@agentic-qe/v3 3.0.0-alpha.10

package/assets/skills/visual-testing-advanced/SKILL.md

@@ -0,0 +1,219 @@
+---
+name: visual-testing-advanced
+description: "Advanced visual regression testing with pixel-perfect comparison, AI-powered diff analysis, responsive design validation, and cross-browser visual consistency. Use when detecting UI regressions, validating designs, or ensuring visual consistency."
+category: specialized-testing
+priority: high
+tokenEstimate: 900
+agents: [qe-visual-tester, qe-test-executor, qe-quality-gate]
+implementation_status: optimized
+optimization_version: 1.0
+last_optimized: 2025-12-02
+dependencies: []
+quick_reference_card: true
+tags: [visual, regression, screenshot, pixel-diff, percy, playwright, responsive]
+---
+
+# Advanced Visual Testing
+
+<default_to_action>
+When detecting visual regressions or validating UI:
+1. CAPTURE baseline screenshots (first run establishes baseline)
+2. COMPARE new screenshots against baseline (pixel-by-pixel or AI)
+3. MASK dynamic content (timestamps, ads, user counts)
+4. TEST across devices (desktop, tablet, mobile viewports)
+5. REVIEW and approve intentional changes, fail on regressions
+
+**Quick Visual Testing Steps:**
+- Set up baseline on main branch
+- Compare feature branch against baseline
+- Mask dynamic elements (timestamps, avatars)
+- Use AI-powered comparison to reduce false positives
+- Integrate in CI/CD to block visual regressions
+
+**Critical Success Factors:**
+- Functional tests don't catch visual bugs
+- AI-powered tools reduce false positives
+- Review diffs, don't just auto-approve
+</default_to_action>
+
+## Quick Reference Card
+
+### When to Use
+- UI component changes
+- CSS/styling modifications
+- Responsive design validation
+- Cross-browser consistency checks
+
+### Visual Bug Types
+| Bug Type | Description |
+|----------|-------------|
+| Layout shift | Elements moved position |
+| Color change | Unintended color modification |
+| Font rendering | Typography issues |
+| Alignment | Spacing/alignment problems |
+| Missing images | Broken image paths |
+| Overflow | Content clipping |
+
+### Comparison Algorithms
+| Algorithm | Best For |
+|-----------|----------|
+| **Pixel diff** | Exact match requirement |
+| **Structural similarity** | Handle anti-aliasing |
+| **AI semantic** | Ignore insignificant changes |
+
+---
+
+## Visual Regression with Playwright
+
+```javascript
+import { test, expect } from '@playwright/test';
+
+test('homepage visual regression', async ({ page }) => {
+  await page.goto('https://example.com');
+
+  // Capture and compare screenshot
+  await expect(page).toHaveScreenshot('homepage.png');
+  // First run: saves baseline
+  // Subsequent runs: compares to baseline
+});
+
+test('responsive design', async ({ page }) => {
+  // Mobile viewport
+  await page.setViewportSize({ width: 375, height: 667 });
+  await page.goto('https://example.com');
+  await expect(page).toHaveScreenshot('homepage-mobile.png');
+
+  // Tablet viewport
+  await page.setViewportSize({ width: 768, height: 1024 });
+  await expect(page).toHaveScreenshot('homepage-tablet.png');
+});
+```
+
+---
+
+## Handling Dynamic Content
+
+```javascript
+test('mask dynamic elements', async ({ page }) => {
+  await page.goto('https://example.com');
+
+  await expect(page).toHaveScreenshot({
+    mask: [
+      page.locator('.timestamp'),     // Dynamic time
+      page.locator('.user-count'),    // Live counter
+      page.locator('.advertisement'), // Ads
+      page.locator('.avatar')         // User avatars
+    ]
+  });
+});
+```
+
+---
+
+## AI-Powered Visual Testing (Percy)
+
+```javascript
+import percySnapshot from '@percy/playwright';
