agentic-qe 3.6.4 → 3.6.6

package/.claude/helpers/v3/quality-criteria/validate-quality-criteria.ts

@@ -0,0 +1,167 @@
+#!/usr/bin/env npx ts-node
+/**
+ * Quality Criteria Output Validator
+ * Validates HTML output from qe-quality-criteria-recommender agent
+ *
+ * Usage: npx ts-node scripts/validate-quality-criteria.ts <path-to-html>
+ */
+
+import * as fs from 'fs';
+import * as path from 'path';
+
+interface ValidationResult {
+  passed: boolean;
+  gate: string;
+  message: string;
+  count?: number;
+}
+
+interface ValidationReport {
+  file: string;
+  timestamp: string;
+  passed: boolean;
+  gatesPassed: number;
+  gatesTotal: number;
+  results: ValidationResult[];
+}
+
+const QUALITY_GATES = [
+  {
+    name: 'No confidence percentages',
+    pattern: /\d+%\s*(confidence|confident)/gi,
+    shouldFind: false,
+    message: 'Found confidence percentages - use evidence types instead',
+  },
+  {
+    name: 'Evidence types present',
+    pattern: /<span class="evidence-type (direct|inferred|claimed)">/gi,
+    shouldFind: true,
+    minCount: 1,
+    message: 'Missing evidence type classifications',
+  },
+  {
+    name: 'Coverage explicitly defined',
+    pattern: /\d+\s*of\s*10\s*HTSM\s*Categories/i,
+    shouldFind: true,
+    message: 'Coverage must show "X of 10 HTSM Categories" format',
+  },
+  {
+    name: 'File:line traceability',
+    pattern: /<code>[^<]+\.(ts|js|md|json|html):\d+-\d+<\/code>/gi,
+    shouldFind: true,
+    minCount: 1,
+    message: 'Evidence must have file:line references',
+  },
+  {
+    name: 'No "Lines X-Y" without file',
+    pattern: /Lines?\s+\d+[-–]\d+(?![^<]*\.(ts|js|md))/gi,
+    shouldFind: false,
+    message: 'Found "Lines X-Y" without file path',
+  },
+  {
+    name: 'Correct footer text',
+    pattern: /AI Semantic Understanding/i,
+    shouldFind: true,
+    message: 'Footer must say "AI Semantic Understanding" not "Heuristic analysis"',
+  },
+  {
+    name: 'No heuristic analysis mention',
+    pattern: /heuristic\s+analysis|keyword\s+matching/gi,
+    shouldFind: false,
+    message: 'Found "heuristic analysis" or "keyword matching" - forbidden',
+  },
+  {
+    name: 'Light body background',
+    pattern: /body\s*\{[^}]*background:\s*linear-gradient\([^)]*#f5f7fa/i,
+    shouldFind: true,
+    message: 'Body must have light gradient background (#f5f7fa)',
+  },
+  {
+    name: 'Dark header background',
+    pattern: /\.header\s*\{[^}]*background:\s*linear-gradient\([^)]*var\(--primary\)/i,
+    shouldFind: true,
+    message: 'Header must have dark gradient background (var(--primary))',
+  },
+  {
+    name: 'Reasoning column present',
+    pattern: /<th[^>]*>Reasoning<\/th>/i,
+    shouldFind: true,
+    message: 'Evidence tables must have "Reasoning" column',
+  },
+];
+
+function validateFile(filePath: string): ValidationReport {
+  const content = fs.readFileSync(filePath, 'utf-8');
+  const results: ValidationResult[] = [];
+
+  for (const gate of QUALITY_GATES) {
+    const matches = content.match(gate.pattern);
+    const count = matches?.length || 0;
+
+    let passed: boolean;
+    if (gate.shouldFind) {
+      passed = gate.minCount ? count >= gate.minCount : count > 0;
+    } else {
+      passed = count === 0;
+    }
+
+    results.push({
+      passed,
+      gate: gate.name,
+      message: passed ? 'OK' : gate.message,
+      count,
+    });
+  }
+
+  const gatesPassed = results.filter(r => r.passed).length;
+
+  return {
+    file: path.basename(filePath),
+    timestamp: new Date().toISOString(),
+    passed: gatesPassed === results.length,
+    gatesPassed,
+    gatesTotal: results.length,
+    results,
+  };
+}
+
+function printReport(report: ValidationReport): void {
+  console.log('\n' + '='.repeat(60));
+  console.log('Quality Criteria Validation Report');
+  console.log('='.repeat(60));
+  console.log(`File: ${report.file}`);
+  console.log(`Time: ${report.timestamp}`);
+  console.log(`Result: ${report.passed ? '✅ PASSED' : '❌ FAILED'}`);
+  console.log(`Gates: ${report.gatesPassed}/${report.gatesTotal}`);
+  console.log('-'.repeat(60));
+
+  for (const result of report.results) {
+    const icon = result.passed ? '✅' : '❌';
+    const countStr = result.count !== undefined ? ` (${result.count} found)` : '';
+    console.log(`${icon} ${result.gate}${countStr}`);
+    if (!result.passed) {
+      console.log(`   → ${result.message}`);
+    }
+  }
+
+  console.log('='.repeat(60) + '\n');
+}
+
+// Main execution
+const args = process.argv.slice(2);
+if (args.length === 0) {
+  console.error('Usage: npx ts-node scripts/validate-quality-criteria.ts <path-to-html>');
+  process.exit(1);
+}
+
+const filePath = args[0];
+if (!fs.existsSync(filePath)) {
+  console.error(`File not found: ${filePath}`);
+  process.exit(1);
+}
+
+const report = validateFile(filePath);
+printReport(report);
+
+// Exit with appropriate code
+process.exit(report.passed ? 0 : 1);

