55 Commits

Author	SHA1	Message	Date
Greyson LaLonde	6c7ea422e7	refactor: convert LLM classes to Pydantic BaseModel	2026-03-31 07:07:11 +08:00
Lucas Gomide	ac14b9127e	fix: handle GPT-5.x models not supporting the stop API parameter (#5144) ... GPT-5.x models reject the `stop` parameter at the API level with "Unsupported parameter: 'stop' is not supported with this model". This breaks CrewAI executions when routing through LiteLLM (e.g. via OpenAI-compatible gateways like Asimov), because the LiteLLM fallback path always includes `stop` in the API request params. The native OpenAI provider was unaffected because it never sends `stop` to the API — it applies stop words client-side via `_apply_stop_words()`. However, when the request goes through LiteLLM (custom endpoints, proxy gateways), `stop` is sent as an API parameter and GPT-5.x rejects it. Additionally, the existing retry logic that catches this error only matched the OpenAI API error format ("Unsupported parameter") but missed LiteLLM's own pre-validation error format ("does not support parameters"), so the self-healing retry never triggered for LiteLLM-routed calls.	2026-03-30 11:36:51 -04:00
Lorenze Jay	32d7b4a8d4	Lorenze/feat/plan execute pattern (#4817) ... * feat: introduce PlanningConfig for enhanced agent planning capabilities (#4344) * feat: introduce PlanningConfig for enhanced agent planning capabilities This update adds a new PlanningConfig class to manage agent planning configurations, allowing for customizable planning behavior before task execution. The existing reasoning parameter is deprecated in favor of this new configuration, ensuring backward compatibility while enhancing the planning process. Additionally, the Agent class has been updated to utilize this new configuration, and relevant utility functions have been adjusted accordingly. Tests have been added to validate the new planning functionality and ensure proper integration with existing agent workflows. * dropping redundancy * fix test * revert handle_reasoning here * refactor: update reasoning handling in Agent class This commit modifies the Agent class to conditionally call the handle_reasoning function based on the executor class being used. The legacy CrewAgentExecutor will continue to utilize handle_reasoning, while the new AgentExecutor will manage planning internally. Additionally, the PlanningConfig class has been referenced in the documentation to clarify its role in enabling or disabling planning. Tests have been updated to reflect these changes and ensure proper functionality. * improve planning prompts * matching * refactor: remove default enabled flag from PlanningConfig in Agent class * more cassettes * fix test * refactor: update planning prompt and remove deprecated methods in reasoning handler * improve planning prompt * Lorenze/feat planning pt 2 todo list gen (#4449) * feat: introduce PlanningConfig for enhanced agent planning capabilities This update adds a new PlanningConfig class to manage agent planning configurations, allowing for customizable planning behavior before task execution. The existing reasoning parameter is deprecated in favor of this new configuration, ensuring backward compatibility while enhancing the planning process. Additionally, the Agent class has been updated to utilize this new configuration, and relevant utility functions have been adjusted accordingly. Tests have been added to validate the new planning functionality and ensure proper integration with existing agent workflows. * dropping redundancy * fix test * revert handle_reasoning here * refactor: update reasoning handling in Agent class This commit modifies the Agent class to conditionally call the handle_reasoning function based on the executor class being used. The legacy CrewAgentExecutor will continue to utilize handle_reasoning, while the new AgentExecutor will manage planning internally. Additionally, the PlanningConfig class has been referenced in the documentation to clarify its role in enabling or disabling planning. Tests have been updated to reflect these changes and ensure proper functionality. * improve planning prompts * matching * refactor: remove default enabled flag from PlanningConfig in Agent class * more cassettes * fix test * feat: enhance agent planning with structured todo management This commit introduces a new planning system within the AgentExecutor class, allowing for the creation of structured todo items from planning steps. The TodoList and TodoItem models have been added to facilitate tracking of plan execution. The reasoning plan now includes a list of steps, improving the clarity and organization of agent tasks. Additionally, tests have been added to validate the new planning functionality and ensure proper integration with existing workflows. * refactor: update planning prompt and remove deprecated methods in reasoning handler * improve planning prompt * improve handler * linted * linted * Lorenze/feat/planning pt 3 todo list execution (#4450) * feat: introduce PlanningConfig for enhanced agent planning capabilities This update adds a new PlanningConfig class to manage agent planning configurations, allowing for customizable planning behavior before task execution. The existing reasoning parameter is deprecated in favor of this new configuration, ensuring backward compatibility while enhancing the planning process. Additionally, the Agent class has been updated to utilize this new configuration, and relevant utility functions have been adjusted accordingly. Tests have been added to validate the new planning functionality and ensure proper integration with existing agent workflows. * dropping redundancy * fix test * revert handle_reasoning here * refactor: update reasoning handling in Agent class This commit modifies the Agent class to conditionally call the handle_reasoning function based on the executor class being used. The legacy CrewAgentExecutor will continue to utilize handle_reasoning, while the new AgentExecutor will manage planning internally. Additionally, the PlanningConfig class has been referenced in the documentation to clarify its role in enabling or disabling planning. Tests have been updated to reflect these changes and ensure proper functionality. * improve planning prompts * matching * refactor: remove default enabled flag from PlanningConfig in Agent class * more cassettes * fix test * feat: enhance agent planning with structured todo management This commit introduces a new planning system within the AgentExecutor class, allowing for the creation of structured todo items from planning steps. The TodoList and TodoItem models have been added to facilitate tracking of plan execution. The reasoning plan now includes a list of steps, improving the clarity and organization of agent tasks. Additionally, tests have been added to validate the new planning functionality and ensure proper integration with existing workflows. * refactor: update planning prompt and remove deprecated methods in reasoning handler * improve planning prompt * improve handler * execute todos and be able to track them * feat: introduce PlannerObserver and StepExecutor for enhanced plan execution This commit adds the PlannerObserver and StepExecutor classes to the CrewAI framework, implementing the observation phase of the Plan-and-Execute architecture. The PlannerObserver analyzes step execution results, determines plan validity, and suggests refinements, while the StepExecutor executes individual todo items in isolation. These additions improve the overall planning and execution process, allowing for more dynamic and responsive agent behavior. Additionally, new observation events have been defined to facilitate monitoring and logging of the planning process. * refactor: enhance final answer synthesis in AgentExecutor This commit improves the synthesis of final answers in the AgentExecutor class by implementing a more coherent approach to combining results from multiple todo items. The method now utilizes a single LLM call to generate a polished response, falling back to concatenation if the synthesis fails. Additionally, the test cases have been updated to reflect the changes in planning and execution, ensuring that the results are properly validated and that the plan-and-execute architecture is functioning as intended. * refactor: enhance final answer synthesis in AgentExecutor This commit improves the synthesis of final answers in the AgentExecutor class by implementing a more coherent approach to combining results from multiple todo items. The method now utilizes a single LLM call to generate a polished response, falling back to concatenation if the synthesis fails. Additionally, the test cases have been updated to reflect the changes in planning and execution, ensuring that the results are properly validated and that the plan-and-execute architecture is functioning as intended. * refactor: implement structured output handling in final answer synthesis This commit enhances the final answer synthesis process in the AgentExecutor class by