feat: add spec-compliant streaming error event for Responses API

[gyliu513]

Summary

Replace the ad-hoc OpenAIErrorResponse dict-based error event in SSE streaming with a spec-compliant OpenAIResponseObjectStreamError Pydantic model.

Problem: When errors occur mid-stream (e.g., ValueError from a provider), the SSE generator previously emitted an OpenAIErrorResponse — which is the OpenAI HTTP error response format ({"error": {"message": "...", "code": "..."}}). This is the wrong format for streaming. OpenAI's streaming API uses a distinct ResponseErrorEvent with type: "error" as a top-level SSE event (openai-python SDK reference).

Fix: Introduce OpenAIResponseObjectStreamError matching OpenAI's ResponseErrorEvent schema:

{"type": "error", "code": "400", "message": "not found", "sequence_number": 5}

This allows OpenAI-compatible client SDKs to correctly deserialize streaming errors.

[github-actions]

✱ Stainless preview builds

This PR will update the llama-stack-client SDKs with the following commit message.

feat: add spec-compliant streaming error event for Responses API

Edit this comment to update it. It will appear in the SDK's changelogs.

✅ llama-stack-client-openapi studio · code · diff

Your SDK build had at least one "warning" diagnostic, but this did not represent a regression.
generate ⚠️

✅ llama-stack-client-go studio · conflict

Your SDK build resulted in a merge conflict between your custom code and the newly generated changes, but this did not represent a regression.

✅ llama-stack-client-node studio · conflict

Your SDK build resulted in a merge conflict between your custom code and the newly generated changes, but this did not represent a regression.

✅ llama-stack-client-python studio · conflict

Your SDK build resulted in a merge conflict between your custom code and the newly generated changes, but this did not represent a regression.

---

This comment is auto-generated by GitHub Actions and is automatically kept up to date as you push.
If you push custom code to the preview branch, re-run this workflow to update the comment.
Last updated: 2026-03-26 12:48:03 UTC

[cdoern]

can you please add a description to this PR

[gyliu513]

@cdoern Done, this is a draft PR, so I did not add description when submit it, it is still draft, I may need more test and the description may be updated later.