Fix triple-shot second pass caused by merge recommendations#662
Merged
Fix triple-shot second pass caused by merge recommendations#662
Conversation
When the judge recommends "merge" strategy, it populates the
suggested_changes field. LLMs frequently write this as a plain string
instead of []string, causing json.Unmarshal to fail. The parse failure
made VerifyWork return false, the bridge called gate.Fail(), and with
defaultMaxRetries=2 the task retried — spawning a duplicate judge.
Add FlexibleStringSlice type (mirrors existing FlexibleString) to
tolerate string/array mismatches in all LLM-parsed sentinel file
structs: Evaluation, AttemptEvaluationItem, AdversarialReviewFile.
Also log SetMaxRetries errors instead of silently discarding, and
consolidate the redundant Team("judge") lookup in startJudge.
Iron-Ham
force-pushed
the
Iron-Ham/fix-tripleshot-merge-second-pass
branch
from
216dc56 to
6426b1d
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
suggested_changesin the evaluation JSON. LLMs frequently write this as a plain string instead of[]string, causingjson.Unmarshalto fail →VerifyWorkreturns false → bridge callsgate.Fail()→ withdefaultMaxRetries=2, the task retries and spawns a duplicate judge instanceFlexibleStringSlicetype (mirrors existingFlexibleString) that accepts bothstringand[]stringJSON values. Applied to all[]stringfields in LLM-parsed structs:Evaluation,AttemptEvaluationItem,AdversarialReviewFileEvaluation.ReasoninguseFlexibleStringfor the same resilienceSetMaxRetrieserrors instead of silently discarding with_ =Team("judge")lookup instartJudgeTest plan
TestParseEvaluationFile_FlexibleFieldswith 4 cases: string-as-suggested_changes, array-as-suggested_changes, reasoning-as-array, strengths/weaknesses-as-string-racego build ./...cleango vet ./...clean