* feat: implement LLM call hooks and enhance agent execution context
- Introduced LLM call hooks to allow modification of messages and responses during LLM interactions.
- Added support for before and after hooks in the CrewAgentExecutor, enabling dynamic adjustments to the execution flow.
- Created LLMCallHookContext for comprehensive access to the executor state, facilitating in-place modifications.
- Added validation for hook callables to ensure proper functionality.
- Enhanced tests for LLM hooks and tool hooks to verify their behavior and error handling capabilities.
- Updated LiteAgent and CrewAgentExecutor to accommodate the new crew context in their execution processes.
* feat: implement LLM call hooks and enhance agent execution context
- Introduced LLM call hooks to allow modification of messages and responses during LLM interactions.
- Added support for before and after hooks in the CrewAgentExecutor, enabling dynamic adjustments to the execution flow.
- Created LLMCallHookContext for comprehensive access to the executor state, facilitating in-place modifications.
- Added validation for hook callables to ensure proper functionality.
- Enhanced tests for LLM hooks and tool hooks to verify their behavior and error handling capabilities.
- Updated LiteAgent and CrewAgentExecutor to accommodate the new crew context in their execution processes.
* fix verbose
* feat: introduce crew-scoped hook decorators and refactor hook registration
- Added decorators for before and after LLM and tool calls to enhance flexibility in modifying execution behavior.
- Implemented a centralized hook registration mechanism within CrewBase to automatically register crew-scoped hooks.
- Removed the obsolete base.py file as its functionality has been integrated into the new decorators and registration system.
- Enhanced tests for the new hook decorators to ensure proper registration and execution flow.
- Updated existing hook handling to accommodate the new decorator-based approach, improving code organization and maintainability.
* feat: enhance hook management with clear and unregister functions
- Introduced functions to unregister specific before and after hooks for both LLM and tool calls, improving flexibility in hook management.
- Added clear functions to remove all registered hooks of each type, facilitating easier state management and cleanup.
- Implemented a convenience function to clear all global hooks in one call, streamlining the process for testing and execution context resets.
- Enhanced tests to verify the functionality of unregistering and clearing hooks, ensuring robust behavior in various scenarios.
* refactor: enhance hook type management for LLM and tool hooks
- Updated hook type definitions to use generic protocols for better type safety and flexibility.
- Replaced Callable type annotations with specific BeforeLLMCallHookType and AfterLLMCallHookType for clarity.
- Improved the registration and retrieval functions for before and after hooks to align with the new type definitions.
- Enhanced the setup functions to handle hook execution results, allowing for blocking of LLM calls based on hook logic.
- Updated related tests to ensure proper functionality and type adherence across the hook management system.
* feat: add execution and tool hooks documentation
- Introduced new documentation for execution hooks, LLM call hooks, and tool call hooks to provide comprehensive guidance on their usage and implementation in CrewAI.
- Updated existing documentation to include references to the new hooks, enhancing the learning resources available for users.
- Ensured consistency across multiple languages (English, Portuguese, Korean) for the new documentation, improving accessibility for a wider audience.
- Added examples and troubleshooting sections to assist users in effectively utilizing hooks for agent operations.
