Add configurable reviewers list to review-implementation step#79
Merged
Conversation
Replace the single `cmd`/`timeout`/`max_retries` step-level keys with a `reviewers` list, where each entry carries its own `name`, `cmd`, `timeout`, and `max_retries`. Reviewers run sequentially; an empty stdout from a reviewer means approved (no commit), non-empty stdout triggers the address loop which produces one commit per reviewer on success. State tracking moves from flat step-level keys to a per-reviewer map under `reviewers.<name>.*`, with a legacy-state guard that aborts cleanly if an old `state.json` shape is detected. Log files are now named `review-implementation.<name>.<suffix>.log`. Config validation rejects the removed top-level keys with an actionable migration message.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
cmd/timeout/max_retriesstep-level keys with areviewers:list; each reviewer runs Phase A (invoke) + Phase B (address loop) independently and produces its own commit on rejectreviewers[].{key};validate_reviewer_argv0sreplacesvalidate_review_cmd_argv0andhas_any_reviewerreplaceshas_review_cmdincommand_create.pystep_data["review-implementation"]["reviewers"][<name>]; log files usereview-implementation.<name>.<suffix>.lognaming; Phase-A infra failures now raiseStepErrorrather than silently skippingTest plan
tests/draft/test_review_implementation.pycovers: empty reviewers early-return, single approve, single reject+address, three reviewers (all approve, mixed), Phase-A infra failure, Phase-B max-retries exhaustion, no-changes-on-attempt-1,DRAFT_REVIEWER_NAMEenv, per-reviewer log paths,{{REVIEWER_NAME}}substitution, resume skipping completed reviewers, resume restarting in-progress reviewers, legacy-state guard, and README content assertiontests/draft/test_config.pyextended with validation tests for all new schema branches (removed keys,reviewersshape, name regex, duplicate names, cmd/timeout/max_retries ranges, unknown keys) andvalidate_reviewer_argv0steststests/draft/test_commands.pyupdated to usehas_any_reviewerkeyword in_compose_active_stepstests