fix(#724): block convergence on actionable review findings (#728)

* fix(#724): block convergence on actionable review findings

* merge: integrate clean next (#936 inline) onto author tip + re-apply cursor fixes (Mode field, REVIEWS.md extraction) and review hardening (#724)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Jeremy McSpadden
2026-06-10 13:54:15 -05:00
committed by GitHub
parent fb37fa7dd5
commit f61b97276e
10 changed files with 250 additions and 79 deletions

View File

@@ -205,7 +205,7 @@ See [Package Legitimacy Gate in the User Guide](USER-GUIDE.md#package-legitimacy
### `/gsd-plan-review-convergence`
Cross-AI plan convergence loop — replan with review feedback until no HIGH concerns remain. Runs `plan-phase → review → replan → re-review` cycles (max 3 cycles by default). Spawns isolated agents for planning and review; orchestrator handles loop control, HIGH-concern counting, stall detection, and escalation.
Cross-AI plan convergence loop — replan with review feedback until no HIGH concerns remain and no actionable MEDIUM/LOW findings remain outside `PLAN.md`. Runs `plan-phase → review → replan → re-review` cycles (max 3 cycles by default). Plan-phase runs inline (bare Skill at depth 0 so it can spawn gsd-planner/gsd-plan-checker at depth 1); only gsd-review runs in an isolated Agent. Orchestrator handles loop control, unresolved review counting (HIGH + actionable non-HIGH), stall detection, and escalation.
| Argument / Flag | Required | Description |
|-----------------|----------|-------------|
@@ -214,7 +214,7 @@ Cross-AI plan convergence loop — replan with review feedback until no HIGH con
| `--all` | No | Run every configured reviewer in parallel |
| `--max-cycles N` | No | Override cycle cap (default 3) |
**Exit behavior:** Loop exits when HIGH count hits zero. Stall detection warns when HIGH count is not decreasing across cycles. Escalation gate asks the user to proceed or review manually when `--max-cycles` is hit with HIGH concerns still open.
**Exit behavior:** Loop exits when both `current_high` and `current_actionable` hit zero. Stall detection warns when the total unresolved review count is not decreasing across cycles. Escalation gate asks the user to proceed or review manually when `--max-cycles` is hit with HIGH or actionable non-HIGH concerns still open.
```bash
/gsd-plan-review-convergence 3 # Default reviewers, 3 cycles