v1.13.0 (2025-11-10)

What's Changed

• Ignore empty text parts in GoogleModel by @naveen-corpusant in #3360
• Add AgentRun.{all,new}_messages{_json} by @tibbe in #3354
• Update known models on Cerebras and Heroku by @Kludex in #3375
• feat(gateway): support api_type by @Kludex in #3362
• feat(gateway): support profile and routing_group by @Kludex in #3361

New Contributors

• @tibbe made their first contribution in #3354
• @cjohnhanson made their first contribution in #3371

Full Changelog: v1.12.0...v1.13.0

v1.12.0 (2025-11-06)

What's Changed

• Fix tool call incorrectly being considered approved when agent run is resumed with history ending in unapproved tool call by @DouweM in #3355
• Bump temporalio to v1.18.2 as v1.18.0 is broken by @crossk3 in #3356
• docs: Add Braintrust to integrations by @choochootrain in #3346

New Contributors

• @choochootrain made their first contribution in #3346
• @crossk3 made their first contribution in #3356

Full Changelog: v1.11.1...v1.12.0

v1.11.1 (2025-11-05)

What's Changed

• FallbackModel support for Native output mode and ModelProfile.default_structured_output_mode by @DouweM in #3303
• Fix task cancellation bug in graph beta API triggered by using MCPServerStreamableHTTP with agent.run_stream by @dmontagu in #3338
• Fix type annotation for DuckDuckGoTool with latest version of ddgs package by @jhammarstedt in #3330
• Fix typo in docs variable name by @DenysMoskalenko in #3343

New Contributors

• @jhammarstedt made their first contribution in #3330

Full Changelog: v1.11.0...v1.11.1

v1.11.0 (2025-11-04)

What's Changed

• Improve validation error retry message by @dmontagu in #3193
• OpenAI gpt-5-chat does not support (encrypted) reasoning by @DouweM in #3332
• Complete thinking.md documentation with AWS Bedrock examples by @daniilr in #3328
• Fix graph execution bug with multiple joins downstream of same fork by @dmontagu in #3337
• Skip installing outlines dependencies mlx, vllm, torch on Intel Macs by @pcustic in #3312
• Let additional instructions be provided at agent.run time. by @baek54321 in #3309
• Add partial_output to RunContext provided to output validators by @petersli in #3286

New Contributors

• @daniilr made their first contribution in #3328
• @pcustic made their first contribution in #3312
• @baek54321 made their first contribution in #3309
• @petersli made their first contribution in #3286

Full Changelog: v1.10.0...v1.11.0

v1.10.0 (2025-11-03)

What's Changed

• Fix MCPServer error handling with Temporal by @wreed4 in #3299
• Update directory path in ag-ui.md example by @sabman in #3310
• Implement OpenAIResponsesModel.base_url property by @chasefarmer-pixee in #3281
• Fix types to let OpenRouterProvider be created with only http_client by @xcpky in #3308
• Add Agent.run_stream_sync method and sync convenience methods on StreamedRunResult by @ajac-zero in #3146
• Fix typevar variance for agent deps by @dmontagu in #3319
• Add support for detecting and handling application/msword files. by @DenysMoskalenko in #3318
• Ensure AG-UI ToolCallStartEvent doesn't use a parent_message_id from a previous request/response by @DouweM in #3325

New Contributors

• @wreed4 made their first contribution in #3299
• @sabman made their first contribution in #3310
• @chasefarmer-pixee made their first contribution in #3281
• @xcpky made their first contribution in #3308
• @ajac-zero made their first contribution in #3146
• @DenysMoskalenko made their first contribution in #3318

Full Changelog: v1.9.1...v1.10.0

v1.9.1 (2025-10-30)

What's Changed

• Support AsyncAnthropicVertex as AnthropicProvider.anthropic_client by @DouweM in #3292
• Set AG-UI frontend state directly on provided deps so it can be read from on_complete handler by @DouweM in #3297
• Retry instead of error when Google response is empty with MALFORMED_FUNCTION_CALL or other recoverable finish reason by @ArneZsng in #3300
• Add Version Policy to docs by @DouweM in #3301

Full Changelog: v1.9.0...v1.9.1

v1.9.0 (2025-10-29)

What's Changed

• Support Vercel AI Data Stream Protocol by @samuelcolvin in #2923
• Fix docs custom retry logic example by @yf-yang in #3276

New Contributors

• @yf-yang made their first contribution in #3276

Full Changelog: v1.8.0...v1.9.0

v1.8.0 (2025-10-29)

What's Changed

• Add experiment metadata by @dmontagu in #3263
• Respect openai_supports_tool_choice_required model profile setting in OpenAIResponsesModel by @pamelafox in #3272
• Use latest OpenAI, Google, Anthropic models in all examples by @DouweM in #3278
• Fix agent name inference when using run_stream_events by @DouweM in #3279

New Contributors

• @pamelafox made their first contribution in #3272

Full Changelog: v1.7.0...v1.8.0

v1.7.0 (2025-10-27)

What's Changed

• Add OutlinesModel to run local models using Transformers, Llama.cpp, MLXLM, SGLang and vLLM via Outlines by @RobinPicard in #2623
• Fix pydantic-graph importing pydantic-ai by @dmontagu in #3265

New Contributors

• @RobinPicard made their first contribution in #2623

Full Changelog: v1.6.0...v1.7.0

v1.6.0 (2025-10-24)

What's Changed

• Add FastMCPToolset by @strawgate in #2784
• Add OpenAIModelProfile.openai_responses_requires_function_call_status_none flag to satisfy vLLM Responses API by @DouweM in #3246
• Sanitize auto-generated output tool name to support generic types by @lionpeloux in #2979
• Ensure ToolCallPart.args resulting from TestModel(custom_output_args=...) is always a dict by @DouweM in #3254

Full Changelog: v1.5.0...v1.6.0