* 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.
* feat: display task name in verbose output
- Modified event_listener.py to pass task names to the formatter
- Updated console_formatter.py to display task names when available
- Maintains backward compatibility by showing UUID for tasks without names
- Makes verbose output more informative and readable
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: remove unnecessary f-string prefixes in console formatter
Remove extraneous f prefixes from string literals without placeholders
in console_formatter.py to resolve ruff F541 linting errors.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* 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.
* for ephemeral traces
* default false
* simpler and consolidated
* keep raising exception but catch it and continue if its for trace batches
* cleanup
* more cleanup
* not using logger
* refactor: rename TEMP_TRACING_RESOURCE to EPHEMERAL_TRACING_RESOURCE for clarity and consistency in PlusAPI; update related method calls accordingly
* default true
* drop print
* feat: add tracing support to Crew and Flow classes
- Introduced a new `tracing` optional field in both the `Crew` and `Flow` classes to enable tracing functionality.
- Updated the initialization logic to conditionally set up the `TraceCollectionListener` based on the `tracing` flag or the `CREWAI_TRACING_ENABLED` environment variable.
- Removed the obsolete `interfaces.py` file related to tracing.
- Enhanced the `TraceCollectionListener` to accept a `tracing` parameter and adjusted its internal logic accordingly.
- Added tests to verify the correct setup of the trace listener when tracing is enabled.
This change improves the observability of the crew execution process and allows for better debugging and performance monitoring.
* fix flow name
* refactor: replace _send_batch method with finalize_batch calls in TraceCollectionListener
- Updated the TraceCollectionListener to use the batch_manager's finalize_batch method instead of the deprecated _send_batch method for handling trace events.
- This change improves the clarity of the code and ensures that batch finalization is consistently managed through the batch manager.
- Removed the obsolete _send_batch method to streamline the listener's functionality.
* removed comments
* refactor: enhance tracing functionality by introducing utility for tracing checks
- Added a new utility function `is_tracing_enabled` to streamline the logic for checking if tracing is enabled based on the `CREWAI_TRACING_ENABLED` environment variable.
- Updated the `Crew` and `Flow` classes to utilize this utility for improved readability and maintainability.
- Refactored the `TraceCollectionListener` to simplify tracing checks and ensure consistent behavior across components.
- Introduced a new module for tracing utilities to encapsulate related functions, enhancing code organization.
* refactor: remove unused imports from crew and flow modules
- Removed unnecessary `os` imports from both `crew.py` and `flow.py` files to enhance code cleanliness and maintainability.
* initial setup
* feat: enhance CrewKickoffCompletedEvent to include total token usage
- Added total_tokens attribute to CrewKickoffCompletedEvent for better tracking of token usage during crew execution.
- Updated Crew class to emit total token usage upon kickoff completion.
- Removed obsolete context handler and execution context tracker files to streamline event handling.
* cleanup
* remove print statements for loggers
* feat: add CrewAI base URL and improve logging in tracing
- Introduced `CREWAI_BASE_URL` constant for easy access to the CrewAI application URL.
- Replaced print statements with logging in the `TraceSender` class for better error tracking.
- Enhanced the `TraceBatchManager` to provide default values for flow names and removed unnecessary comments.
- Implemented singleton pattern in `TraceCollectionListener` to ensure a single instance is used.
- Added a new test case to verify that the trace listener correctly collects events during crew execution.
* clear
* fix: update datetime serialization in tracing interfaces
- Removed the 'Z' suffix from datetime serialization in TraceSender and TraceEvent to ensure consistent ISO format.
- Added new test cases to validate the functionality of the TraceBatchManager and event collection during crew execution.
- Introduced fixtures to clear event bus listeners before each test to maintain isolation.
* test: enhance tracing tests with mock authentication token
- Added a mock authentication token to the tracing tests to ensure proper setup and event collection.
- Updated test methods to include the mock token, improving isolation and reliability of tests related to the TraceListener and BatchManager.
- Ensured that the tests validate the correct behavior of event collection during crew execution.
* test: refactor tracing tests to improve mock usage
- Moved the mock authentication token patching inside the test class to enhance readability and maintainability.
- Updated test methods to remove unnecessary mock parameters, streamlining the test signatures.
- Ensured that the tests continue to validate the correct behavior of event collection during crew execution while improving isolation.
* test: refactor tracing tests for improved mock usage and consistency
- Moved mock authentication token patching into individual test methods for better clarity and maintainability.