+
+test('AI-powered visual test', async ({ page }) => {
+  await page.goto('https://example.com');
+
+  // Percy uses AI to ignore anti-aliasing, minor font differences
+  await percySnapshot(page, 'Homepage');
+});
+
+test('component visual test', async ({ page }) => {
+  await page.goto('https://example.com/components');
+
+  // Snapshot specific component
+  const button = page.locator('.primary-button');
+  await percySnapshot(page, 'Primary Button', {
+    scope: button
+  });
+});
+```
+
+---
+
+## Playwright Configuration
+
+```javascript
+// playwright.config.js
+export default {
+  expect: {
+    toHaveScreenshot: {
+      maxDiffPixels: 100,      // Allow 100 pixel difference
+      maxDiffPixelRatio: 0.01, // Or 1% of image
+      threshold: 0.2,          // Color similarity threshold
+      animations: 'disabled',  // Disable animations
+      caret: 'hide'            // Hide cursor
+    }
+  }
+};
+```
+
+---
+
+## Agent-Driven Visual Testing
+
+```typescript
+// Comprehensive visual regression
+await Task("Visual Regression Suite", {
+  baseline: 'main-branch',
+  current: 'feature-branch',
+  pages: ['homepage', 'product', 'checkout'],
+  devices: ['desktop', 'tablet', 'mobile'],
+  browsers: ['chrome', 'firefox', 'safari'],
+  threshold: 0.01
+}, "qe-visual-tester");
+
+// Returns:
+// {
+//   comparisons: 27,  // 3 pages × 3 devices × 3 browsers
+//   differences: 2,
+//   report: 'visual-regression-report.html'
+// }
+```
+
+---
+
+## Agent Coordination Hints
+
+### Memory Namespace
+```
+aqe/visual-testing/
+├── baselines/*          - Baseline screenshots
+├── comparisons/*        - Diff results
+├── components/*         - Component snapshots
+└── reports/*            - Visual regression reports
+```
+
+### Fleet Coordination
+```typescript
+const visualFleet = await FleetManager.coordinate({
+  strategy: 'visual-testing',
+  agents: [
+    'qe-visual-tester',   // Screenshot comparison
+    'qe-test-executor',   // Cross-browser execution
+    'qe-quality-gate'     // Block on visual regressions
+  ],
+  topology: 'parallel'
+});
+```
+
+---
+
+## Related Skills
+- [accessibility-testing](../accessibility-testing/) - Visual a11y checks
+- [compatibility-testing](../compatibility-testing/) - Cross-browser visuals
+- [regression-testing](../regression-testing/) - Regression suite
+
+---
+
+## Remember
+
+**Functional tests don't catch visual bugs.** Layout shifts, color changes, font rendering, alignment issues - all invisible to functional tests but visible to users.
+
+**AI-powered tools reduce false positives.** Percy, Applitools use AI to ignore insignificant differences (anti-aliasing, minor font rendering).
+
+**With Agents:** `qe-visual-tester` automates visual regression across browsers and devices, uses AI to filter noise, and generates visual diff reports. Catches UI regressions before users see them.

package/assets/skills/xp-practices/SKILL.md

@@ -0,0 +1,229 @@
+---
+name: xp-practices
+description: "Apply XP practices including pair programming, ensemble programming, continuous integration, and sustainable pace. Use when implementing agile development practices, improving team collaboration, or adopting technical excellence practices."
+category: methodology
+priority: medium
+tokenEstimate: 1000
+agents: [qe-quality-analyzer, qe-test-executor, qe-code-reviewer]
+implementation_status: optimized
+optimization_version: 1.0
+last_optimized: 2025-12-03
+dependencies: []
+quick_reference_card: true
+tags: [xp, agile, pair-programming, tdd, continuous-integration, collaboration]
+---
+
+# Extreme Programming (XP) Practices
+
+<default_to_action>
+When applying XP practices:
+1. START with practices that give immediate value
+2. BUILD supporting practices gradually
+3. ADAPT to your context
+4. MEASURE results
+
+**Core XP Practices (Prioritized):**
+| Practice | Start Here | Why First |
+|----------|------------|-----------|
+| TDD | ✅ Yes | Foundation for everything |
+| Continuous Integration | ✅ Yes | Fast feedback |
+| Pair Programming | ✅ Yes | Knowledge sharing |
+| Collective Ownership | After CI+TDD | Needs safety net |
+| Small Releases | After CI | Infrastructure dependent |
+
+**Pairing Quick Start:**
+```
+Driver-Navigator (Classic):
+- Driver: Writes code
+- Navigator: Reviews, thinks ahead
+- Rotate every 20-30 min
+
+Ping-Pong (with TDD):
+A: Write failing test
+B: Make test pass + refactor
+B: Write next failing test
+A: Make test pass + refactor
+```
+</default_to_action>
+
+## Quick Reference Card
+
+### The Five XP Values
+
+| Value | Meaning | Practice |
+|-------|---------|----------|
+| **Communication** | Everyone knows what everyone does | Daily standups, pairing |
+| **Simplicity** | Simplest thing that works | YAGNI, small design |
+| **Feedback** | Get feedback early and often | TDD, CI, short iterations |
+| **Courage** | Tell truth, adapt | Refactor, admit mistakes |
+| **Respect** | Everyone contributes value | Sustainable pace, pairing |
+
+### Core Practices
+
+| Practice | Description | Benefit |
+|----------|-------------|---------|
+| **Pair Programming** | Two devs, one workstation | Quality + knowledge sharing |
+| **TDD** | Red-Green-Refactor | Confidence + design |
+| **CI** | Integrate multiple times/day | Fast feedback |
+| **Collective Ownership** | Anyone can change anything | No bottlenecks |
+| **Sustainable Pace** | 40-hour weeks | Long-term productivity |
+| **Small Releases** | Ship frequently | Risk reduction |
+
+---
+
+## Pair Programming
+
+### When to Pair
+
+| Context | Pair? | Why |
+|---------|-------|-----|
+| Complex/risky code | ✅ Always | Needs multiple perspectives |
+| New technology | ✅ Always | Learning accelerator |
+| Onboarding | ✅ Always | Knowledge transfer |
+| Critical bugs | ✅ Always | Two heads better |
+| Simple tasks | ❌ Skip | Not worth overhead |
+| Research spikes | ❌ Skip | Pair to discuss findings |
+
+### Pairing Dos and Don'ts
+
+**Do:**
+- ✅ Switch roles every 20-30 min
+- ✅ Take breaks together
+- ✅ Think out loud
+- ✅ Ask questions
+- ✅ Keep sessions 2-4 hours max
+
+**Don't:**
+- ❌ Grab keyboard without asking
+- ❌ Check phone while pairing
+- ❌ Dominate conversation
+- ❌ Pair all day (exhausting)
+
+---
+
+## Ensemble (Mob) Programming
+
+**Setup:** 3+ developers, one screen, rotating driver
+
+```
+[Screen]
+   ↓
+[Driver] ← Directions from navigators
+   ↑
+[Navigator 1] [Navigator 2] [Navigator 3]
+```
+
+**Rotation:** Driver switches every 5-10 min
+
+**Best for:**
+- Complex problem solving
+- Architectural decisions
+- Learning new frameworks
+- Resolving blockers
+
+---
+
+## Continuous Integration
+
+**CI Workflow:**
+```
+1. Pull latest from main
+2. Make small change (<2 hrs work)
+3. Run tests locally (all pass)
+4. Commit and push
+5. CI runs tests automatically
+6. If fail → fix immediately
+```
+
+**Best Practices:**
+- Commit frequently (small changes)
+- Keep build fast (<10 min)
+- Fix broken builds immediately
+- Never commit to broken build
+
+---
+
+## Four Rules of Simple Design
+
+(In priority order)
+1. **Passes all tests** - Works correctly
+2. **Reveals intention** - Clear, expressive code
+3. **No duplication** - DRY principle
+4. **Fewest elements** - No speculative code
+
+---
+
+## Agent Integration
+
+```typescript
+// Agent-human pair testing
+const charter = "Test payment edge cases";
