fix(openai): instrument responses.parse() for structured-output tracing#4198
Merged
Conversation
Calls to openai.responses.parse() (the canonical structured-output entry point for the Responses API) produced no LLM span, token usage, or cost, because only Responses.create / retrieve / cancel were patched. Wire .parse (sync + async) through the existing responses_get_or_create_wrapper and add matching unwrap entries. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughWraps OpenAI v1 ChangesResponses.parse() Instrumentation
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@packages/opentelemetry-instrumentation-openai/tests/traces/test_responses.py`:
- Around line 471-474: Replace the hardcoded API key passed to the OpenAI
constructor in the test (the OpenAI(...) call) with a value read from the
environment; update the instantiation to source api_key from an environment
variable (e.g., via os.getenv("OPENAI_API_KEY") or os.environ["OPENAI_API_KEY"])
and, if needed for CI, provide a non-secret fallback via test configuration
rather than a literal string in code so no API key is committed.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 731a76c4-4162-44fd-bc26-8f5b5e2d001e
📒 Files selected for processing (2)
packages/opentelemetry-instrumentation-openai/opentelemetry/instrumentation/openai/v1/__init__.pypackages/opentelemetry-instrumentation-openai/tests/traces/test_responses.py
doronkopit5
reviewed
May 28, 2026
Replace MockTransport-based test with VCR-recorded sync + async tests that exercise the real OpenAI Responses API. Cassettes scrub auth headers via the existing conftest filter. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
Actionable comments posted: 0 |
doronkopit5
reviewed
May 28, 2026
| spans = span_exporter.get_finished_spans() | ||
| assert len(spans) == 1, f"expected one openai.response span, got {len(spans)}" | ||
| span = spans[0] | ||
| assert span.name == "openai.response" |
Member
There was a problem hiding this comment.
i guess we want to assert something about the instrumentation in matter of span input messages/output messages to make the test stronger
same about the async test
Strengthen the parse tests to verify the user prompt is captured under gen_ai.input.messages and the structured JSON response under gen_ai.output.messages, and that the captured text round-trips back to the Pydantic model and matches response.output_parsed. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
Actionable comments posted: 0 |
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
2 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.
Summary
openai.responses.parse()(the canonical structured-output method for the Responses API + Pydantic models) was silently uninstrumented — calls produced no LLM span, token usage, or cost.Responses.create/retrieve/cancelwere patched inv1/__init__.py. This wires.parse(sync + async) through the existingresponses_get_or_create_wrapperand adds matchingunwrapentries.ParsedResponsesubclassesResponse, so the existing wrapper handles the response shape without changes.responses.stream()is similarly uninstrumented but has a context-manager shape — tracked as a follow-up.Test plan
test_responses_parse_emits_span— useshttpx.MockTransportso it runs in CI without anOPENAI_API_KEYor VCR cassette, asserts the span is emitted withgen_ai.request.model+gen_ai.usage.input_tokens+gen_ai.usage.output_tokens.got 0 spans) without the_try_wraplines, passes with them.test_responses.py(24 tests) passes — no regressions.🤖 Generated with Claude Code
Summary by CodeRabbit
New Features
Tests