introducing support for structured outputs when a response model is specified. The synthesis method now utilizes the response model to produce outputs that conform to the expected schema, while still falling back to concatenation in case of synthesis failures. This change ensures that intermediate steps yield free-text results, but the final output can be structured, improving the overall coherence and usability of the synthesized answers. * regen tests * linted * fix * Enhance PlanningConfig and AgentExecutor with Reasoning Effort Levels This update introduces a new attribute in the class, allowing users to customize the observation and replanning behavior during task execution. The class has been modified to utilize this new attribute, routing step observations based on the specified reasoning effort level: low, medium, or high. Additionally, tests have been added to validate the functionality of the reasoning effort levels, ensuring that the agent behaves as expected under different configurations. This enhancement improves the adaptability and efficiency of the planning process in agent execution. * regen cassettes for test and fix test * cassette regen * fixing tests * dry * Refactor PlannerObserver and StepExecutor to Utilize I18N for Prompts This update enhances the PlannerObserver and StepExecutor classes by integrating the I18N utility for managing prompts and messages. The system and user prompts are now retrieved from the I18N module, allowing for better localization and maintainability. Additionally, the code has been cleaned up to remove hardcoded strings, improving readability and consistency across the planning and execution processes. * Refactor PlannerObserver and StepExecutor to Utilize I18N for Prompts This update enhances the PlannerObserver and StepExecutor classes by integrating the I18N utility for managing prompts and messages. The system and user prompts are now retrieved from the I18N module, allowing for better localization and maintainability. Additionally, the code has been cleaned up to remove hardcoded strings, improving readability and consistency across the planning and execution processes. * consolidate agent logic * fix datetime * improving step executor * refactor: streamline observation and refinement process in PlannerObserver - Updated the PlannerObserver to apply structured refinements directly from observations without requiring a second LLM call. - Renamed method to for clarity. - Enhanced documentation to reflect changes in how refinements are handled. - Removed unnecessary LLM message building and parsing logic, simplifying the refinement process. - Updated event emissions to include summaries of refinements instead of raw data. * enhance step executor with tool usage events and validation - Added event emissions for tool usage, including started and finished events, to track tool execution. - Implemented validation to ensure expected tools are called during step execution, raising errors when not. - Refactored the method to handle tool execution with event logging. - Introduced a new method for parsing tool input into a structured format. - Updated tests to cover new functionality and ensure correct behavior of tool usage events. * refactor: enhance final answer synthesis logic in AgentExecutor - Updated the finalization process to conditionally skip synthesis when the last todo result is sufficient as a complete answer. - Introduced a new method to determine if the last todo result can be used directly, improving efficiency. - Added tests to verify the new behavior, ensuring synthesis is skipped when appropriate and maintained when a response model is set. * fix: update observation handling in PlannerObserver for LLM errors - Modified the error handling in the PlannerObserver to default to a conservative replan when an LLM call fails. - Updated the return values to indicate that the step was not completed successfully and that a full replan is needed. - Added a new test to verify the behavior of the observer when an LLM error occurs, ensuring the correct replan logic is triggered. * refactor: enhance planning and execution flow in agents - Updated the PlannerObserver to accept a kickoff input for standalone task execution, improving flexibility in task handling. - Refined the step execution process in StepExecutor to support multi-turn action loops, allowing for iterative tool execution and observation. - Introduced a method to extract relevant task sections from descriptions, ensuring clarity in task requirements. - Enhanced the AgentExecutor to manage step failures more effectively, triggering replans only when necessary and preserving completed task history. - Updated translations to reflect changes in planning principles and execution prompts, emphasizing concrete and executable steps. * refactor: update setup_native_tools to include tool_name_mapping - Modified the setup_native_tools function to return an additional mapping of tool names. - Updated StepExecutor and AgentExecutor classes to accommodate the new return value from setup_native_tools. * fix tests * linted * linted * feat: enhance image block handling in Anthropic provider and update AgentExecutor logic - Added a method to convert OpenAI-style image_url blocks to Anthropic's required format. - Updated AgentExecutor to handle cases where no todos are ready, introducing a needs_replan return state. - Improved fallback answer generation in AgentExecutor to prevent RuntimeErrors when no final output is produced. * lint * lint * 1. Added failed to TodoStatus (planning_types.py) - TodoStatus now includes failed as a valid state: Literal[pending, running, completed, failed] - Added mark_failed(step_number, result) method to TodoList - Added get_failed_todos() method to TodoList - Updated is_complete to treat both completed and failed as terminal states - Updated replace_pending_todos docstring to mention failed items are preserved 2. Mark running todos as failed before replan (agent_executor.py) All three effort-level handlers now call mark_failed() on the current todo before routing to replan_now: - Low effort (handle_step_observed_low): hard-failure branch - Medium effort (handle_step_observed_medium): needs_full_replan branch - High effort (decide_next_action): both needs_full_replan and step_completed_successfully=False branches 3. Updated _should_replan to use get_failed_todos() Previously filtered on todo.status == failed which was dead code. Now uses the proper accessor method that will actually find failed items. What this fixes: Before these changes, a step that triggered a replan would stay in running status permanently, causing is_complete to never return True and next_pending to skip it — leading to stuck execution states. Now failed steps are properly tracked, replanning context correctly reports them, and LiteAgentOutput.failed_todos will actually return results. * fix test * imp on failed states * adjusted the var name from AgentReActState to AgentExecutorState * addressed p0 bugs * more improvements * linted * regen cassette * addressing crictical comments * ensure configurable timeouts, max_replans and max step iterations * adjusted tools * dropping debug statements * addressed comment * fix linter * lints and test fixes * fix: default observation parse fallback to failure and clean up plan-execute types When _parse_observation_response fails all parse attempts, default to step_completed_successfully=False instead of True to avoid silently masking failures. Extract duplicate _extract_task_section into a shared utility in agent_utils. Type PlanningConfig.llm as str | BaseLLM | None instead of str | Any | None. Make StepResult a frozen dataclass for immutability consistency with StepExecutionContext. * fix: remove Any from function_calling_llm union type in step_executor * fix: make BaseTool usage count thread-safe for parallel step execution Add _usage_lock and _claim_usage() to BaseTool for atomic check-and-increment of current_usage_count. This prevents race conditions when parallel plan steps invoke the same tool concurrently via execute_todos_parallel. Remove the racy pre-check from execute_single_native_tool_call since the limit is now enforced atomically inside tool.run(). --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com> Co-authored-by: Greyson LaLonde <greyson@crewai.com>	2026-03-15 18:33:17 -07:00