+const tests = await Task("Generate Tests", { charter }, "qe-test-generator");
+const reviewed = await human.review(tests);
+await Task("Implement", { tests: reviewed }, "qe-test-generator");
+
+// Continuous integration with agents
+await Task("Risk Analysis", { prDiff }, "qe-regression-risk-analyzer");
+await Task("Generate Tests", { changes: prDiff }, "qe-test-generator");
+await Task("Execute Tests", { scope: 'affected' }, "qe-test-executor");
+
+// Sustainable pace: agents handle grunt work
+const agentWork = ['regression', 'data-generation', 'coverage-analysis'];
+const humanWork = ['exploratory', 'risk-assessment', 'strategy'];
+```
+
+---
+
+## Agent Coordination Hints
+
+### Memory Namespace
+```
+aqe/xp-practices/
+├── pairing-sessions/*   - Pair/ensemble session logs
+├── ci-metrics/*         - CI health metrics
+├── velocity/*           - Team velocity data
+└── retrospectives/*     - XP retrospective notes
+```
+
+### Fleet Coordination
+```typescript
+const xpFleet = await FleetManager.coordinate({
+  strategy: 'xp-workflow',
+  agents: [
+    'qe-test-generator',   // TDD support
+    'qe-test-executor',    // CI integration
+    'qe-code-reviewer'     // Collective ownership
+  ],
+  topology: 'parallel'
+});
+```
+
+---
+
+## Common Objections
+
+| Objection | Response |
+|-----------|----------|
+| "Pairing is 2x slower" | 15% slower writing, 15% fewer bugs, net positive |
+| "No time for TDD" | Debugging takes longer than testing |
+| "CI is hard to setup" | Start simple: one action, one test |
+| "Collective ownership = chaos" | Only without tests + CI |
+
+---
+
+## Related Skills
+- [tdd-london-chicago](../tdd-london-chicago/) - TDD deep dive
+- [refactoring-patterns](../refactoring-patterns/) - Safe refactoring
+- [pair-programming](../pair-programming/) - AI-assisted pairing
+
+---
+
+## Remember
+
+**XP practices work as a system.** Don't cherry-pick randomly:
+- TDD enables collective ownership
+- CI enables small releases
+- Pairing enables collective ownership
+- Sustainable pace enables everything
+
+**With Agents:** Agents amplify XP. Pair humans with agents. Agents handle repetitive work, humans provide judgment and creativity.

package/dist/benchmarks/performance-benchmarks.d.ts

@@ -0,0 +1,92 @@
+/**
+ * Agentic QE v3 - Performance Benchmarks
+ *
+ * REAL benchmarks that measure actual performance.
+ * Run these BEFORE claiming any O(log n) or performance improvements.
+ *
+ * @module benchmarks/performance-benchmarks
+ */
+export interface BenchmarkResult {
+    name: string;
+    operation: string;
+    inputSize: number;
+    iterations: number;
+    totalTimeMs: number;
+    avgTimeMs: number;
+    medianTimeMs: number;
+    minTimeMs: number;
+    maxTimeMs: number;
+    opsPerSecond: number;
+    complexity: string;
+    verified: boolean;
+    details: string;
+}
+export interface BenchmarkSuite {
+    suiteName: string;
+    timestamp: string;
+    environment: {
+        nodeVersion: string;
+        platform: string;
+        arch: string;
+        cpuCores: number;
+    };
+    results: BenchmarkResult[];
+    summary: string;
+}
+/**
+ * Run a benchmark with multiple iterations and collect statistics
+ */
+export declare function runBenchmark(name: string, operation: string, fn: () => Promise<void> | void, options?: {
+    iterations?: number;
+    warmupIterations?: number;
+    inputSize?: number;
+}): Promise<BenchmarkResult>;
+/**
+ * Verify O(log n) complexity by measuring at different input sizes
+ */
+export declare function verifyLogNComplexity(name: string, setupFn: (size: number) => Promise<{
+    runFn: () => Promise<void> | void;
+    cleanup?: () => Promise<void>;
