v0.13.6

What's Changed

• fix: #2863 lazy-load SQLiteSession exports by @seratch in #2864
• fix: #2856 stop recursive trace preview truncation by @seratch in #2860
• fix: harden SQLAlchemySession against transient SQLite locks by @seratch in #2854

Documentation & Other Changes

• docs: updates for #2844 changes by @seratch in #2845
• docs: update translated document pages by @github-actions[bot] in #2847
• docs(tracing): add HoneyHive to tracing integrations list by @m1lestones in #2851
• docs: update translated document pages by @github-actions[bot] in #2853
• Release 0.13.6 by @github-actions[bot] in #2861

New Contributors

• @m1lestones made their first contribution in #2851

Full Changelog: v0.13.5...v0.13.6

v0.13.5

What's Changed

• feat: #2807 support callable approval policies for local MCP servers by @seratch in #2818
• feat: #2135 add public flush_traces API by @seratch in #2844
• fix: #2823 AnyLLM reasoning extraction for iterable vLLM/any-llm Reasoning objects by @ziqi-cn in #2822
• fix: serialize SQLite session writes with shared file locks by @seratch in #2843

Documentation & Other Changes

• chore(deps): bump openai/codex-action from 1.4 to 1.6 by @dependabot[bot] in #2819
• chore(deps): bump astral-sh/setup-uv from 7.3.1 to 8.0.0 by @dependabot[bot] in #2820
• docs: sync examples.md with current examples directory by @AbdullahBapra in #2827
• docs: update translated document pages by @github-actions[bot] in #2828
• Release 0.13.5 by @github-actions[bot] in #2821

New Contributors

• @AbdullahBapra made their first contribution in #2827
• @ziqi-cn made their first contribution in #2822

Full Changelog: v0.13.4...v0.13.5

v0.13.4

What's Changed

• fix: #2806 sanitize AnyLLM responses replay input before validation by @seratch in #2813

Documentation & Other Changes

• fix: map extensions changes to the feature:extensions label by @seratch in #2814
• Release 0.13.4 by @github-actions[bot] in #2815

Full Changelog: v0.13.3...v0.13.4

v0.13.3

What's Changed

• fix: #2798 avoid stale hydrated input ids in server conversation tracker by @seratch in #2800
• fix: #2797 accept raw image_url content parts on chat completions input by @seratch in #2799

Documentation & Other Changes

• docs: add non-OpenAI provider code example by @Muttaqi110 in #2792
• docs: update translated document pages by @github-actions[bot] in #2793
• chore: add Codex Stop hook for targeted Ruff tidy by @seratch in #2795
• Release 0.13.3 by @github-actions[bot] in #2801

New Contributors

• @Muttaqi110 made their first contribution in #2792

Full Changelog: v0.13.2...v0.13.3

v0.13.2

What's Changed

• fix: #2783 depend on griffelib directly for docstring parsing by @seratch in #2791
• fix: #2776 keep private tool metadata out of persisted session items by @seratch in #2781
• fix: #2778 keep LiteLLM reasoning_effort portable across providers by @seratch in #2782
• fix: update default reasoning effort for newer models by @seratch in #2773
• feat: add external_web_access to WebSearchTool by @ymuichiro in #2786
• fix: pin LiteLLM upper bound to 1.82.6 to mitigate supply chain attack by @gn00295120 in #2772

Documentation & Other Changes

• docs: update pages to add any-llm adapter by @seratch in #2715
• docs: update translated document pages by @github-actions[bot] in #2771
• fix: improve a flaky test for realtime module by @seratch in #2787
• Release 0.13.2 by @github-actions[bot] in #2774

New Contributors

• @ymuichiro made their first contribution in #2786

Full Changelog: v0.13.1...v0.13.2

v0.13.1

Key Changes

Any-LLM extension

Since this version, the extension module includes a new any-llm adapter as well. Please refer to the updated documentation and examples at https://github.com/openai/openai-agents-python/tree/main/examples/model_providers

What's Changed

• feat: add any-llm model support with responses-compatible routing by @seratch in #2706
• fix: preserve static MCP meta in converted function tools by @seratch in #2769
• fix: #2760 wait for realtime response.done before follow-up response.create by @seratch in #2763
• fix: handle cancelled single function tools as tool failures by @elainegan-openai in #2762
• fix: optionize initialized notification tolerance by @elainegan-openai in #2765
• fix: remove duplicate CompactionItem from RunItem union by @KanchiShimono in #2761

Documentation & Other Changes

• docs: add 0.13 changelog by @seratch in #2744
• docs: update translated document pages by @github-actions[bot] in #2759
• fix: harden example auto-runs against PATH and port conflicts by @seratch in #2770
• Release 0.13.1 by @github-actions[bot] in #2768

Full Changelog: v0.13.0...v0.13.1

v0.13.0

Key Changes

This minor release does not introduce a breaking change, but it includes a notable Realtime default update plus new MCP capabilities and runtime stability fixes. Highlights are:

