v1.0.9 (2025-09-18)

What's Changed

• Stream built-in tool calls from OpenAI, Google, Anthropic and return them on next request (required for OpenAI reasoning) by @DouweM in #2877
• Include built-in tool calls and results in OTel messages by @DouweM in #2954
• Add RunContext.max_retries and .last_attempt by @DouweM in #2952
• Fix StreamedResponse.model_name for Azure OpenAI with content filter by @DouweM in #2951
• Fix TemporalAgent dropping model-specific ModelSettings (e.g. openai_reasoning_effort) by @DouweM in #2938
• Don't send item IDs to Responses API for non-reasoning models by @DouweM in #2950
• Update DBOS version by @qianl15 in #2939

Full Changelog: v1.0.8...v1.0.9

v1.0.8 (2025-09-16)

What's Changed

• Tools can now return AG-UI events separate from result sent to model by @DouweM in #2922
• Fix bug causing doubled reasoning tokens usage by deepcopying by @DouweM in #2920
• Fix auto-detection of HTTP proxy settings by @maxnilz in #2917
• Fix new_messages() and capture_run_messages() when history processors are used by @DouweM in #2921
• chore: Remove 'text' from RunUsage docstrings by @alexmojaki in #2919

New Contributors

• @maxnilz made their first contribution in #2917

Full Changelog: v1.0.7...v1.0.8

v1.0.7 (2025-09-15)

What's Changed

• Added MCP metadata and annotations to ToolDefinition.metadata for use in filtering by @ChuckJonas in #2880
• When starting run with message history ending in ModelRequest, make its content available in RunContext.prompt by @DouweM in #2891
• Let FunctionToolset take default values for strict, sequential, requires_approval, metadata by @DouweM in #2909
• Don't require mcp or logfire to use Temporal or DBOS by @DouweM in #2908
• Combine consecutive AG-UI user and assistant messages into the same model request/response by @DouweM in #2912
• Fix new_messages() when deferred_tool_results is used with message_history ending in ToolReturnParts by @DouweM in #2913

Full Changelog: v1.0.6...v1.0.7

v1.0.6 (2025-09-12)

What's Changed

• Add support for previous_response_id from Responses API by @GDaamn in #2756
• Let MCP servers be loaded from file by @Kludex in #2698
• Fix how thinking summaries are sent back to Responses API by @DouweM in #2883
• Bump Cohere SDK and remove incorrect typing workaround by @DouweM in #2886
• Update MCP tool call customisation docs by @MasterOdin in #2817

New Contributors

• @MasterOdin made their first contribution in #2817

Full Changelog: v1.0.5...v1.0.6

v1.0.5 (2025-09-11)

What's Changed

• Don't lose Azure OpenAI Responses encrypted_content if no summary was included by @DouweM in #2874
• Store OpenAI Responses text part ID to prevent error with reasoning by @DouweM in #2882
• Make OpenAIResponsesModel work with reasoning from other models and modified history by @DouweM in #2881

Full Changelog: v1.0.4...v1.0.5

v1.0.4 (2025-09-11)

What's Changed

• Add Pydantic AI Gateway provider by @Kludex in #2816, #2863
• Fix OpenAI Responses API tool calls with reasoning by @DouweM in #2869
• Support OpenAI Responses API returning encrypted reasoning content without summary by @DouweM in #2866
• Don't ask for OpenAI Responses API to include encrypted reasoning content for models that don't support it by @DouweM in #2867
• docs: update builtin-tools md by @tberends in #2857

New Contributors

• @tberends made their first contribution in #2857

Full Changelog: v1.0.3...v1.0.4

v1.0.3 (2025-09-10)

What's Changed

• Include thinking parts in subsequent model requests to improve performance and cache hit rates by @DouweM in #2823
• Add on_complete callback to AG-UI functions to get access to AgentRunResult by @ChuckJonas in #2429
• Support ModelSettings.seed in GoogleModel by @DouweM in #2842
• Add with agent.sequential_tool_calls(): contextmanager and use it in DBOSAgent by @DouweM in #2856
• Ensure ModelResponse fields are set from actual model response when streaming by @DouweM in #2848
• Send AG-UI thinking start and end events by @DouweM in #2855
• Support models that return output tool args as {"response': "<JSON string>"} by @shaheerzaman in #2836
• Support NativeOutput with FunctionModel by @DouweM in #2843
• Raise error when WebSearchTool is used with OpenAIChatModel and unsupported model by @safina57 in #2824

New Contributors

• @safina57 made their first contribution in #2824
• @shaheerzaman made their first contribution in #2836

Full Changelog: v1.0.2...v1.0.3

v1.0.2 (2025-09-08)

