pydantic-ai
https://github.com/pydantic/pydantic-ai
Python
GenAI Agent Framework, the Pydantic way
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported4 Subscribers
Add a CodeTriage badge to pydantic-ai
Help out
- Issues
- BedrockModel refuses thinking + output tools, but Bedrock accepts it (Sonnet 4.6 / Sonnet 5)
- A per-run capability's `@durable_operation` methods silently run outside any Prefect task
- Align Bedrock Claude tool choice with Anthropic adaptive thinking
- Standard tool-level speculation-safety declarations (`side_effect_free`, `idempotent`, `stable_for`, resource keys)
- Report averages hide how many cases a score actually covers
- Fix LLM judge prompt rendering for `bytes`, `bytearray`, and `memoryview` values
- Preserve extra keys in `tool_search` and `load_capability` typed message parts
- Expose OpenAI response `service_tier` in `ModelResponse.provider_details`
- [roundtrip-sweep] `ModelMessagesTypeAdapter`: typed `tool_kind` narrowers (`tool-search` call/return, `capability-load` call) silently drop extra [Content truncated due to length]
- Expose the actual OpenAI response service tier on ModelResponse
- Docs
- Python not yet supported