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* feat: add `apps` & `actions` attributes to Agent (#3504)
* feat: add app attributes to Agent
* feat: add actions attribute to Agent
* chore: resolve linter issues
* refactor: merge the apps and actions parameters into a single one
* fix: remove unnecessary print
* feat: logging error when CrewaiPlatformTools fails
* chore: export CrewaiPlatformTools directly from crewai_tools
* style: resolver linter issues
* test: fix broken tests
* style: solve linter issues
* fix: fix broken test
* feat: monorepo restructure and test/ci updates
- Add crewai workspace member
- Fix vcr cassette paths and restore test dirs
- Resolve ci failures and update linter/pytest rules
* chore: update python version to 3.13 and package metadata
* feat: add crewai-tools workspace and fix tests/dependencies
* feat: add crewai-tools workspace structure
* Squashed 'temp-crewai-tools/' content from commit 9bae5633
git-subtree-dir: temp-crewai-tools
git-subtree-split: 9bae56339096cb70f03873e600192bd2cd207ac9
* feat: configure crewai-tools workspace package with dependencies
* fix: apply ruff auto-formatting to crewai-tools code
* chore: update lockfile
* fix: don't allow tool tests yet
* fix: comment out extra pytest flags for now
* fix: remove conflicting conftest.py from crewai-tools tests
* fix: resolve dependency conflicts and test issues
- Pin vcrpy to 7.0.0 to fix pytest-recording compatibility
- Comment out types-requests to resolve urllib3 conflict
- Update requests requirement in crewai-tools to >=2.32.0
* chore: update CI workflows and docs for monorepo structure
* chore: update CI workflows and docs for monorepo structure
* fix: actions syntax
* chore: ci publish and pin versions
* fix: add permission to action
* chore: bump version to 1.0.0a1 across all packages
- Updated version to 1.0.0a1 in pyproject.toml for crewai and crewai-tools
- Adjusted version in __init__.py files for consistency
* WIP: v1 docs (#3626)
(cherry picked from commit d46e20fa09bcd2f5916282f5553ddeb7183bd92c)
* docs: parity for all translations
* docs: full name of acronym AMP
* docs: fix lingering unused code
* docs: expand contextual options in docs.json
* docs: add contextual action to request feature on GitHub (#3635)
* chore: apply linting fixes to crewai-tools
* feat: add required env var validation for brightdata
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
* fix: handle properly anyOf oneOf allOf schema's props
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
* feat: bump version to 1.0.0a2
* Lorenze/native inference sdks (#3619)
* ruff linted
* using native sdks with litellm fallback
* drop exa
* drop print on completion
* Refactor LLM and utility functions for type consistency
- Updated `max_tokens` parameter in `LLM` class to accept `float` in addition to `int`.
- Modified `create_llm` function to ensure consistent type hints and return types, now returning `LLM | BaseLLM | None`.
- Adjusted type hints for various parameters in `create_llm` and `_llm_via_environment_or_fallback` functions for improved clarity and type safety.
- Enhanced test cases to reflect changes in type handling and ensure proper instantiation of LLM instances.
* fix agent_tests
* fix litellm tests and usagemetrics fix
* drop print
* Refactor LLM event handling and improve test coverage
- Removed commented-out event emission for LLM call failures in `llm.py`.
- Added `from_agent` parameter to `CrewAgentExecutor` for better context in LLM responses.
- Enhanced test for LLM call failure to simulate OpenAI API failure and updated assertions for clarity.
- Updated agent and task ID assertions in tests to ensure they are consistently treated as strings.
* fix test_converter
* fixed tests/agents/test_agent.py
* Refactor LLM context length exception handling and improve provider integration
- Renamed `LLMContextLengthExceededException` to `LLMContextLengthExceededExceptionError` for clarity and consistency.
- Updated LLM class to pass the provider parameter correctly during initialization.
- Enhanced error handling in various LLM provider implementations to raise the new exception type.
- Adjusted tests to reflect the updated exception name and ensure proper error handling in context length scenarios.
* Enhance LLM context window handling across providers
- Introduced CONTEXT_WINDOW_USAGE_RATIO to adjust context window sizes dynamically for Anthropic, Azure, Gemini, and OpenAI LLMs.
- Added validation for context window sizes in Azure and Gemini providers to ensure they fall within acceptable limits.
- Updated context window size calculations to use the new ratio, improving consistency and adaptability across different models.
- Removed hardcoded context window sizes in favor of ratio-based calculations for better flexibility.
* fix test agent again
* fix test agent
* feat: add native LLM providers for Anthropic, Azure, and Gemini
- Introduced new completion implementations for Anthropic, Azure, and Gemini, integrating their respective SDKs.
- Added utility functions for tool validation and extraction to support function calling across LLM providers.
- Enhanced context window management and token usage extraction for each provider.
- Created a common utility module for shared functionality among LLM providers.
