agentic-qe 1.9.3 → 2.0.0

package/.claude/skills/testability-scoring/scripts/run-assessment.sh

@@ -0,0 +1,70 @@
+#!/bin/bash
+set -e
+
+# Testability Scoring Assessment Runner
+# Usage: ./run-assessment.sh <URL> [browser]
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../../.." && pwd)"
+TEST_FILE="$PROJECT_ROOT/tests/testability-scoring/testability-scoring.spec.js"
+
+# Colors
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+YELLOW='\033[1;33m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+# Check if URL provided
+if [ -z "$1" ]; then
+    echo -e "${RED}Error: URL required${NC}"
+    echo "Usage: $0 <URL> [browser]"
+    echo "Example: $0 https://example.com chromium"
+    exit 1
+fi
+
+TARGET_URL="$1"
+BROWSER="${2:-chromium}"
+
+echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+echo -e "${GREEN}🎯 Testability Assessment${NC}"
+echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+echo ""
+echo -e "  ${YELLOW}URL:${NC}     $TARGET_URL"
+echo -e "  ${YELLOW}Browser:${NC} $BROWSER"
+echo ""
+echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+echo ""
+
+# Change to project root
+cd "$PROJECT_ROOT"
+
+# Run Playwright tests with TEST_URL environment variable
+echo -e "${YELLOW}⏳ Running assessment...${NC}\n"
+
+TEST_URL="$TARGET_URL" npx playwright test "$TEST_FILE" --project="$BROWSER" --workers=1
+
+# Check if tests passed
+if [ $? -eq 0 ]; then
+    echo ""
+    echo -e "${GREEN}✅ Assessment completed successfully!${NC}"
+    
+    # Find the latest JSON report
+    LATEST_JSON=$(ls -t "$PROJECT_ROOT/tests/reports/testability-results-"*.json 2>/dev/null | head -1)
+    
+    if [ -n "$LATEST_JSON" ]; then
+        # Generate HTML report
+        echo -e "\n${YELLOW}📊 Generating HTML report...${NC}\n"
+        node "$SCRIPT_DIR/generate-html-report.js" "$LATEST_JSON"
+        
+        echo ""
+        echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+        echo -e "${GREEN}✓ Complete! Check your browser for the report.${NC}"
+        echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+    else
+        echo -e "${YELLOW}⚠️  JSON report not found${NC}"
+    fi
+else
+    echo -e "\n${RED}❌ Assessment failed${NC}"
+    exit 1
+fi

package/CHANGELOG.md

@@ -7,6 +7,122 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [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
+
+This release delivers critical fixes to the memory, learning, and patterns system based on thorough investigation (Sherlock Investigation Report). All QE agents now have a fully functional learning system with proper vector embeddings, Q-value reinforcement learning, and persistent pattern storage.
+
+### Fixed
+
+- **Vector embeddings now stored correctly** (was storing NULL): Fixed `RealAgentDBAdapter.store()` to properly store 384-dimension embeddings as BLOB data instead of NULL
+- **SQL parameter style bug**: Fixed agentdb's `SqlJsDatabase` wrapper to use spread params (`stmt.run(a, b, c)`) instead of array params (`stmt.run([a,b,c])`) which caused "NOT NULL constraint failed" errors
+- **HNSW index schema mismatch**: Added `pattern_id` generated column for agentdb's HNSWIndex compatibility which requires this column for vector search
+- **Learning experience retrieval**: Added missing getter methods that were referenced but didn't exist
+- **Hooks saving to wrong database**: Fixed all Claude Code hooks to explicitly export `AGENTDB_PATH=.agentic-qe/agentdb.db` so learning data is saved to the project database instead of the root directory
+- **CI failures due to ARM64-only ruvector packages**: Moved `@ruvector/node-linux-arm64-gnu` and `ruvector-core-linux-arm64-gnu` from dependencies to optionalDependencies. Added x64 variants for CI compatibility
+
+### Added
+
+- **New SwarmMemoryManager methods for learning data retrieval**:
+  - `getBestAction(agentId, stateKey)` - Q-learning best action selection
+  - `getRecentLearningExperiences(agentId, limit)` - Recent experience retrieval
+  - `getLearningExperiencesByTaskType(agentId, taskType, limit)` - Task-filtered experiences
+  - `getHighRewardExperiences(agentId, minReward, limit)` - Successful experience extraction
+  - `getLearningStats(agentId)` - Aggregate learning statistics (total, avg, max, min rewards)
+
+- **Hooks integration**: Added `AGENTDB_PATH` environment variable to connect Claude Code hooks to the QE database
+
+- **New modules (Phase 4 Alerting & Reporting)**:
+  - `src/alerting/` - AlertManager, FeedbackRouter, StrategyApplicator (1,394 LOC)
+  - `src/reporting/` - ResultAggregator, reporters (3,030 LOC)
+  - Quality gate scripts and GitHub Actions workflow
+
+- **Integration test**: `tests/integration/memory-learning-loop.test.ts` - Comprehensive 7-phase test validating the full learning cycle:
+  1. Pattern storage with embeddings
+  2. Learning experience capture
+  3. Q-value reinforcement learning
+  4. Memory persistence
+  5. Pattern retrieval
+  6. Vector similarity search
+  7. Full learning loop simulation
+
+### Changed
+
+- **RealAgentDBAdapter**: Now properly retrieves stored embeddings when querying patterns instead of using placeholder values
+- **Pattern table schema**: Added generated column `pattern_id TEXT GENERATED ALWAYS AS (id) STORED` for HNSW compatibility
+
+### Technical Details
+
+- Vector embeddings: 384 dimensions × 4 bytes = 1,536 bytes per pattern
+- AgentDB version: v1.6.1 with ReasoningBank (16 learning tables)
+- HNSW index: 150x faster vector search enabled
+- All 12 integration tests pass
+
+---
+
 ## [1.9.3] - 2025-11-26
 
