release: 3.9.0

[openai-sdks]

Automated Release PR

3.9.0 (2026-09-05)

Features

• api: Add prompt cache diagnostics (#3800) (8326784)
• api: correct function argument completion event fields (openapi-545) (#3801) (2a98f6a)

Bug Fixes

• api: accept incomplete web search call statuses (#3786) (3cc8d78)
• refuse overflowing server retry delays (#3799) (88b4d43)

Chores

• api: document throttling and model overload responses — SDK-235 (#3803) (be92815)
• migrate to forked steady (#3795) (b24aeda)

---

This PR was generated with Release Please. See documentation.

[openai-sdks]

OkTest Summary

✅ 237/237 SDK tests passed in 11.683s for Python SDK PR #3796.

Test results — 42 files

Test	Result	Time
tests/chat-completions-complex-body.test.ts	✅ Passed	184ms
tests/chat-completions-create.test.ts	✅ Passed	234ms
tests/chat-completions-stream.test.ts	✅ Passed	156ms
tests/files-content-binary.test.ts	✅ Passed	214ms
tests/files-create-multipart.test.ts	✅ Passed	241ms
tests/files-list-pagination.test.ts	✅ Passed	172ms
tests/initialize-config.test.ts	✅ Passed	181ms
tests/instance-isolation.test.ts	✅ Passed	212ms
tests/models-list.test.ts	✅ Passed	137ms
tests/responses-background-lifecycle.test.ts	✅ Passed	232ms
tests/responses-body-method-errors.test.ts	✅ Passed	335ms
tests/responses-cancel-timeout.test.ts	✅ Passed	195ms
tests/responses-cancel.test.ts	✅ Passed	274ms
tests/responses-compact-retries.test.ts	✅ Passed	352ms
tests/responses-compact.test.ts	✅ Passed	355ms
tests/responses-create-advanced-stream.test.ts	✅ Passed	129ms
tests/responses-create-advanced.test.ts	✅ Passed	314ms
tests/responses-create-disconnect.test.ts	✅ Passed	1.248s
tests/responses-create-errors.test.ts	✅ Passed	228ms
tests/responses-create-malformed-api-responses.test.ts	✅ Passed	295ms
tests/responses-create-retries.test.ts	✅ Passed	244ms
tests/responses-create-stream-failures.test.ts	✅ Passed	144ms
tests/responses-create-stream-timeout.test.ts	✅ Passed	214ms
tests/responses-create-stream-wire.test.ts	✅ Passed	4.009s
tests/responses-create-stream.test.ts	✅ Passed	121ms
tests/responses-create-terminal-states.test.ts	✅ Passed	247ms
tests/responses-create-timeout.test.ts	✅ Passed	207ms
tests/responses-create.test.ts	✅ Passed	352ms
tests/responses-delete.test.ts	✅ Passed	223ms
tests/responses-input-items-errors.test.ts	✅ Passed	338ms
tests/responses-input-items-list.test.ts	✅ Passed	429ms
tests/responses-input-items-options.test.ts	✅ Passed	357ms
tests/responses-input-tokens-count-timeout.test.ts	✅ Passed	238ms
tests/responses-input-tokens-count.test.ts	✅ Passed	279ms
tests/responses-malformed-inputs.test.ts	✅ Passed	3.068s
tests/responses-not-found-errors.test.ts	✅ Passed	263ms
tests/responses-parse.test.ts	✅ Passed	449ms
tests/responses-retrieve-retries.test.ts	✅ Passed	294ms
tests/responses-retrieve.test.ts	✅ Passed	261ms
tests/responses-stored-method-errors.test.ts	✅ Passed	561ms
tests/retry-behavior.test.ts	✅ Passed	3.106s
tests/sdk-error-shape.test.ts	✅ Passed	318ms

View OkTest run #33977395963

_{SDK merge (f3fb71853fbe) · head (f7f90fe2cb52) · base (be928151372e) · OkTest (2b1bdfd25e98)}

[github-actions]

Castiron custom code

✅ No new custom-code files detected.

36 mixed files remain; 0 existing customizations changed.

Compared be928151372e → f7f90fe2cb52. Generated baselines verified.

36 existing customizations unchanged

• api.md
• scripts/castiron/README.md
• scripts/castiron/custom_code_report.py
• scripts/castiron/test_custom_code_report.py
• src/openai/init.py
• src/openai/_client.py
• src/openai/resources/audio/transcriptions.py
• src/openai/resources/audio/translations.py
• src/openai/resources/beta/beta.py
• src/openai/resources/beta/responses/responses.py
• src/openai/resources/beta/threads/runs/runs.py
• src/openai/resources/beta/threads/threads.py
• src/openai/resources/chat/completions/completions.py
• src/openai/resources/embeddings.py
• src/openai/resources/files.py
• src/openai/resources/realtime/realtime.py
• src/openai/resources/responses/responses.py
• src/openai/resources/uploads/uploads.py
• src/openai/resources/vector_stores/file_batches.py
• src/openai/resources/vector_stores/files.py
• src/openai/resources/videos.py
• src/openai/resources/webhooks/init.py
• src/openai/resources/webhooks/webhooks.py
• src/openai/types/chat/init.py
• src/openai/types/chat/chat_completion_message_tool_call.py
• src/openai/types/fine_tuning/fine_tuning_job_integration.py
• src/openai/types/responses/init.py
• src/openai/types/responses/response.py
• src/openai/types/responses/response_function_web_search.py
• src/openai/types/responses/response_function_web_search_param.py
• src/openai/types/responses/responses_client_event.py
• src/openai/types/responses/responses_client_event_param.py
• src/openai/types/responses/tool.py
• src/openai/types/responses/tool_param.py
• src/openai/types/webhooks/init.py
• tests/api_resources/test_videos.py

A changed generated baseline means this report cannot reliably identify which handwritten lines changed.

Inspect the custom-code diff

Download the exact patch produced by this run (requires repository access):

gh run download 33977410909 --repo openai/openai-python \
  --name castiron-custom-code-33977410909-1 --dir /tmp/castiron-custom-code-33977410909-1
git apply --stat /tmp/castiron-custom-code-33977410909-1/custom-code.patch
cat /tmp/castiron-custom-code-33977410909-1/custom-code.patch

Or reproduce it from an SDK checkout containing the vendored reporter:

git fetch --no-tags origin be928151372e4b62adb4a1571cda52ad759b38be f7f90fe2cb52870a7088dee4bcdc4f787fc29802
python3 scripts/castiron/custom_code_report.py report \
  --base be928151372e4b62adb4a1571cda52ad759b38be \
  --head f7f90fe2cb52870a7088dee4bcdc4f787fc29802 --fetch --require-head-hash --public \
  --out /tmp/castiron-custom-code-f7f90fe2cb52
cat /tmp/castiron-custom-code-f7f90fe2cb52/custom-code.patch

This is the current full custom patch for mixed files, not an attribution of only the handwritten lines changed by this PR.

Full report and patch

[openai-sdks]

🤖 Created releases:

• v3.9.0

🌻