Rip&Tear	fb2323b3de	Code interpreter sandbox escape (#4791) ... * [SECURITY] Fix sandbox escape vulnerability in CodeInterpreterTool (F-001) This commit addresses a critical security vulnerability where the CodeInterpreterTool could be exploited via sandbox escape attacks when Docker was unavailable. Changes: - Remove insecure fallback to restricted sandbox in run_code_safety() - Now fails closed with RuntimeError when Docker is unavailable - Mark run_code_in_restricted_sandbox() as deprecated and insecure - Add clear security warnings to SandboxPython class documentation - Update tests to reflect secure-by-default behavior - Add test demonstrating the sandbox escape vulnerability - Update README with security requirements and best practices The previous implementation would fall back to a Python-based 'restricted sandbox' when Docker was unavailable. However, this sandbox could be easily bypassed using Python object introspection to recover the original __import__ function, allowing arbitrary module access and command execution on the host. The fix enforces Docker as a requirement for safe code execution. Users who cannot use Docker must explicitly enable unsafe_mode=True, acknowledging the security risks. Security Impact: - Prevents RCE via sandbox escape when Docker is unavailable - Enforces fail-closed security model - Maintains backward compatibility via unsafe_mode flag References: - https://docs.crewai.com/tools/ai-ml/codeinterpretertool Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com> * Add security fix documentation for F-001 Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com> * Add Slack summary for security fix Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com> * Delete SECURITY_FIX_F001.md * Delete SLACK_SUMMARY.md * chore: regen cassettes * chore: regen more cassettes * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com> Co-authored-by: Greyson LaLonde <greyson@crewai.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>	2026-03-15 13:18:02 +08:00
Greyson LaLonde	b7af26ff60	ci: add slack notification on successful pypi publish	2026-03-13 12:05:52 -04:00
Greyson LaLonde	48eb7c6937	fix: propagate contextvars across all thread and executor boundaries	2026-03-13 00:32:22 -04:00
Lorenze Jay	7cffcab84a	ensure we support tool search - saving tokens and dynamically inject appropriate tools during execution - anthropic (#4779) ... * ensure we support tool search * linted * dont tool search if there is only one tool	2026-03-10 10:48:13 -07:00
Greyson LaLonde	b371f97a2f	fix: map output_pydantic/output_json to native structured output ... * fix: map output_pydantic/output_json to native structured output * test: add crew+tools+structured output integration test for Gemini * fix: re-record stale cassette for test_crew_testing_function * fix: re-record remaining stale cassettes for native structured output * fix: enable native structured output for lite agent and fix mypy errors	2026-02-25 17:13:34 -05:00
Lorenze Jay	d09656664d	supporting parallel tool use (#4513) ... * supporting parallel tool use * ensure we respect max_usage_count * ensure result_as_answer, hooks, and cache parodity * improve crew agent executor * address test comments	2026-02-19 14:07:28 -08:00
João Moura	18d266c8e7	New Unified Memory System (#4420) ... * chore: update memory management and dependencies - Enhance the memory system by introducing a unified memory API that consolidates short-term, long-term, entity, and external memory functionalities. - Update the `.gitignore` to exclude new memory-related files and blog directories. - Modify `conftest.py` to handle missing imports for vcr stubs more gracefully. - Add new development dependencies in `pyproject.toml` for testing and memory management. - Refactor the `Crew` class to utilize the new unified memory system, replacing deprecated memory attributes. - Implement memory context injection in `LiteAgent` to improve memory recall during agent execution. - Update documentation to reflect changes in memory usage and configuration. * feat: introduce Memory TUI for enhanced memory management - Add a new command to the CLI for launching a Textual User Interface (TUI) to browse and recall memories. - Implement the MemoryTUI class to facilitate user interaction with memory scopes and records. - Enhance the unified memory API by adding a method to list records within a specified scope. - Update `pyproject.toml` to include the `textual` dependency for TUI functionality. - Ensure proper error handling for missing dependencies when accessing the TUI. * feat: implement consolidation flow for memory management - Introduce the ConsolidationFlow class to handle the decision-making process for inserting, updating, or deleting memory records based on new content. - Add new data models: ConsolidationAction and ConsolidationPlan to structure the actions taken during consolidation. - Enhance the memory types with new fields for consolidation thresholds and limits. - Update the unified memory API to utilize the new consolidation flow for managing memory records. - Implement embedding functionality for new content to facilitate similarity checks. - Refactor existing memory analysis methods to integrate with the consolidation process. - Update translations to include prompts for consolidation actions and user interactions. * feat: enhance Memory TUI with Rich markup and improved UI elements - Update the MemoryTUI class to utilize Rich markup for better visual representation of memory scope information. - Introduce a color palette for consistent branding across the TUI interface. - Refactor the CSS styles to improve the layout and aesthetics of the memory browsing experience. - Enhance the display of memory entries, including better formatting for records and importance ratings. - Implement loading indicators and error messages with Rich styling for improved user feedback during recall operations. - Update the action bindings and navigation prompts for a more intuitive user experience. * feat: enhance Crew class memory management and configuration - Update the Crew class to allow for more flexible memory configurations by accepting Memory, MemoryScope, or MemorySlice instances. - Refactor memory initialization logic to support custom memory configurations while maintaining backward compatibility. - Improve documentation for memory-related fields to clarify usage and expectations. - Introduce a recall oversample factor to optimize memory recall processes. - Update related memory types and configurations to ensure consistency across the memory management system. * chore: update dependency overrides and enhance memory management - Added an override for the 'rich' dependency to allow compatibility with 'textual' requirements. - Updated the 'pyproject.toml' and 'uv.lock' files to reflect the new dependency specifications. - Refactored the Crew class to simplify memory configuration handling by allowing any type for the memory attribute. - Improved error messages in the CLI for missing 'textual' dependency to guide users on installation. - Introduced new packages and dependencies in the project to enhance functionality and maintain compatibility. * refactor: enhance thread safety in flow management - Updated LockedListProxy and LockedDictProxy to subclass list and dict respectively, ensuring compatibility with libraries requiring strict type checks. - Improved documentation to clarify the purpose of these proxies and their thread-safe operations. - Ensured that all mutations are protected by locks while reads delegate to the underlying data structures, enhancing concurrency safety. * chore: update dependency versions and improve Python compatibility - Downgraded 'vcrpy' dependency to version 7.0.0 for compatibility. - Enhanced 'uv.lock' to include more granular resolution markers for Python versions and implementations, ensuring better compatibility across different environments. - Updated 'urllib3' and 'selenium' dependencies to specify versions based on Python implementation, improving stability and performance. - Removed deprecated resolution markers for 'fastembed' and streamlined its dependencies for better clarity. * fix linter * chore: update uv.lock for improved dependency management and memory management enhancements - Incremented revision number in uv.lock to reflect changes. - Added a new development dependency group in uv.lock, specifying versions for tools like pytest, mypy, and pre-commit to streamline development workflows. - Enhanced error handling in CLI memory functions to provide clearer feedback on missing dependencies. - Refactored memory management classes to improve type hints and maintainability, ensuring better compatibility with future updates. * fix tests * refactor: remove obsolete RAGStorage tests and clean up error handling - Deleted outdated tests for RAGStorage that were no longer relevant, including tests for client failures, save operation failures, and reset failures. - Cleaned up the test suite to focus on current functionality and improve maintainability. - Ensured that remaining tests continue to validate the expected behavior of knowledge storage components. * fix test * fix texts * fix tests * forcing new commit * fix: add location parameter to Google Vertex embedder configuration for memory integration tests * debugging CI * adding debugging for CI * refactor: remove unnecessary logging for memory checks in agent execution - Eliminated redundant logging statements related to memory checks in the Agent and CrewAgentExecutor classes. - Simplified the memory retrieval logic by directly checking for available memory without logging intermediate states. - Improved code readability and maintainability