* chore: update dependencies and improve context management
- Removed direct dependency on `litellm` from the main dependencies and added it under extras for better modularity.
- Updated the `litellm` dependency specification to allow for greater flexibility in versioning.
- Refactored context length exception handling across various LLM providers to use a consistent error class.
- Enhanced platform-specific dependency markers for NVIDIA packages to ensure compatibility across different systems.
* refactor(tests): update LLM instantiation to include is_litellm flag in test cases
- Modified multiple test cases in test_llm.py to set the is_litellm parameter to True when instantiating the LLM class.
- This change ensures that the tests are aligned with the latest LLM configuration requirements and improves consistency across test scenarios.
- Adjusted relevant assertions and comments to reflect the updated LLM behavior.
* linter
* linted
* revert constants
* fix(tests): correct type hint in expected model description
- Updated the expected description in the test_generate_model_description_dict_field function to use 'Dict' instead of 'dict' for consistency with type hinting conventions.
- This change ensures that the test accurately reflects the expected output format for model descriptions.
* refactor(llm): enhance LLM instantiation and error handling
- Updated the LLM class to include validation for the model parameter, ensuring it is a non-empty string.
- Improved error handling by logging warnings when the native SDK fails, allowing for a fallback to LiteLLM.
- Adjusted the instantiation of LLM in test cases to consistently include the is_litellm flag, aligning with recent changes in LLM configuration.
- Modified relevant tests to reflect these updates, ensuring better coverage and accuracy in testing scenarios.
* fixed test
* refactor(llm): enhance token usage tracking and add copy methods
- Updated the LLM class to track token usage and log callbacks in streaming mode, improving monitoring capabilities.
- Introduced shallow and deep copy methods for the LLM instance, allowing for better management of LLM configurations and parameters.
- Adjusted test cases to instantiate LLM with the is_litellm flag, ensuring alignment with recent changes in LLM configuration.
* refactor(tests): reorganize imports and enhance error messages in test cases
- Cleaned up import statements in test_crew.py for better organization and readability.
- Enhanced error messages in test cases to use `re.escape` for improved regex matching, ensuring more robust error handling.
- Adjusted comments for clarity and consistency across test scenarios.
- Ensured that all necessary modules are imported correctly to avoid potential runtime issues.
* feat: add base devtooling
* fix: ensure dep refs are updated for devtools
* fix: allow pre-release
* feat: allow release after tag
* feat: bump versions to 1.0.0a3
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* fix: match tag and release title, ignore devtools build for pypi
* fix: allow failed pypi publish
* feat: introduce trigger listing and execution commands for local development (#3643)
* chore: exclude tests from ruff linting
* chore: exclude tests from GitHub Actions linter
* fix: replace print statements with logger in agent and memory handling
* chore: add noqa for intentional print in printer utility
* fix: resolve linting errors across codebase
* feat: update docs with new approach to consume Platform Actions (#3675)
* fix: remove duplicate line and add explicit env var
* feat: bump versions to 1.0.0a4 (#3686)
* Update triggers docs (#3678)
* docs: introduce triggers list & triggers run command
* docs: add KO triggers docs
* docs: ensure CREWAI_PLATFORM_INTEGRATION_TOKEN is mentioned on docs (#3687)
* Lorenze/bedrock llm (#3693)
* feat: add AWS Bedrock support and update dependencies
- Introduced BedrockCompletion class for AWS Bedrock integration in LLM.
- Added boto3 as a new dependency in both pyproject.toml and uv.lock.
- Updated LLM class to support Bedrock provider.
- Created new files for Bedrock provider implementation.
* using converse api
* converse
* linted
* refactor: update BedrockCompletion class to improve parameter handling
- Changed max_tokens from a fixed integer to an optional integer.
- Simplified model ID assignment by removing the inference profile mapping method.
- Cleaned up comments and unnecessary code related to tool specifications and model-specific parameters.
* feat: improve event bus thread safety and async support
Add thread-safe, async-compatible event bus with read–write locking and
handler dependency ordering. Remove blinker dependency and implement
direct dispatch. Improve type safety, error handling, and deterministic
event synchronization.
