agentic-qe 1.9.4 → 2.1.0

package/CHANGELOG.md

@@ -7,6 +7,116 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.1.0] - 2025-12-03
+
+### 🚀 Comprehensive QX Analysis & Skills Optimization
+
+This release delivers significant improvements to QX (Quality Experience) analysis, optimized skills format across all 38 QE skills, and enhanced agent coordination capabilities.
+
+### Added
+
+#### Comprehensive QX Analysis (PR #104 by @fndlalit)
+- **23+ QX Heuristics**: Detailed findings, issues, and recommendations per heuristic
+- **Domain-Specific Failure Detection**: Automatic detection for e-commerce, SaaS, content/blog, and form-heavy sites
+- **Contextual Page Content Extraction**: Real page content analysis (headings, navigation, buttons, forms, links, main content)
+- **Rule of Three Problem Analysis**: Ensures minimum 3 potential failure modes identified per issue
+- **Comprehensive QX Formatter**: `scripts/contextualizers/comprehensive-qx-formatter.js` for detailed reports matching manual analysis structure
+
+#### Skills Optimization (PR #102)
+- **38 QE Skills Optimized**: Agent-focused format with 40-60% token reduction
+- **`<default_to_action>` Blocks**: Immediate actionable guidance at top of each skill
+- **Quick Reference Cards**: Tables and command examples for rapid lookup
+- **Fleet Coordination Hints**: Memory namespace organization and `FleetManager.coordinate()` patterns
+- **Standardized Frontmatter**: `tokenEstimate`, `agents`, `implementation_status`, `optimization_version`, `last_optimized`
+
+#### Testability Scoring Skill v2.1
+- Optimized skill format with proper metadata
+- Fleet coordination and memory namespace hints
+- Agent integration examples
+- Contributor attribution (`@fndlalit`)
+
+### Changed
+
+#### QX Partner Agent v2.1
+- Updated implementation status to v2.1 with new capabilities
+- Added domain-specific failure detection capability
+- Added contextual page content extraction capability
+- Added comprehensive report formatting capability
+- Added Rule of Three problem analysis capability
+- Enhanced memory namespace with new coordination paths
+
+#### Dependency Updates
+- **@modelcontextprotocol/sdk**: Bumped version (PR #105)
+
+### Contributors
+
+- **@fndlalit**: Comprehensive QX Analysis with detailed heuristics (PR #104)
+- **Dependabot**: @modelcontextprotocol/sdk dependency update (PR #105)
+
+---
+
+## [2.0.0] - 2025-12-02
+
+### 🚀 Major Release: Agentic QE Fleet v2
+
+This major release delivers significant improvements across the entire Agentic QE Fleet, including proper QUIC transport, enhanced visualization, testability scoring skill, QX Partner agent, and contributor features.
+
+### ⚠️ Breaking Changes
+
+- **QUIC Transport**: Replaced fake HTTP/2-based implementation with proper QUIC via Rust/WASM (`@agentic-flow/quic-wasm`)
+- **Skills Manifest**: Reduced from 68 to 41 QE-only skills (removed Claude Flow platform skills)
+- **EventType in emit-event.ts**: Changed from string to enum mapping for type safety
+
+### Added
+
+#### Real-Time Visualization Dashboard (PR #96 by @fndlalit)
+- WebSocket connection on port 8080 for backend compatibility
+- LifecycleTimeline support for `agent:spawned`, `agent:started`, `agent:completed`, `agent:error` events
+- New `emit-event.ts` module with convenience functions for agent lifecycle events
+- CLI event emission via `scripts/emit-agent-event.ts`
+- Hook integration with `emit-task-spawn.sh` and `emit-task-complete.sh`
+
+#### Testability Scoring Skill (PR #98 by @fndlalit)
+- Comprehensive context collection for all 10 testability principles
+- Contextual, site-specific recommendations based on actual measurements
+- HTML report generation with principle breakdown table
+- `run-assessment.sh` shell script with colored terminal output
+- Browser auto-open support (chromium/firefox/webkit)
+- Complete skill package at `.claude/skills/testability-scoring/`
+
+#### QX Partner Agent
+- New `QXPartnerAgent.ts` with balance analysis and oracle detection
+- Comprehensive documentation at `docs/agents/QX-PARTNER-AGENT.md`
+- Example implementations in `examples/qx-partner/`
+
+#### Proper QUIC Transport Layer
+- `src/core/transport/quic.ts` - QUIC via Rust/WASM with 0-RTT, stream multiplexing, TLS 1.3
+- `src/core/transport/quic-loader.ts` - Automatic WebSocket fallback when WASM unavailable
+- `src/types/agentic-flow-quic-wasm.d.ts` - Dedicated type declarations for optional WASM module
+- 21 transport tests passing
+
+#### Skills Manifest Cleanup
+- `.claude/skills/skills-manifest.json` with 41 QE-only skills
+- Categories: qe-core, testing-methodologies, test-design, specialized-testing, analysis-review, infrastructure, development-practices, bug-management
+
+### Fixed
+
+- **emit-event.ts TypeScript errors**: EventType mapping and string ID handling
+- **UnifiedMemoryCoordinator.ts**: Logger.getInstance(), correct method signatures
+- **Visualization WebSocket**: Port 8080, timestamp handling, MindMap null checks
+- **express security vulnerability**: Updated to 5.2.1 (CVE-2024-51999)
+
+### Changed
+
+- Agent definitions streamlined (removed redundant content from 14 agent files)
+- Skills manifest reorganized with proper categorization
+- Transport layer architecture (QUIC with WebSocket fallback)
+
+### Contributors
+
+- **@fndlalit**: Real-time visualization dashboard, testability scoring skill
+- **Dependabot**: Security updates (express 5.2.1)
+
 ## [1.9.4] - 2025-11-30
 