by reducing clutter in the logging output. * udpating desp * feat: enhance thread safety in LockedListProxy and LockedDictProxy - Added equality comparison methods (__eq__ and __ne__) to LockedListProxy and LockedDictProxy to allow for safe comparison of their contents. - Implemented consistent locking mechanisms to prevent deadlocks during comparisons. - Improved the overall robustness of these proxy classes in multi-threaded environments. * feat: enhance memory functionality in Flows documentation and memory system - Added a new section on memory usage within Flows, detailing built-in methods for storing and recalling memories. - Included an example of a Research and Analyze Flow demonstrating the integration of memory for accumulating knowledge over time. - Updated the Memory documentation to clarify the unified memory system and its capabilities, including adaptive-depth recall and composite scoring. - Introduced a new configuration parameter, `recall_oversample_factor`, to improve the effectiveness of memory retrieval processes. * update docs * refactor: improve memory record handling and pagination in unified memory system - Simplified the `get_record` method in the Memory class by directly accessing the storage's `get_record` method. - Enhanced the `list_records` method to include an `offset` parameter for pagination, allowing users to skip a specified number of records. - Updated documentation for both methods to clarify their functionality and parameters, improving overall code clarity and usability. * test: update memory scope assertions in unified memory tests - Modified assertions in `test_lancedb_list_scopes_get_scope_info` and `test_memory_list_scopes_info_tree` to check for the presence of the "/team" scope instead of the root scope. - Clarified comments to indicate that `list_scopes` returns child scopes rather than the root itself, enhancing test clarity and accuracy. * feat: integrate memory tools for agents and crews - Added functionality to inject memory tools into agents during initialization, enhancing their ability to recall and remember information mid-task. - Implemented a new `_add_memory_tools` method in the Crew class to facilitate the addition of memory tools when memory is available. - Introduced `RecallMemoryTool` and `RememberTool` classes in a new `memory_tools.py` file, providing agents with active recall and memory storage capabilities. - Updated English translations to include descriptions for the new memory tools, improving user guidance on their usage. * refactor: streamline memory recall functionality across agents and tools - Removed the 'depth' parameter from memory recall calls in LiteAgent and Agent classes, simplifying the recall process. - Updated the MemoryTUI to use 'deep' depth by default for more comprehensive memory retrieval. - Enhanced the MemoryScope and MemorySlice classes to default to 'deep' depth, improving recall accuracy. - Introduced a new 'recall_queries' field in QueryAnalysis to optimize semantic vector searches with targeted phrases. - Updated documentation and comments to reflect changes in memory recall behavior and parameters. * refactor: optimize memory management in flow classes - Enhanced memory auto-creation logic in Flow class to prevent unnecessary Memory instance creation for internal flows (RecallFlow, ConsolidationFlow) by introducing a _skip_auto_memory flag. - Removed the deprecated time_hints field from QueryAnalysis and replaced it with a more flexible time_filter field to better handle time-based queries. - Updated documentation and comments to reflect changes in memory handling and query analysis structure, improving clarity and usability. * updates tests * feat: introduce EncodingFlow for enhanced memory encoding pipeline - Added a new EncodingFlow class to orchestrate the encoding process for memory, integrating LLM analysis and embedding. - Updated the Memory class to utilize EncodingFlow for saving content, improving the overall memory management and conflict resolution. - Enhanced the unified memory module to include the new EncodingFlow in its public API, facilitating better memory handling. - Updated tests to ensure proper functionality of the new encoding flow and its integration with existing memory features. * refactor: optimize memory tool integration and recall flow - Streamlined the addition of memory tools in the Agent class by using list comprehension for cleaner code. - Enhanced the RecallFlow class to build task lists more efficiently with list comprehensions, improving readability and performance. - Updated the RecallMemoryTool to utilize list comprehensions for formatting memory results, simplifying the code structure. - Adjusted test assertions in LiteAgent to reflect the default behavior of memory recall depth, ensuring clarity in expected outcomes. * Potential fix for pull request finding 'Empty except' Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com> * chore: gen missing cassette * fix * test: enhance memory extraction test by mocking recall to prevent LLM calls Updated the test for memory extraction to include a mock for the recall method, ensuring that the test focuses on the save path without invoking external LLM calls. This improves test reliability and clarity. * refactor: enhance memory handling by adding agent role parameter Updated memory storage methods across multiple classes to include an optional `agent_role` parameter, improving the context of stored memories. Additionally, modified the initialization of several flow classes to suppress flow events, enhancing performance and reducing unnecessary event triggers. * feat: enhance agent memory functionality with recall and save mechanisms Implemented memory context injection during agent kickoff, allowing for memory recall before execution and passive saving of results afterward. Added new methods to handle memory saving and retrieval, including error handling for memory operations. Updated the BaseAgent class to support dynamic memory resolution and improved memory record structure with source and privacy attributes for better provenance tracking. * test * feat: add utility method to simplify tools field in console formatter Introduced a new static method `_simplify_tools_field` in the console formatter to transform the 'tools' field from full tool objects to a comma-separated string of tool names. This enhancement improves the readability of tool information in the output. * refactor: improve lazy initialization of LLM and embedder in Memory class Refactored the Memory class to implement lazy initialization for the LLM and embedder, ensuring they are only created when first accessed. This change enhances the robustness of the Memory class by preventing initialization failures when constructed without an API key. Additionally, updated error handling to provide clearer guidance for users on resolving initialization issues. * refactor: consolidate memory saving methods for improved efficiency Refactored memory handling across multiple classes to replace individual memory saving calls with a batch method, `remember_many`, enhancing performance and reducing redundancy. Updated related tools and schemas to support single and multiple item memory operations, ensuring a more streamlined interface for memory interactions. Additionally, improved documentation and test coverage for the new functionality. * feat: enhance MemoryTUI with improved layout and entry handling Updated the MemoryTUI class to incorporate a new vertical layout, adding an OptionList for displaying entries and enhancing the detail view for selected records. Introduced methods for populating entry and recall lists, improving user interaction and data presentation. Additionally, refined CSS styles for better visual organization and focus handling. * fix test * feat: inject memory tools into LiteAgent for enhanced functionality Added logic to the LiteAgent class to inject memory tools if memory is configured, ensuring that memory tools are only added if they are not already present. This change improves the agent's capability to utilize memory effectively during execution. * feat: add synchronous execution method to ConsolidationFlow for improved integration Introduced a new `run_sync()` method in the ConsolidationFlow class to facilitate procedural execution of the consolidation pipeline without relying on asynchronous event loops. Updated the EncodingFlow class to utilize this method for conflict resolution, ensuring compatibility within its async context. This change enhances the flow's ability to manage memory records effectively during nested executions. * refactor: update ConsolidationFlow and EncodingFlow for improved async handling Removed the synchronous `run_sync()` method from ConsolidationFlow and refactored the consolidate method in EncodingFlow to be asynchronous. This change allows for direct awaiting of the ConsolidationFlow's kickoff method, enhancing compatibility within the async event loop and preventing nested asyncio.run() issues. Additionally, updated