Refactor tests to auto-wait for async handlers, ensure clean teardown,
and add comprehensive concurrency coverage. Replace thread-local state
in AgentEvaluator with instance-based locking for correct cross-thread
access. Enhance tracing reliability and event finalization.
* feat: enhance OpenAICompletion class with additional client parameters (#3701)
* feat: enhance OpenAICompletion class with additional client parameters
- Added support for default_headers, default_query, and client_params in the OpenAICompletion class.
- Refactored client initialization to use a dedicated method for client parameter retrieval.
- Introduced new test cases to validate the correct usage of OpenAICompletion with various parameters.
* fix: correct test case for unsupported OpenAI model
- Updated the test_openai.py to ensure that the LLM instance is created before calling the method, maintaining proper error handling for unsupported models.
- This change ensures that the test accurately checks for the NotFoundError when an invalid model is specified.
* fix: enhance error handling in OpenAICompletion class
- Added specific exception handling for NotFoundError and APIConnectionError in the OpenAICompletion class to provide clearer error messages and improve logging.
- Updated the test case for unsupported models to ensure it raises a ValueError with the appropriate message when a non-existent model is specified.
- This change improves the robustness of the OpenAI API integration and enhances the clarity of error reporting.
* fix: improve test for unsupported OpenAI model handling
- Refactored the test case in test_openai.py to create the LLM instance after mocking the OpenAI client, ensuring proper error handling for unsupported models.
- This change enhances the clarity of the test by accurately checking for ValueError when a non-existent model is specified, aligning with recent improvements in error handling for the OpenAICompletion class.
* feat: bump versions to 1.0.0b1 (#3706)
* Lorenze/tools drop litellm (#3710)
* completely drop litellm and correctly pass config for qdrant
* feat: add support for additional embedding models in EmbeddingService
- Expanded the list of supported embedding models to include Google Vertex, Hugging Face, Jina, Ollama, OpenAI, Roboflow, Watson X, custom embeddings, Sentence Transformers, Text2Vec, OpenClip, and Instructor.
- This enhancement improves the versatility of the EmbeddingService by allowing integration with a wider range of embedding providers.
* fix: update collection parameter handling in CrewAIRagAdapter
- Changed the condition for setting vectors_config in the CrewAIRagAdapter to check for QdrantConfig instance instead of using hasattr. This improves type safety and ensures proper configuration handling for Qdrant integration.
* moved stagehand as optional dep (#3712)
* feat: bump versions to 1.0.0b2 (#3713)
* feat: enhance AnthropicCompletion class with additional client parame… (#3707)
* feat: enhance AnthropicCompletion class with additional client parameters and tool handling
- Added support for client_params in the AnthropicCompletion class to allow for additional client configuration.
- Refactored client initialization to use a dedicated method for retrieving client parameters.
- Implemented a new method to handle tool use conversation flow, ensuring proper execution and response handling.
- Introduced comprehensive test cases to validate the functionality of the AnthropicCompletion class, including tool use scenarios and parameter handling.
* drop print statements
* test: add fixture to mock ANTHROPIC_API_KEY for tests
- Introduced a pytest fixture to automatically mock the ANTHROPIC_API_KEY environment variable for all tests in the test_anthropic.py module.
- This change ensures that tests can run without requiring a real API key, improving test isolation and reliability.
* refactor: streamline streaming message handling in AnthropicCompletion class
- Removed the 'stream' parameter from the API call as it is set internally by the SDK.
- Simplified the handling of tool use events and response construction by extracting token usage from the final message.
- Enhanced the flow for managing tool use conversation, ensuring proper integration with the streaming API response.
* fix streaming here too
* fix: improve error handling in tool conversion for AnthropicCompletion class
- Enhanced exception handling during tool conversion by catching KeyError and ValueError.
- Added logging for conversion errors to aid in debugging and maintain robustness in tool integration.
* feat: enhance GeminiCompletion class with client parameter support (#3717)
* feat: enhance GeminiCompletion class with client parameter support
- Added support for client_params in the GeminiCompletion class to allow for additional client configuration.