 ### 🔧 Critical Fixes: Memory/Learning/Patterns System

package/README.md

@@ -9,11 +9,11 @@
 <img alt="NPM Downloads" src="https://img.shields.io/npm/dw/agentic-qe">
 
 
-**Version 1.9.4** (Memory & Learning System Fixes) | [Changelog](CHANGELOG.md) | [Issues](https://github.com/proffesor-for-testing/agentic-qe/issues) | [Discussions](https://github.com/proffesor-for-testing/agentic-qe/discussions)
+**Version 2.1.0** | [Changelog](CHANGELOG.md) | [Issues](https://github.com/proffesor-for-testing/agentic-qe/issues) | [Discussions](https://github.com/proffesor-for-testing/agentic-qe/discussions)
 
-> Agentic test automation with AI learning, real-time visualization, OpenTelemetry observability, persistent event storage, constitutional AI governance, and intelligent model routing.
+> Agentic test automation with AI learning, real-time visualization, QUIC transport, testability scoring, OpenTelemetry observability, persistent event storage, constitutional AI governance, and intelligent model routing.
 
-🎨 **Real-Time Visualization** | 📊 **Interactive Dashboards** | 🧠 **QE Agent Learning** | 💾 **Event Sourcing** | 📋 **Constitution System** | 📚 **38 QE Skills** | 🎯 **Flaky Detection** | 💰 **Multi-Model Router**
+🎨 **Real-Time Visualization** | 📊 **Testability Scoring** | 🧠 **QE Agent Learning** | 🚀 **QUIC Transport** | 📋 **Constitution System** | 📚 **41 QE Skills** | 🎯 **Flaky Detection** | 💰 **Multi-Model Router**
 