- Corrected the backstory string in the `Agent` instantiation to fix a typo.
- Ensured that all tests validate the correct behavior of event collection during crew execution while enhancing isolation and readability.
* test: add new tracing test for disabled trace listener
- Introduced a new test case to verify that the trace listener does not make HTTP calls when tracing is disabled via environment variables.
- Enhanced existing tests by mocking PlusAPI HTTP calls to avoid authentication and network requests, improving test isolation and reliability.
- Updated the test setup to ensure proper initialization of the trace listener and its components during crew execution.
* refactor: update LLM class to utilize new completion function and improve cost calculation
- Replaced direct calls to `litellm.completion` with a new import for better clarity and maintainability.
- Introduced a new optional attribute `completion_cost` in the LLM class to track the cost of completions.
- Updated the handling of completion responses to ensure accurate cost calculations and improved error handling.
- Removed outdated test cassettes for gemini models to streamline test suite and avoid redundancy.
- Enhanced existing tests to reflect changes in the LLM class and ensure proper functionality.
* test: enhance tracing tests with additional request and response scenarios
- Added new test cases to validate the behavior of the trace listener and batch manager when handling 404 responses from the tracing API.
- Updated existing test cassettes to include detailed request and response structures, ensuring comprehensive coverage of edge cases.
- Improved mock setup to avoid unnecessary network calls and enhance test reliability.
- Ensured that the tests validate the correct behavior of event collection during crew execution, particularly in scenarios where the tracing service is unavailable.
* feat: enable conditional tracing based on environment variable
- Added support for enabling or disabling the trace listener based on the `CREWAI_TRACING_ENABLED` environment variable.
- Updated the `Crew` class to conditionally set up the trace listener only when tracing is enabled, improving performance and resource management.
- Refactored test cases to ensure proper cleanup of event bus listeners before and after each test, enhancing test reliability and isolation.
- Improved mock setup in tracing tests to validate the behavior of the trace listener when tracing is disabled.
* fix: downgrade litellm version from 1.74.9 to 1.74.3
- Updated the `pyproject.toml` and `uv.lock` files to reflect the change in the `litellm` dependency version.
- This downgrade addresses compatibility issues and ensures stability in the project environment.
* refactor: improve tracing test setup by moving mock authentication token patching
- Removed the module-level patch for the authentication token and implemented a fixture to mock the token for all tests in the class, enhancing test isolation and readability.
- Updated the event bus clearing logic to ensure original handlers are restored after tests, improving reliability of the test environment.
- This refactor streamlines the test setup and ensures consistent behavior across tracing tests.
* test: enhance tracing test setup with comprehensive mock authentication
- Expanded the mock authentication token patching to cover all instances where `get_auth_token` is used across different modules, ensuring consistent behavior in tests.
- Introduced a new fixture to reset tracing singleton instances between tests, improving test isolation and reliability.
- This update enhances the overall robustness of the tracing tests by ensuring that all necessary components are properly mocked and reset, leading to more reliable test outcomes.
* just drop the test for now
* refactor: comment out completion-related code in LLM and LLM event classes
- Commented out the `completion` and `completion_cost` imports and their usage in the `LLM` class to prevent potential issues during execution.
- Updated the `LLMCallCompletedEvent` class to comment out the `response_cost` attribute, ensuring consistency with the changes in the LLM class.
- This refactor aims to streamline the code and prepare for future updates without affecting current functionality.
* refactor: update LLM response handling in LiteAgent
- Commented out the `response_cost` attribute in the LLM response handling to align with recent refactoring in the LLM class.
- This change aims to maintain consistency in the codebase and prepare for future updates without affecting current functionality.
* refactor: remove commented-out response cost attributes in LLM and LiteAgent
- Commented out the `response_cost` attribute in both the `LiteAgent` and `LLM` classes to maintain consistency with recent refactoring efforts.
- This change aligns with previous updates aimed at streamlining the codebase and preparing for future enhancements without impacting current functionality.
* bring back litellm upgrade version
Replace inefficient split()[0] operations with partition()[0] for better performance
when extracting the first part of a string before a delimiter.
