This commit fixes the race condition described in issue #4168 where
token tracking was inaccurate when multiple async tasks from the same
agent ran concurrently.
The fix introduces:
1. Per-agent locks to serialize async task execution for accurate token
tracking when multiple async tasks from the same agent run concurrently
2. Token capture callback that captures both tokens_before and tokens_after
inside the thread (after acquiring the lock), not when the task is queued
3. Updated _process_async_tasks to handle the new return type from
execute_async which now returns (TaskOutput, tokens_before, tokens_after)
This ensures that token deltas are accurately attributed to each task
even when multiple async tasks from the same agent overlap in execution.
Tests added:
- test_async_task_token_tracking_uses_per_agent_lock
- test_async_task_token_callback_captures_tokens_inside_thread
- test_async_task_per_agent_lock_serializes_execution
Co-Authored-By: João <joao@crewai.com>
* Refactor EventListener and TraceCollectionListener for improved event handling
- Removed unused threading and method branches from EventListener to simplify the code.
- Updated event handling methods in EventListener to use new formatter methods for better clarity and consistency.
- Refactored TraceCollectionListener to eliminate unnecessary parameters in formatter calls, enhancing readability.
- Simplified ConsoleFormatter by removing outdated tree management methods and focusing on panel-based output for status updates.
- Enhanced ToolUsage to track run attempts for better tool usage metrics.
* clearer for knowledge retrieval and dropped some reduancies
* Refactor EventListener and ConsoleFormatter for improved clarity and consistency
- Removed the MCPToolExecutionCompletedEvent handler from EventListener to streamline event processing.
- Updated ConsoleFormatter to enhance output formatting by adding line breaks for better readability in status content.
- Renamed status messages for MCP Tool execution to provide clearer context during tool operations.
* fix run attempt incrementation
* task name consistency
* memory events consistency
* ensure hitl works
* linting
* WIP gh pr refactor: update agent executor handling and introduce flow-based executor
* wip
* refactor: clean up comments and improve code clarity in agent executor flow
- Removed outdated comments and unnecessary explanations in and classes to enhance code readability.
- Simplified parameter updates in the agent executor to avoid confusion regarding executor recreation.
- Improved clarity in the method to ensure proper handling of non-final answers without raising errors.
* bumping pytest-randomly numpy
* also bump versions of anthropic sdk
* ensure flow logs are not passed if its on executor
* revert anthropic bump
* fix
* refactor: update dependency markers in uv.lock for platform compatibility
- Enhanced dependency markers for , , , and others to ensure compatibility across different platforms (Linux, Darwin, and architecture-specific conditions).
- Removed unnecessary event emission in the class during kickoff.
- Cleaned up commented-out code in the class for better readability and maintainability.
* drop dupllicate
* test: enhance agent executor creation and stop word assertions
- Added calls to create_agent_executor in multiple test cases to ensure proper agent execution setup.
- Updated assertions for stop words in the agent tests to remove unnecessary checks and improve clarity.
- Ensured consistency in task handling by invoking create_agent_executor with the appropriate task parameter.
* refactor: reorganize agent executor imports and introduce CrewAgentExecutorFlow
- Removed the old import of CrewAgentExecutorFlow and replaced it with the new import from the experimental module.
- Updated relevant references in the codebase to ensure compatibility with the new structure.
- Enhanced the organization of imports in core.py and base_agent.py for better clarity and maintainability.
* updating name
* dropped usage of printer here for rich console and dropped non-added value logging
* address i18n
* Enhance concurrency control in CrewAgentExecutorFlow by introducing a threading lock to prevent concurrent executions. This change ensures that the executor instance cannot be invoked while already running, improving stability and reliability during flow execution.
* string literal returns
* string literal returns
* Enhance CrewAgentExecutor initialization by allowing optional i18n parameter for improved internationalization support. This change ensures that the executor can utilize a provided i18n instance or fallback to the default, enhancing flexibility in multilingual contexts.
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* feat: introduce human feedback events and decorator for flow methods
- Added HumanFeedbackRequestedEvent and HumanFeedbackReceivedEvent classes to handle human feedback interactions within flows.
- Implemented the @human_feedback decorator to facilitate human-in-the-loop workflows, allowing for feedback collection and routing based on responses.
- Enhanced Flow class to store human feedback history and manage feedback outcomes.
- Updated flow wrappers to preserve attributes from methods decorated with @human_feedback.
- Added integration and unit tests for the new human feedback functionality, ensuring proper validation and routing behavior.
* adding deployment docs
* New docs
* fix printer
* wrong change
* Adding Async Support
feat: enhance human feedback support in flows
- Updated the @human_feedback decorator to use 'message' parameter instead of 'request' for clarity.
- Introduced new FlowPausedEvent and MethodExecutionPausedEvent to handle flow and method pauses during human feedback.
- Added ConsoleProvider for synchronous feedback collection and integrated async feedback capabilities.
- Implemented SQLite persistence for managing pending feedback context.
- Expanded documentation to include examples of async human feedback usage and best practices.
