Preserve provider errors from failed benchmark grading - #1
Merged
Merged
Conversation
jrh-mann
marked this pull request as ready for review
September 15, 2026 14:40
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When a benchmark grader fails, the auditor currently truncates the exception to 500 characters. A long model request can consume that space and hide the provider error, as happened with all 23 SQAV pilot grader probes.
Follow explicit exception causes and preserve the underlying error message. The failure remains a recoverable tool error so the auditor can record the blocked check.
Validation: all nine grade-tool tests pass, including a regression with a long request wrapper hiding the underlying failure. Changes are limited to error reporting and its existing test.