(
self, base_prompt: str, conversation_state: ConversationState | None
) -> str:
# Add custom instructions
return base_prompt
def process_response(
self, agent_response: Any, conversation_state: ConversationState | None
) -> Any:
# Modify response if needed
return agent_response
"""

View File

@@ -77,7 +77,6 @@ def extract_a2a_agent_ids_from_config(
else:
configs = a2a_config
# Filter to only client configs (those with endpoint)
client_configs: list[A2AClientConfigTypes] = [
config for config in configs if isinstance(config, (A2AConfig, A2AClientConfig))
]

View File

@@ -98,6 +98,7 @@ from crewai.utilities.converter import Converter, ConverterError
from crewai.utilities.env import get_env_context
from crewai.utilities.guardrail import process_guardrail
from crewai.utilities.guardrail_types import GuardrailCallable, GuardrailType
from crewai.utilities.i18n import I18N_DEFAULT
from crewai.utilities.llm_utils import create_llm
from crewai.utilities.prompts import Prompts, StandardPromptResult, SystemPromptResult
from crewai.utilities.pydantic_schema_utils import generate_model_description
@@ -499,8 +500,8 @@ class Agent(BaseAgent):
self.tools_handler.last_used_tool = None
task_prompt = task.prompt()
task_prompt = build_task_prompt_with_schema(task, task_prompt, self.i18n)
task_prompt = format_task_with_context(task_prompt, context, self.i18n)
task_prompt = build_task_prompt_with_schema(task, task_prompt)
task_prompt = format_task_with_context(task_prompt, context)
return self._retrieve_memory_context(task, task_prompt)
def _finalize_task_prompt(
@@ -562,7 +563,7 @@ class Agent(BaseAgent):
m.format() for m in matches
)
if memory.strip() != "":
task_prompt += self.i18n.slice("memory").format(memory=memory)
task_prompt += I18N_DEFAULT.slice("memory").format(memory=memory)
crewai_event_bus.emit(
self,
@@ -968,14 +969,13 @@ class Agent(BaseAgent):
agent=self,
has_tools=len(raw_tools) > 0,
use_native_tool_calling=use_native_tool_calling,
i18n=self.i18n,
use_system_prompt=self.use_system_prompt,
system_template=self.system_template,
prompt_template=self.prompt_template,
response_template=self.response_template,
).task_execution()
stop_words = [self.i18n.slice("observation")]
stop_words = [I18N_DEFAULT.slice("observation")]
if self.response_template:
stop_words.append(
self.response_template.split("{{ .Response }}")[1].strip()
@@ -1017,7 +1017,6 @@ class Agent(BaseAgent):
self.agent_executor = self.executor_class(
llm=self.llm,
task=task,
i18n=self.i18n,
agent=self,
crew=self.crew,
tools=parsed_tools,
@@ -1262,10 +1261,10 @@ class Agent(BaseAgent):
from_agent=self,
),
)
query = self.i18n.slice("knowledge_search_query").format(
query = I18N_DEFAULT.slice("knowledge_search_query").format(
task_prompt=task_prompt
)
rewriter_prompt = self.i18n.slice("knowledge_search_query_system_prompt")
rewriter_prompt = I18N_DEFAULT.slice("knowledge_search_query_system_prompt")
if not isinstance(self.llm, BaseLLM):
self._logger.log(
"warning",
@@ -1342,7 +1341,6 @@ class Agent(BaseAgent):
raw_tools: list[BaseTool] = self.tools or []
# Inject memory tools for standalone kickoff (crew path handles its own)
agent_memory = getattr(self, "memory", None)
if agent_memory is not None:
from crewai.tools.memory_tools import create_memory_tools
@@ -1384,7 +1382,6 @@ class Agent(BaseAgent):
request_within_rpm_limit=rpm_limit_fn,
callbacks=[TokenCalcHandler(self._token_process)],
response_model=response_format,
i18n=self.i18n,
)
all_files: dict[str, Any] = {}
@@ -1401,7 +1398,6 @@ class Agent(BaseAgent):
if input_files:
all_files.update(input_files)
# Inject memory context for standalone kickoff (recall before execution)
if agent_memory is not None:
try:
crewai_event_bus.emit(
@@ -1420,7 +1416,7 @@ class Agent(BaseAgent):
m.format() for m in matches
)
if memory_block:
formatted_messages += "\n\n" + self.i18n.slice("memory").format(
formatted_messages += "\n\n" + I18N_DEFAULT.slice("memory").format(
memory=memory_block
)
crewai_event_bus.emit(
@@ -1487,8 +1483,6 @@ class Agent(BaseAgent):
Note:
For explicit async usage outside of Flow, use kickoff_async() directly.
"""
# Magic auto-async: if inside event loop (e.g., inside a Flow),
# return coroutine for Flow to await
if is_inside_event_loop():
return self.kickoff_async(messages, response_format, input_files)
@@ -1624,7 +1618,7 @@ class Agent(BaseAgent):
try:
model_schema = generate_model_description(response_format)
schema = json.dumps(model_schema, indent=2)
instructions = self.i18n.slice("formatted_task_instructions").format(
instructions = I18N_DEFAULT.slice("formatted_task_instructions").format(
output_format=schema
)
@@ -1639,7 +1633,7 @@ class Agent(BaseAgent):
if isinstance(conversion_result, BaseModel):
formatted_result = conversion_result
except ConverterError:
pass # Keep raw output if conversion fails
pass
else:
raw_output = str(output) if not isinstance(output, str) else output
@@ -1721,7 +1715,6 @@ class Agent(BaseAgent):
elif callable(self.guardrail):
guardrail_callable = self.guardrail
else:
# Should not happen if called from kickoff with guardrail check
return output
guardrail_result = process_guardrail(

Some files were not shown because too many files have changed in this diff Show More