* ci: support python 3.13 on CI
* docs: update docs about support python version
* build: adds requires python <3.14
* build: explicit tokenizers dependency
Added explicit tokenizers dependency: Added tokenizers>=0.20.3 to ensure a version compatible with Python 3.13 is used.
* build: drop fastembed is not longer used
* build: attempt to build PyTorch on Python 3.13
* feat: upgrade fastavro, pyarrow and lancedb
* build: ensure tiktoken greather than 0.8.0 due Python 3.13 compatibility
This commit includes several enhancements to the MCP integration guide:
- Adds a section on connecting to multiple MCP servers with a runnable example.
- Ensures consistent mention and examples for Streamable HTTP transport.
- Adds a manual lifecycle example for Streamable HTTP.
- Clarifies Stdio command examples.
- Refines definitions of Stdio, SSE, and Streamable HTTP transports.
- Simplifies comments in code examples for clarity.
* docs: Fix major memory system documentation issues - Remove misleading deprecation warnings, fix confusing comments, clearly separate three memory approaches, provide accurate examples that match implementation
* fix: Correct broken image paths in README - Update crewai_logo.png and asset.png paths to point to docs/images/ directory instead of docs/ directly
* docs: Add system prompt transparency and customization guide - Add 'Understanding Default System Instructions' section to address black-box concerns - Document what CrewAI automatically injects into prompts - Provide code examples to inspect complete system prompts - Show 3 methods to override default instructions - Include observability integration examples with Langfuse - Add best practices for production prompt management
* docs: Fix implementation accuracy issues in memory documentation - Fix Ollama embedding URL parameter and remove unsupported Cohere input_type parameter
* docs: Reference observability docs instead of showing specific tool examples
* docs: Reorganize knowledge documentation for better developer experience - Move quickstart examples right after overview for immediate hands-on experience - Create logical learning progression: basics → configuration → advanced → troubleshooting - Add comprehensive agent vs crew knowledge guide with working examples - Consolidate debugging and troubleshooting in dedicated section - Organize best practices by topic in accordion format - Improve content flow from simple concepts to advanced features - Ensure all examples are grounded in actual codebase implementation
* docs: enhance custom LLM documentation with comprehensive examples and accurate imports
* docs: reorganize observability tools into dedicated section with comprehensive overview and improved navigation
* docs: rename how-to section to learn and add comprehensive overview page
* docs: finalize documentation reorganization and update navigation labels
* docs: enhance README with comprehensive badges, navigation links, and getting started video
* Add Common Room tracking to documentation - Script will track all documentation page views - Follows Mintlify custom JS implementation pattern - Enables comprehensive docs usage insights
* docs: move human-in-the-loop guide to enterprise section and update navigation - Move human-in-the-loop.mdx from learn to enterprise/guides - Update docs.json navigation to reflect new organization
* docs: Fix major memory system documentation issues - Remove misleading deprecation warnings, fix confusing comments, clearly separate three memory approaches, provide accurate examples that match implementation
* fix: Correct broken image paths in README - Update crewai_logo.png and asset.png paths to point to docs/images/ directory instead of docs/ directly
* docs: Add system prompt transparency and customization guide - Add 'Understanding Default System Instructions' section to address black-box concerns - Document what CrewAI automatically injects into prompts - Provide code examples to inspect complete system prompts - Show 3 methods to override default instructions - Include observability integration examples with Langfuse - Add best practices for production prompt management
* docs: Fix implementation accuracy issues in memory documentation - Fix Ollama embedding URL parameter and remove unsupported Cohere input_type parameter
* docs: Reference observability docs instead of showing specific tool examples
* docs: Reorganize knowledge documentation for better developer experience - Move quickstart examples right after overview for immediate hands-on experience - Create logical learning progression: basics → configuration → advanced → troubleshooting - Add comprehensive agent vs crew knowledge guide with working examples - Consolidate debugging and troubleshooting in dedicated section - Organize best practices by topic in accordion format - Improve content flow from simple concepts to advanced features - Ensure all examples are grounded in actual codebase implementation
* docs: enhance custom LLM documentation with comprehensive examples and accurate imports
* docs: reorganize observability tools into dedicated section with comprehensive overview and improved navigation
* docs: rename how-to section to learn and add comprehensive overview page
* docs: finalize documentation reorganization and update navigation labels
* docs: enhance README with comprehensive badges, navigation links, and getting started video
- Remove state modification from _should_trigger_reasoning method
- Ensure counter is incremented after each step in invoke loop
- Counter is properly reset when reasoning occurs
- Fixes test failures in reasoning_interval_test.py
Co-Authored-By: Joe Moura <joao@crewai.com>
- Fix type errors by converting deque to list when passing to handle_mid_execution_reasoning
- Add proper type annotation for tools_used
- Fix agent type error by casting BaseAgent to Agent
- Fix _should_trigger_reasoning logic to correctly handle reasoning_interval
- All type checking passes (mypy clean)
Addresses all code quality suggestions from PR review.
Co-Authored-By: Joe Moura <joao@crewai.com>
- Remove unused imports (json, re)
- Add validation for reasoning_interval parameter
- Use deque for tools_used to prevent memory leaks
- Add type hints to all new methods
- Refactor adaptive reasoning logic for better readability
- Centralize event handling logic
- Expand test coverage with parametrized tests
Co-Authored-By: Joe Moura <joao@crewai.com>
* Add usage limit feature to BaseTool class
- Add max_usage_count and current_usage_count attributes to BaseTool
- Implement usage limit checking in ToolUsage._use method
- Add comprehensive tests for usage limit functionality
- Maintain backward compatibility with None default for unlimited usage
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix CI failures and address code review feedback
- Add max_usage_count/current_usage_count to CrewStructuredTool
- Add input validation for positive max_usage_count
- Add reset_usage_count method to BaseTool
- Extract usage limit check into separate method
- Add comprehensive edge case tests
- Add proper type hints throughout
- Fix linting issues
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>
* docs: enterprise hallucination guardrails
Documents the `HallucinationGuardrail` feature for enterprise users, including usage examples, configuration options, and integration patterns.
* fix: update import
in the tin
* chore: add docs.json route
Add route for hallucination guardrail mdx
