ReleaseBytes
python Pydantic AI Releases · · 2.45.0

Pydantic AI Library v2.45.0 Adds TypeSafeModel and Bedrock Converse Support

sdkaigaengineerpython-agentic
feature patch

Pydantic AI Library v2.45.0 introduces `TypeSafeModel` for improved type safety with TypeSafe's Jev integration. This release also includes several bug fixes, expanding Bedrock Converse support to include `gpt-5.6-sol`, `gpt-5.6-luna`, and `gpt-5.6-terra` models. Internal improvements resolve dynamic toolset and MCP server session management, ensuring more efficient and stable agent execution. Developers leveraging Pydantic for AI models and Bedrock integrations will benefit from these updates.

  • →Add TypeSafeModel for TypeSafe's Jev by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/8450
  • →Pass xhigh effort through on Bedrock when the model profile supports it by @willfrey in https://github.com/pydantic/pydantic-ai/pull/8392
  • →Allow gpt-5.6-sol, gpt-5.6-luna, and gpt-5.6-terra on Bedrock Converse by @pydanty in https://github.com/pydantic/pydantic-ai/pull/7825
  • →Hold one MCP server session per durable run instead of one per durable unit by @DouweM in https://github.com/pydantic/pydantic-ai/pull/8463
  • →Preserve tool history in MCPSamplingModel by @DouweM in https://github.com/pydantic/pydantic-ai/pull/8466
Features (1) ›
  • Add TypeSafeModel for TypeSafe's Jev by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/8450
Fixes (7) ›
  • Pass xhigh effort through on Bedrock when the model profile supports it by @willfrey in https://github.com/pydantic/pydantic-ai/pull/8392
  • Allow gpt-5.6-sol, gpt-5.6-luna, and gpt-5.6-terra on Bedrock Converse by @pydanty in https://github.com/pydantic/pydantic-ai/pull/7825

  • Resolve a DynamicToolset once per durable run instead of inside every durable unit by @DouweM in https://github.com/pydantic/pydantic-ai/pull/8455

  • Hold one MCP server session per durable run instead of one per durable unit by @DouweM in https://github.com/pydantic/pydantic-ai/pull/8463
  • Preserve tool history in MCPSamplingModel by @DouweM in https://github.com/pydantic/pydantic-ai/pull/8466

  • Stop importing legacy httpx in pydantic_ai.mcp, which a FastMCP 4 install does not ship by @DouweM in https://github.com/pydantic/pydantic-ai/pull/8461

  • Report each agent run's own usage on its span by @DouweM in https://github.com/pydantic/pydantic-ai/pull/8456
Read the original announcement →

https://github.com/pydantic/pydantic-ai/releases/tag/v2.45.0

Related releases