package/.claude/skills/README.md

@@ -4,16 +4,16 @@ This directory contains Quality Engineering skills managed by Agentic QE.
 
 ## Summary
 
-- **Total QE Skills**: 63
-- **V2 Methodology Skills**: 49
-- **V3 Domain Skills**: 14
-- **Platform Skills**: 34 (Claude Flow managed)
+- **Total QE Skills**: 75
+- **V2 Methodology Skills**: 60
+- **V3 Domain Skills**: 15
+- **Platform Skills**: 35 (Claude Flow managed)
 - **Validation Infrastructure**: ✅ Installed
 
 > **Note**: Platform skills (agentdb, github, flow-nexus, etc.) are managed by claude-flow.
 > Only QE-specific skills are installed/updated by `aqe init`.
 
-## V2 Methodology Skills (49)
+## V2 Methodology Skills (60)
 
 Version-agnostic quality engineering best practices from the QE community.
 
@@ -32,9 +32,12 @@ Version-agnostic quality engineering best practices from the QE community.
 - **context-driven-testing**: Apply context-driven testing principles where practices are chosen based on project context, not universal
 - **contract-testing**: Consumer-driven contract testing for microservices using Pact, schema validation, API versioning, and backward compatibility testing. Use when testing API contracts or coordinating distributed teams.
 - **database-testing**: Database schema validation, data integrity testing, migration testing, transaction isolation, and query performance. Use when testing data persistence, ensuring referential integrity, or validating database migrations.
+- **debug-loop**: Hypothesis-driven autonomous debugging with real command validation
+- **enterprise-integration-testing**: Orchestration skill for enterprise integration testing across SAP, middleware, WMS, and backend systems. Covers E2E enterprise flows, SAP-specific patterns (RFC, BAPI, IDoc, OData, Fiori), cross-system data validation, and enterprise quality gates.
 - **exploratory-testing-advanced**: Advanced exploratory testing techniques with Session-Based Test Management (SBTM), RST heuristics, and test tours. Use when planning exploration sessions, investigating bugs, or discovering unknown quality risks.
 - **holistic-testing-pact**: Apply the Holistic Testing Model evolved with PACT (Proactive, Autonomous, Collaborative, Targeted) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices.
 - **localization-testing**: Internationalization (i18n) and localization (l10n) testing for global products including translations, locale formats, RTL languages, and cultural appropriateness. Use when launching in new markets or building multi-language products.
+- **middleware-testing-patterns**: Enterprise middleware testing patterns for message routing, transformation, DLQ, protocol mediation, ESB error handling, and EIP patterns. Use when testing middleware layers, message brokers, ESBs, or integration buses.
 - **mobile-testing**: Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants.
 - **mutation-testing**: Test quality validation through mutation testing, assessing test suite effectiveness by introducing code mutations and measuring kill rate. Use when evaluating test quality, identifying weak tests, or proving tests actually catch bugs.
 - **n8n-expression-testing**: n8n expression syntax validation, context-aware testing, common pitfalls detection, and performance optimization. Use when validating n8n expressions and data transformations.
@@ -42,15 +45,21 @@ Version-agnostic quality engineering best practices from the QE community.
 - **n8n-security-testing**: Credential exposure detection, OAuth flow validation, API key management testing, and data sanitization verification for n8n workflows. Use when validating n8n workflow security.
 - **n8n-trigger-testing-strategies**: Webhook testing, schedule validation, event-driven triggers, and polling mechanism testing for n8n workflows. Use when testing how workflows are triggered.
 - **n8n-workflow-testing-fundamentals**: Comprehensive n8n workflow testing including execution lifecycle, node connection patterns, data flow validation, and error handling strategies. Use when testing n8n workflow automation applications.
+- **observability-testing-patterns**: Observability and monitoring validation patterns for dashboards, alerting, log aggregation, APM traces, and SLA/SLO verification. Use when testing monitoring infrastructure, dashboard accuracy, alert rules, or metric pipelines.
 - **pair-programming**: AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
 - **performance-testing**: Test application performance, scalability, and resilience. Use when planning load testing, stress testing, or optimizing system performance.
+- **pr-review**: Scope-aware GitHub PR review with user-friendly tone and trust tier validation
+- **qcsd-cicd-swarm**: QCSD Verification phase swarm for CI/CD pipeline quality gates using regression analysis, flaky test detection, quality gate enforcement, and deployment readiness assessment. Consumes Development outputs (SHIP/CONDITIONAL/HOLD decisions, quality metrics) and produces signals for Production monitoring.
