e2e-test-loop

# E2E Test Loop - Browser Automation Testing

**Current branch:** !`git branch --show-current 2>/dev/null || echo "not in git repo"`

The E2E test loop systematically adds end-to-end tests for user flows using
Playwright, with page objects for maintainable test code.

## State Management

**Single Source of Truth**: `.claude/e2e-state-{session}.json` stores all state including
the embedded progress log. No separate progress.txt file.

**What Hook Updates:**
- Appends to state.json's `log` array automatically
- Iteration markers are optional (hook auto-detects from git)

## When to Use E2E Test Loop

- Need to test critical user flows
- Adding browser automation tests
- Ensuring features work end-to-end
- Integration testing across components

## Starting the Loop

```bash
/e2e "Cover checkout flow"                           # Basic
/e2e "Test auth" --max-iterations 5                  # Limited
/e2e "Add E2E" --test-command "npx playwright test"  # Custom command
```

## Iteration Workflow

Each iteration follows this sequence:

1. **Identify flow** - Find user flow lacking E2E coverage
2. **Create page object** - `*.e2e.page.ts` for reusable locators/actions
3. **Write ONE test** - `*.e2e.ts` using page objects
4. **Run linters** - Ensure code quality
5. **Verify passing** - Run the E2E test
6. **Run reviewers** - code-simplifier + kieran reviewer (MANDATORY)
7. **Commit** - `test(e2e): describe user flow`

## File Naming Convention

```
e2e/
├── checkout.e2e.page.ts    # Page object (locators, setup, actions)
├── checkout.e2e.ts         # Test file (concise tests)
├── auth.e2e.page.ts
└── auth.e2e.ts
```

## Playwright Patterns

### Locator Priority (Semantic First)

| Priority | Locator | Example |
|----------|---------|---------|
| 1 | `getByRole` | `page.getByRole('button', { name: 'Submit' })` |
| 2 | `getByLabel` | `page.getByLabel('Email address')` |
| 3 | `getByText` | `page.getByText('Welcome back')` |
| 4 | `getByTestId` | `page.getByTestId('submit-btn')`