Fix extractJson picking up non-JSON brace groups (e.g., C# code)#100
Merged
Conversation
extractJson now validates each brace-matched candidate with JSON.parse before returning it. If the candidate isn't valid JSON (even after escape sanitization), it skips to the next brace group. This prevents C# code snippets or other non-JSON content from being mistakenly extracted as the judge's JSON response. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes a bug in the extractJson function where non-JSON brace groups (such as C# code snippets) could be mistakenly extracted as JSON responses from LLM outputs. The fix adds validation to each brace-matched candidate using JSON.parse before returning it, with a fallback attempt using escape sequence sanitization. If a candidate fails validation, the function moves to the next brace group instead of returning invalid content.
Changes:
- Enhanced
extractJsonto validate each brace-matched candidate with JSON.parse before returning, skipping non-JSON content - Modified
extractOutermostJsonto return position metadata to enable searching for subsequent brace groups - Updated error message expectations in tests to reflect new "contained no JSON" behavior when no valid JSON is found
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| eng/skill-validator/src/llm-json.ts | Added validation loop to extractJson that tries JSON.parse on each candidate; modified extractOutermostJson to return endIndex for iteration |
| eng/skill-validator/tests/llm-json.test.ts | Added tests for skipping C# code, multiple non-JSON groups, and all-invalid scenarios |
| eng/skill-validator/tests/judge.test.ts | Updated test error message expectations from specific parse failures to "contained no JSON" |
| eng/skill-validator/tests/pairwise-judge.test.ts | Updated test error message expectations from specific parse failures to "contained no JSON" |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
JanKrivanek
approved these changes
Feb 24, 2026
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
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.
extractJson now validates each brace-matched candidate with JSON.parse before returning it. If the candidate isn't valid JSON (even after escape sanitization), it skips to the next brace group. This prevents C# code snippets or other non-JSON content from being mistakenly extracted as the judge's JSON response.