What's Changed

• Add support for durable execution with DBOS by @qianl15 in #2638
• Support sequential tool calling by @strawgate in #2718
• Add GoogleModelSettings.google_cached_content to pass cached_content by @Hojland in #2832
• Add ModelResponse.finish_reason and set provider_response_id while streaming by @fatelei in #2590
• Add support for gen_ai.response.id by @Kludex in #2831
• Only send tool choice to Bedrock Converse API for Anthropic and Nova models by @DouweM in #2819
• Handle errors in cost calculation in InstrumentedModel by @alexmojaki in #2834

New Contributors

• @Hojland made their first contribution in #2832
• @qianl15 made their first contribution in #2638
• @fatelei made their first contribution in #2590

Full Changelog: v1.0.1...v1.0.2

v1.0.1 (2025-09-05)

Breaking Changes

The following breaking change was slated to go into v1.0.0 but accidentally left out. Because it's a security issue, an uncommonly used feature, and few people will have updated to v1 yet within 24 hours, we decided it was justified to make an exception to the no-breaking-changes policy to get it out ASAP.

• Remove Python evaluator from pydantic_evals for security reasons by @dmontagu in #2808

Other Changes

• Remove eval-type-backport dependency by @Viicos in #2814

Full Changelog: v1.0.0...v1.0.1

v1.0.0 (2025-09-04)

What's Changed

• Drop support for Python 3.9 by @Kludex in #2725
• Deprecate OpenAIModelProfile.openai_supports_sampling_settings by @Kludex in #2730
• Add support for human-in-the-loop tool call approval by @DouweM in #2581
• Add tool_calls_limit to UsageLimits and tool_calls to RunUsage by @tradeqvest in #2633
• Add LiteLLM provider for OpenAI API compatible models by @mochow13 in #2606
• Add identifier field to FileUrl and subclasses by @kyuam32 in #2636
• Support NativeOutput with Groq by @DouweM in #2772
• Add docstring_format, require_parameter_descriptions, schema_generator to FunctionToolset by @g-eoj in #2601
• Gracefully handle errors in evals by @dmontagu in #2295
• Include logfire with pydantic-ai package by @Kludex in #2683
• Let almost all types used in docs examples be imported directly from pydantic_ai by @DouweM in #2736
• Bump temporalio to 1.17.0 by @DouweM in #2811
• Default InstrumentationSettings version to 2 by @alexmojaki in #2726
• Remove cases and averages from eval span by @DouweM in #2715
• Make many more dataclasses kw-only by @dmontagu in #2738
• Don't emit empty AG-UI thinking message events by @DouweM in #2754
• Update mcp package version by @BrokenDuck in #2741
• Raise error if MCP server __aexit__ is called when _running_count is already 0 by @federicociner in #2696
• Fix error when streaming from Gemini includes only executable_code or code_execution_result by @binaryCrossEntropy in #2719
• Close original response when retrying HTTP request by @DouweM in #2753
• Agent.__aenter__ returns Self, use default instrumentation for MCP sampling model by @alexmojaki in #2765
• Fix Anthropic streaming usage counting by @DouweM in #2771
• Create separate ThinkingParts for separate OpenAI Responses reasoning summary parts by @DouweM in #2775
• Handle Groq tool_use_failed errors by getting model to retry by @DouweM in #2774
• Raise error when trying to use Google built-in tools with user/output tools by @DouweM in #2777
• Move mcp-run-python to its own repo by @samuelcolvin in #2776
• Fix Azure OpenAI streaming when async content filter is enabled by @frednijsvrt in #2763
• Don't emit AG-UI text message content events with empty text part deltas by @celeritatem in #2779
• Handle streaming thinking signature deltas from Bedrock Converse API by @DouweM in #2785
• Don't require MCPServerStreamableHTTP and MCPServerSSE url to be a keyword argument by @franciscovilchezv in #2758
• Add operation.cost span attribute to model request spans, rename ModelResponse.price() to .cost() by @alexmojaki in #2767
• Ensure that old ModelResponses stored in a DB can still be deserialized by @DouweM in #2792
• Type ModelRequest.parts and ModelResponse.parts as Sequence by @moritzwilksch in #2798
• Always run event_stream_handler inside Temporal activity by @DouweM in #2806
• Document that various functions need to be async to be used with Temporal by @DouweM in #2809

New Contributors

• @BrokenDuck made their first contribution in #2741
• @federicociner made their first contribution in #2696
• @g-eoj made their first contribution in #2601
• @binaryCrossEntropy made their first contribution in #2719
• @Trollgeir made their first contribution in #2729
• @kyuam32 made their first contribution in #2636
• @richhuth made their first contribution in #2680
• @frednijsvrt made their first contribution in #2763
• @celeritatem made their first contribution in #2779
• @mochow13 made their first contribution in #2606
• @franciscovilchezv made their first contribution in #2758
• @moritzwilksch made their first contribution in #2798

Full Changelog: v0.8.1...v1.0.0