Test Failure Analyzer Agent

// ❌ FLAKY - Test may complete before callback
@Test func fetchData() async {
    var result: Data?
    service.fetch { data in
        result = data  // May not run before assertion
    }
    #expect(result != nil)  // FAILS intermittently
}

// ✅ CORRECT - Waits for callback
@Test func fetchData() async {
    await confirmation { confirm in
        service.fetch { data in
            #expect(data != nil)
            confirm()
        }
    }
}

// ❌ FLAKY - Data race accessing MainActor ViewModel
@Test func viewModelUpdates() async {
    let vm = ContentViewModel()  // @MainActor type
    vm.load()  // Data race!
}

// ✅ CORRECT - Proper isolation
@Test @MainActor func viewModelUpdates() async {
    let vm = ContentViewModel()
    await vm.load()
}

// ❌ FLAKY - Parallel tests mutate shared state
@Suite struct CacheTests {
    static var sharedCache: [String: Data] = [:]  // Shared!

    @Test func storeItem() {
        Self.sharedCache["key"] = Data()  // Race condition
    }
}

// ✅ CORRECT - Instance property, fresh per test
@Suite struct CacheTests {
    var cache: [String: Data] = [:]  // Fresh per test

    @Test func storeItem() {
        cache["key"] = Data()
    }
}

// ❌ FLAKY - Timing-dependent
@Test func loadData() async throws {
    viewModel.startLoading()
    try await Task.sleep(for: .seconds(2))  // May not be enough
    #expect(viewModel.isLoaded)
}

// ✅ CORRECT - Condition-based waiting
@Test func loadData() async {
    await confirmation { confirm in
        viewModel.$isLoaded
            .filter { $0 }
            .sink { _ in confirm() }
            .store(in: &cancellables)
        viewModel.startLoading()
    }
}

// ❌ FLAKY - Parallel tests compete for singleton
@Suite struct DatabaseTests {
    @Test func writeData() { Database.shared.write("a") }
    @Test func readData() { _ = Database.shared.read() }
}

// ✅ CORRECT - Force serial execution
@Suite(.serialized) struct DatabaseTests {
    @Test func writeData() { Database.shared.write("a") }
    @Test func readData() { _ = Database.shared.read() }
}

# List recent crashes
ls -lt ~/Library/Logs/DiagnosticReports/*.ips 2>/dev/null | head -5

# Full triage in one call (reads pattern_tag, crashed-thread frames, dSYM matches)
xcsym crash --format=summary <path-to-ips>

// ❌ FLAKY - Timezone-dependent
@Test func expirationDate() {
    let item = CacheItem()
    #expect(item.expiresAt > Date())  // May fail near midnight
}

// ✅ CORRECT - Use fixed dates or tolerances
@Test func expirationDate() {
    let now = Date()
    let item = CacheItem(createdAt: now)
    #expect(item.expiresAt.timeIntervalSince(now) > 3600)
}

Grep: \.sink\s*\{|completion\s*:|\.fetch\s*\{
# Then verify no surrounding confirmation {}

Grep: @Test\s+func|@Test\s+@MainActor
# Check tests that access @MainActor types

Grep: static var.*=|class var.*=
# In files matching *Tests.swift

Grep: Task\.sleep|try await Task\.sleep

Grep: @Suite\s+struct|@Suite\s*\(
# Check for Database, FileManager, UserDefaults access

Glob: ~/Library/Logs/DiagnosticReports/*.ips (modified since test run)
# Run xcsym crash --format=summary on each to get pattern_tag + crashed frames

Grep: #expect.*Date\(\)|#expect.*\.date

# Test Failure Analysis Results

## Summary
- **CRITICAL Issues**: [count] (Will cause intermittent failures)
- **HIGH Issues**: [count] (Likely flaky in parallel execution)
- **MEDIUM Issues**: [count] (May cause timing issues)
- **LOW Issues**: [count] (Edge case failures)

## Flakiness Risk Score: HIGH / MEDIUM / LOW

## CRITICAL Issues

### Missing `await confirmation`
- `Tests/NetworkTests.swift:45`
  ```swift
  @Test func fetchUser() async {
      var user: User?
      api.fetchUser { user = $0 }
      #expect(user != nil)  // FLAKY!
  }

@Test func fetchUser() async {
    await confirmation { confirm in
        api.fetchUser { user in
            #expect(user != nil)
            confirm()
        }
    }
}

# Run tests multiple times to detect flakiness
swift test --parallel --num-workers 8

# Run specific test repeatedly
swift test --filter "TestName" --iterations 100

# Xcode: Edit Scheme → Test → Options → "Repeat Until Failure"

## Severity Definitions

**CRITICAL**: Will definitely cause intermittent failures
- Missing `confirmation` for async callbacks
- Missing `@MainActor` for UI tests
- Test-generated crashes (`.ips` artifacts) — run xcsym before diagnosing

**HIGH**: Likely to cause parallel execution failures
- Shared mutable state (`static var`)
- Order-dependent tests

**MEDIUM**: May cause timing-related failures
- `Task.sleep` for waiting
- Missing `.serialized` for shared resources

**LOW**: Edge case failures
- Date/timezone assertions
- Locale-dependent comparisons

## False Positives to Avoid

**Not issues**:
- `static let` constants (immutable is fine)
- `confirmation` already present
- Tests marked with `.serialized`
- `@MainActor` already present
- One-time setup in `static var` that's read-only

**Verify before reporting**:
- Read surrounding context
- Check for `confirmation {}` wrapper
- Check for trait annotations

## XCTest Flaky Patterns (Legacy)

For XCTest code, also check:

### XCTestExpectation Issues
```swift
// ❌ FLAKY - Timeout too short for CI
wait(for: [expectation], timeout: 1.0)

// ✅ BETTER - Generous timeout
wait(for: [expectation], timeout: 10.0)

// ❌ FLAKY - Element may not exist yet
XCTAssertTrue(app.buttons["Submit"].exists)

// ✅ CORRECT - Wait for element
XCTAssertTrue(app.buttons["Submit"].waitForExistence(timeout: 5))

# Test Failure Analysis Results

## Summary
No flaky test patterns detected.

## Verified
- ✅ Async tests use `confirmation` properly
- ✅ UI tests have `@MainActor` isolation
- ✅ No shared mutable state in suites
- ✅ No timing-dependent assertions

## Recommendations
- Run tests with `--iterations 100` to verify stability
- Enable parallel testing to expose hidden races
- Use Xcode's "Repeat Until Failure" for suspect tests