- Refactored client initialization into a dedicated method for improved parameter handling.
- Introduced a new method to retrieve client parameters, ensuring compatibility with the base class.
- Enhanced error handling during client initialization to provide clearer messages for missing configuration.
- Updated documentation to reflect the changes in client parameter usage.
* add optional dependancies
* refactor: update test fixture to mock GOOGLE_API_KEY
- Renamed the fixture from `mock_anthropic_api_key` to `mock_google_api_key` to reflect the change in the environment variable being mocked.
- This update ensures that all tests in the module can run with a mocked GOOGLE_API_KEY, improving test isolation and reliability.
* fix tests
* feat: enhance BedrockCompletion class with advanced features
* feat: enhance BedrockCompletion class with advanced features and error handling
- Added support for guardrail configuration, additional model request fields, and custom response field paths in the BedrockCompletion class.
- Improved error handling for AWS exceptions and added token usage tracking with stop reason logging.
- Enhanced streaming response handling with comprehensive event management, including tool use and content block processing.
- Updated documentation to reflect new features and initialization parameters.
- Introduced a new test suite for BedrockCompletion to validate functionality and ensure robust integration with AWS Bedrock APIs.
* chore: add boto typing
* fix: use typing_extensions.Required for Python 3.10 compatibility
---------
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
* feat: azure native tests
* feat: add Azure AI Inference support and related tests
- Introduced the `azure-ai-inference` package with version `1.0.0b9` and its dependencies in `uv.lock` and `pyproject.toml`.
- Added new test files for Azure LLM functionality, including tests for Azure completion and tool handling.
- Implemented comprehensive test cases to validate Azure-specific behavior and integration with the CrewAI framework.
- Enhanced the testing framework to mock Azure credentials and ensure proper isolation during tests.
* feat: enhance AzureCompletion class with Azure OpenAI support
- Added support for the Azure OpenAI endpoint in the AzureCompletion class, allowing for flexible endpoint configurations.
- Implemented endpoint validation and correction to ensure proper URL formats for Azure OpenAI deployments.
- Enhanced error handling to provide clearer messages for common HTTP errors, including authentication and rate limit issues.
- Updated tests to validate the new endpoint handling and error messaging, ensuring robust integration with Azure AI Inference.
- Refactored parameter preparation to conditionally include the model parameter based on the endpoint type.
* refactor: convert project module to metaclass with full typing
* Lorenze/OpenAI base url backwards support (#3723)
* fix: enhance OpenAICompletion class base URL handling
- Updated the base URL assignment in the OpenAICompletion class to prioritize the new `api_base` attribute and fallback to the environment variable `OPENAI_BASE_URL` if both are not set.
- Added `api_base` to the list of parameters in the OpenAICompletion class to ensure proper configuration and flexibility in API endpoint management.
* feat: enhance OpenAICompletion class with api_base support
- Added the `api_base` parameter to the OpenAICompletion class to allow for flexible API endpoint configuration.
- Updated the `_get_client_params` method to prioritize `base_url` over `api_base`, ensuring correct URL handling.
- Introduced comprehensive tests to validate the behavior of `api_base` and `base_url` in various scenarios, including environment variable fallback.
- Enhanced test coverage for client parameter retrieval, ensuring robust integration with the OpenAI API.
* fix: improve OpenAICompletion class configuration handling
- Added a debug print statement to log the client configuration parameters during initialization for better traceability.
- Updated the base URL assignment logic to ensure it defaults to None if no valid base URL is provided, enhancing robustness in API endpoint configuration.
- Refined the retrieval of the `api_base` environment variable to streamline the configuration process.
* drop print
* feat: improvements on import native sdk support (#3725)
* feat: add support for Anthropic provider and enhance logging
- Introduced the `anthropic` package with version `0.69.0` in `pyproject.toml` and `uv.lock`, allowing for integration with the Anthropic API.
- Updated logging in the LLM class to provide clearer error messages when importing native providers, enhancing debugging capabilities.