+- **qcsd-development-swarm**: QCSD Development phase swarm for in-sprint code quality assurance using TDD adherence, code complexity analysis, coverage gap detection, and defect prediction. Consumes Refinement outputs (BDD scenarios, SFDIPOT priorities) and produces signals for Verification.
 - **qcsd-ideation-swarm**: QCSD Ideation phase swarm for Quality Criteria sessions using HTSM v6.3, Risk Storming, and Testability analysis before development begins. Uses 5-tier browser cascade: Vibium → agent-browser → Playwright+Stealth → WebFetch → WebSearch-fallback.
+- **qcsd-refinement-swarm**: QCSD Refinement phase swarm for Sprint Refinement sessions using SFDIPOT product factors, BDD scenario generation, and requirements validation.
 - **quality-metrics**: Measure quality effectively with actionable metrics. Use when establishing quality dashboards, defining KPIs, or evaluating test effectiveness.
 - **refactoring-patterns**: Apply safe refactoring patterns to improve code structure without changing behavior. Use when cleaning up code, reducing technical debt, or improving maintainability.
 - **regression-testing**: Strategic regression testing with test selection, impact analysis, and continuous regression management. Use when verifying fixes don
 - **risk-based-testing**: Focus testing effort on highest-risk areas using risk assessment and prioritization. Use when planning test strategy, allocating testing resources, or making coverage decisions.
 - **security-testing**: Test for security vulnerabilities using OWASP principles. Use when conducting security audits, testing auth, or implementing security practices.
 - **security-visual-testing**: Security-first visual testing combining URL validation, PII detection, and visual regression with parallel viewport support. Use when testing web applications that handle sensitive data, need visual regression coverage, or require WCAG accessibility compliance.
+- **sfdipot-product-factors**: James Bach
 - **sherlock-review**: Evidence-based investigative code review using deductive reasoning to determine what actually happened versus what was claimed. Use when verifying implementation claims, investigating bugs, validating fixes, or conducting root cause analysis. Elementary approach to finding truth through systematic observation.
 - **shift-left-testing**: Move testing activities earlier in the development lifecycle to catch defects when they
 - **shift-right-testing**: Testing in production with feature flags, canary deployments, synthetic monitoring, and chaos engineering. Use when implementing production observability or progressive delivery.
@@ -61,17 +70,20 @@ Version-agnostic quality engineering best practices from the QE community.
 - **test-data-management**: Strategic test data generation, management, and privacy compliance. Use when creating test data, handling PII, ensuring GDPR/CCPA compliance, or scaling data generation for realistic testing scenarios.
 - **test-design-techniques**: Systematic test design with boundary value analysis, equivalence partitioning, decision tables, state transition testing, and combinatorial testing. Use when designing comprehensive test cases, reducing redundant tests, or ensuring systematic coverage.
 - **test-environment-management**: Test environment provisioning, infrastructure as code for testing, Docker/Kubernetes for test environments, service virtualization, and cost optimization. Use when managing test infrastructure, ensuring environment parity, or optimizing testing costs.
+- **test-idea-rewriting**: Transform passive
 - **test-reporting-analytics**: Advanced test reporting, quality dashboards, predictive analytics, trend analysis, and executive reporting for QE metrics. Use when communicating quality status, tracking trends, or making data-driven decisions.
 - **testability-scoring**: AI-powered testability assessment using 10 principles of intrinsic testability with Playwright and optional Vibium integration. Evaluates web applications against Observability, Controllability, Algorithmic Simplicity, Transparency, Stability, Explainability, Unbugginess, Smallness, Decomposability, and Similarity. Use when assessing software testability, evaluating test readiness, identifying testability improvements, or generating testability reports.
 - **verification-quality**: Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
 - **visual-testing-advanced**: 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.
+- **wms-testing-patterns**: Warehouse Management System testing patterns for inventory operations, pick/pack/ship workflows, wave management, EDI X12/EDIFACT compliance, RF/barcode scanning, and WMS-ERP integration. Use when testing WMS platforms (Blue Yonder, Manhattan, SAP EWM).
 - **xp-practices**: 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.
 
