- Make task parameter required in CrewAgentExecutor.__init__
- Update Agent.create_agent_executor to require task parameter
- Handle cases where crew can be None (standalone agent usage)
- Update base class signatures to match
- Remove unnecessary create_agent_executor calls during setup
- Add missing type annotations in base_agent_executor_mixin
- Fix all type errors in base_agent.py using Self return type
- Add assert for agent_executor before use
- Fix crew access checks to handle None case
- Add proper type parameters for EmbeddingFunction generics
- Fix ChromaDB query response handling with proper type checking
- Add missing return type annotations to telemetry methods
- Fix trace listener type annotations and imports
- Handle potential None values in nested list indexing
- Improve type safety in RAG and knowledge storage modules
- Fixed rag_storage.py embedder type compatibility and query response handling
- Fixed knowledge_storage.py dict type parameters and return types
- Added comprehensive type annotations to telemetry.py methods
- Added type annotations to trace_listener.py event handlers and methods
- Fixed ChromaDB response indexing safety checks
- Applied proper decorator typing with ParamSpec and typing_extensions.Self
- Fixed event bus decorator to preserve type information
- Added type annotations to BaseEventListener and TraceCollectionListener
- Fixed LongTermMemory.search to handle None return from storage.load
- Resolved all type errors tracked in strict mode
Added type annotations to 10 files to resolve mypy type checking errors:
- Added return type annotations to methods missing them
- Added parameter type annotations where missing
- Fixed Optional type hints to be explicit
- Removed redundant type cast in crew.py
- Changed _execute_with_timeout return type from str to Any in agent.py
Additional type errors remain in other files throughout the codebase.
- Fix tool_usage.py: rename result variable to avoid redefinition
- Fix lite_agent.py: import TaskOutput from correct module and add type casts
- Add explicit type annotation for data dict in tool_usage.py
- Fix tool_usage.py: proper type annotations for result and fingerprint metadata
- Fix lite_agent.py: proper Union type for guardrail callable accepting both LiteAgentOutput and TaskOutput
- Add missing return type annotations to task_output_storage_handler.py methods
- Fix crew.py: replace Json generic check with str, remove unused type:ignore and redundant cast
- Fix return type and argument handling in cache_tools.py
- Add missing return statements in agent.py
- Fix _inject_date_to_task signature to accept Task object
- Remove unused type:ignore comments in tool_usage.py
- Add type annotations to internal methods in mem0_storage.py
- Updated `crewai-tools` dependency from version 0.65.0 to 0.69.0 in `pyproject.toml` and `uv.lock`.
- Bumped crewAI version from 0.175.0 to 0.177.0 in `__init__.py`.
- Updated dependency versions in CLI templates for crew, flow, and tool projects to reflect the new crewAI version.
* fix: suppress Pydantic deprecation warnings in initialization
- Implemented a function to filter out Pydantic deprecation warnings, enhancing the user experience by preventing unnecessary warning messages during execution.
- Removed the previous warning filter setup to streamline the warning suppression process.
- Updated the User-Agent header formatting for consistency.
* fix type check
* dropped
* fix: update type-checker workflow and suppress warnings
- Updated the Python version matrix in the type-checker workflow to use double quotes for consistency.
- Added the `# type: ignore[assignment]` comment to the warning suppression assignment in `__init__.py` to address type checking issues.
- Ensured that the mypy command in the workflow allows for untyped calls and generics, enhancing type checking flexibility.
* better
- Replace Optional with union syntax
- Rename input parameter to input_data to avoid shadowing
- Add JSON serialization for dict cache keys
- Add thread-safety TODO note
chore(dev): update tooling & CI workflows
- Upgrade ruff, mypy (strict), pre-commit; add hooks, stubs, config consolidation
- Add bandit to dev deps and update uv.lock
- Enhance ruff rules (modern Python style, B006 for mutable defaults)
- Update workflows to use uv, matrix strategy, and changed-file type checking
- Include tests in type checking; fix job names and add summary job for branch protection
refactor(events): relocate events module & update imports
- Move events from utilities/ to top-level events/ with types/, listeners/, utils/ structure
- Update all source/tests/docs to new import paths
- Add backwards compatibility stubs in crewai.utilities.events with deprecation warnings
- Restore test mocks and fix related test imports
* fix: enhance LLM event handling with task and agent metadata
- Added `from_task` and `from_agent` parameters to LLM event emissions for improved traceability.
- Updated `_send_events_to_backend` method in TraceBatchManager to return status codes for better error handling.
- Modified `CREWAI_BASE_URL` to remove trailing slash for consistency.
- Improved logging and graceful failure handling in event sending process.