Key improvements:
• Agent role processing: 29% faster with partition()
• Model provider extraction: 16% faster
• Console formatting: Improved responsiveness
• Better readability and explicit intent
Changes:
- agent_utils.py: Use partition('\n')[0] for agent role extraction
- console_formatter.py: Optimize agent role processing in logging
- llm_utils.py: Improve model provider parsing
- llm.py: Optimize model name parsing
Performance impact: 15-30% improvement in string processing operations
that are frequently used in agent execution and console output.
cliu_whu@yeah.net
Co-authored-by: chiliu <chiliu@paypal.com>
* feat: add exchanged messages in LLMCallCompletedEvent
* feat: add GoalAlignment metric for Agent evaluation
* feat: add SemanticQuality metric for Agent evaluation
* feat: add Tool Metrics for Agent evaluation
* feat: add Reasoning Metrics for Agent evaluation, still in progress
* feat: add AgentEvaluator class
This class will evaluate Agent' results and report to user
* fix: do not evaluate Agent by default
This is a experimental feature we still need refine it further
* test: add Agent eval tests
* fix: render all feedback per iteration
* style: resolve linter issues
* style: fix mypy issues
* fix: allow messages be empty on LLMCallCompletedEvent
Add crew context tracking using OpenTelemetry baggage for thread-safe propagation. Context is set during kickoff and cleaned up in finally block. Added thread safety tests with mocked agent execution.
* feat: add capability to track LLM calls by task and agent
This makes it possible to filter or scope LLM events by specific agents or tasks, which can be very useful for debugging or analytics in real-time application
* feat: add docs about LLM tracking by Agents and Tasks
* fix incompatible BaseLLM.call method signature
* feat: support to filter LLM Events from Lite Agent
* Added Union of List of Task, None, NotSpecified
* Seems like a flaky test
* Fixed run time issue
* Fixed Linting issues
* fix pydantic error
* aesthetic changes
---------
Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
* fix: possible fix for Thinking stuck
* feat: add agent logging events for execution tracking
- Introduced AgentLogsStartedEvent and AgentLogsExecutionEvent to enhance logging capabilities during agent execution.
- Updated CrewAgentExecutor to emit these events at the start and during execution, respectively.
- Modified EventListener to handle the new logging events and format output accordingly in the console.
- Enhanced ConsoleFormatter to display agent logs in a structured format, improving visibility of agent actions and outputs.
* drop emoji
* refactor: improve code structure and logging in LiteAgent and ConsoleFormatter
- Refactored imports in lite_agent.py for better readability.
- Enhanced guardrail property initialization in LiteAgent.
- Updated logging functionality to emit AgentLogsExecutionEvent for better tracking.
- Modified ConsoleFormatter to include tool arguments and final output in status updates.
- Improved output formatting for long text in ConsoleFormatter.
* fix tests
---------
Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>
* Fix issue 2993: Prevent Flow status logs from hiding human input
- Add pause_live_updates() and resume_live_updates() methods to ConsoleFormatter
- Modify _ask_human_input() to pause Flow status updates during human input
- Add comprehensive tests for pause/resume functionality and integration
- Ensure Live session is properly managed during human input prompts
- Fix prevents Flow status logs from overwriting user input prompts
Fixes#2993
Co-Authored-By: João <joao@crewai.com>
* Fix lint: Remove unused pytest import
- Remove unused pytest import from test_console_formatter_pause_resume.py
- Fixes F401 lint error identified in CI
Co-Authored-By: João <joao@crewai.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: João <joao@crewai.com>
* feat: add guardrail support for Agents when using direct kickoff calls
* refactor: expose guardrail func in a proper utils file
* fix: resolve Self import on python 3.10
* docs: add organization management in our CLI docs
* feat: improve user feedback when user is not authenticated
* feat: improve logging about current organization while publishing/install a Tool
* feat: improve logging when Agent repository is not found during fetch
* fix linter offences
* test: fix auth token error
Previously, we only supported tools from the crewai-tools open-source repository. Now, we're introducing improved support for private tool repositories.
- Add `HallucinationGuardrail` class as enterprise feature placeholder
- Update LLM guardrail events to support `HallucinationGuardrail` instances
- Add comprehensive tests for `HallucinationGuardrail` initialization and behavior
- Add integration tests for `HallucinationGuardrail` with task execution system
- Ensure no-op behavior always returns True
* Refactor Crew class memory initialization and enhance event handling
- Simplified the initialization of the external memory attribute in the Crew class.
- Updated memory system retrieval logic for consistency in key usage.
- Introduced a singleton pattern for the Telemetry class to ensure a single instance.
- Replaced telemetry usage in CrewEvaluator with event bus emissions for test results.
- Added new CrewTestResultEvent to handle crew test results more effectively.
- Updated event listener to process CrewTestResultEvent and log telemetry data accordingly.