the execution plan to listen for multiple paths, streamlining the consolidation process. * fix: update flow documentation and remove unused ConsolidationFlow Corrected the comment in Flow class regarding internal flows, replacing "ConsolidationFlow" with "EncodingFlow". Removed the ConsolidationFlow class as it is no longer needed, streamlining the memory handling process. Updated related imports and ensured that the memory module reflects these changes, enhancing clarity and maintainability. * feat: enhance memory handling with background saving and query analysis optimization Implemented a background saving mechanism in the Memory class to allow non-blocking memory operations, improving performance during high-load scenarios. Added a query analysis threshold to skip LLM calls for short queries, optimizing recall efficiency. Updated related methods and documentation to reflect these changes, ensuring a more responsive and efficient memory management system. * fix test * fix test * fix: handle synchronous fallback for save operations in Memory class Updated the Memory class to implement a synchronous fallback mechanism for save operations when the background thread pool is shut down. This change ensures that late save requests still succeed, improving reliability in memory management during shutdown scenarios. * feat: implement HITL learning features in human feedback decorator Added support for learning from human feedback in the human feedback decorator. Introduced parameters to enable lesson distillation and pre-review of outputs based on past feedback. Updated related tests to ensure proper functionality of the learning mechanism, including memory interactions and default LLM usage. --------- Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com> Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2026-02-13 21:34:37 -03:00
Lorenze Jay	2ed0c2c043	imp compaction (#4399) ... * imp compaction * fix lint * cassette gen * cassette gen * improve assert * adding azure * fix global docstring	2026-02-11 15:52:03 -08:00
Lorenze Jay	0341e5aee7	supporting prompt cache results show (#4447) ... * supporting prompt cache * droped azure tests * fix tests --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2026-02-11 14:07:15 -08:00
Greyson LaLonde	7d498b29be	fix: event ordering; flow state locks, routing ... * fix: add current task id context and flow updates introduce a context var for the current task id in `crewai.context` to track task scope. update `Flow._execute_single_listener` to return `(result, event_id)` and adjust callers to unpack it and append `FlowMethodName(str(result))` to `router_results`. set/reset the current task id at the start/end of task execution (async + sync) with minor import and call-site tweaks. * fix: await event futures and flush event bus call `crewai_event_bus.flush()` after crew kickoff. in `Flow`, await event handler futures instead of just collecting them: await pending `_event_futures` before finishing, await emitted futures immediately with try/except to log failures, then clear `_event_futures`. ensures handlers complete and errors surface. * fix: continue iteration on tool completion events expand the loop bridge listener to also trigger on tool completion events (`tool_completed` and `native_tool_completed`) so agent iteration resumes after tools finish. add a `requests.post` mock and response fixture in the liteagent test to simulate platform tool execution. refresh and sanitize vcr cassettes (updated model responses, timestamps, and header placeholders) to reflect tool-call flows and new recordings. * fix: thread-safe state proxies & native routing add thread-safe state proxies and refactor native tool routing. * introduce `LockedListProxy` and `LockedDictProxy` in `flow.py` and update `StateProxy` to return them for list/dict attrs so mutations are protected by the flow lock. * update `AgentExecutor` to use `StateProxy` on flow init, guard the messages setter with the state lock, and return a `StateProxy` from the temp state accessor. * convert `call_llm_native_tools` into a listener (no direct routing return) and add `route_native_tool_result` to route based on state (pending tool calls, final answer, or context error). * minor cleanup in `continue_iteration` to drop orphan listeners on init. * update test cassettes for new native tool call responses, timestamps, and ids. improves concurrency safety for shared state and makes native tool routing explicit. * chore: regen cassettes * chore: regen cassettes, remove duplicate listener call path	2026-02-06 14:02:43 -05:00
Lorenze Jay	3fec4669af	Lorenze/fix/anthropic available functions call (#4360) ... * feat: enhance AnthropicCompletion to support available functions in tool execution - Updated the `_prepare_completion_params` method to accept `available_functions` for better tool handling. - Modified tool execution logic to directly return results from tools when `available_functions` is provided, aligning behavior with OpenAI's model. - Added new test cases to validate the execution of tools with available functions, ensuring correct argument passing and result formatting. This change improves the flexibility and usability of the Anthropic LLM integration, allowing for more complex interactions with tools. * refactor: remove redundant event emission in AnthropicCompletion * fix test * dry up	2026-02-03 16:30:43 -08:00
Vini Brasil	576b74b2ef	Add call_id to LLM events for correlating requests (#4281) ... When monitoring LLM events, consumers need to know which events belong to the same API call. Before this change, there was no way to correlate LLMCallStartedEvent, LLMStreamChunkEvent, and LLMCallCompletedEvent belonging to the same request.	2026-02-03 10:10:33 -03:00
Greyson LaLonde	9d7f45376a	fix: use contextvars for flow execution context	2026-02-02 11:24:02 -05:00
Greyson LaLonde	102b6ae855	feat: add a2a liteagent, auth, transport negotiation, and file support ... * feat: add server-side auth schemes and protocol extensions - add server auth scheme base class and implementations (api key, bearer token, basic/digest auth, mtls) - add server-side extension system for a2a protocol extensions - add extensions middleware for x-a2a-extensions header management - add extension validation and registry utilities - enhance auth utilities with server-side support - add async intercept method to match client call interceptor protocol - fix type_checking import to resolve mypy errors with a2aconfig * feat: add transport negotiation and content type handling - add transport negotiation logic with fallback support - add content type parser and encoder utilities - add transport configuration models (client and server) - add transport types and enums - enhance config with transport settings - add negotiation events for transport and content type * feat: add a2a delegation support to LiteAgent * feat: add file input support to a2a delegation and tasks Introduces handling of file inputs in A2A delegation flows by converting file dictionaries to protocol-compatible parts and propagating them through delegation and task execution functions. Updates include utility functions for file conversion, changes to message construction, and passing input_files through relevant APIs. * feat: liteagent a2a delegation support to kickoff methods	2026-01-30 17:10:00 -05:00
Lorenze Jay	19ce56032c	fix: improve output handling and response model integration in agents (#4307) ... * fix: improve output handling and response model integration in agents - Refactored output handling in the Agent class to ensure proper conversion and formatting of outputs, including support for BaseModel instances. - Enhanced the AgentExecutor class to correctly utilize response models during execution, improving the handling of structured outputs. - Updated the Gemini and Anthropic completion providers to ensure compatibility with new response model handling, including the addition of strict mode for function definitions. - Improved the OpenAI completion provider to enforce strict adherence to function schemas. - Adjusted translations to clarify instructions regarding output formatting and schema adherence. * drop what was a print that didnt get deleted properly * fixes gemini * azure working * bedrock works * added tests * adjust test * fix tests and regen * fix tests and regen * refactor: ensure stop words are applied correctly in Azure, Gemini, and OpenAI completions; add tests to validate behavior with structured outputs * linting	2026-01-30 12:27:46 -08:00
Lorenze Jay	2d05e59223	Lorenze/improve tool response pt2 (#4297) ... * no need post tool reflection on native tools * refactor: update prompt generation to prevent thought leakage - Modified the prompt structure to ensure agents without tools use a simplified format, avoiding ReAct instructions. - Introduced a new 'task_no_tools' slice for agents lacking tools, ensuring clean output without Thought: prefixes. - Enhanced test coverage to verify that prompts do not encourage thought leakage, ensuring outputs remain focused and direct. - Added integration tests to validate that real LLM calls produce clean outputs without internal reasoning artifacts. * dont forget the cassettes	2026-01-28 16:53:19 -08:00