-## V3 Domain Skills (14)
+## V3 Domain Skills (15)
 
 V3-specific implementation guides for the 12 DDD bounded contexts.
 
 - **aqe-v2-v3-migration**: Migrate Agentic QE projects from v2 to v3 with zero data loss
+- **pentest-validation**: Orchestrate security finding validation through graduated exploitation. 4-phase pipeline: recon (SAST/DAST), analysis (code review), validation (exploit proof), report (No Exploit, No Report gate). Eliminates false positives by proving exploitability.
 - **qe-chaos-resilience**: Chaos engineering and resilience testing including fault injection, load testing, and system recovery validation.
 - **qe-code-intelligence**: Knowledge graph-based code understanding with semantic search and 80% token reduction through intelligent context retrieval.
 - **qe-contract-testing**: Consumer-driven contract testing for APIs including REST, GraphQL, and event-driven systems with schema validation.
@@ -86,7 +98,7 @@ V3-specific implementation guides for the 12 DDD bounded contexts.
 - **qe-test-generation**: AI-powered test generation using pattern recognition, code analysis, and intelligent test synthesis for comprehensive test coverage.
 - **qe-visual-accessibility**: Visual regression testing, responsive design validation, and WCAG accessibility compliance testing.
 
-## Platform Skills (34)
+## Platform Skills (35)
 
 Claude Flow platform skills (managed separately).
 
@@ -110,6 +122,7 @@ Claude Flow platform skills (managed separately).
 - performance-analysis
 - reasoningbank-agentdb
 - reasoningbank-intelligence
+- release
 - skill-builder
 - sparc-methodology
 - stream-chain
@@ -138,4 +151,4 @@ See `.validation/README.md` for usage instructions.
 
