feat(api): update usage APIs and documentation

[apcha-oai]

Summary

Updates organization usage filtering, Responses and Chat Completions usage types, and API documentation.

Changes

• Add optional line_items filtering to organization cost usage requests, allowing results to be limited to exact cost line-item names
• Remove the unlaunched compute_units field from Responses and Chat Completions usage types
• Refresh model examples, documentation links, and reasoning-model guidance across affected API documentation

[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 2026-09-01T21:49:43.430536Z	3390805	Draft marked ready
🔒 Security Review	✅ Completed 2026-09-01T21:51:12.098586Z	3390805	Draft marked ready

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; 11 generated baselines changed.

Compared 2359a02dd22f → 3390805348c2. Generated baselines verified.

File	Result	Current custom patch
lib/openai/models/chat/completion_create_params.rb	Generated baseline changed	+21 / −5
lib/openai/models/responses/response.rb	Generated baseline changed	+20 / −0
lib/openai/models/responses/response_create_params.rb	Generated baseline changed	+9 / −1
lib/openai/resources/chat/completions.rb	Generated baseline changed	+42 / −0
lib/openai/resources/responses.rb	Generated baseline changed	+164 / −3
rbi/openai/models/chat/completion_create_params.rbi	Generated baseline changed	+79 / −41
rbi/openai/models/responses/response.rbi	Generated baseline changed	+5 / −0
rbi/openai/models/responses/response_create_params.rbi	Generated baseline changed	+10 / −1
rbi/openai/resources/chat/completions.rbi	Generated baseline changed	+26 / −17
rbi/openai/resources/responses.rbi	Generated baseline changed	+274 / −16
sig/openai/models/responses/response.rbs	Generated baseline changed	+2 / −0

36 existing customizations unchanged

• lib/openai.rb
• lib/openai/client.rb
• lib/openai/models/chat/chat_completion_message.rb
• lib/openai/models/chat/chat_completion_message_function_tool_call.rb
• lib/openai/models/response_format_json_schema.rb
• lib/openai/models/responses/function_tool.rb
• lib/openai/models/responses/response_format_text_config.rb
• lib/openai/models/responses/response_format_text_json_schema_config.rb
• lib/openai/models/responses/response_function_tool_call.rb
• lib/openai/models/responses/response_function_web_search.rb
• lib/openai/models/responses/response_output_text.rb
• lib/openai/models/responses/tool.rb
• lib/openai/resources/beta/threads.rb
• lib/openai/resources/files.rb
• lib/openai/resources/vector_stores/file_batches.rb
• lib/openai/resources/vector_stores/files.rb
• lib/openai/resources/webhooks.rb
• rbi/openai/client.rbi
• rbi/openai/models/chat/chat_completion_message.rbi
• rbi/openai/models/chat/chat_completion_message_function_tool_call.rbi
• rbi/openai/models/response_format_json_schema.rbi
• rbi/openai/models/responses/response_function_tool_call.rbi
• rbi/openai/models/responses/response_function_web_search.rbi
• rbi/openai/models/responses/response_output_text.rbi
• rbi/openai/resources/files.rbi
• rbi/openai/resources/vector_stores/file_batches.rbi
• rbi/openai/resources/vector_stores/files.rbi
• scripts/castiron/README.md
• scripts/castiron/custom_code_report.py
• scripts/castiron/test_custom_code_report.py
• sig/openai/client.rbs
• sig/openai/models/responses/response_function_web_search.rbs
• sig/openai/resources/files.rbs
• sig/openai/resources/responses.rbs
• sig/openai/resources/vector_stores/file_batches.rbs
• sig/openai/resources/vector_stores/files.rbs

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 33572010913 --repo openai/openai-ruby \
  --name castiron-custom-code-33572010913-1 --dir /tmp/castiron-custom-code-33572010913-1
git apply --stat /tmp/castiron-custom-code-33572010913-1/custom-code.patch
cat /tmp/castiron-custom-code-33572010913-1/custom-code.patch

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

git fetch --no-tags origin 2359a02dd22fbf599250aaa97e755863562abf53 3390805348c2a68a3f1c821e3edf375b73a682f7
python3 scripts/castiron/custom_code_report.py report \
  --base 2359a02dd22fbf599250aaa97e755863562abf53 \
  --head 3390805348c2a68a3f1c821e3edf375b73a682f7 --fetch --require-head-hash --public \
  --out /tmp/castiron-custom-code-3390805348c2
cat /tmp/castiron-custom-code-3390805348c2/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

✅ 237/237 SDK tests passed in 10.081s for Ruby SDK PR #566.

