Pydantic-AI v2.32.0 Introduces AI Model Suggestions, xAI Support, and Tooling Enhancements
Pydantic-AI v2.32.0 is now available, bringing new features including suggestions for known AI model names for invalid identifiers, support for xAI attachment search lifecycle, and surfacing OpenRouter web-search sources. The release also adds instrumentation version 6 for emitting tool results and addresses several bug fixes related to synchronous hooks, run context cancellation, and tool call handling. This update primarily benefits developers building AI applications with Pydantic-AI, enhancing debugging, integration with external AI services, and overall stability.
- →Suggest known model names for invalid identifiers by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7325
- →Support xAI attachment search lifecycle by @colesmcintosh in https://github.com/pydantic/pydantic-ai/pull/7156
- →Surface OpenRouter web-search sources in provider_details["annotations"] by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7458
- →Add instrumentation version 6, emitting tool results under role: 'tool' by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7582
- →Only list available tools in the unknown-tool retry message by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/7572
Features (4) ›
- Suggest known model names for invalid identifiers by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7325
- Support xAI attachment search lifecycle by @colesmcintosh in https://github.com/pydantic/pydantic-ai/pull/7156
- Surface OpenRouter web-search sources in provider_details["annotations"] by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7458
- Add instrumentation version 6, emitting tool results under role: 'tool' by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7582
Fixes (6) ›
Run sync hooks in a thread pool and enforce timeout= for blocking sync tools and hooks by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/7557
Record RunContext.cancel() from setup-phase for_run hooks instead of raising UserError by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/7567
Treat a response containing only empty text parts as having no text output by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/7568
- Only list available tools in the unknown-tool retry message by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/7572
Sort tool results ahead of tool availability announcements so Bedrock accepts turns revealing multiple tools by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/7571
- Drop native tool calls the replayed payload has no result block for by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7504
https://github.com/pydantic/pydantic-ai/releases/tag/v2.32.0
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 ·