fix(openai-agents): resolve missing response field execution for Gene…#4320
Open
Toshika-Kamble wants to merge 2 commits into
Open
fix(openai-agents): resolve missing response field execution for Gene…#4320Toshika-Kamble wants to merge 2 commits into
Toshika-Kamble wants to merge 2 commits into
Conversation
|
|
📝 WalkthroughWalkthrough
ChangesOpenAI Agents generation span end handling
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~5 minutes Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 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-agents/opentelemetry/instrumentation/openai_agents/_hooks.py`:
- Around line 983-989: Surface response-extraction failures in the span closure
path instead of swallowing them in `_extract_response_attributes()` handling:
keep the try/except around the `response_source` block in `_hooks.py`, but
replace the silent `pass` with recording or logging the caught exception so the
`GenerationSpanData` fallback loss of `gen_ai.output.*` attributes is visible
while preserving non-throwing behavior.
🪄 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: 539f0ad5-5e66-495b-a467-853055d5055b
📒 Files selected for processing (1)
packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py
Comment on lines
+983
to
+989
| # Wrap this tightly so an internal attribute error won't abort the entire span closure | ||
| if response_source is not None: | ||
| try: | ||
| _extract_response_attributes(otel_span, response_source, trace_content) | ||
| except Exception as e: | ||
| # This keeps the span alive and lets us see if other tests pass | ||
| pass |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Map the relevant file and nearby symbols first.
ast-grep outline packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py --view expanded || true
# Show the target region with line numbers.
sed -n '940,1010p' packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py
# Find tests touching GenerationSpanData / response extraction / response_source.
rg -n "GenerationSpanData|response_source|_extract_response_attributes|record_exception|gen_ai\.output|no response must not raise" packages/opentelemetry-instrumentation-openai-agents -g '*test*' -g '*.py'Repository: traceloop/openllmetry
Length of output: 23296
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Show any tests around the suspected behavior in the package.
fd -a . packages/opentelemetry-instrumentation-openai-agents | rg 'test|tests'Repository: traceloop/openllmetry
Length of output: 4062
🏁 Script executed:
#!/bin/bash
set -euo pipefail
ast-grep outline packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py --view expanded || true
printf '\n--- FILE REGION ---\n'
sed -n '940,1010p' packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py
printf '\n--- MATCHES ---\n'
rg -n "GenerationSpanData|response_source|_extract_response_attributes|record_exception|gen_ai\.output|no response must not raise" packages/opentelemetry-instrumentation-openai-agents -g '*test*' -g '*.py'Repository: traceloop/openllmetry
Length of output: 23334
🏁 Script executed:
#!/bin/bash
set -euo pipefail
fd -a . packages/opentelemetry-instrumentation-openai-agents | rg 'test|tests'Repository: traceloop/openllmetry
Length of output: 4062
🏁 Script executed:
#!/bin/bash
set -euo pipefail
ast-grep outline packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py --view expanded || true
printf '\n--- FILE REGION ---\n'
sed -n '940,1010p' packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py
printf '\n--- MATCHES ---\n'
rg -n "GenerationSpanData|response_source|_extract_response_attributes|record_exception|gen_ai\.output|no response must not raise" packages/opentelemetry-instrumentation-openai-agents -g '*test*' -g '*.py'Repository: traceloop/openllmetry
Length of output: 23334
🏁 Script executed:
#!/bin/bash
set -euo pipefail
ast-grep outline packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py --view expanded || true
printf '\n--- FILE REGION ---\n'
sed -n '940,1010p' packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py
printf '\n--- MATCHES ---\n'
rg -n "GenerationSpanData|response_source|_extract_response_attributes|record_exception|gen_ai\.output|no response must not raise" packages/opentelemetry-instrumentation-openai-agents -g '*test*' -g '*.py'Repository: traceloop/openllmetry
Length of output: 23334
Surface response-extraction failures instead of swallowing them. _extract_response_attributes() can still fail here, and except Exception: pass will drop the GenerationSpanData fallback’s gen_ai.output.* attrs silently. Keep the non-throwing behavior, but record or log the exception instead.
🤖 Prompt for 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.
In
`@packages/opentelemetry-instrumentation-openai-agents/opentelemetry/instrumentation/openai_agents/_hooks.py`
around lines 983 - 989, Surface response-extraction failures in the span closure
path instead of swallowing them in `_extract_response_attributes()` handling:
keep the try/except around the `response_source` block in `_hooks.py`, but
replace the silent `pass` with recording or logging the caught exception so the
`GenerationSpanData` fallback loss of `gen_ai.output.*` attributes is visible
while preserving non-throwing behavior.
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.
Description
This PR addresses an issue where
GenerationSpanDatawas missing a standaloneresponsefield, preventing_extract_response_attributesfrom executing duringon_span_end.Changes
response_source = span_datawhen handlingGenerationSpanDataif a standaloneresponseattribute is absent.Verification Results
fix(openai-agents): ....Closes 🐛 Bug Report: GenerationSpanData missing response field causes _extract_response_attributes to never execute #4157
Summary by CodeRabbit