feat(api): add gpt-6-astra and related features - #969
Merged
Conversation
Castiron-Internal-PR: openai/openai-java-internal#55 Castiron-Source-SHA: d78518a3bc3dcb4a6e087dbf1c0a89cb97f11806 Castiron-Public-Base-SHA: d3191b0
apcha-oai
marked this pull request as ready for review
September 3, 2026 19:36
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. |
Contributor
Contributor
Castiron custom code✅ No new custom-code files detected. 53 mixed files remain; 0 existing customizations changed; 16 generated baselines changed. Compared
37 existing customizations unchanged
A changed generated baseline means this report cannot reliably identify which handwritten lines changed. Inspect the custom-code diffDownload the exact patch produced by this run (requires repository access): gh run download 33797459399 --repo openai/openai-java \
--name castiron-custom-code-33797459399-1 --dir /tmp/castiron-custom-code-33797459399-1
git apply --stat /tmp/castiron-custom-code-33797459399-1/custom-code.patch
cat /tmp/castiron-custom-code-33797459399-1/custom-code.patchOr reproduce it from an SDK checkout containing the vendored reporter: git fetch --no-tags origin d3191b0db2f456882fd2e2edc3dce126f85505e1 239c0bcb05cf6b473ebf5aefbbdc446486c2500d
python3 scripts/castiron/custom_code_report.py report \
--base d3191b0db2f456882fd2e2edc3dce126f85505e1 \
--head 239c0bcb05cf6b473ebf5aefbbdc446486c2500d --fetch --require-head-hash --public \
--out /tmp/castiron-custom-code-239c0bcb05cf
cat /tmp/castiron-custom-code-239c0bcb05cf/custom-code.patchThis is the current full custom patch for mixed files, not an attribution of only the handwritten lines changed by this PR. |
Merged
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 239c0bcb05
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".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Comment on lines
40
to
+43
| class ResponsesClientEvent | ||
| @JsonCreator(mode = JsonCreator.Mode.DISABLED) | ||
| private constructor( | ||
| private val type: JsonValue, | ||
| private val background: JsonField<Boolean>, | ||
| private val contextManagement: JsonField<List<ContextManagement>>, | ||
| private val conversation: JsonField<Conversation>, | ||
| private val include: JsonField<List<ResponseIncludable>>, | ||
| private val input: JsonField<Input>, | ||
| private val instructions: JsonField<String>, | ||
| private val maxOutputTokens: JsonField<Long>, | ||
| private val maxToolCalls: JsonField<Long>, | ||
| private val metadata: JsonField<Metadata>, | ||
| private val model: JsonField<ResponsesModel>, | ||
| private val moderation: JsonField<Moderation>, | ||
| private val parallelToolCalls: JsonField<Boolean>, | ||
| private val previousResponseId: JsonField<String>, | ||
| private val prompt: JsonField<ResponsePrompt>, | ||
| private val promptCacheKey: JsonField<String>, | ||
| private val promptCacheOptions: JsonField<PromptCacheOptions>, | ||
| private val promptCacheRetention: JsonField<PromptCacheRetention>, | ||
| private val reasoning: JsonField<Reasoning>, | ||
| private val safetyIdentifier: JsonField<String>, | ||
| private val serviceTier: JsonField<ServiceTier>, | ||
| private val store: JsonField<Boolean>, | ||
| private val stream: JsonField<Boolean>, | ||
| private val streamId: JsonField<String>, | ||
| private val streamOptions: JsonField<StreamOptions>, | ||
| private val temperature: JsonField<Double>, | ||
| private val text: JsonField<ResponseTextConfig>, | ||
| private val toolChoice: JsonField<ToolChoice>, | ||
| private val tools: JsonField<List<Tool>>, | ||
| private val topLogprobs: JsonField<Long>, | ||
| private val topP: JsonField<Double>, | ||
| private val truncation: JsonField<Truncation>, | ||
| private val user: JsonField<String>, | ||
| private val additionalProperties: MutableMap<String, JsonValue>, | ||
| private val responseCreate: ResponseCreate? = null, | ||
| private val responseSteer: ResponseSteerEvent? = null, |
There was a problem hiding this comment.
Existing WebSocket clients that construct ResponsesClientEvent.builder().model(...).build() or reference nested types such as ResponsesClientEvent.ContextManagement will no longer compile after upgrading, and already-compiled clients can fail with NoSuchMethodError, because this change replaces the released concrete event API with a union and moves the create payload under ResponseCreate without a compatibility façade. Retain deprecated builder/accessor/type bridges while exposing the new steering variant.
AGENTS.md reference: AGENTS.md:L5-L8
Useful? React with 👍 / 👎.
Comment on lines
+264
to
+265
| private val message: Message? = null, | ||
| private val functionCallOutput: FunctionCallOutput? = null, |
There was a problem hiding this comment.
When a caller uses this typed functionCallOutput variant, the serializer emits a tool-output item in response.steer.input, even though the newly added ResponseSteerEvent.input contract explicitly permits only user messages and says tool outputs are unsupported; such an event is therefore rejected as invalid input despite being constructible through the SDK. Align the authoritative steering-item schema with that contract and regenerate both stable and beta models.
AGENTS.md reference: AGENTS.md:L5-L8
Useful? React with 👍 / 👎.
apcha-oai
pushed a commit
that referenced
this pull request
Sep 3, 2026
Automated Release PR --- ## [4.57.0](v4.56.0...v4.57.0) (2026-09-03) ### Features * **api:** add gpt-6-astra and related features ([#969](#969)) ([39f1715](39f1715)) --- 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>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add GPT-6 Astra support, safety alert retrieval and webhooks, and response steering across the stable and beta Responses APIs. Expand model, tool, and error types for asynchronous tools, steering guidance, and safety metadata.
Changes
GPT_6_ASTRAmodel constant and support it in relevant chat and Responses model selectors.