• The default websocket Realtime model is now gpt-realtime-1.5, so new Realtime agent setups use the newer model without extra configuration.
• MCPServer now exposes list_resources(), list_resource_templates(), and read_resource(), and MCPServerStreamableHttp now exposes session_id so streamable HTTP sessions can be resumed across reconnects or stateless workers.
• Chat Completions integrations can now opt into reasoning-content replay via should_replay_reasoning_content, improving provider-specific reasoning/tool-call continuity for adapters such as LiteLLM/DeepSeek.
• Fixed several runtime and session edge cases, including concurrent first writes in SQLAlchemySession, compaction requests with orphaned assistant message IDs after reasoning stripping, remove_all_tools() leaving MCP/reasoning items behind, and a race in the function-tool batch executor.

What's Changed

• fix: default realtime websocket model to gpt-realtime-1.5 by @seratch in #2737
• fix: #2729 avoid eager-task race in function tool batch executor by @seratch in #2731
• fix: preserve streamed output guardrail tripwires in the run loop by @seratch in #2758
• fix(compaction): strip orphaned assistant message IDs after reasoning removal by @Ratnaditya-J in #2728
• feat: #2669 add opt-in reasoning content replay for chat completion models by @seratch in #2670
• fix: remove_all_tools missing MCP and reasoning item types by @joaquinhuigomez in #2700
• feat(mcp): expose list_resources, list_resource_templates, and read_resource on MCPServer by @adityasingh2400 in #2721
• feat(mcp): expose session_id on MCPServerStreamableHttp by @adityasingh2400 in #2708
• fix(memory): make SQLAlchemySession first writes race-safe by @FelmonFekadu in #2725

Documentation & Other Changes

• docs: add PromptLayer integration link to tracing documentation by @adagradschool in #2718
• docs: update translated document pages by @github-actions[bot] in #2719
• docs: highlight gpt-realtime-1.5 in public docs by @teri-oai in #2724
• docs: update translated document pages by @github-actions[bot] in #2726
• docs: clarify cancel-after-turn streaming guidance by @FelmonFekadu in #2710
• docs: update translated document pages by @github-actions[bot] in #2730
• docs: rebrand Keywords AI to Respan by @drPod in #2757
• chore: add runtime behavior probe skill by @seratch in #2743
• chore: parallelize code-change-verification after format by @seratch in #2751
• Release 0.13.0 by @github-actions[bot] in #2738

New Contributors

• @adagradschool made their first contribution in #2718
• @teri-oai made their first contribution in #2724
• @FelmonFekadu made their first contribution in #2725
• @Ratnaditya-J made their first contribution in #2728
• @joaquinhuigomez made their first contribution in #2700
• @drPod made their first contribution in #2757

Full Changelog: v0.12.5...v0.13.0

v0.12.5

What's Changed

• feat(mcp): expose auth and httpx_client_factory in SSE/StreamableHttp params by @adityasingh2400 in #2713
• fix: recover streamed nested agent output before cancellation fallback by @elainegan-openai in #2714
• fix(mcp): retry ClosedResourceError on isolated session by @elainegan-openai in #2711
• fix(mcp): retry MCP 408s on isolated session by @elainegan-openai in #2709

Documentation & Other Changes

• Release 0.12.5 by @github-actions[bot] in #2716

Full Changelog: v0.12.4...v0.12.5

v0.12.4

What's Changed

• fix: normalize cancelled MCP invocations into tool errors by @elainegan-openai in #2704
• fix: retry transient streamable-http MCP tool failures on isolated session by @elainegan-openai in #2703
• fix(memory): honor custom table names in AdvancedSQLiteSession by @seratch in #2694
• fix(retry): cap jittered delay to max_delay by @Dhakshin2007 in #2676

Documentation & Other Changes

• ci: harden PR auto-labeling against diff and output drift by @seratch in #2691
• docs: streamline models page and UI tweak by @seratch in #2696
• docs: update translated document pages by @github-actions[bot] in #2697
• Release 0.12.4 by @github-actions[bot] in #2705

New Contributors

• @Dhakshin2007 made their first contribution in #2676

Full Changelog: v0.12.3...v0.12.4

v0.12.3

What's Changed

• fix: handle inner MCP tool cancellations as tool errors by @elainegan-openai in #2681
• fix: serialize streamable-http MCP requests per session by @elainegan-openai in #2682

Documentation & Other Changes

• docs: update translated document pages by @github-actions[bot] in #2668
• docs: fix minor typos in provider comments and test name by @luojiyin1987 in #2674
• Release 0.12.3 by @github-actions[bot] in #2684

New Contributors

• @luojiyin1987 made their first contribution in #2674
• @elainegan-openai made their first contribution in #2681

Full Changelog: v0.12.2...v0.12.3