[Release] crewaiInc/crewAI 1.14.7a2: 1.14.7a2

crewAI v1.14.7a2 introduces conversational flow traces support with enhanced LLM event transparency, including real finish_reason, sampling parameters, and response IDs. The release refactors the flow DSL into focused decorator modules and implements a chat API for conversational flows. Key improvements include type-aware route decorators, overridable locking backends, and flattened LiteLLM usage tracking, alongside new NVIDIA Nemotron documentation and monorepo deployment guides.

Key Points

• •Conversational flow traces now supported with improved observability and debugging capabilities
• •LLM events now surface real finish_reason, sampling parameters, and response.id for better transparency
• •Type DSL triggers implemented as route-aware decorators for more flexible flow control
• •Chat API implemented for conversational flows enabling interactive agent interactions
• •Flow DSL refactored from monolith into focused, maintainable decorator modules
• •Lock store backend made overridable for custom locking implementations
• •LiteLLM cache and reasoning usage sub-counts flattened in _usage_to_dict for cleaner metrics
• •FlowDefinition can now be built directly from Flow DSL metadata
• •New NVIDIA Nemotron LLM integration guide added to documentation
• •Monorepo deployment documentation added for multi-package deployments

Workflow Diagram

Concepts