Test results — 42 files

Test	Result	Time
tests/chat-completions-complex-body.test.ts	✅ Passed	184ms
tests/chat-completions-create.test.ts	✅ Passed	236ms
tests/chat-completions-stream.test.ts	✅ Passed	139ms
tests/files-content-binary.test.ts	✅ Passed	351ms
tests/files-create-multipart.test.ts	✅ Passed	199ms
tests/files-list-pagination.test.ts	✅ Passed	192ms
tests/initialize-config.test.ts	✅ Passed	184ms
tests/instance-isolation.test.ts	✅ Passed	259ms
tests/models-list.test.ts	✅ Passed	177ms
tests/responses-background-lifecycle.test.ts	✅ Passed	231ms
tests/responses-body-method-errors.test.ts	✅ Passed	413ms
tests/responses-cancel-timeout.test.ts	✅ Passed	257ms
tests/responses-cancel.test.ts	✅ Passed	277ms
tests/responses-compact-retries.test.ts	✅ Passed	240ms
tests/responses-compact.test.ts	✅ Passed	268ms
tests/responses-create-advanced-stream.test.ts	✅ Passed	148ms
tests/responses-create-advanced.test.ts	✅ Passed	226ms
tests/responses-create-disconnect.test.ts	✅ Passed	1.007s
tests/responses-create-errors.test.ts	✅ Passed	261ms
tests/responses-create-malformed-api-responses.test.ts	✅ Passed	198ms
tests/responses-create-retries.test.ts	✅ Passed	296ms
tests/responses-create-stream-failures.test.ts	✅ Passed	182ms
tests/responses-create-stream-timeout.test.ts	✅ Passed	218ms
tests/responses-create-stream-wire.test.ts	✅ Passed	2.344s
tests/responses-create-stream.test.ts	✅ Passed	103ms
tests/responses-create-terminal-states.test.ts	✅ Passed	312ms
tests/responses-create-timeout.test.ts	✅ Passed	256ms
tests/responses-create.test.ts	✅ Passed	311ms
tests/responses-delete.test.ts	✅ Passed	305ms
tests/responses-input-items-errors.test.ts	✅ Passed	199ms
tests/responses-input-items-list.test.ts	✅ Passed	189ms
tests/responses-input-items-options.test.ts	✅ Passed	257ms
tests/responses-input-tokens-count-timeout.test.ts	✅ Passed	286ms
tests/responses-input-tokens-count.test.ts	✅ Passed	286ms
tests/responses-malformed-inputs.test.ts	✅ Passed	2.059s
tests/responses-not-found-errors.test.ts	✅ Passed	344ms
tests/responses-parse.test.ts	✅ Passed	217ms
tests/responses-retrieve-retries.test.ts	✅ Passed	282ms
tests/responses-retrieve.test.ts	✅ Passed	236ms
tests/responses-stored-method-errors.test.ts	✅ Passed	770ms
tests/retry-behavior.test.ts	✅ Passed	2.971s
tests/sdk-error-shape.test.ts	✅ Passed	373ms

View OkTest run #33562991613

_{SDK merge (7e0edfda11a4) · head (3390805348c2) · base (2359a02dd22f) · OkTest (2b1bdfd25e98)}

[jbeckwith-oai]

Blocking scope issue: the stated outcome is limited to removing the unlaunched compute_units usage fields, but this exact diff also promotes unrelated schema and public-surface changes—for example, a new organization-cost line_items filter, a new max_messages incomplete-reason value, and broad model/example/documentation updates. Those changes are not narrowly necessary for the field removal and make the patch carry behavior/API surface that the PR does not describe. Please regenerate from a baseline/config containing only the compute_units removal, or split and explicitly document/approve the broader promotion. I understand the compatibility/breaking-change checks triggered by the intentional field removal; that expected break is not this finding.

[jbeckwith-oai]

Thanks for broadening the description. One public-surface change is still missing from the stated scope: this diff adds max_messages to the Responses/Beta Responses incomplete-reason enum/type in addition to the usage and documentation changes. That is a generated public API change, not merely a documentation refresh. Please explicitly include it in the description (or remove it) so the reviewed scope matches the exact diff.

[HAYDEN-OAI]

Reviewed the complete diff at 3390805348c2, including the intentional removal of the unlaunched compute_units field, optional organization-cost line_items filtering, stable/beta max_messages reason support, and schema/documentation updates. Checked Ruby/RBI/RBS parity, unknown response-field retention, filter omission/query encoding, admin authentication, and stable/beta reason handling.

No substantive issues found. Static source review only.