 ---
 
-*Generated by AQE v3 init on 2026-02-03T14:30:46.976Z*
+*Generated by AQE v3 init on 2026-02-13T14:17:15.624Z*

package/.claude/skills/skills-manifest.json

@@ -904,7 +904,7 @@
   },
   "metadata": {
     "generatedBy": "Agentic QE Fleet",
-    "fleetVersion": "3.6.4",
+    "fleetVersion": "3.6.6",
     "manifestVersion": "1.3.0",
     "lastUpdated": "2026-02-04T00:00:00.000Z",
     "contributors": [

package/README.md

@@ -27,35 +27,33 @@
 # Install globally
 npm install -g agentic-qe
 
-# Initialize your project
+# Initialize your project (interactive mode)
 cd your-project
-aqe init --wizard
+aqe init
 
-# Or with auto-configuration
+# Or with auto-configuration (no prompts, configures MCP automatically)
 aqe init --auto
-
-# Start MCP server (agent-agnostic)
-aqe-mcp
-
-# Or without global install
-npx agentic-qe mcp
 ```
 
+> **Note:** `aqe init` automatically configures the MCP server in `.mcp.json` — Claude Code will auto-start it when connecting. For standalone MCP server usage (non-Claude-Code clients), run `aqe-mcp` or `npx agentic-qe mcp`.
+
 ### Use from MCP-compatible agent clients (Claude, Codex, others)
 
 AQE is exposed as an MCP server and can be used from any client that supports MCP tool connections.
 
 ```bash
-# 1) Start MCP server
-npx agentic-qe mcp
-
-# 2) Register/connect from your MCP-capable client
-#    (Claude Code, Codex-compatible client, or other MCP hosts)
-
-# 3) Ask the client to invoke AQE agents/tools, e.g.:
-#    - qe-test-architect for test generation
-#    - qe-queen-coordinator for orchestration
-#    - qe-flaky-hunter for flaky analysis
+# For Claude Code: aqe init --auto configures .mcp.json automatically
+# Claude Code will auto-start the MCP server on connection
+
+# For other MCP clients: start the server manually
+aqe-mcp                  # if installed globally
+npx agentic-qe mcp       # without global install
+
+# Then ask your client to invoke AQE tools (prefixed mcp__agentic-qe__):
+#    - fleet_init (required first step)
+#    - test_generate_enhanced for test generation
+#    - task_orchestrate for multi-agent coordination
+#    - quality_assess for quality gate evaluation
 ```
 
 For client-specific setup examples, see `docs/integration/mcp-clients.md`.
@@ -80,21 +78,19 @@ For client-specific setup examples, see `docs/integration/mcp-clients.md`.
 # 1. Install
 npm install -g agentic-qe
 
-# 2. Initialize (auto-detects your project, enables all 13 domains)
+# 2. Initialize (auto-detects your project, enables all 13 domains, configures MCP)
 cd your-project && aqe init --auto
 
-# 3. Start AQE MCP server
-npx agentic-qe mcp
-
-# 4. Use your MCP-capable client to run test generation and quality assessment
-# (see docs/integration/mcp-clients.md)
+# 3. Use from Claude Code — MCP tools are available immediately (prefix: mcp__agentic-qe__)
+# Or start MCP server manually for other clients: aqe-mcp
 ```
 
 **What happens:**
 1. **Auto-configuration** detects your tech stack (TypeScript/JS, testing framework, CI setup)
 2. **All 13 DDD domains** enabled automatically - no "No factory registered" errors
-3. **Pattern learning** kicks in - your project's test patterns are learned and reused
-4. **AI agents** generate tests, analyze coverage, and provide actionable recommendations
+3. **MCP server** configured in `.mcp.json` — Claude Code auto-connects on next session
+4. **Pattern learning** kicks in - your project's test patterns are learned and reused
+5. **AI agents** generate tests, analyze coverage, and provide actionable recommendations
 
 ---
 
@@ -190,7 +186,7 @@ V3.1.0 adds full browser automation support via **@claude-flow/browser** integra
 claude "Use security-visual-testing skill to test https://example.com across mobile, tablet, desktop viewports"
 
 # Load and execute a workflow template
-aqe workflow load login-flow --vars '{"username": "test", "password": "secret"}'
+aqe workflow run login-flow --vars '{"username": "test", "password": "secret"}'
 ```
 
 ---
@@ -267,11 +263,11 @@ V3 agents learn and improve through the **ReasoningBank** pattern storage:
 | **Cross-Project Transfer** | Share patterns between projects |
 
