Pydantic-AI v2.31.1 Patch Release Addresses Model-Specific Output Issues
Pydantic-AI v2.31.1 is a patch release focused on improving compatibility with various large language models. It fixes an issue where native structured output was denied for Claude Sonnet 5 and Fable 5 on AWS Bedrock. Additionally, the update ensures graceful fallback to a lower `thinking_level` for Gemini models that reject the `MINIMAL` setting. These changes enhance the reliability of structured output generation for developers using these specific AI platforms.
Fixes (2) ›
Deny native structured output for Claude Sonnet 5 and Fable 5 on Bedrock by @pydanty[bot] in https://github.com/pydantic/pydantic-ai/pull/7374
Fall back to thinking_level='LOW' for Gemini models that reject MINIMAL by @pydanty[bot] in https://github.com/pydantic/pydantic-ai/pull/7469
https://github.com/pydantic/pydantic-ai/releases/tag/v2.31.1
Related releases
- Pydantic AI v2.34.0 Introduces LangChain Migration and GLM-5.3 Model Support Pydantic AI Releases ·
- pydantic-ai v2.33.0 Enhances Anthropic SDK Compatibility, Resolves Runtime Issues Pydantic AI Releases ·
- Pydantic-AI v2.32.2 Delivers Critical Bug Fixes Pydantic AI Releases ·
- Pydantic-AI v2.32.1 Patch Addresses Agent Execution and Anthropic Integration Bugs Pydantic AI Releases ·
- crewAI 1.15.17 Enhances Conversational Flows and Resolves Tooling Issues CrewAI Releases ·
- LangGraph Python SDK 0.4.3 Adds Decryption Feature and Fixes Cron Management LangGraph Releases ·