+}>, sizes?: number[]): Promise<{
+    verified: boolean;
+    ratio: number;
+    expectedRatio: number;
+    details: string;
+    results: BenchmarkResult[];
+}>;
+/**
+ * Compare two implementations
+ */
+export declare function compareImplementations(name: string, impl1: {
+    name: string;
+    fn: () => Promise<void> | void;
+}, impl2: {
+    name: string;
+    fn: () => Promise<void> | void;
+}, iterations?: number): Promise<{
+    winner: string;
+    speedup: number;
+    impl1Result: BenchmarkResult;
+    impl2Result: BenchmarkResult;
+}>;
+/**
+ * Benchmark HNSW index operations
+ */
+export declare function benchmarkHNSWIndex(): Promise<BenchmarkResult[]>;
+/**
+ * Benchmark coverage parsing operations
+ */
+export declare function benchmarkCoverageParser(): Promise<BenchmarkResult[]>;
+/**
+ * Benchmark security scanner operations
+ */
+export declare function benchmarkSecurityScanner(): Promise<BenchmarkResult[]>;
+/**
+ * Run all benchmarks and generate a comprehensive report
+ */
+export declare function runFullBenchmarkSuite(): Promise<BenchmarkSuite>;
+/**
+ * Format benchmark results as markdown
+ */
+export declare function formatBenchmarkReport(suite: BenchmarkSuite): string;
+//# sourceMappingURL=performance-benchmarks.d.ts.map

package/dist/benchmarks/performance-benchmarks.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"performance-benchmarks.d.ts","sourceRoot":"","sources":["../../src/benchmarks/performance-benchmarks.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAMH,MAAM,WAAW,eAAe;IAC9B,IAAI,EAAE,MAAM,CAAC;IACb,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,MAAM,CAAC;IACnB,WAAW,EAAE,MAAM,CAAC;IACpB,SAAS,EAAE,MAAM,CAAC;IAClB,YAAY,EAAE,MAAM,CAAC;IACrB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,YAAY,EAAE,MAAM,CAAC;IACrB,UAAU,EAAE,MAAM,CAAC;IACnB,QAAQ,EAAE,OAAO,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;CACjB;AAED,MAAM,WAAW,cAAc;IAC7B,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,WAAW,EAAE;QACX,WAAW,EAAE,MAAM,CAAC;QACpB,QAAQ,EAAE,MAAM,CAAC;QACjB,IAAI,EAAE,MAAM,CAAC;QACb,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC;IACF,OAAO,EAAE,eAAe,EAAE,CAAC;IAC3B,OAAO,EAAE,MAAM,CAAC;CACjB;AAMD;;GAEG;AACH,wBAAsB,YAAY,CAChC,IAAI,EAAE,MAAM,EACZ,SAAS,EAAE,MAAM,EACjB,EAAE,EAAE,MAAM,OAAO,CAAC,IAAI,CAAC,GAAG,IAAI,EAC9B,OAAO,GAAE;IACP,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,SAAS,CAAC,EAAE,MAAM,CAAC;CACf,GACL,OAAO,CAAC,eAAe,CAAC,CA8C1B;AAED;;GAEG;AACH,wBAAsB,oBAAoB,CACxC,IAAI,EAAE,MAAM,EACZ,OAAO,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,OAAO,CAAC;IAAE,KAAK,EAAE,MAAM,OAAO,CAAC,IAAI,CAAC,GAAG,IAAI,CAAC;IAAC,OAAO,CAAC,EAAE,MAAM,OAAO,CAAC,IAAI,CAAC,CAAA;CAAE,CAAC,EACxG,KAAK,GAAE,MAAM,EAA+B,GAC3C,OAAO,CAAC;IACT,QAAQ,EAAE,OAAO,CAAC;IAClB,KAAK,EAAE,MAAM,CAAC;IACd,aAAa,EAAE,MAAM,CAAC;IACtB,OAAO,EAAE,MAAM,CAAC;IAChB,OAAO,EAAE,eAAe,EAAE,CAAC;CAC5B,CAAC,CAyCD;AAED;;GAEG;AACH,wBAAsB,sBAAsB,CAC1C,IAAI,EAAE,MAAM,EACZ,KAAK,EAAE;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,EAAE,EAAE,MAAM,OAAO,CAAC,IAAI,CAAC,GAAG,IAAI,CAAA;CAAE,EACvD,KAAK,EAAE;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,EAAE,EAAE,MAAM,OAAO,CAAC,IAAI,CAAC,GAAG,IAAI,CAAA;CAAE,EACvD,UAAU,GAAE,MAAY,GACvB,OAAO,CAAC;IACT,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,MAAM,CAAC;IAChB,WAAW,EAAE,eAAe,CAAC;IAC7B,WAAW,EAAE,eAAe,CAAC;CAC9B,CAAC,CAYD;AAiDD;;GAEG;AACH,wBAAsB,kBAAkB,IAAI,OAAO,CAAC,eAAe,EAAE,CAAC,CAkJrE;AAMD;;GAEG;AACH,wBAAsB,uBAAuB,IAAI,OAAO,CAAC,eAAe,EAAE,CAAC,CAwE1E;AAMD;;GAEG;AACH,wBAAsB,wBAAwB,IAAI,OAAO,CAAC,eAAe,EAAE,CAAC,CAwE3E;AAMD;;GAEG;AACH,wBAAsB,qBAAqB,IAAI,OAAO,CAAC,cAAc,CAAC,CAmDrE;AAED;;GAEG;AACH,wBAAgB,qBAAqB,CAAC,KAAK,EAAE,cAAc,GAAG,MAAM,CAiCnE"}