fix: guard against empty choices and message=None in LLM responses#39
Open
qizwiz wants to merge 1 commit into
Open
fix: guard against empty choices and message=None in LLM responses#39qizwiz wants to merge 1 commit into
qizwiz wants to merge 1 commit into
Conversation
OpenAI-compatible APIs can return empty choices (IndexError) or choices[0].message=None on filtered content (HTTP 200, AttributeError). Adds guard before 3 bare choices[0].message.content accesses in evaluate/ and reproduce/ scripts. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
OpenAI-compatible APIs can fail in two ways that crash the evaluation pipeline:
IndexError):response.choicesis[]when the API returns no completionsmessage=None(AttributeError):response.choices[0].messageisNonewhen content is filtered (e.g., Gemini returns HTTP 200 withPROHIBITED_CONTENT,message=None)Affected files
evaluate/evaluate_by_scoring.py— 1 siteevaluate/evaluate_by_selection.py— 1 sitereproduce/Step_2_extract_question.py— 1 site3 total sites guarded. 6 lines added, 0 deleted.
Fix pattern
Verification
Detected by pact static analysis. Confirmed live: Gemini 2.5 Flash returns HTTP 200 with
choices[0].message=Noneon prohibited content.