Lorenze Jay	f53bdb28ac	feat: implement before and after tool call hooks in CrewAgentExecutor… (#4287) ... * feat: implement before and after tool call hooks in CrewAgentExecutor and AgentExecutor - Added support for before and after tool call hooks in both CrewAgentExecutor and AgentExecutor classes. - Introduced ToolCallHookContext to manage context for hooks, allowing for enhanced control over tool execution. - Implemented logic to block tool execution based on before hooks and to modify results based on after hooks. - Added integration tests to validate the functionality of the new hooks, ensuring they work as expected in various scenarios. - Enhanced the overall flexibility and extensibility of tool interactions within the CrewAI framework. * Potential fix for pull request finding 'Unused local variable' Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com> * Potential fix for pull request finding 'Unused local variable' Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com> * test: add integration test for before hook blocking tool execution in Crew - Implemented a new test to verify that the before hook can successfully block the execution of a tool within a crew. - The test checks that the tool is not executed when the before hook returns False, ensuring proper control over tool interactions. - Enhanced the validation of hook calls to confirm that both before and after hooks are triggered appropriately, even when execution is blocked. - This addition strengthens the testing coverage for tool call hooks in the CrewAI framework. * drop unused * refactor(tests): remove OPENAI_API_KEY check from tool hook tests - Eliminated the check for the OPENAI_API_KEY environment variable in the test cases for tool hooks. - This change simplifies the test setup and allows for running tests without requiring the API key to be set, improving test accessibility and flexibility. --------- Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>	2026-01-27 14:56:50 -08:00
Lorenze Jay	58b866a83d	Lorenze/supporting vertex embeddings (#4282) ... * feat: introduce GoogleGenAIVertexEmbeddingFunction for dual SDK support - Added a new embedding function to support both the legacy vertexai.language_models SDK and the new google-genai SDK for Google Vertex AI. - Updated factory methods to route to the new embedding function. - Enhanced VertexAIProvider and related configurations to accommodate the new model options. - Added integration tests for Google Vertex embeddings with Crew memory, ensuring compatibility and functionality with both authentication methods. This update improves the flexibility and compatibility of Google Vertex AI embeddings within the CrewAI framework. * fix test count * rm comment * regen cassettes * regen * drop variable from .envtest * dreict to relevant trest only	2026-01-26 14:55:03 -08:00
Greyson LaLonde	9797567342	feat: add structured outputs and response_format support across providers (#4280) ... * feat: add response_format parameter to Azure and Gemini providers * feat: add structured outputs support to Bedrock and Anthropic providers * chore: bump anthropic dep * fix: use beta structured output for new models	2026-01-26 11:03:33 -08:00
Lorenze Jay	0cb40374de	Enhance Gemini LLM Tool Handling and Add Test for Float Responses (#4273) ... - Updated the GeminiCompletion class to handle non-dict values returned from tools, ensuring that floats are wrapped in a dictionary format for consistent response handling. - Introduced a new YAML cassette to test the Gemini LLM's ability to process tools that return float values, verifying that the agent can correctly utilize the sum_numbers tool and return the expected results. - Added a comprehensive test case to validate the integration of the sum_numbers tool within the Gemini LLM, ensuring accurate calculations and proper response formatting. These changes improve the robustness of tool interactions within the Gemini LLM and enhance testing coverage for float return values. Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2026-01-25 12:50:49 -08:00
Greyson LaLonde	c4c9208229	feat: native multimodal file handling; openai responses api ... - add input_files parameter to Crew.kickoff(), Flow.kickoff(), Task, and Agent.kickoff() - add provider-specific file uploaders for OpenAI, Anthropic, Gemini, and Bedrock - add file type detection, constraint validation, and automatic format conversion - add URL file source support for multimodal content - add streaming uploads for large files - add prompt caching support for Anthropic - add OpenAI Responses API support	2026-01-23 15:13:25 -05:00
Lorenze Jay	bd4d039f63	Lorenze/imp/native tool calling (#4258) ... * wip restrcuturing agent executor and liteagent * fix: handle None task in AgentExecutor to prevent errors Added a check to ensure that if the task is None, the method returns early without attempting to access task properties. This change improves the robustness of the AgentExecutor by preventing potential errors when the task is not set. * refactor: streamline AgentExecutor initialization by removing redundant parameters Updated the Agent class to simplify the initialization of the AgentExecutor by removing unnecessary task and crew parameters in standalone mode. This change enhances code clarity and maintains backward compatibility by ensuring that the executor is correctly configured without redundant assignments. * wip: clean * ensure executors work inside a flow due to flow in flow async structure * refactor: enhance agent kickoff preparation by separating common logic Updated the Agent class to introduce a new private method that consolidates the common setup logic for both synchronous and asynchronous kickoff executions. This change improves code clarity and maintainability by reducing redundancy in the kickoff process, while ensuring that the agent can still execute effectively within both standalone and flow contexts. * linting and tests * fix test * refactor: improve test for Agent kickoff parameters Updated the test for the Agent class to ensure that the kickoff method correctly preserves parameters. The test now verifies the configuration of the agent after kickoff, enhancing clarity and maintainability. Additionally, the test for asynchronous kickoff within a flow context has been updated to reflect the Agent class instead of LiteAgent. * refactor: update test task guardrail process output for improved validation Refactored the test for task guardrail process output to enhance the validation of the output against the OpenAPI schema. The changes include a more structured request body and updated response handling to ensure compliance with the guardrail requirements. This update aims to improve the clarity and reliability of the test cases, ensuring that task outputs are correctly validated and feedback is appropriately provided. * test fix cassette * test fix cassette * working * working cassette * refactor: streamline agent execution and enhance flow compatibility Refactored the Agent class to simplify the execution method by removing the event loop check and clarifying the behavior when called from synchronous and asynchronous contexts. The changes ensure that the method operates seamlessly within flow methods, improving clarity in the documentation. Additionally, updated the AgentExecutor to set the response model to None, enhancing flexibility. New test cassettes were added to validate the functionality of agents within flow contexts, ensuring robust testing for both synchronous and asynchronous operations. * fixed cassette * Enhance Flow Execution Logic - Introduced conditional execution for start methods in the Flow class. - Unconditional start methods are prioritized during kickoff, while conditional starts are executed only if no unconditional starts are present. - Improved handling of cyclic flows by allowing re-execution of conditional start methods triggered by routers. - Added checks to continue execution chains for completed conditional starts. These changes improve the flexibility and control of flow execution, ensuring that the correct methods are triggered based on the defined conditions. * Enhance Agent and Flow Execution Logic - Updated the Agent class to automatically detect the event loop and return a coroutine when called within a Flow, simplifying async handling for users. - Modified Flow class to execute listeners sequentially, preventing race conditions on shared state during listener execution. - Improved handling of coroutine results from synchronous methods, ensuring proper execution flow and state management. These changes enhance the overall execution logic and user experience when working with agents and flows in CrewAI. * Enhance Flow Listener Logic and Agent Imports - Updated the Flow class to track fired OR listeners, ensuring that multi-source OR