---
description: Run QA validation loop with automatic fixes
argument-hint: [feature-name] - Optional, uses current feature if omitted
---

# QA Review and Fix Loop

Run iterative QA review with automatic fix attempts. The system will review code, identify issues, and attempt fixes up to 50 iterations.

## Configuration

- **MAX_ITERATIONS**: 50
- **AUTO_FIX**: Ask user before each fix round

## Input

- **Feature name**: $ARGUMENTS or infer from current active build

## Workflow

### 1. Initialize

- Determine feature from argument or find active build in status files
- Load spec and plan from `.auto-build/specs/{feature-name}/`
- Create QA iteration directory: `.auto-build-data/cache/qa-iterations/{feature-name}/`
- Set iteration counter to 0
- Update status to `QA_REVIEW`

### 2. Review Loop

```
iteration = 0
while iteration < MAX_ITERATIONS:

    # 2a. Launch QA Reviewer
    Launch qa-reviewer agent with:
    - Spec and plan context
    - List of modified files (from status.json)
    - Previous iteration results (if any)

    # 2b. Collect Issues
    Agent returns issues with severity:
    - error: Must fix
    - warning: Should fix
    - info: Nice to fix

    Save to: `.auto-build-data/cache/qa-iterations/{feature-name}/iteration-{n}.json`

    # 2c. Check Exit Condition
    if no errors and no warnings:
        status = "PASSED"
        break

    # 2d. Present Issues
    Display:
    ```
    QA Review - Iteration {n}

    Found 3 issues:
    [ERROR] src/api/users.ts:42 - Potential null dereference
    [WARNING] src/types/user.ts:15 - Missing type annotation
    [INFO] src/utils/format.ts:8 - Could use const instead of let

    Auto-fix these issues? [Yes] [Select] [Skip] [Abort]
    ```

    # 2e. Fix Issues
    if user says yes:
        for each error/warning:
            Launch qa-fixer agent with issue details
            Track fix result

    # 2f. Increment
    iteration++
```

### 3. Exit Conditions

| Condition | Status | Action |
|-----------|--------|--------|
| No errors/warnings | `PASSED` | Proceed to completion |
| Max iterations | `NEEDS_MANUAL_REVIEW` | Show remaining issues |
| User abort | `ABORTED` | Save current state |

### 4. Final Report

```
======================================
  QA Review Complete
======================================

Status: PASSED (after 3 iterations)

Summary:
- Total issues found: 8
- Issues fixed: 7
- Issues skipped: 1 (info level)

Iterations:
1. Found 5 issues, fixed 5
2. Found 2 issues, fixed 2
3. Found 1 issue (info), skipped

Files reviewed: 12
Files modified during fixes: 6

Next steps:
- Save learnings: /ab:memory-save
- If using worktree: /ab:worktree cleanup feature-name
```

## Iteration Record Format

`.auto-build-data/cache/qa-iterations/{feature-name}/iteration-{n}.json` (local cache):
```json
{
  "iteration": 1,
  "timestamp": "2025-01-15T14:30:00Z",
  "issues_found": [
    {
      "severity": "error",
      "category": "correctness",
      "file": "src/api/users.ts",
      "line": 42,
      "code": "const x = data.value",
      "description": "Potential null dereference - data could be undefined",
      "suggestion": "Add null check: const x = data?.value ?? defaultValue"
    }
  ],
  "issues_fixed": [
    {
      "issue_id": 0,
      "fix_applied": "Added optional chaining and default value",
      "success": true
    }
  ],
  "issues_remaining": 0,
  "status": "all_fixed"
}
```

## QA Categories

The qa-reviewer checks for:

1. **Correctness**
   - Logic errors
   - Null/undefined handling
   - Type mismatches

2. **Patterns**
   - Following codebase conventions
   - Consistent error handling

3. **Security**
   - Input validation
   - Injection risks

4. **Performance**
   - Unnecessary loops
   - N+1 queries

5. **Maintainability**
   - Code clarity
   - DRY violations

## User Controls

- **Yes**: Fix all errors and warnings automatically
- **Select**: Choose which issues to fix
- **Skip**: Move to next iteration without fixing
- **Abort**: Stop QA review, save current state