- Improved error handling in the AnthropicCompletion class to guide users on installation via the updated error message format.
- Refactored import error handling in other provider classes to maintain consistency in error messaging and installation instructions.
* feat: enhance LLM support with Bedrock provider and update dependencies
- Added support for the `bedrock` provider in the LLM class, allowing integration with AWS Bedrock APIs.
- Updated `uv.lock` to replace `boto3` with `bedrock` in the dependencies, reflecting the new provider structure.
- Introduced `SUPPORTED_NATIVE_PROVIDERS` to include `bedrock` and ensure proper error handling when instantiating native providers.
- Enhanced error handling in the LLM class to raise informative errors when native provider instantiation fails.
- Added tests to validate the behavior of the new Bedrock provider and ensure fallback mechanisms work correctly for unsupported providers.
* test: update native provider fallback tests to expect ImportError
* adjust the test with the expected bevaior - raising ImportError
* this is exoecting the litellm format, all gemini native tests are in test_google.py
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* fix: remove stdout prints, improve test determinism, and update trace handling
Removed `print` statements from the `LLMStreamChunkEvent` handler to prevent
LLM response chunks from being written directly to stdout. The listener now
only tracks chunks internally.
Fixes#3715
Added explicit return statements for trace-related tests.
Updated cassette for `test_failed_evaluation` to reflect new behavior where
an empty trace dict is used instead of returning early.
Ensured deterministic cleanup order in test fixtures by making
`clear_event_bus_handlers` depend on `setup_test_environment`. This guarantees
event bus shutdown and file handle cleanup occur before temporary directory
deletion, resolving intermittent “Directory not empty” errors in CI.
* chore: remove lib/crewai exclusion from pre-commit hooks
* feat: enhance task guardrail functionality and validation
* feat: enhance task guardrail functionality and validation
- Introduced support for multiple guardrails in the Task class, allowing for sequential processing of guardrails.
- Added a new `guardrails` field to the Task model to accept a list of callable guardrails or string descriptions.
- Implemented validation to ensure guardrails are processed correctly, including handling of retries and error messages.
- Enhanced the `_invoke_guardrail_function` method to manage guardrail execution and integrate with existing task output processing.
- Updated tests to cover various scenarios involving multiple guardrails, including success, failure, and retry mechanisms.
This update improves the flexibility and robustness of task execution by allowing for more complex validation scenarios.
* refactor: enhance guardrail type handling in Task model
- Updated the Task class to improve guardrail type definitions, introducing GuardrailType and GuardrailsType for better clarity and type safety.
- Simplified the validation logic for guardrails, ensuring that both single and multiple guardrails are processed correctly.
- Enhanced error messages for guardrail validation to provide clearer feedback when incorrect types are provided.
- This refactor improves the maintainability and robustness of task execution by standardizing guardrail handling.
* feat: implement per-guardrail retry tracking in Task model
- Introduced a new private attribute `_guardrail_retry_counts` to the Task class for tracking retry attempts on a per-guardrail basis.
- Updated the guardrail processing logic to utilize the new retry tracking, allowing for independent retry counts for each guardrail.
- Enhanced error handling to provide clearer feedback when guardrails fail validation after exceeding retry limits.
- Modified existing tests to validate the new retry tracking behavior, ensuring accurate assertions on guardrail retries.
This update improves the robustness and flexibility of task execution by allowing for more granular control over guardrail validation and retry mechanisms.
* chore: 1.0.0b3 bump (#3734)
* chore: full ruff and mypy
improved linting, pre-commit setup, and internal architecture. Configured Ruff to respect .gitignore, added stricter rules, and introduced a lock pre-commit hook with virtualenv activation. Fixed type shadowing in EXASearchTool using a type_ alias to avoid PEP 563 conflicts and resolved circular imports in agent executor and guardrail modules. Removed agent-ops attributes, deprecated watson alias, and dropped crewai-enterprise tools with corresponding test updates. Refactored cache and memoization for thread safety and cleaned up structured output adapters and related logic.