listeners only trigger once during execution. This prevents redundant executions and improves flow efficiency. - Cleared fired OR listeners during cyclic flow resets to allow re-execution in new cycles. - Modified the Agent class imports to include Coroutine from collections.abc, enhancing type handling for asynchronous operations. These changes improve the control and performance of flow execution in CrewAI, ensuring more predictable behavior in complex scenarios. * adjusted test due to new cassette * ensure native tool calling works with liteagent * ensure response model is respected * Enhance Tool Name Handling for LLM Compatibility - Added a new function to replace invalid characters in function names with underscores, ensuring compatibility with LLM providers. - Updated the function to sanitize tool names before validation. - Modified the function to use sanitized names for tool registration. These changes improve the robustness of tool name handling, preventing potential issues with invalid characters in function names. * ensure we dont finalize batch on just a liteagent finishing * max tools per turn wip and ensure we drop print times * fix sync main issues * fix llm_call_completed event serialization issue * drop max_tools_iterations * for fixing model dump with state * Add extract_tool_call_info function to handle various tool call formats - Introduced a new utility function to extract tool call ID, name, and arguments from different provider formats (OpenAI, Gemini, Anthropic, and dictionary). - This enhancement improves the flexibility and compatibility of tool calls across multiple LLM providers, ensuring consistent handling of tool call information. - The function returns a tuple containing the call ID, function name, and function arguments, or None if the format is unrecognized. * Refactor AgentExecutor to support batch execution of native tool calls - Updated the method to process all tools from in a single batch, enhancing efficiency and reducing the number of interactions with the LLM. - Introduced a new utility function to streamline the extraction of tool call details, improving compatibility with various tool formats. - Removed the parameter, simplifying the initialization of the . - Enhanced logging and message handling to provide clearer insights during tool execution. - This refactor improves the overall performance and usability of the agent execution flow. * Update English translations for tool usage and reasoning instructions - Revised the `post_tool_reasoning` message to clarify the analysis process after tool usage, emphasizing the need to provide only the final answer if requirements are met. - Updated the `format` message to simplify the instructions for deciding between using a tool or providing a final answer, enhancing clarity for users. - These changes improve the overall user experience by providing clearer guidance on task execution and response formatting. * fix * fixing azure tests * organizae imports * dropped unused * Remove debug print statements from AgentExecutor to clean up the code and improve readability. This change enhances the overall performance of the agent execution flow by eliminating unnecessary console output during LLM calls and iterations. * linted * updated cassette * regen cassette * revert crew agent executor * adjust cassettes and dropped tests due to native tool implementation * adjust * ensure we properly fail tools and emit their events * Enhance tool handling and delegation tracking in agent executors - Implemented immediate return for tools with result_as_answer=True in crew_agent_executor.py. - Added delegation tracking functionality in agent_utils.py to increment delegations when specific tools are used. - Updated tool usage logic to handle caching more effectively in tool_usage.py. - Enhanced test cases to validate new delegation features and tool caching behavior. This update improves the efficiency of tool execution and enhances the delegation capabilities of agents. * Enhance tool handling and delegation tracking in agent executors - Implemented immediate return for tools with result_as_answer=True in crew_agent_executor.py. - Added delegation tracking functionality in agent_utils.py to increment delegations when specific tools are used. - Updated tool usage logic to handle caching more effectively in tool_usage.py. - Enhanced test cases to validate new delegation features and tool caching behavior. This update improves the efficiency of tool execution and enhances the delegation capabilities of agents. * fix cassettes * fix * regen cassettes * regen gemini * ensure we support bedrock * supporting bedrock * regen azure cassettes * Implement max usage count tracking for tools in agent executors - Added functionality to check if a tool has reached its maximum usage count before execution in both crew_agent_executor.py and agent_executor.py. - Enhanced error handling to return a message when a tool's usage limit is reached. - Updated tool usage logic in tool_usage.py to increment usage counts and print current usage status. - Introduced tests to validate max usage count behavior for native tool calling, ensuring proper enforcement and tracking. This update improves tool management by preventing overuse and providing clear feedback when limits are reached. * fix other test * fix test * drop logs * better tests * regen * regen all azure cassettes * regen again placeholder for cassette matching * fix: unify tool name sanitization across codebase * fix: include tool role messages in save_last_messages * fix: update sanitize_tool_name test expectations Align test expectations with unified sanitize_tool_name behavior that lowercases and splits camelCase for LLM provider compatibility. * fix: apply sanitize_tool_name consistently across codebase Unify tool name sanitization to ensure consistency between tool names shown to LLMs and tool name matching/lookup logic. * regen * fix: sanitize tool names in native tool call processing - Update extract_tool_call_info to return sanitized tool names - Fix delegation tool name matching to use sanitized names - Add sanitization in crew_agent_executor tool call extraction - Add sanitization in experimental agent_executor - Add sanitization in LLM.call function lookup - Update streaming utility to use sanitized names - Update base_agent_executor_mixin delegation check * Extract text content from parts directly to avoid warning about non-text parts * Add test case for Gemini token usage tracking - Introduced a new YAML cassette for tracking token usage in Gemini API responses. - Updated the test for Gemini to validate token usage metrics and response content. - Ensured proper integration with the Gemini model and API key handling. --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2026-01-22 17:44:03 -08:00
Greyson LaLonde	7a65baeb9c	feat: add event ordering and parent-child hierarchy ... adds emission sequencing, parent-child event hierarchy with scope management, and integrates both into the event bus. introduces flush() for deterministic handling, resets emission counters for test isolation, and adds chain tracking via previous_event_id/triggered_by_event_id plus context variables populated during emit and listener execution. includes tracing listener typing/sorting improvements, safer tool event pairing with try/finally, additional stack checks and cache-hit formatting, context isolation fixes, cassette regen/decoding, and test updates to handle vcr race conditions and flaky behavior.	2026-01-21 11:12:10 -05:00
Lorenze Jay	741bf12bf4	Lorenze/enh decouple executor from crew (#4209) ... * wip restrcuturing agent executor and liteagent * fix: handle None task in AgentExecutor to prevent errors Added a check to ensure that if the task is None, the method returns early without attempting to access task properties. This change improves the robustness of the AgentExecutor by preventing potential errors when the task is not set. * refactor: streamline AgentExecutor initialization by removing redundant parameters Updated the Agent class to simplify the initialization of the AgentExecutor by removing unnecessary task and crew parameters in standalone mode. This change enhances code clarity and maintains backward compatibility by ensuring that the executor is correctly configured without redundant assignments. * ensure executors work inside a flow due to flow in flow async structure * refactor: enhance agent kickoff preparation by separating common logic Updated the Agent class to introduce a new private method that consolidates the common setup logic for both synchronous and asynchronous kickoff executions. This change improves code clarity and maintainability by reducing redundancy in the kickoff process, while ensuring that the agent can still execute effectively within both standalone and flow contexts. * linting and tests * fix test * refactor: improve test for Agent kickoff parameters Updated the test for the Agent class to ensure that the kickoff method correctly preserves parameters. The test