* linter
* fix
* migrating off printer
* updating docs
* new tests
* doc update
* fix: use CREWAI_PLUS_URL env var in precedence over PlusAPI configured value
* feat: bypass TLS certificate verification when calling platform
* test: fix test
- Replace Python representation with JsonSchema for tool arguments
- Remove deprecated PydanticSchemaParser in favor of direct schema generation
- Add handling for VAR_POSITIONAL and VAR_KEYWORD parameters
- Improve tool argument schema collection
* fix: gracefully terminate the future when executing a task async
* core: add unit test
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* supporting thinking for anthropic models
* drop comments here
* thinking and tool calling support
* fix: properly mock tool use and text block types in Anthropic tests
- Updated the test for the Anthropic tool use conversation flow to include type attributes for mocked ToolUseBlock and text blocks, ensuring accurate simulation of tool interactions during testing.
* feat: add AnthropicThinkingConfig for enhanced thinking capabilities
This update introduces the AnthropicThinkingConfig class to manage thinking parameters for the Anthropic completion model. The LLM and AnthropicCompletion classes have been updated to utilize this new configuration. Additionally, new test cassettes have been added to validate the functionality of thinking blocks across interactions.
Adds async support for tools with tests, async execution in the agent executor, and async operations for memory (with aiosqlite). Improves tool decorator typing, ensures _run backward compatibility, updates docs and docstrings, adds tests, and regenerates lockfiles.
Introduces async tool support with new tests, adds async execution to the agent executor, improves tool decorator typing, ensures _run backward compatibility, updates docs and docstrings, and adds additional tests.
* refactor: enhance model validation and provider inference in LLM class
- Updated the model validation logic to support pattern matching for new models and "latest" versions, improving flexibility for various providers.
- Refactored the `_validate_model_in_constants` method to first check hardcoded constants and then fall back to pattern matching.
- Introduced `_matches_provider_pattern` to streamline provider-specific model checks.
- Enhanced the `_infer_provider_from_model` method to utilize pattern matching for better provider inference.
This refactor aims to improve the extensibility of the LLM class, allowing it to accommodate new models without requiring constant updates to the hardcoded lists.
* feat: add new Anthropic model versions to constants
- Introduced "claude-opus-4-5-20251101" and "claude-opus-4-5" to the AnthropicModels and ANTHROPIC_MODELS lists for enhanced model support.
- Added "anthropic.claude-opus-4-5-20251101-v1:0" to BedrockModels and BEDROCK_MODELS to ensure compatibility with the latest model offerings.
- Updated test cases to ensure proper environment variable handling for model validation, improving robustness in testing scenarios.
* dont infer this way - dropped
* Adding drop parameters
* Adding test case
* Just some spacing addition
* Adding drop params to maintain consistency
* Changing variable name
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* feat: enhance flow event state management
- Added `state` attribute to `FlowFinishedEvent` to capture the flow's state as a JSON-serialized dictionary.
- Updated flow event emissions to include the serialized state, improving traceability and debugging capabilities during flow execution.
* fix: improve state serialization in Flow class
- Enhanced the `_copy_and_serialize_state` method to handle exceptions during JSON serialization of Pydantic models, ensuring robustness in state management.
- Updated test assertions to access the state as a dictionary, aligning with the new state structure.
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* Add gemini-3-pro-preview
Also refactors the tool support check for better forward compatibility.
* Add cassette for Gemini 3 Pro
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
- add trust_remote_completion_status flag to A2AConfig, Adds configuration flag to control whether to trust A2A agent completion status. Resolves#3899
- update docs
* 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>
- Added support for before and after LLM call hooks to allow modification of messages and responses during LLM interactions.
- Introduced LLMCallHookContext to provide hooks with access to the executor state, enabling in-place modifications of messages.
- Updated get_llm_response function to utilize the new hooks, ensuring that modifications persist across iterations.
- Enhanced tests to verify the functionality of the hooks and their error handling capabilities, ensuring robust execution flow.
* feat: add messages to task and agent outputs
- Introduced a new field in and to capture messages from the last task execution.
- Updated the class to store the last messages and provide a property for easy access.
- Enhanced the and classes to include messages in their outputs.
- Added tests to ensure that messages are correctly included in task outputs and agent outputs during execution.
* using typing_extensions for 3.10 compatability
* feat: add last_messages attribute to agent for improved task tracking
- Introduced a new `last_messages` attribute in the agent class to store messages from the last task execution.
- Updated the `Crew` class to handle the new messages attribute in task outputs.
- Enhanced existing tests to ensure that the `last_messages` attribute is correctly initialized and utilized across various guardrail scenarios.
* fix: add messages field to TaskOutput in tests for consistency
- Updated multiple test cases to include the new `messages` field in the `TaskOutput` instances.
- Ensured that all relevant tests reflect the latest changes in the TaskOutput structure, maintaining consistency across the test suite.
- This change aligns with the recent addition of the `last_messages` attribute in the agent class for improved task tracking.
* feat: preserve messages in task outputs during replay
- Added functionality to the Crew class to store and retrieve messages in task outputs.
- Enhanced the replay mechanism to ensure that messages from stored task outputs are preserved and accessible.
- Introduced a new test case to verify that messages are correctly stored and replayed, ensuring consistency in task execution and output handling.
- This change improves the overall tracking and context retention of task interactions within the CrewAI framework.
* fix original test, prev was debugging