* New MCL DSL (#3738)
* Adding MCP implementation
* New tests for MCP implementation
* fix tests
* update docs
* Revert "New tests for MCP implementation"
This reverts commit 0bbe6dee90.
* linter
* linter
* fix
* verify mcp pacakge exists
* adjust docs to be clear only remote servers are supported
* reverted
* ensure args schema generated properly
* properly close out
---------
Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
* feat: a2a experimental
experimental a2a support
---------
Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Tony Kipkemboi <iamtonykipkemboi@gmail.com>
Co-authored-by: Mike Plachta <mplachta@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
Fixes nested boolean conditions being flattened in @listen, @start, and @router decorators. The or_() and and_() combinators now preserve their nested structure using a "conditions" key instead of flattening to a list. Added recursive evaluation logic to properly handle complex patterns like or_(and_(A, B), and_(C, D)).
* feat: enhance knowledge event handling in Agent class
- Updated the Agent class to include task context in knowledge retrieval events.
- Emitted new events for knowledge retrieval and query processes, capturing task and agent details.
- Refactored knowledge event classes to inherit from a base class for better structure and maintainability.
- Added tracing for knowledge events in the TraceCollectionListener to improve observability.
This change improves the tracking and management of knowledge queries and retrievals, facilitating better debugging and performance monitoring.
* refactor: remove task_id from knowledge event emissions in Agent class
- Removed the task_id parameter from various knowledge event emissions in the Agent class to streamline event handling.
- This change simplifies the event structure and focuses on the essential context of knowledge retrieval and query processes.
This refactor enhances the clarity of knowledge events and aligns with the recent improvements in event handling.
* surface association for guardrail events
* fix: improve LLM selection logic in converter
- Updated the logic for selecting the LLM in the convert_with_instructions function to handle cases where the agent may not have a function_calling_llm attribute.
- This change ensures that the converter can still function correctly by falling back to the standard LLM if necessary, enhancing robustness and preventing potential errors.
This fix improves the reliability of the conversion process when working with different agent configurations.
* fix test
* fix: enforce valid LLM instance requirement in converter
- Updated the convert_with_instructions function to ensure that a valid LLM instance is provided by the agent.
- If neither function_calling_llm nor the standard llm is available, a ValueError is raised, enhancing error handling and robustness.
- Improved error messaging for conversion failures to provide clearer feedback on issues encountered during the conversion process.
This change strengthens the reliability of the conversion process by ensuring that agents are properly configured with a valid LLM.
- prefix provider env vars with embeddings_
- rename watson → watsonx in providers
- add deprecation warning and alias for legacy 'watson' key (to be removed in v1.0.0)
- introduce baseembeddingsprovider and helper for embedding functions
- add core embedding types and migrate providers, factory, and storage modules
- remove unused type aliases and fix pydantic schema error
- update providers with env var support and related fixes
- add batch_size field to baseragconfig (default=100)
- update chromadb/qdrant clients and factories to use batch_size
- extract and filter batch_size from embedder config in knowledgestorage
- fix large csv files exceeding embedder token limits (#3574)
- remove unneeded conditional for type
Co-authored-by: Vini Brasil <vini@hey.com>
- support nested config format with embedderconfig typeddict
- fix parsing for model/model_name compatibility
- add validation, typing_extensions, and improved type hints
- enhance embedding factory with env var injection and provider support
- add tests for openai, azure, and all embedding providers
- misc fixes: test file rename, updated mocking patterns
* chore: update dependencies and versioning for CrewAI
- Bump `crewai-tools` dependency version from `0.71.0` to `0.73.0` in `pyproject.toml`.
- Update CrewAI version from `0.186.1` to `0.193.0` in `__init__.py`.
- Adjust dependency versions in CLI templates for crew, flow, and tool to reflect the new CrewAI version.
This update ensures compatibility with the latest features and improvements in CrewAI.
* remove embedchain mock
* fix: remove last embedchain mocks
* fix: remove langchain_openai from tests
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
- 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.