now verifies the configuration of the agent after kickoff, enhancing clarity and maintainability. Additionally, the test for asynchronous kickoff within a flow context has been updated to reflect the Agent class instead of LiteAgent. * refactor: update test task guardrail process output for improved validation Refactored the test for task guardrail process output to enhance the validation of the output against the OpenAPI schema. The changes include a more structured request body and updated response handling to ensure compliance with the guardrail requirements. This update aims to improve the clarity and reliability of the test cases, ensuring that task outputs are correctly validated and feedback is appropriately provided. * test fix cassette * test fix cassette * working * working cassette * refactor: streamline agent execution and enhance flow compatibility Refactored the Agent class to simplify the execution method by removing the event loop check and clarifying the behavior when called from synchronous and asynchronous contexts. The changes ensure that the method operates seamlessly within flow methods, improving clarity in the documentation. Additionally, updated the AgentExecutor to set the response model to None, enhancing flexibility. New test cassettes were added to validate the functionality of agents within flow contexts, ensuring robust testing for both synchronous and asynchronous operations. * fixed cassette * Enhance Flow Execution Logic - Introduced conditional execution for start methods in the Flow class. - Unconditional start methods are prioritized during kickoff, while conditional starts are executed only if no unconditional starts are present. - Improved handling of cyclic flows by allowing re-execution of conditional start methods triggered by routers. - Added checks to continue execution chains for completed conditional starts. These changes improve the flexibility and control of flow execution, ensuring that the correct methods are triggered based on the defined conditions. * Enhance Agent and Flow Execution Logic - Updated the Agent class to automatically detect the event loop and return a coroutine when called within a Flow, simplifying async handling for users. - Modified Flow class to execute listeners sequentially, preventing race conditions on shared state during listener execution. - Improved handling of coroutine results from synchronous methods, ensuring proper execution flow and state management. These changes enhance the overall execution logic and user experience when working with agents and flows in CrewAI. * Enhance Flow Listener Logic and Agent Imports - Updated the Flow class to track fired OR listeners, ensuring that multi-source OR listeners only trigger once during execution. This prevents redundant executions and improves flow efficiency. - Cleared fired OR listeners during cyclic flow resets to allow re-execution in new cycles. - Modified the Agent class imports to include Coroutine from collections.abc, enhancing type handling for asynchronous operations. These changes improve the control and performance of flow execution in CrewAI, ensuring more predictable behavior in complex scenarios. * adjusted test due to new cassette * ensure we dont finalize batch on just a liteagent finishing * feat: cancellable parallelized flow methods * feat: allow methods to be cancelled & run parallelized * feat: ensure state is thread safe through proxy * fix: check for proxy state * fix: mimic BaseModel method * chore: update final attr checks; test * better description * fix test * chore: update test assumptions * extra --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2026-01-20 21:44:45 -08:00
Lorenze Jay	b267bb4054	Lorenze/fix google vertex api using api keys (#4243) ... * supporting vertex through api key use - expo mode * docs update here * docs translations --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2026-01-20 09:34:36 -08:00
Vidit Ostwal	1c4f44af80	Adding usage info in llm.py (#4172) ... * Adding usage info everywhere * Changing the check * Changing the logic * Adding tests * Adding casellets * Minor change * Fixing testcase * remove the duplicated test case, thanks to cursor * Adding async test cases * Updating test case --------- Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>	2026-01-07 10:42:27 -08:00
Greyson LaLonde	09014215a9	feat: add a2a update mechanisms (poll/stream/push) with handlers, config, and tests ... introduces structured update config, shared task helpers/error types, polling + streaming handlers with activated events, and a push notification protocol/events + handler. refactors handlers into a unified protocol with shared message sending logic and python-version-compatible typing. adds a2a integration tests + async update docs, fixes push config propagation, response model parsing safeguards, failure-state handling, stream cleanup, polling timeout catching, agent-card fallback behavior, and prevents duplicate artifacts.	2026-01-07 11:36:36 -05:00
Greyson LaLonde	f8deb0fd18	feat: add streaming tool call events; fix provider id tracking; add tests and cassettes ... Adds support for streaming tool call events with test coverage, fixes tool-stream ID tracking (including OpenAI-style tracking for Azure), improves Gemini tool calling + streaming tests, adds Anthropic tests, generates Azure cassettes, and fixes Azure cassette URIs.	2026-01-05 14:33:36 -05:00
Greyson LaLonde	bdafe0fac7	fix: ensure token usage recording, validate response model on stream	2025-12-10 20:32:10 -05:00
Lorenze Jay	6125b866fd	supporting thinking for anthropic models (#3978) ... * 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.	2025-12-08 15:34:54 -08:00
Greyson LaLonde	f2f994612c	fix: ensure otel span is closed	2025-12-05 13:23:26 -05:00
Lorenze Jay	c456e5c5fa	Lorenze/ensure hooks work with lite agents flows (#3981) ... * liteagent support hooks * wip llm.call hooks work - needs tests for this * fix tests * fixed more * more tool hooks test cassettes	2025-12-04 09:38:39 -08:00
Greyson LaLonde	20704742e2	feat: async llm support ... feat: introduce async contract to BaseLLM feat: add async call support for: Azure provider Anthropic provider OpenAI provider Gemini provider Bedrock provider LiteLLM provider chore: expand scrubbed header fields (conftest, anthropic, bedrock) chore: update docs to cover async functionality chore: update and harden tests to support acall; re-add uri for cassette compatibility chore: generate missing cassette fix: ensure acall is non-abstract and set supports_tools = true for supported Anthropic models chore: improve Bedrock async docstring and general test robustness	2025-12-01 18:56:56 -05:00
Greyson LaLonde	c925d2d519	chore: restructure test env, cassettes, and conftest; fix flaky tests ... Consolidates pytest config, standardizes env handling, reorganizes cassette layout, removes outdated VCR configs, improves sync with threading.Condition, updates event-waiting logic, ensures cleanup, regenerates Gemini cassettes, and reverts unintended test changes.	2025-11-29 16:55:24 -05:00
Greyson LaLonde	d2b9c54931	fix: re-add openai response_format param, add test	2025-11-24 17:13:20 -05:00
Greyson LaLonde	f3c5d1e351	feat: add streaming result support to flows and crews ... * feat: add streaming result support to flows and crews * docs: add streaming execution documentation and integration tests	2025-11-24 15:43:48 -05:00
Mark McDonald	a978267fa2	feat: Add gemini-3-pro-preview (#3950) ... * 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>	2025-11-24 14:49:29 -05:00
Greyson LaLonde	a559cedbd1	chore: ensure proper cassettes for agent tests ... * chore: ensure proper cassettes for agent tests * chore: tweak eval test to avoid race condition	2025-11-24 12:29:11 -05:00
Greyson LaLonde	b546982690	fix: ensure instrumentation flags	2025-11-15 20:48:40 -05:00
Lorenze Jay	528d812263	Lorenze/feat hooks (#3902) ... * 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>	2025-11-13 10:11:50 -08:00
Lorenze Jay	c205d2e8de	feat: implement before and after LLM call hooks in CrewAgentExecutor (#3893) ... - 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.	2025-11-12 08:38:13 -08:00
Lorenze Jay	6b52587c67	feat: expose messages to TaskOutput and LiteAgentOutputs (#3880) ... * 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	2025-11-10 17:38:30 -08:00
Greyson LaLonde	19c5b9a35e	fix: properly handle agent max iterations ... fixes #3847	2025-11-07 13:54:11 -05:00
Greyson LaLonde	40a2d387a1	fix: keep stopwords updated	2025-11-06 21:10:25 -05:00
Greyson LaLonde	9e5906c52f	feat: add pydantic validation dunder to BaseInterceptor	2025-11-06 15:27:07 -05:00
Greyson LaLonde	7e6171d5bc	fix: ensure lite agents course-correct on validation errors ... * fix: ensure lite agents course-correct on validation errors * chore: update cassettes and test expectations * fix: ensure multiple guardrails propogate	2025-11-05 19:02:11 -05:00
Greyson LaLonde	61ad1fb112	feat: add support for llm message interceptor hooks	2025-11-05 11:38:44 -05:00