- Enhanced tests to validate the singleton pattern in Telemetry and the new event handling logic.
* linted
* Remove unused telemetry attribute from Crew class memory initialization
* fix ordering of test
* Implement thread-safe singleton pattern in Telemetry class
- Introduced a threading lock to ensure safe instantiation of the Telemetry singleton.
- Updated the __new__ method to utilize double-checked locking for instance creation.
* Add reasoning attribute to Agent class
Co-Authored-By: Joe Moura <joao@crewai.com>
* Address PR feedback: improve type hints, error handling, refactor reasoning handler, and enhance tests and docs
Co-Authored-By: Joe Moura <joao@crewai.com>
* Implement function calling for reasoning and move prompts to translations
Co-Authored-By: Joe Moura <joao@crewai.com>
* Simplify function calling implementation with better error handling
Co-Authored-By: Joe Moura <joao@crewai.com>
* Enhance system prompts to leverage agent context (role, goal, backstory)
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix lint and type-checker issues
Co-Authored-By: Joe Moura <joao@crewai.com>
* Enhance system prompts to better leverage agent context
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix backstory access in reasoning handler for Python 3.12 compatibility
Co-Authored-By: Joe Moura <joao@crewai.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
* Enhance string interpolation to support hyphens in variable names and add corresponding test cases. Update existing tests for consistency and formatting.
* Refactor tests in task_test.py by removing unused Task instances to streamline test cases for the interpolate_only method and related functions.
* feat: implement knowledge retrieval events in Agent
This commit introduces a series of knowledge retrieval events in the Agent class, enhancing its ability to handle knowledge queries. New events include KnowledgeRetrievalStartedEvent, KnowledgeRetrievalCompletedEvent, KnowledgeQueryGeneratedEvent, KnowledgeQueryFailedEvent, and KnowledgeSearchQueryCompletedEvent. The Agent now emits these events during knowledge retrieval processes, allowing for better tracking and handling of knowledge queries. Additionally, the console formatter has been updated to handle these new events, providing visual feedback during knowledge retrieval operations.
* refactor: update knowledge query handling in Agent
This commit refines the knowledge query processing in the Agent class by renaming variables for clarity and optimizing the query rewriting logic. The system prompt has been updated in the translation file to enhance clarity and context for the query rewriting process. These changes aim to improve the overall readability and maintainability of the code.
* fix: add missing newline at end of en.json file
* fix broken tests
* refactor: rename knowledge query events and enhance retrieval handling
This commit renames the KnowledgeQueryGeneratedEvent to KnowledgeQueryStartedEvent to better reflect its purpose. It also updates the event handling in the EventListener and ConsoleFormatter classes to accommodate the new event structure. Additionally, the retrieval knowledge is now included in the KnowledgeRetrievalCompletedEvent, improving the overall knowledge retrieval process.
* docs for transparancy
* refactor: improve error handling in knowledge query processing
This commit refactors the knowledge query handling in the Agent class by changing the order of checks for LLM compatibility. It now logs a warning and emits a failure event if the LLM is not an instance of BaseLLM before attempting to call the LLM. Additionally, the task_prompt attribute has been removed from the KnowledgeQueryFailedEvent, simplifying the event structure.
* test: add unit test for knowledge search query and VCR cassette
This commit introduces a new test, `test_get_knowledge_search_query`, to verify that the `_get_knowledge_search_query` method in the Agent class correctly interacts with the LLM using the appropriate prompts. Additionally, a VCR cassette is added to record the interactions with the OpenAI API for this test, ensuring consistent and reliable test results.
* build(dev): add pytest-randomly dependency
By randomizing the test execution order, this helps identify tests
that unintentionally depend on shared state or specific execution
order, which can lead to flaky or unreliable test behavior.
* build(dev): add pytest-timeout
This will prevent a test from running indefinitely
* test: block external requests in CI and set default 10s timeout per test
* test: adding missing cassettes
We notice that those cassettes are missing after enabling block-network on CI
* test: increase tests timeout on CI
* test: fix flaky test ValueError: Circular reference detected (id repeated)
* fix: prevent crash when event handler raises exception
Previously, if a registered event handler raised an exception during execution,
it could crash the entire application or interrupt the event dispatch process.
This change wraps handler execution in a try/except block within the `emit` method,
ensuring that exceptions are caught and logged without affecting other handlers or flow.
This improves the resilience of the event bus, especially when handling third-party
or temporary listeners.