 </div>
 
@@ -62,7 +62,7 @@ claude "Use qe-flaky-test-hunter to analyze the last 100 test runs and identify
 - ✅ ML Flaky Detection (100% accuracy)
 - ✅ 19 Specialized agent definitions (including qe-code-complexity)
 - ✅ 11 TDD subagent definitions (RED/GREEN/REFACTOR phases + specialized)
-- ✅ 40 World-class QE skills library (accessibility, shift-left/right, verification, visual testing, XP practices)
+- ✅ 41 World-class QE skills library (accessibility, shift-left/right, verification, visual testing, XP practices, **testability-scoring** by [@fndlalit](https://github.com/fndlalit))
 - ✅ 8 AQE slash commands
 - ✅ Modular init system with comprehensive project setup
 
@@ -193,7 +193,7 @@ open http://localhost:3000
 - **Performance Testing**: k6, JMeter, Gatling integration
 - **Real-Time Streaming**: Live progress updates for all operations
 
-### 🎓 38 QE Skills Library (v1.9.0)
+### 🎓 41 QE Skills Library (v1.9.0)
 **95%+ coverage of modern QE practices**
 
 <details>
@@ -214,7 +214,7 @@ open http://localhost:3000
 **Phase 3: Advanced Quality Engineering Skills (4 skills)**
 - **Strategic Testing Methodologies (4)**: six-thinking-hats, brutal-honesty-review, sherlock-review, cicd-pipeline-qe-orchestrator
 
-**Total: 38 QE Skills** - Includes accessibility testing, shift-left/right testing, verification & quality assurance, visual testing advanced, XP practices, and technical writing
+**Total: 41 QE Skills** - Includes accessibility testing, shift-left/right testing, verification & quality assurance, visual testing advanced, XP practices, and technical writing
 
 </details>
 
@@ -354,6 +354,33 @@ mcp__agentic_qe__coverage_analyze({
 })
 ```
 
+**All 102 MCP Tools Available:**
+- Fleet Management (9 tools): init, spawn, status, coordinate, orchestrate
+- Test Generation (4 tools): generate, enhanced, unit, integration  
+- Test Execution (3 tools): execute, parallel, stream
+- Coverage Analysis (6 tools): analyze, gaps, trends, risk scoring, ML detection, recommendations
+- Quality Gates (5 tools): execute, validate, assess risk, policy check, generate report
+- Flaky Test Detection (3 tools): detect, analyze patterns, auto-stabilize
+- Performance Testing (4 tools): benchmark, monitor, analyze bottlenecks, generate report
+- Security Scanning (5 tools): comprehensive scan, vulnerabilities, auth validation, authz check, dependencies
+- Visual Testing (3 tools): compare screenshots, accessibility validation, regression detection
+- API Contract Testing (3 tools): validate, breaking changes, versioning
+- Test Data Management (3 tools): generate, mask, analyze schema
+- Requirements Engineering (2 tools): validate, generate BDD
+- Code Quality (2 tools): complexity analysis, metrics
+- Memory & Collaboration (5 tools): store, retrieve, query, share, backup
+- Blackboard System (2 tools): post, read
+- Consensus Mechanisms (2 tools): propose, vote
+- Workflow Management (4 tools): create, execute, checkpoint, resume
+- Event System (2 tools): emit, subscribe
+- Regression Analysis (2 tools): risk analyze, select tests
+- Production Monitoring (2 tools): incident replay, RUM analyze
+- Mutation Testing (1 tool): execute
+- Deployment Readiness (1 tool): check
+- Artifact Management (1 tool): manifest
+- Task Management (1 tool): status
+- Learning System (4 tools): store experience, store Q-value, store pattern, query
+
 ### CLI Direct Usage
 
 ```bash
@@ -645,28 +672,35 @@ The test generator automatically delegates to subagents for a complete RED-GREEN
 
 ---
 
-## 📝 What's New in v1.9.4
+## 📝 What's New in v2.1.0
 
-🔧 **Critical Memory & Learning System Fixes** (2025-11-30)
+🚀 **Comprehensive QX Analysis & Skills Optimization** (2025-12-03)
 
-This release delivers critical fixes to the memory, learning, and patterns system. All QE agents now have a fully functional learning system with proper vector embeddings, Q-value reinforcement learning, and persistent pattern storage.
+This release delivers comprehensive QX (Quality Experience) analysis improvements, optimized skills format, and enhanced agent coordination.
 
