CrewAI 1.15.22 Enhances Agent Capabilities and Adds New LLM Integrations
sdkaiazuregaengineerpython-agentic
feature patch
Version 1.15.22 of CrewAI introduces several new features and bug fixes to its agentic AI framework. Key additions include improved LLM routing with a `llm_overlay` context variable and enhanced tracing for human feedback and pause events. The update also expands platform integrations, exposes the application catalog, and adds OpenRouter as a supported embedding provider, increasing the framework's flexibility for developers. Numerous bug fixes address issues with tool calls, persistence, prompt handling, and platform-specific behaviors like Azure wire indexing, improving overall stability and developer experience.
- →Support aliases as connection identifiers
- →Record reasons for deployment creation failures
- →Collect human feedback and pause events in tracing
- →Add llm_overlay context variable to route agent roles to models
- →Carry task_prompt and output in agent execution payloads
Features (9) ›
- Support aliases as connection identifiers
- Record reasons for deployment creation failures
- Collect human feedback and pause events in tracing
- Add llm_overlay context variable to route agent roles to models
- Carry task_prompt and output in agent execution payloads
- Validate platform integrations during crew setup
- Add platform tools to JSON crew wizard
- Expose CrewAI Platform application catalog
- Add OpenRouter as a supported embedding provider
Fixes (19) ›
- Accept CRLF in inline skill definitions
- Load text file URLs through the safe fetcher
- Close SQLite connections in kickoff task outputs storage
- Carry from_cache on the native tool path's ToolUsageFinishedEvent
- Raise ValueError instead of bare raise in uploader
- Support non-primitive types in SQLiteFlowPersistence
- Improve coding agents instructions
- Read JSON checkpoints as UTF-8
- Overwrite stale poetry.lock backup on Windows
- Key streamed tool calls by wire index in Azure
- Preserve file data content parts in Gemini
- Honor read_only on update() and recall() access times
- Send reasoning_effort to every OpenAI reasoning model
- Prevent crashes in the run TUI when streamed output contains a literal [...]
- Reject replay when stored tasks differ
- Use sys.platform guards for mypy compatibility on Windows
- Request the forced final answer as a user turn
- Keep null in the task output schema embedded in the prompt
- Align DOCXSearchTool with standard RAG fixed schema pattern
Maintenance (2) ›
- Add xpu to embedding device options
- List all workspace packages
Read the original announcement →
https://github.com/crewAIInc/crewAI/releases/tag/1.15.22
Related releases
- ADK Python v2.9.1 Enhances Visibility into Claude's Reasoning Steps Google ADK (Python) Releases ·
- Pydantic-AI v2.43.0 Enhances CLI Experience and Fixes OpenAI Chat Model Behavior Pydantic AI Releases ·
- ADK-Python v2.9.0 enhances agent resilience, voice integration, and workflow management Google ADK (Python) Releases ·
- CrewAI 1.15.21 Release Introduces Telemetry and Resolves Multiple Bugs CrewAI Releases ·
- OpenAI Python Agents SDK v0.22.2 Released OpenAI Agents SDK (Python) Releases ·
- Pydantic-AI v2.42.0 Enhances GitHub Copilot Integration and Fixes Bugs Pydantic AI Releases ·