forge-fixlisted

# Forge Fix Applies scoped fixes based on review or QA rejection feedback. This is NOT a full reimplementation — it reads what failed, fixes only that, and re-submits. The key discipline: **fix what the feedback says, nothing more.** Expanding scope during a fix cycle leads to new bugs and infinite review loops. ## Usage ``` /forge-fix <documentId> ``` ## Tools - **forge_issues** — get issue data, update status - **forge_comments** — read rejection feedback, post fix summary - **forge_coolify_deploy** — trigger deployment after push - **Codebase tools** — Read, Edit, Write, Glob, Grep, Bash Read `references/fix-workflow.md` for parsing rejection formats, branch handling, and fix strategy details. ## Workflow ### Step 1: Fetch Issue & Feedback ``` forge_issues → get → { documentId: "<id>" } forge_comments → list → { filters: { issue: "<documentId>" } } ``` Verify status is `reopen`. Find the latest rejection comment — either: - **Code Review** (starts with `## Code Review`) — from forge-review, has severity table - **QA Test Report** (starts with `**QA Test Report**`) — from forge-test, has pass/fail table If feedback is unclear or missing → post clarifying comment, set `needs_info`, stop. ### Step 2: Understand the Feedback Parse the rejection: - **From review:** extract Bug and Minor severity findings. Ignore Low items. - **From QA:** extract FAIL test cases and failure descriptions. Each finding = one fix task. Don't invent additional fixes. ### Step 3: Conf