-### Key Fixes
+### Key Features
+
+- **Comprehensive QX Analysis** (PR #104 by @fndlalit): 23+ heuristics with detailed findings, domain-specific failure detection (e-commerce, SaaS, content/blog, forms), contextual page content extraction
+- **38 QE Skills Optimized** (PR #102): Agent-focused format with `<default_to_action>` blocks, quick reference cards, 40-60% token reduction
+- **Testability Scoring v2.1**: Optimized skill format, Fleet coordination hints, improved memory namespace organization
+- **QX Partner Agent v2.1**: Enhanced capabilities for Rule of Three analysis, domain-specific detection, comprehensive report formatting
+
+### Skills Optimization
 
-- **Vector embeddings now stored correctly**: Fixed `RealAgentDBAdapter.store()` to properly store 384-dimension embeddings as BLOB data
-- **SQL parameter style bug**: Fixed agentdb's `SqlJsDatabase` wrapper to use spread params instead of array params
-- **HNSW index schema mismatch**: Added `pattern_id` generated column for agentdb's HNSWIndex compatibility
-- **Learning experience retrieval**: Added missing getter methods for Q-learning and experience replay
-- **Hooks saving to wrong database**: Fixed all Claude Code hooks to explicitly export `AGENTDB_PATH` so learning data is saved correctly
-- **CI platform compatibility**: Moved ARM64-only ruvector packages to optionalDependencies for x64 CI compatibility
+All 38 QE skills now feature:
+- Optimized frontmatter with `tokenEstimate`, `agents`, `implementation_status`, `optimization_version`
+- `<default_to_action>` blocks for immediate actionable guidance
+- Quick reference cards with tables and command examples
+- Fleet coordination and memory namespace hints
 
-### New Features
+### QX Analysis Improvements
 
-- **SwarmMemoryManager learning methods**: `getBestAction()`, `getRecentLearningExperiences()`, `getLearningStats()`, and more
-- **Phase 4 Alerting & Reporting**: AlertManager, FeedbackRouter, StrategyApplicator modules
-- **Quality Gate CI workflow**: GitHub Actions integration for automated quality validation
+- **23+ Heuristics**: Detailed findings, issues, and recommendations per heuristic
+- **Domain Detection**: Automatic failure mode detection by site type
+- **Contextual Extraction**: Real page content analysis (headings, navigation, buttons, forms, links)
+- **Rule of Three**: Problem complexity assessment ensuring minimum 3 failure modes identified
 
-**Upgrade**: `npm install agentic-qe@1.9.4`
+**Upgrade**: `npm install agentic-qe@2.1.0`
 
