Fix completeness gate for truncation and parse failures - #78
Merged
Conversation
…lures The two-way exception split (transient vs. everything-else-is-skipped) let max_tokens truncation and parse errors be absorbed as "skipped", so the completeness gate reported `complete: true` even with data loss. - Add `MetricNotApplicableError` for genuine inapplicability (e.g. distractor metric on true/false questions) - Three-way handler: transient → retry, not-applicable → skip, other → failed - `complete = (transient + failed) == 0` instead of ignoring non-transient errors - Clean paper-specific references from test docstrings Co-Authored-By: Claude Opus 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
MetricNotApplicableError(skip) vsTransientLLMError(retry) vs everything else (failed). Previously,max_tokenstruncation and parse errors were silently absorbed as "skipped".complete = (transient + failed) == 0— truncation now correctly fails the run instead of reporting success.Test plan
test_truncation_error_fails_completeness— verifies truncation flipscompletetofalsetest_skipped_error_does_not_fail_completeness— verifiesMetricNotApplicableErroris still a clean skip🤖 Generated with Claude Code