 ### 🐛 Bugfix: NPM Package Missing Files

package/README.md

@@ -9,11 +9,11 @@
 <img alt="NPM Downloads" src="https://img.shields.io/npm/dw/agentic-qe">
 
 
-**Version 1.9.3** (NPM Package Fix) | [Changelog](CHANGELOG.md) | [Issues](https://github.com/proffesor-for-testing/agentic-qe/issues) | [Discussions](https://github.com/proffesor-for-testing/agentic-qe/discussions)
+**Version 2.0.0** | [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** | 📚 **40 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
 
-### 🎓 40 QE Skills Library (v1.9.0)
+### 🎓 41 QE Skills Library (v1.9.0)
 **95%+ coverage of modern QE practices**
 
 <details>
@@ -206,7 +206,7 @@ open http://localhost:3000
 - **Code Quality**: code-review-quality, refactoring-patterns, quality-metrics
 - **Communication**: bug-reporting-excellence, technical-writing, consultancy-practices
 
-**Phase 2: Expanded QE Skills Library (18 skills)**
+**Phase 2: Expanded QE Skills Library (16 skills)**
 - **Testing Methodologies (7)**: regression-testing, shift-left-testing, shift-right-testing, test-design-techniques, mutation-testing, test-data-management, verification-quality
 - **Specialized Testing (9)**: accessibility-testing, mobile-testing, database-testing, contract-testing, chaos-engineering-resilience, compatibility-testing, localization-testing, compliance-testing, visual-testing-advanced
 - **Testing Infrastructure (2)**: test-environment-management, test-reporting-analytics
@@ -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: 40 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
@@ -645,6 +672,31 @@ The test generator automatically delegates to subagents for a complete RED-GREEN
 
 ---
 
+## 📝 What's New in v1.9.4
+
+🔧 **Critical Memory & Learning System Fixes** (2025-11-30)
+
+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.
+
+### Key Fixes
+
+- **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
+
+### New Features
+
+- **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
+
+**Upgrade**: `npm install agentic-qe@1.9.4`
+
+---
+
 ## 📝 What's New in v1.9.3
 
 📦 **NPM Package Fix** (2025-11-26)

package/config/.env.otel.example

@@ -0,0 +1,25 @@
+# OTEL Stack Environment Variables
+# Agentic QE Fleet - Issue #71
+#
+# Copy this file to .env.otel and customize as needed
+# Usage: docker-compose -f config/docker-compose.otel.yml --env-file config/.env.otel up -d
+
+# Deployment environment
+DEPLOYMENT_ENVIRONMENT=development
+
+# Grafana credentials (CHANGE IN PRODUCTION!)
+GRAFANA_ADMIN_USER=admin
+GRAFANA_ADMIN_PASSWORD=admin
+
+# OTEL Collector settings
+OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318
+OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf
+
+# Service configuration
+SERVICE_NAME=agentic-qe-fleet
+SERVICE_NAMESPACE=agentic-qe
+SERVICE_VERSION=1.9.3
+
+# Prometheus retention
+PROMETHEUS_RETENTION_TIME=15d
+PROMETHEUS_RETENTION_SIZE=10GB

