agentic-qe 2.3.0 → 2.3.2

package/CHANGELOG.md

@@ -7,6 +7,68 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.3.2] - 2025-12-09
+
+### Fixed
+
+#### Dependency Resolution (Install Failure)
+Fixed npm install failure caused by transitive dependency issue:
+- **Root Cause**: `ruvector@latest` (0.1.25+) depends on `@ruvector/core@^0.1.25` which doesn't exist on npm (latest is 0.1.17)
+- **Solution**: Pinned `ruvector` to exact version `0.1.24` (removed caret `^`) which correctly depends on `@ruvector/core@^0.1.15`
+- Users can now successfully run `npm install -g agentic-qe@latest`
+
+## [2.3.1] - 2025-12-08
+
+### Fixed
+
+#### MCP Tools Validation (Issues #116, #120)
+Fixed critical MCP tools validation that had degraded from 26% to 5% coverage. The validation script now properly recognizes:
+- **Composite Handlers**: Phase2ToolsHandler (15 tools) and Phase3DomainToolsHandler (42 tools)
+- **Streaming Handlers**: TestExecuteStreamHandler and CoverageAnalyzeStreamHandler in dedicated streaming directory
+
+**Validation Results:**
+- Before: 5% (4/82 tools valid)
+- After: 100% (82/82 tools valid)
+
+### Added
+
+#### Comprehensive Handler Test Coverage
+Added 18 new test files with 300+ test cases following TDD RED phase patterns:
+
+**Memory Handler Tests (6 files):**
+- `memory-share.test.ts` - Memory sharing between agents
+- `memory-backup.test.ts` - Backup and restore functionality
+- `blackboard-post.test.ts` - Blackboard posting operations
+- `blackboard-read.test.ts` - Blackboard reading with filters
+- `consensus-propose.test.ts` - Consensus proposal creation
+- `consensus-vote.test.ts` - Consensus voting mechanics
+
+**Coordination Handler Tests (6 files):**
+- `workflow-create.test.ts` - Workflow definition and validation
+- `workflow-execute.test.ts` - Workflow execution with OODA loop
+- `workflow-checkpoint.test.ts` - State checkpoint creation
+- `workflow-resume.test.ts` - Checkpoint restoration
+- `task-status.test.ts` - Task progress tracking
+- `event-emit.test.ts` - Event emission system
+
+**Test Handler Tests (4 files):**
+- `test-execute.test.ts` - Test execution orchestration
+- `test-execute-parallel.test.ts` - Parallel test execution
+- `test-optimize-sublinear.test.ts` - O(log n) test optimization
+- `test-report-comprehensive.test.ts` - Multi-format reporting
+
+**Prediction/Learning Tests (2 files):**
+- `deployment-readiness-check.test.ts` - Deployment readiness assessment
+- `learning-handlers.test.ts` - All 4 learning tools coverage
+
+### Changed
+
+#### Validation Script Improvements
+- Added `COMPOSITE_HANDLERS` mapping for Phase2/Phase3 tool routing
+- Added `STREAMING_HANDLER_FILES` mapping for streaming directory
+- Enhanced `findHandler()` with streaming directory search
+- Enhanced `findTests()` with composite handler test discovery
+
 ## [2.3.0] - 2025-12-08
 
 ### Added

package/README.md

@@ -9,7 +9,7 @@
 <img alt="NPM Downloads" src="https://img.shields.io/npm/dw/agentic-qe">
 
 
-**Version 2.3.0** | [Changelog](CHANGELOG.md) | [Contributors](CONTRIBUTORS.md) | [Issues](https://github.com/proffesor-for-testing/agentic-qe/issues) | [Discussions](https://github.com/proffesor-for-testing/agentic-qe/discussions)
+**Version 2.3.2** | [Changelog](CHANGELOG.md) | [Contributors](CONTRIBUTORS.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, QUIC transport, testability scoring, OpenTelemetry observability, persistent event storage, constitutional AI governance, and intelligent model routing.
 