 ---
 

package/dist/agents/QXPartnerAgent.d.ts

@@ -0,0 +1,146 @@
+/**
+ * QXPartnerAgent - Quality Experience (QX) Analysis Agent
+ *
+ * QX = Marriage between QA (Quality Advocacy) and UX (User Experience)
+ * Goal: Co-create Quality Experience for everyone associated with the product
+ *
+ * Based on: https://talesoftesting.com/quality-experienceqx-co-creating-quality-experience-for-everyone-associated-with-the-product/
+ *
+ * Key Capabilities:
+ * - Problem understanding and analysis (Rule of Three)
+ * - User needs vs Business needs analysis
+ * - Oracle problem detection and resolution
+ * - Comprehensive impact analysis (visible & invisible)
+ * - UX testing heuristics application
+ * - Integration with testability scoring
+ * - Contextual recommendations generation
+ */
+import { BaseAgent } from './BaseAgent';
+import { QETask, AgentContext, MemoryStore } from '../types';
+import { EventEmitter } from 'events';
+import { QXPartnerConfig } from '../types/qx';
+interface Logger {
+    info(message: string, ...args: unknown[]): void;
+    warn(message: string, ...args: unknown[]): void;
+    error(message: string, ...args: unknown[]): void;
+    debug(message: string, ...args: unknown[]): void;
+}
+export declare class QXPartnerAgent extends BaseAgent {
+    private readonly config;
+    protected readonly logger: Logger;
+    private heuristicsEngine?;
+    private oracleDetector?;
+    private impactAnalyzer?;
+    private browser;
+    private page;
+    constructor(config: QXPartnerConfig & {
+        context: AgentContext;
+        memoryStore: MemoryStore;
+        eventBus: EventEmitter;
+    });
+    /**
+     * Get default capabilities for QX Partner Agent
+     */
+    private static getDefaultCapabilities;
+    /**
+     * Initialize QX analysis components
+     */
+    protected initializeComponents(): Promise<void>;
+    /**
+     * Load QX knowledge and historical patterns
+     */
+    protected loadKnowledge(): Promise<void>;
+    /**
+     * Clean up QX analysis resources
+     */
+    protected cleanup(): Promise<void>;
+    /**
+     * Perform QX analysis task
+     */
+    protected performTask(task: QETask): Promise<unknown>;
+    /**
+     * Perform comprehensive QX analysis
+     */
+    private performFullQXAnalysis;
+    /**
+     * Collect QX context from target using Playwright
+     */
+    private collectQXContext;
+    /**
+     * Detect domain-specific failure modes based on site type
+     */
+    private detectDomainSpecificFailures;
+    /**
+     * Analyze problem using Rule of Three and complexity assessment
+     */
+    private analyzeProblem;
+    /**
+     * Analyze user needs
+     */
+    private analyzeUserNeeds;
+    /**
+     * Analyze business needs
+     */
+    private analyzeBusinessNeeds;
+    /**
+     * Detect oracle problems from analysis context
+     */
+    private detectOracleProblemsFromContext;
+    /**
+     * Perform impact analysis
+     */
+    private analyzeImpact;
+    /**
+     * Apply all enabled heuristics
+     */
+    private applyAllHeuristics;
+    /**
+     * Generate QX recommendations
+     */
+    private generateRecommendations;
+    private formatHeuristicName;
+    /**
+     * Calculate overall QX score
+     */
+    private calculateOverallQXScore;
+    /**
+     * Convert score to grade
+     */
+    private scoreToGrade;
+    /**
+     * Detect oracle problems (separate task)
+     */
+    private detectOracleProblems;
+    /**
+     * Analyze user vs business balance
+     */
+    private analyzeUserBusinessBalance;
+    private getBalanceRecommendation;
+    /**
+     * Perform impact analysis (separate task)
+     */
+    private performImpactAnalysis;
+    /**
+     * Apply specific heuristic
+     */
+    private applySpecificHeuristic;
+    /**
+     * Generate QX recommendations (separate task)
+     */
+    private generateQXRecommendations;
+    /**
+     * Integrate with testability scoring
+     */
+    private integrateTestabilityScoring;
+    private validateTestabilityScoringAvailability;
+    private setupCollaborationChannels;
+    private initializeDefaultOraclePatterns;
+    private saveQXState;
+    private saveOraclePatterns;
+    private saveHeuristicsInsights;
+    private shareCollaborationInsights;
+    protected onPreInitialization(): Promise<void>;
+    protected onPostInitialization(): Promise<void>;
+}
+export {};
+//# sourceMappingURL=QXPartnerAgent.d.ts.map

