- Merged upstream changes from crewAI-tools main branch
- Resolved conflicts due to monorepo structure (crewai_tools -> src/crewai_tools)
- Removed deprecated embedchain adapters
- Added new RAG loaders and crewai_rag_adapter
- Consolidated dependencies in pyproject.toml
Fixed critical linting issues:
- Added ClassVar annotations for mutable class attributes
- Added timeouts to requests calls (30s default)
- Fixed exception handling with proper 'from' clauses
- Added noqa comments for public API functions (backward compatibility)
- Updated ruff config to ignore expected patterns:
- F401 in __init__ files (intentional re-exports)
- S101 in test files (assertions are expected)
- S607 for subprocess calls (uv/pip commands are safe)
Remaining issues are from upstream code and will be addressed in separate PRs.
* feat(tracing): enhance first-time trace display and auto-open browser
* avoinding line breaking
* set tracing if user enables it
* linted
---------
Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
* docs: update RagTool references from EmbedChain to CrewAI native RAG
* change ref to qdrant
* docs: update RAGTool to use Qdrant and add embedding_model example
- Refactor the default embedding function to utilize OpenAI's embedding function with API key support.
- Import necessary OpenAI embedding function and configure it with the environment variable for the API key.
- Ensure compatibility with existing ChromaDB configuration model.
- Add limit and score_threshold to BaseRagConfig, propagate to clients
- Update default search params in RAG storage, knowledge, and memory (limit=5, threshold=0.6)
- Fix linting (ruff, mypy, PERF203) and refactor save logic
- Update tests for new defaults and ChromaDB behavior
* feat(tracing): implement first-time trace handling and improve event management
- Added FirstTimeTraceHandler for managing first-time user trace collection and display.
- Enhanced TraceBatchManager to support ephemeral trace URLs and improved event buffering.
- Updated TraceCollectionListener to utilize the new FirstTimeTraceHandler.
- Refactored type annotations across multiple files for consistency and clarity.
- Improved error handling and logging for trace-related operations.
- Introduced utility functions for trace viewing prompts and first execution checks.
* brought back crew finalize batch events
* refactor(trace): move instance variables to __init__ in TraceBatchManager
- Refactored TraceBatchManager to initialize instance variables in the constructor instead of as class variables.
- Improved clarity and encapsulation of the class state.
* fix(tracing): improve error handling in user data loading and saving
- Enhanced error handling in _load_user_data and _save_user_data functions to log warnings for JSON decoding and file access issues.
- Updated documentation for trace usage to clarify the addition of tracing parameters in Crew and Flow initialization.
- Refined state management in Flow class to ensure proper handling of state IDs when persistence is enabled.
* add some tests
* fix test
* fix tests
* refactor(tracing): enhance user input handling for trace viewing
- Replaced signal-based timeout handling with threading for user input in prompt_user_for_trace_viewing function.
- Improved user experience by allowing a configurable timeout for viewing execution traces.
- Updated tests to mock threading behavior and verify timeout handling correctly.
* fix(tracing): improve machine ID retrieval with error handling
- Added error handling to the _get_machine_id function to log warnings when retrieving the machine ID fails.
- Ensured that the function continues to provide a stable, privacy-preserving machine fingerprint even in case of errors.
* refactor(flow): streamline state ID assignment in Flow class
- Replaced direct attribute assignment with setattr for improved flexibility in handling state IDs.
- Enhanced code readability by simplifying the logic for setting the state ID when persistence is enabled.
Code QL, when configured through the GUI, does not allow for advanced configuration. This PR upgrades from an advanced file-based config which allows us to exclude certain paths.
- Move tools workflows to root .github/workflows/ with updated paths
- Remove duplicate uv.lock from tools package
- Centralize all CI/CD workflows in monorepo root
- Consolidate dev dependencies to root using PEP 735 dependency groups
- Remove duplicate dependencies between packages
- Remove unused dependencies (pillow, cairosvg, bandit)
- Clean up tool configurations and build targets
- Add crewai-tools as git subtree preserving full history
- Move tools to proper src/ directory structure with git mv
- Configure tools pyproject.toml for workspace dependency on crewai-core
- Update workspace configuration to include both packages
- Fix build configurations for both packages
- Move core CrewAI to packages/crewai with git mv to preserve history
- Create workspace-level pyproject.toml with uv workspace configuration
- Rename core package to crewai-core
- Setup workspace sources for internal package dependencies
- Updated CrewAI version from 0.186.0 to 0.186.1 in `__init__.py`.
- Updated `crewai[tools]` dependency version in `pyproject.toml` for crew, flow, and tool templates to reflect the new CrewAI version.
- Updated `crewai-tools` dependency from version 0.69.0 to 0.71.0 in `pyproject.toml`.
- Bumped CrewAI version from 0.177.0 to 0.186.0 in `__init__.py`.
- Updated dependency versions in CLI templates for crew, flow, and tool to reflect the new CrewAI version.