 ```bash
-# Check what agents have learned
-aqe memory search --query "test patterns" --namespace learning
+# Search learned patterns
+aqe hooks search --query "test patterns"
 
-# View learning metrics
-aqe hooks metrics --v3-dashboard
+# View learning statistics
+aqe learning stats
 ```
 
 ---
@@ -290,10 +286,10 @@ V3 introduces **Dream cycles** for neural consolidation and continuous improveme
 
 ```bash
 # Trigger dream cycle for pattern consolidation
-aqe hooks intelligence --mode dream --consolidate
+aqe learning dream
 
-# View learning trajectory
-aqe hooks intelligence trajectory-start --task "optimize coverage"
+# View learning dashboard and trajectory
+aqe learning dashboard
 ```
 
 ---
@@ -315,11 +311,11 @@ aqe hooks intelligence trajectory-start --task "optimize coverage"
 - **Token budget optimization**: Minimizes cost while maintaining quality
 
 ```bash
-# Check model routing for a task
-aqe hooks model-route --task "fix type errors in user-service.ts"
+# Route a task through TinyDancer
+aqe llm route --task "fix type errors in user-service.ts"
 
-# View routing statistics
-aqe hooks model-stats
+# View routing cost analysis
+aqe llm cost
 ```
 
 ---
@@ -388,11 +384,11 @@ V3.3.3 achieves **full MinCut/Consensus integration across all 13 domains**:
 | **Self-Healing Triggers** | `shouldPauseOperations()` for automatic recovery |
 
 ```bash
-# View consensus status
-aqe coordination consensus --status
+# Check fleet health (includes consensus and topology status)
+aqe fleet status
 
-# Check topology health
-aqe coordination topology --optimize
+# Via MCP tools (from Claude Code)
+# mcp__agentic-qe__fleet_health({ includeTopology: true })
 ```
 
 ---
@@ -424,11 +420,11 @@ V3.3.0 introduces **mathematical coherence verification** using Prime Radiant WA
 - "Coherence Verified" CI/CD badges
 
 ```bash
-# Check coherence of beliefs
-aqe coherence check --beliefs "requirement1,requirement2"
+# Coherence verification is available via MCP tools and programmatic API:
+# mcp__agentic-qe__quality_assess({ scope: "coherence", includeMetrics: true })
 
-# Audit memory for contradictions
-aqe coherence audit --namespace learning
+# Verify learned patterns for consistency
+aqe learning verify
 ```
 
 ---
@@ -717,8 +713,8 @@ aqe migrate status
 # Run migration with backup
 aqe migrate run --backup
 
-# Validate migration
-aqe migrate validate
+# Verify migration
+aqe migrate verify
 ```
 
 **What gets migrated:**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-qe",
-  "version": "3.6.4",
+  "version": "3.6.6",
   "description": "Agentic Quality Engineering V3 - Domain-Driven Design Architecture with 13 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 59 specialized QE agents, mathematical Coherence verification, deep Claude Flow integration",
   "main": "./v3/dist/index.js",
   "types": "./v3/dist/index.d.ts",