package/config/OTEL-QUICK-REFERENCE.md

@@ -0,0 +1,137 @@
+# OTEL Stack Quick Reference Card
+
+## 🚀 One-Line Start
+
+```bash
+docker-compose -f config/docker-compose.otel.yml up -d
+```
+
+## 🌐 Service URLs
+
+| Service | URL | Login |
+|---------|-----|-------|
+| **Grafana** | http://localhost:3001 | admin/admin |
+| **Prometheus** | http://localhost:9090 | - |
+| **Jaeger** | http://localhost:16686 | - |
+| **OTEL Health** | http://localhost:13133/health | - |
+
+## 📡 Send Telemetry
+
+### OTLP Endpoints
+- gRPC: `localhost:4317`
+- HTTP: `localhost:4318`
+
+### Node.js Example
+```javascript
+const exporter = new OTLPTraceExporter({
+  url: 'http://localhost:4318/v1/traces'
+});
+```
+
+### cURL Test
+```bash
+curl http://localhost:4318/v1/traces \
+  -H "Content-Type: application/json" \
+  -d @trace.json
+```
+
+## 🔍 Quick Checks
+
+```bash
+# Verify all services
+./scripts/verify-otel-stack.sh
+
+# Check health
+curl http://localhost:13133/health  # OTEL Collector
+curl http://localhost:9090/-/healthy  # Prometheus
+curl http://localhost:14269/  # Jaeger
+curl http://localhost:3001/api/health  # Grafana
+
+# View logs
+docker-compose -f config/docker-compose.otel.yml logs -f
+```
+
+## 🛠️ Common Commands
+
+```bash
+# Start
+docker-compose -f config/docker-compose.otel.yml up -d
+
+# Stop
+docker-compose -f config/docker-compose.otel.yml down
+
+# Restart
+docker-compose -f config/docker-compose.otel.yml restart
+
+# View status
+docker-compose -f config/docker-compose.otel.yml ps
+
+# Logs
+docker-compose -f config/docker-compose.otel.yml logs -f [service]
+
+# Remove everything (INCLUDING DATA!)
+docker-compose -f config/docker-compose.otel.yml down -v
+```
+
+## 📊 Port Reference
+
+### OTEL Collector
+- 4317 - OTLP gRPC
+- 4318 - OTLP HTTP
+- 8889 - Prometheus metrics
+- 13133 - Health check
+
+### Prometheus
+- 9090 - Web UI
+
+### Jaeger
+- 16686 - UI
+- 14269 - Metrics
+
+### Grafana
+- 3001 - Web UI
+
+## 🔧 Configuration Files
+
+- **Docker Compose**: `config/docker-compose.otel.yml`
+- **OTEL Collector**: `config/otel-collector-config.yaml.example`
+- **Prometheus**: `config/prometheus.yml.example`
+- **Grafana Datasources**: `config/grafana/provisioning/datasources/datasources.yml`
+- **Grafana Dashboards**: `config/grafana/provisioning/dashboards/dashboards.yml`
+
+## 📚 Documentation
+
+- **Quick Start**: `config/README-OTEL.md`
+- **Full Summary**: `docs/implementation-plans/issue-71-completion-summary.md`
+- **Architecture**: `docs/architecture/otel-stack-architecture.md`
+
+## 🐛 Quick Troubleshooting
+
+| Issue | Solution |
+|-------|----------|
+| Services not starting | Check logs: `docker-compose -f config/docker-compose.otel.yml logs` |
+| Port already in use | Change external port in `docker-compose.otel.yml` |
+| Grafana can't connect | Check datasources: Grafana → Configuration → Data Sources |
+| No metrics in Prometheus | Check targets: http://localhost:9090/targets |
+| No traces in Jaeger | Verify OTLP endpoint: `curl http://localhost:4318` |
+
+## 🎯 Grafana Datasources
+
+Pre-configured and auto-loaded:
+
+1. **Prometheus** (default) - `http://prometheus:9090`
+2. **Jaeger** - `http://jaeger:16686`
+3. **OTEL Collector Metrics** - `http://otel-collector:8889`
+
+## ✅ Verification Checklist
+
+- [ ] All 4 services running: `docker-compose ps`
+- [ ] Health checks passing: `./scripts/verify-otel-stack.sh`
+- [ ] OTLP endpoints accessible: `curl http://localhost:4318`
+- [ ] Prometheus targets green: http://localhost:9090/targets
+- [ ] Grafana datasources connected: Grafana UI → Data Sources
+- [ ] Sample dashboard visible: Grafana → Dashboards
+
+---
+
+**Issue #71 - COMPLETED** ✅