fix(M5): Include previous evaluation result in evaluator prompt#461
Merged
Conversation
Previously each evaluator invocation was stateless — it had no memory of what it said before. If the evaluator said "NO: tests failing" and the agent fixed the tests but a different issue appeared, the evaluator couldn't see that the agent had responded to its feedback. Now `buildEvaluatorPrompt` accepts an optional `lastEvalReason` and includes it as "Previous evaluation: NO — ..." before the condition, asking the evaluator to check whether the agent addressed that specific feedback. Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Previously each evaluator invocation was stateless — it had no memory of what it said before. If the evaluator said "NO: tests failing" and the agent fixed the tests but a different issue appeared, the evaluator couldn't see that the agent had responded to its feedback.
Changes:
buildEvaluatorPromptaccepts an optionallastEvalReasonparameterMade with Cursor