feat: add self-review quality loop to implement node - #287
Merged
Conversation
After code generation (Phase 2) and before tests/lint (Phase 3), the implement node now runs a proud + world-class self-review loop (max 3 iterations). The agent reviews its own diff, and if either check returns needs-work, it fixes the issues before proceeding. Inspired by https://github.com/robertbagge/claude-roadhouse-plugin Co-Authored-By: Claude Opus 4.6 <[email protected]>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Changes
packages/workflows/src/lintel/workflows/nodes/_self_review.py—_extract_verdict(),run_self_review_loop()_impl_structured.py— calls self-review loop between Phase 2 (write files) and Phase 3 (test/fix)test_impl_retry.py— patches self-review in existing structured impl testsTest plan
test_self_review_loop.pycovering verdict parsing, loop iterations, exhaustion, prompt content, and token accumulationmake lintpassesmake typecheckpassesCloses work item
7aa85aed-636a-44b4-a014-90d3a907644e🤖 Generated with Claude Code