package/v3/CHANGELOG.md

@@ -5,6 +5,36 @@ All notable changes to Agentic QE will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.6.6] - 2026-02-13
+
+### Fixed
+
+- **Node 22+ crash on `npm install -g`** — `aqe --version` failed with `ERR_MODULE_NOT_FOUND: better-sqlite3` because Node 22's ESM resolver cannot handle packages without an `exports` field. Build scripts now use a `createRequire()` shim for all native modules, eliminating bare ESM imports that triggered `legacyMainResolve` failures.
+- **Hooks writing to wrong database** — Self-learning hooks used `process.cwd()` to find the database, which could resolve to the wrong `.agentic-qe/` directory in monorepos or subdirectories. All hooks and learning commands now use `findProjectRoot()` to always write to the project root database.
+- **Silent hook failures for 8+ days** — Removed 9 dead `npx @claude-flow/cli@latest` hooks and 3 `v3-qe-bridge.sh` hooks from settings.json that silently failed on every tool use. Each hook event now has exactly one working `aqe` handler.
+- **Vector dimension mismatch in hooks** — HNSW index initialized at 128 dimensions while database vectors were 768, causing fallback to in-memory mode. Fixed all `embeddingDimension` defaults across hooks, learning, pattern-store, reasoning-bank, and MCP audit to 768.
+- **Learning experiences not tracked** — `recordOutcome` in `post-task` hook only fired when both `--task-id` and `--agent` were passed, but hooks never pass `--agent`. Relaxed guard to only require `--task-id`, with agent defaulting to `"unknown"`.
+- **FK constraint blocking analytics** — `qe_pattern_usage` table had a foreign key to `qe_patterns`, but hooks write synthetic pattern IDs. Removed the FK constraint so analytics writes succeed.
+- **Statusline missing hook experiences** — Statusline experience count didn't include `qe_pattern_usage` table. Added it as a source, so hook-recorded learning now appears in metrics.
+- **Noisy `[PatternStore] Loaded 0 patterns` log** — Suppressed the zero-count log that printed on every CLI invocation.
+
+### Changed
+
+- **Build system modernized** — `build-cli.js` and `build-mcp.js` now use esbuild's JavaScript API with a `nativeRequirePlugin` instead of shelling out via `execSync`. Native modules (better-sqlite3, @ruvector/*, hnswlib-node, etc.) are shimmed with `createRequire()` for Node 22+ compatibility. `chalk` externalized to avoid CJS `require('os')` failures in ESM context.
+
+## [3.6.5] - 2026-02-13
+
+### Fixed
+
+- **Vector dimension mismatch (#255)** — `fleet_init` crashed with `Vector length mismatch: 128 vs 768` because QE domain HNSW indices were hardcoded to 128-dim while the embedding system produces 768-dim vectors. All 6 QE domain HNSW configs now derive dimensions from `EMBEDDING_CONFIG.DIMENSIONS` (768), and `DEFAULT_VECTOR_DIMENSIONS` aligned from 384 to 768. Coverage-analysis (128-dim custom feature vectors) remains unchanged.
+- **Agent asset learning protocol** — 48 agent templates in `v3/assets/agents/v3/` had broken learning persistence: wrong namespace (`"patterns"` instead of `"learning"`), missing `persist: true`, and malformed key formats. Synced all assets from the correct committed agent definitions.
+- **README CLI commands** — Fixed 13 incorrect CLI commands referencing non-existent flags/subcommands: `aqe init --wizard` → `aqe init`, `aqe memory search` → `aqe hooks search`, `aqe hooks metrics` → `aqe hooks stats`, `aqe hooks intelligence` → `aqe learning dream`, `aqe hooks model-route` → `aqe llm route`, `aqe coordination` → `aqe fleet status`, `aqe coherence` → MCP tools, `aqe migrate validate` → `aqe migrate verify`, `aqe workflow load` → `aqe workflow run`.
+
+### Changed
+
+- **CLAUDE.md init template** — `aqe init` now generates a CLAUDE.md with comprehensive MCP tool usage instructions including `fleet_init` requirement, tool examples with correct `mcp__agentic-qe__` prefix, and full tool reference table.
+- **README MCP setup flow** — Clarified that `aqe init --auto` configures `.mcp.json` automatically; Claude Code auto-starts the MCP server on connection. Manual `aqe-mcp` only needed for non-Claude-Code clients.
+
 ## [3.6.4] - 2026-02-12
 
 ### Added

package/v3/assets/agents/v3/README.md

@@ -8,93 +8,32 @@ This directory contains V3 QE agents installed by `aqe init`.
 