package/dist/agents/QXPartnerAgent.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"QXPartnerAgent.d.ts","sourceRoot":"","sources":["../../src/agents/QXPartnerAgent.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,SAAS,EAAmB,MAAM,aAAa,CAAC;AACzD,OAAO,EAAE,MAAM,EAAgC,YAAY,EAAE,WAAW,EAAE,MAAM,UAAU,CAAC;AAC3F,OAAO,EAAE,YAAY,EAAE,MAAM,QAAQ,CAAC;AAEtC,OAAO,EAEL,eAAe,EAahB,MAAM,aAAa,CAAC;AAGrB,UAAU,MAAM;IACd,IAAI,CAAC,OAAO,EAAE,MAAM,EAAE,GAAG,IAAI,EAAE,OAAO,EAAE,GAAG,IAAI,CAAC;IAChD,IAAI,CAAC,OAAO,EAAE,MAAM,EAAE,GAAG,IAAI,EAAE,OAAO,EAAE,GAAG,IAAI,CAAC;IAChD,KAAK,CAAC,OAAO,EAAE,MAAM,EAAE,GAAG,IAAI,EAAE,OAAO,EAAE,GAAG,IAAI,CAAC;IACjD,KAAK,CAAC,OAAO,EAAE,MAAM,EAAE,GAAG,IAAI,EAAE,OAAO,EAAE,GAAG,IAAI,CAAC;CAClD;AAiBD,qBAAa,cAAe,SAAQ,SAAS;IAC3C,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAkB;IACzC,SAAS,CAAC,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAuB;IACxD,OAAO,CAAC,gBAAgB,CAAC,CAAqB;IAC9C,OAAO,CAAC,cAAc,CAAC,CAAiB;IACxC,OAAO,CAAC,cAAc,CAAC,CAAiB;IACxC,OAAO,CAAC,OAAO,CAAwB;IACvC,OAAO,CAAC,IAAI,CAAqB;gBAErB,MAAM,EAAE,eAAe,GAAG;QAAE,OAAO,EAAE,YAAY,CAAC;QAAC,WAAW,EAAE,WAAW,CAAC;QAAC,QAAQ,EAAE,YAAY,CAAA;KAAE;IAsCjH;;OAEG;IACH,OAAO,CAAC,MAAM,CAAC,sBAAsB;IAmCrC;;OAEG;cACa,oBAAoB,IAAI,OAAO,CAAC,IAAI,CAAC;IAmCrD;;OAEG;cACa,aAAa,IAAI,OAAO,CAAC,IAAI,CAAC;IA+C9C;;OAEG;cACa,OAAO,IAAI,OAAO,CAAC,IAAI,CAAC;IAiCxC;;OAEG;cACa,WAAW,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC;IAqC3D;;OAEG;YACW,qBAAqB;IAiFnC;;OAEG;YACW,gBAAgB;IAqM9B;;OAEG;IACH,OAAO,CAAC,4BAA4B;IA4HpC;;OAEG;YACW,cAAc;IA0H5B;;OAEG;YACW,gBAAgB;IAsG9B;;OAEG;YACW,oBAAoB;IA4FlC;;OAEG;YACW,+BAA+B;IAY7C;;OAEG;YACW,aAAa;IAQ3B;;OAEG;YACW,kBAAkB;IAahC;;OAEG;YACW,uBAAuB;IAgKrC,OAAO,CAAC,mBAAmB;IAO3B;;OAEG;IACH,OAAO,CAAC,uBAAuB;IAgC/B;;OAEG;IACH,OAAO,CAAC,YAAY;IAQpB;;OAEG;YACW,oBAAoB;IASlC;;OAEG;YACW,0BAA0B;IAkBxC,OAAO,CAAC,wBAAwB;IAWhC;;OAEG;YACW,qBAAqB;IAOnC;;OAEG;YACW,sBAAsB;IAiBpC;;OAEG;YACW,yBAAyB;IAKvC;;OAEG;YACW,2BAA2B;YA2B3B,sCAAsC;YAKtC,0BAA0B;YAY1B,+BAA+B;YAW/B,WAAW;YASX,kBAAkB;YAQlB,sBAAsB;YAQtB,0BAA0B;cASxB,mBAAmB,IAAI,OAAO,CAAC,IAAI,CAAC;cAIpC,oBAAoB,IAAI,OAAO,CAAC,IAAI,CAAC;CAGtD"}