1.15.18
📦 crewaiView on GitHub →
✨ 9 features🐛 11 fixes🔧 1 symbols
Summary
This release promotes conversational flows to stable, enhances their documentation and APIs, and introduces several bug fixes including improved tool result handling and correct recording of task failures. It also refines project ID handling and LLM configuration for conversational declarations.
✨ New Features
- Promote conversational flows to stable.
- Record a created deployment with the given UUID.
- Enhance conversational flow documentation and APIs.
- Allow a declaration to name the router's response format.
- Allow a chat flow to declare its own state shape.
- Accept crew-style LLM config in a conversational declaration.
- Report project creation with the minted ID.
- Record whether a run had inputs, without recording the inputs.
- Backfill project ID from every user-invoked project command.
🐛 Bug Fixes
- Preserve tool results when the final answer is empty.
- Map default Claude Sonnet 4.6 to its 1M context window.
- Raise Anthropic default max_tokens for large tool calls.
- Render message content parts as text, not as a Python repr.
- Keep message roles when Agent.kickoff gets a conversation.
- Skip interception hooks on crewai-internal flows.
- Record task failures as failures, not successes.
- Emit the flow lifecycle on a suppressed resume.
- Open the conversational TUI for a declarative chat flow.
- Record crew_memory as a string, not a bool.
- Always emit project_id so absent and empty stay distinct.