* drop print
- Sanitize ChromaDB collection names and use original dir naming
- Add persistent client with file locking to the ChromaDB factory
- Add upsert support to the ChromaDB client
- Suppress ChromaDB deprecation warnings for `model_fields`
- Extract `suppress_logging` into shared `logger_utils`
- Update tests to reflect upsert behavior
- Docs: add additional note
* Bump crewAI version from 0.165.1 to 0.175.0 in __init__.py.
* Update tools dependency from 0.62.1 to 0.65.0 in pyproject.toml and uv.lock files.
* Reflect changes in CLI templates for crew, flow, and tool configurations.
* feat: implement tool usage limit exception handling
- Introduced `ToolUsageLimitExceeded` exception to manage maximum usage limits for tools.
- Enhanced `CrewStructuredTool` to check and raise this exception when the usage limit is reached.
- Updated `_run` and `_execute` methods to include usage limit checks and handle exceptions appropriately, improving reliability and user feedback.
* feat: enhance PlusAPI and ToolUsage with task metadata
- Removed the `send_trace_batch` method from PlusAPI to streamline the API.
- Added timeout parameters to trace event methods in PlusAPI for improved reliability.
- Updated ToolUsage to include task metadata (task name and ID) in event emissions, enhancing traceability and context during tool usage.
- Refactored event handling in LLM and ToolUsage events to ensure task information is consistently captured.
* feat: enhance memory and event handling with task and agent metadata
- Added task and agent metadata to various memory and event classes, improving traceability and context during memory operations.
- Updated the `ContextualMemory` and `Memory` classes to associate tasks and agents, allowing for better context management.
- Enhanced event emissions in `LLM`, `ToolUsage`, and memory events to include task and agent information, facilitating improved debugging and monitoring.
- Refactored event handling to ensure consistent capture of task and agent details across the system.
* drop
* refactor: clean up unused imports in memory and event modules
- Removed unused TYPE_CHECKING imports from long_term_memory.py to streamline the code.
- Eliminated unnecessary import from memory_events.py, enhancing clarity and maintainability.
* fix memory tests
* fix task_completed payload
* fix: remove unused test agent variable in external memory tests
* refactor: remove unused agent parameter from Memory class save method
- Eliminated the agent parameter from the save method in the Memory class to streamline the code and improve clarity.
- Updated the TraceBatchManager class by moving initialization of attributes into the constructor for better organization and readability.
* refactor: enhance ExecutionState and ReasoningEvent classes with optional task and agent identifiers
- Added optional `current_agent_id` and `current_task_id` attributes to the `ExecutionState` class for better tracking of agent and task states.
- Updated the `from_task` attribute in the `ReasoningEvent` class to use `Optional[Any]` instead of a specific type, improving flexibility in event handling.
* refactor: update ExecutionState class by removing unused agent and task identifiers
- Removed the `current_agent_id` and `current_task_id` attributes from the `ExecutionState` class to simplify the code and enhance clarity.
- Adjusted the import statements to include `Optional` for better type handling.
* refactor: streamline LLM event handling in LiteAgent
- Removed unused LLM event emissions (LLMCallStartedEvent, LLMCallCompletedEvent, LLMCallFailedEvent) from the LiteAgent class to simplify the code and improve performance.
- Adjusted the flow of LLM response handling by eliminating unnecessary event bus interactions, enhancing clarity and maintainability.
* flow ownership and not emitting events when a crew is done
* refactor: remove unused agent parameter from ShortTermMemory save method
- Eliminated the agent parameter from the save method in the ShortTermMemory class to streamline the code and improve clarity.
- This change enhances the maintainability of the memory management system by reducing unnecessary complexity.
* runtype check fix
* fixing tests
* fix lints
* fix: update event assertions in test_llm_emits_event_with_lite_agent
- Adjusted the expected counts for completed and started events in the test to reflect the correct behavior of the LiteAgent.
- Updated assertions for agent roles and IDs to match the expected values after recent changes in event handling.
* fix: update task name assertions in event tests
- Modified assertions in `test_stream_llm_emits_event_with_task_and_agent_info` and `test_llm_emits_event_with_task_and_agent_info` to use `task.description` as a fallback for `task.name`. This ensures that the tests correctly validate the task name even when it is not explicitly set.
* fix: update test assertions for output values and improve readability
- Updated assertions in `test_output_json_dict_hierarchical` to reflect the correct expected score value.
- Enhanced readability of assertions in `test_output_pydantic_to_another_task` and `test_key` by formatting the error messages for clarity.
- These changes ensure that the tests accurately validate the expected outputs and improve overall code quality.
* test fixes
* fix crew_test
* added another fixture
* fix: ensure agent and task assignments in contextual memory are conditional
- Updated the ContextualMemory class to check for the existence of short-term, long-term, external, and extended memory before assigning agent and task attributes. This prevents potential attribute errors when memory types are not initialized.
* Added Qdrant provider support with factory, config, and protocols
* Improved default embeddings and type definitions
* Fixed ChromaDB factory embedding assignment