 ## Summary
 
-- **Total Agents**: 1
-- **V3 QE Domain Agents**: 1
+- **Total Agents**: 0
+- **V3 QE Domain Agents**: 0
 - **V3 Subagents**: 0
 
-## V2 → V3 Migration Guide
-
-| V2 Agent | V3 Agent | Domain | Key Changes |
-|----------|----------|--------|-------------|
-| `qe-a11y-ally` | `qe-accessibility-auditor` | visual-accessibility | **MANDATORY video pipeline** |
-| `qe-test-generator` | `qe-test-architect` | test-generation | ReasoningBank learning |
-| `qe-coverage-analyzer` | `qe-coverage-specialist` | coverage-analysis | O(log n) sublinear |
-| `qe-coordinator` | `qe-learning-coordinator` | learning-optimization | Cross-domain patterns |
-| `qe-flaky-investigator` | `qe-flaky-hunter` | defect-intelligence | ML-powered detection |
-
-## Critical: qe-accessibility-auditor
-
-The V3 accessibility auditor has a **MANDATORY video accessibility pipeline**.
-
-### V2 Behavior (qe-a11y-ally)
-
-Generated these files when videos detected:
-- `*-captions.vtt` - For deaf/hard-of-hearing users
-- `*-audiodesc.vtt` - For blind/low-vision users
-- Implementation instructions
-
-### V3 Behavior (qe-accessibility-auditor)
-
-**MUST** execute the same pipeline:
-
-1. **Detect** - Find `<video>`, `<iframe>` elements
-2. **Download** - `curl -L -o video.mp4 URL`
-3. **Extract** - `ffmpeg -vf "fps=1/3" -frames:v 10`
-4. **Analyze** - Read each .jpg with Claude Vision
-5. **Generate** - Create .vtt from actual descriptions
-6. **Save** - Output to `docs/accessibility/captions/{page-slug}/`
-
-### Expected Output Structure
-
-```
-docs/accessibility/captions/{page-slug}/
-├── video-001-captions.vtt     # Captions
-├── video-001-audiodesc.vtt    # Audio descriptions
-├── implementation.md          # HTML integration
-└── audit-report.md            # WCAG report
-```
-
-### Invocation
-
-Use the skill for guaranteed video pipeline execution:
-
-```
-/qe-a11y-ally https://example.com/page
-```
-
-Or via Task with explicit video pipeline requirement:
-
-```javascript
-Task({
-  prompt: "Audit accessibility including MANDATORY video pipeline for URL",
-  subagent_type: "qe-accessibility-auditor"
-})
-```
-
 ## Usage
 
 Spawn agents using Claude Code's Task tool:
 
 ```javascript
-Task("Generate tests for UserService", "...", "qe-test-architect")
-Task("Analyze coverage gaps", "...", "qe-coverage-specialist")
-Task("Audit accessibility with video captions", "...", "qe-accessibility-auditor")
+Task("Generate tests for UserService", "...", "v3-qe-test-architect")
+Task("Analyze coverage gaps", "...", "v3-qe-coverage-specialist")
+Task("Run security scan", "...", "v3-qe-security-scanner")
 ```
 
-## V3 QE Domain Agents (1)
+## V3 QE Domain Agents (0)
 
 Quality Engineering agents mapped to the 12 DDD bounded contexts.
 
-| Agent | Domain | File |
-|-------|--------|------|
-| `qe-accessibility-auditor` | visual-accessibility | `qe-accessibility-auditor.md` |
+
 
 ## V3 Subagents (0)
 
 Specialized sub-task agents for TDD and code review.
 
-*None installed*
+
 
 ---
 
-*Updated 2026-01-26 - Added V2→V3 migration guide and video pipeline documentation*
+*Generated by AQE v3 init on 2026-02-04T16:48:59.207Z*

package/v3/assets/agents/v3/qe-accessibility-auditor.md

@@ -277,18 +277,19 @@ mcp__agentic-qe__memory_store({
 **2. Store Remediation Pattern:**
 ```typescript
 mcp__agentic-qe__memory_store({
-  key: "learning/patterns/accessibility-remediation-{timestamp}",
-  namespace: "patterns",
+  key: "patterns/accessibility-remediation/{timestamp}",
+  namespace: "learning",
   value: {
     pattern: "<accessibility fix pattern>",
     confidence: <0.0-1.0>,
     type: "accessibility-remediation",
     metadata: {
-    wcagCriteria: "<criteria>",
-    violationType: "<type>",
-    codeExample: "<fix>"
-  }
-  }
+      wcagCriteria: "<criteria>",
+      violationType: "<type>",
+      codeExample: "<fix>"
+    }
+  },
+  persist: true
 })
 ```