chore(api): deprecate MCP connector_id

[jbeckwith-oai]

Summary

Updates MCP tool documentation with deprecation guidance for models released after September 1, 2026.

Changes

• Document the connector_id deprecation in Responses, beta Responses, and Realtime MCP tool types.
• Recommend server_url for remote MCP servers or tunnel_id for Secure MCP Tunnels.
• Keep the existing connector field, supported values, and request/response behavior available.

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-09-18T05:38:44.115046Z	1c1c9c7	PR opened
🔒 Security Review	✅ Completed 2026-09-18T05:40:42.048000Z	1c1c9c7	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[github-actions]

Castiron custom code

✅ No new custom-code files detected.

47 mixed files remain; 0 existing customizations changed; 2 generated baselines changed.

Compared 9a11f6e87429 → 1c1c9c7b03da. Generated baselines verified.

File	Result	Current custom patch
src/openai/types/responses/tool.py	Generated baseline changed	+5 / −0
src/openai/types/responses/tool_param.py	Generated baseline changed	+9 / −0

45 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/agents/sessions/sessions.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/live/forks.py
• src/openai/resources/live/live.py
• src/openai/resources/live/sideband.py
• src/openai/resources/realtime/api.md
• 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/beta/agent_session_message.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/realtime/conversation_item_input_audio_transcription_delta_event.py
• src/openai/types/realtime/realtime_error_event.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

5 more in the full report.

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 35311553740 --repo openai/openai-python \
  --name castiron-custom-code-35311553740-1 --dir /tmp/castiron-custom-code-35311553740-1
git apply --stat /tmp/castiron-custom-code-35311553740-1/custom-code.patch
cat /tmp/castiron-custom-code-35311553740-1/custom-code.patch

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

git fetch --no-tags origin 9a11f6e874292230633073fb64ea6202ad22a1df 1c1c9c7b03dadb610c19f12cb62eb5f30b668409
python3 scripts/castiron/custom_code_report.py report \
  --base 9a11f6e874292230633073fb64ea6202ad22a1df \
  --head 1c1c9c7b03dadb610c19f12cb62eb5f30b668409 --fetch --require-head-hash --public \
  --out /tmp/castiron-custom-code-1c1c9c7b03da
cat /tmp/castiron-custom-code-1c1c9c7b03da/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]

OkTest Summary

✅ 236/236 SDK tests passed in 11.955s for Python SDK PR #3894.

Test results — 42 files

Test	Result	Time
tests/chat-completions-complex-body.test.ts	✅ Passed	201ms
tests/chat-completions-create.test.ts	✅ Passed	374ms
tests/chat-completions-stream.test.ts	✅ Passed	233ms
tests/files-content-binary.test.ts	✅ Passed	211ms
tests/files-create-multipart.test.ts	✅ Passed	228ms
tests/files-list-pagination.test.ts	✅ Passed	146ms
tests/initialize-config.test.ts	✅ Passed	186ms
tests/instance-isolation.test.ts	✅ Passed	203ms
tests/models-list.test.ts	✅ Passed	259ms
tests/responses-background-lifecycle.test.ts	✅ Passed	428ms
tests/responses-body-method-errors.test.ts	✅ Passed	365ms
tests/responses-cancel-timeout.test.ts	✅ Passed	204ms
tests/responses-cancel.test.ts	✅ Passed	287ms
tests/responses-compact-retries.test.ts	✅ Passed	478ms
tests/responses-compact.test.ts	✅ Passed	255ms
tests/responses-create-advanced-stream.test.ts	✅ Passed	138ms
tests/responses-create-advanced.test.ts	✅ Passed	220ms
tests/responses-create-disconnect.test.ts	✅ Passed	1.274s
tests/responses-create-errors.test.ts	✅ Passed	191ms
tests/responses-create-malformed-api-responses.test.ts	✅ Passed	233ms
tests/responses-create-retries.test.ts	✅ Passed	284ms
tests/responses-create-stream-failures.test.ts	✅ Passed	214ms
tests/responses-create-stream-timeout.test.ts	✅ Passed	256ms
tests/responses-create-stream-wire.test.ts	✅ Passed	4.065s
tests/responses-create-stream.test.ts	✅ Passed	81ms
tests/responses-create-terminal-states.test.ts	✅ Passed	248ms
tests/responses-create-timeout.test.ts	✅ Passed	206ms
tests/responses-create.test.ts	✅ Passed	192ms
tests/responses-delete.test.ts	✅ Passed	235ms
tests/responses-input-items-errors.test.ts	✅ Passed	677ms
tests/responses-input-items-list.test.ts	✅ Passed	337ms
tests/responses-input-items-options.test.ts	✅ Passed	336ms
tests/responses-input-tokens-count-timeout.test.ts	✅ Passed	246ms
tests/responses-input-tokens-count.test.ts	✅ Passed	210ms
tests/responses-malformed-inputs.test.ts	✅ Passed	2.972s
tests/responses-not-found-errors.test.ts	✅ Passed	263ms
tests/responses-parse.test.ts	✅ Passed	540ms
tests/responses-retrieve-retries.test.ts	✅ Passed	232ms
tests/responses-retrieve.test.ts	✅ Passed	260ms
tests/responses-stored-method-errors.test.ts	✅ Passed	578ms
tests/retry-behavior.test.ts	✅ Passed	3.154s
tests/sdk-error-shape.test.ts	✅ Passed	275ms

View OkTest run #35311536328

_{SDK merge (a7b78d766161) · head (1c1c9c7b03da) · base (9a11f6e87429) · OkTest (cdb90acd46e5)}

[markstuart-oai]

Approved. I checked both upstream MCP connector_id schema definitions and the ten generated Python field docstrings. They consistently mark the field as deprecated for post-September 1, 2026 models and point users to server_url or tunnel_id, while preserving the existing field, alternatives, and executable behavior. I found no consequential issue.

Validation: isolated exact-head source review, Python parsing/AST comparison with the base, and git diff --check; no executable statements changed. Exact-head CI tests, lint, compatibility, and security checks are green. I did not run a runtime suite for this documentation-only change.

Codex task: codex://threads/01a0a21f-84b6-7c21-b7a7-30a1e64ab2f9