- 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.
- 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.
- 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.
- OpenAI: Use Uploads API for files > 512MB with chunked streaming
- Gemini: Pass file path directly to SDK for FilePath sources
- Bedrock: Use upload_fileobj with TransferConfig for automatic multipart
- Add tests for file processing constraints and validators
- Add tests for FileProcessor and FileResolver
- Add tests for resolved file types
- Add tests for file store operations
- Add unit tests for multimodal LLM support
- Add input_files parameter to Task for file attachments
- Add file_handling mode to Crew for processing behavior
- Integrate file injection in CrewAgentExecutor
- Update prepare_kickoff to handle KickoffInputs type
- Add format_multimodal_content() to all LLM providers
- Support inline base64 and file reference formats
- Add FileResolver integration for upload caching
- Add module exports for files package