* test: add test to ensure tool is called only once during crew execution
- Introduced a new test case to validate that the counting_tool is executed exactly once during crew execution.
- Created a CountingTool class to track execution counts and log call history.
- Enhanced the test suite with a YAML cassette for consistent tool behavior verification.
* ensure tool function called only once
* refactor: simplify error handling in CrewStructuredTool
- Removed unnecessary try-except block around the tool function call to streamline execution flow.
- Ensured that the tool function is called directly, improving readability and maintainability.
* linted
* need to ignore for now as we cant infer the complex generic type within pydantic create_model_func
* fix tests
- Update to Python 3.10+ typing across LLM, callbacks, storage, and errors
- Complete typing updates for crew_chat and hitl
- Add stop attr to mock LLM, suppress test warnings
- Add type-ignore for aisuite import
* fix: support to define MPC connection timeout on CrewBase instance
* fix: resolve linter issues
* chore: ignore specific rule N802 on CrewBase class
* fix: ignore untyped import
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
- 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
* 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.
### RAG Config System
* Added ChromaDB client creation via config with sensible defaults
* Introduced optional imports and shared RAG config utilities/schema
* Enabled embedding function support with ChromaDB provider integration
* Refactored configs for immutability and stronger type safety
* Removed unused code and expanded test coverage
Add ChromaDB client implementation with async support
- Implement core collection operations (create, get_or_create, delete)
- Add search functionality with cosine similarity scoring
- Include both sync and async method variants
- Add type safety with NamedTuples and TypeGuards
- Extract utility functions to separate modules
- Default to cosine distance metric for text similarity
- Add comprehensive test coverage
TODO:
- l2, ip score calculations are not settled on
fix: resolve flaky tests and race conditions in test suite
- Fix telemetry/event tests by patching class methods instead of instances
- Use unique temp files/directories to prevent CI race conditions
- Reset singleton state between tests
- Mock embedchain.Client.setup() to prevent JSON corruption
- Rename test files to test_*.py convention
- Move agent tests to tests/agents directory
- Fix repeated tool usage detection
- Remove database-dependent tools causing initialization errors
* fix: flow listener resumability for HITL and cyclic flows
- Add resumption context flag to distinguish HITL resumption from cyclic execution
- Skip method re-execution only during HITL resumption, not for cyclic flows
- Ensure cyclic flows like test_cyclic_flow continue to work correctly
* fix: prevent duplicate execution of conditional start methods in flows
* fix: resolve type error in flow.py line 1040 assignment
* feat: adding additional parameter to Flow' start methods
When the `crewai_trigger_payload` parameter exists in the input Flow, we will add it in the start Flow methods as parameter
* fix: support crewai_trigger_payload in async Flow start methods
* feat: enhance BaseTool and CrewStructuredTool with usage tracking
This commit introduces a mechanism to track the usage count of tools within the CrewAI framework. The `BaseTool` class now includes a `_increment_usage_count` method that updates the current usage count, which is also reflected in the associated `CrewStructuredTool`. Additionally, a new test has been added to ensure that the maximum usage count is respected when invoking tools, enhancing the overall reliability and functionality of the tool system.
* feat: add max usage count feature to tools documentation
This commit introduces a new section in the tools overview documentation that explains the maximum usage count feature for tools within the CrewAI framework. Users can now set a limit on how many times a tool can be used, enhancing control over tool usage. An example of implementing the `FileReadTool` with a maximum usage count is also provided, improving the clarity and usability of the documentation.
* undo field string
* Refactor tracing logic to consolidate conditions for enabling tracing in Crew class and update TraceBatchManager to handle ephemeral batches more effectively. Added tests for trace listener handling of both ephemeral and authenticated user batches.
* drop print
* linted
* refactor: streamline ephemeral handling in TraceBatchManager
This commit removes the ephemeral parameter from the _send_events_to_backend and _finalize_backend_batch methods, replacing it with internal logic that checks the current batch's ephemeral status. This change simplifies the method signatures and enhances the clarity of the code by directly using the is_current_batch_ephemeral attribute for conditional logic.
