Repository navigation
feat(api): add response tool usage models - #4201
Conversation
Castiron-Internal-PR: openai/openai-python-internal#370 Castiron-Source-SHA: a8e3aeb6d14653046c1b7dbcfcba3569140267b3 Castiron-Public-Base-SHA: 77fd116
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
markstuart-oai
left a comment
markstuart-oai
left a comment
There was a problem hiding this comment.
Approved. The stable and beta response models match the added schema: optional hosted tool usage, required image and web-search groups, and optional cache/output details. Existing response fields remain unchanged.
The nested models use the existing parser and keep absent fields out of explicitly set fields. Both response models remain below 1,000 lines. The generated-file inventory matches the changed models. These are cohesive output declarations; no new dispatch layer or structural regression was found.
The public diff matches the already reviewed internal candidate byte for byte. Reviewed all five changed files with an independent source review. No tests, builds or generation ran here. Hosted checks passed where completed; skipped checks and any remaining CI are separate validation limits.
Reviewed head: 06fddc2852e79b5730d03316dfe1df60e8d7bb04; base: 77fd116d2326bc828bb23d4fd7960142972293a4.
Automated Release PR --- ## [3.41.0](openai/openai-python@v3.40.0...v3.41.0) (2026-10-28) ### Features * **api:** accept typed references in Realtime response inputs ([openai#4189](openai#4189)) ([8ecb487](openai@8ecb487)) * **api:** add response tool usage models ([openai#4201](openai#4201)) ([55fc500](openai@55fc500)) * **api:** filter agent sessions by metadata ([openai#4200](openai#4200)) ([77fd116](openai@77fd116)) * **websocket:** recover queued binary frames after reconnect ([openai#4191](openai#4191)) ([f079868](openai@f079868)) ### Bug Fixes * **examples:** detect incomplete WebSocket responses ([openai#4187](openai#4187)) ([8559299](openai@8559299)) * **examples:** handle interruptions and disconnects in push-to-talk ([openai#4192](openai#4192)) ([35fc9f3](openai@35fc9f3)) * keep consumer fixtures clean under strict Pyright ([openai#4204](openai#4204)) ([5012565](openai@5012565)) ### Chores * **api:** document upcoming model shutdowns ([openai#4199](openai#4199)) ([5b43cce](openai@5b43cce)) * **api:** update image-model documentation ([openai#4198](openai#4198)) ([fa67521](openai@fa67521)) * enforce generated-file ownership ([openai#4193](openai#4193)) ([1b37b9a](openai@1b37b9a)) * migrate development type checking to ty ([openai#4202](openai#4202)) ([45b9531](openai@45b9531)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). Co-authored-by: openai-sdks[bot] <284451331+openai-sdks[bot]@users.noreply.github.com>
Summary
Adds optional hosted tool usage to stable and beta Responses, separately from model token usage.
Changes