package/dist/core/memory/HNSWVectorMemory.js

@@ -507,7 +507,7 @@ class HNSWVectorMemory {
     getImplementationInfo() {
         return {
             type: 'agentdb',
-            version: '2.3.0',
+            version: '2.3.2',
             features: ['hnsw', 'vector-search', 'persistence', 'batch-operations'],
         };
     }

package/dist/mcp/server-instructions.d.ts

@@ -6,7 +6,7 @@
  */
 export declare const SERVER_INSTRUCTIONS = "\n# Agentic QE Fleet - MCP Tool Guide\n\n## Overview\nAgentic QE provides 96 specialized quality engineering tools organized into a hierarchical system for efficient context usage.\n\n## Quick Start\n1. **Discover available tools:** Use `tools_discover` to see all domains\n2. **Load domain tools:** Use `tools_load_domain` to load specialized tools\n3. **Auto-loading:** Domain tools auto-load when relevant keywords are detected\n\n---\n\n## Core Tools (Always Available - 14 tools)\n\n### Fleet Management\n- `fleet_init` - Initialize QE fleet with topology\n- `agent_spawn` - Spawn specialized QE agent\n- `fleet_status` - Get fleet and agent status\n\n### Testing\n- `test_generate_enhanced` - AI test generation with pattern recognition\n- `test_execute_parallel` - Parallel test execution with retry\n- `test_report_comprehensive` - Multi-format test reports\n\n### Memory & Coordination\n- `memory_store` - Store data with TTL & namespacing\n- `memory_retrieve` - Retrieve stored data\n- `memory_query` - Pattern-based memory search\n\n### Quality & Orchestration\n- `quality_analyze` - Analyze quality metrics\n- `task_orchestrate` - Orchestrate tasks across agents\n- `task_status` - Check task progress\n\n### Discovery\n- `tools_discover` - List available tool domains\n- `tools_load_domain` - Load tools for a domain\n\n---\n\n## Domain Tools (Load as Needed)\n\n| Domain | Keywords | Tools | Use Case |\n|--------|----------|-------|----------|\n| **Security** | security, vulnerability, audit, owasp | 4 tools | Security scanning, vulnerability detection |\n| **Performance** | benchmark, bottleneck, profiling | 4 tools | Performance testing, bottleneck analysis |\n| **Coverage** | coverage, gap, uncovered | 5 tools | Coverage analysis, gap detection |\n| **Quality** | quality gate, deploy, release | 6 tools | Quality gates, deployment readiness |\n| **Flaky** | flaky, unstable, retry | 3 tools | Flaky test detection and stabilization |\n| **Visual** | screenshot, accessibility, wcag | 3 tools | Visual regression, accessibility testing |\n| **Requirements** | bdd, gherkin, acceptance | 2 tools | Requirements validation, BDD generation |\n\n### Loading Domain Tools\n```\n# Explicit load\ntools_load_domain({ domain: 'security' })\n\n# Auto-load: Just mention keywords in your request\n\"I need to run a security scan\" \u2192 Security tools auto-load\n```\n\n---\n\n## Specialized Tools (Expert Use)\n\n### Learning Domain (4 tools)\nFor persistent learning and pattern storage across sessions.\nLoad with: `tools_load_domain({ domain: 'learning' })`\n\n### Advanced Domain (7 tools)\nFor mutation testing, API contract validation, production incident replay.\nLoad with: `tools_load_domain({ domain: 'advanced' })`\n\n---\n\n## Best Practices\n\n1. **Start with core tools** - They handle 80% of use cases\n2. **Let auto-load work** - Mention keywords naturally\n3. **Use tools_discover** - When unsure what's available\n4. **Batch operations** - Use parallel execution for speed\n5. **Check fleet_status** - Monitor agent health\n\n---\n\n## Common Workflows\n\n### Test Generation & Execution\n1. `test_generate_enhanced` - Generate tests\n2. `test_execute_parallel` - Run tests\n3. `test_report_comprehensive` - Generate report\n\n### Quality Gate Check\n1. Load quality domain if not auto-loaded\n2. `quality_analyze` - Analyze metrics\n3. `qe_qualitygate_evaluate` - Make go/no-go decision\n\n### Security Audit\n1. `tools_load_domain({ domain: 'security' })`\n2. `qe_security_scan_comprehensive` - Full scan\n3. `qe_security_detect_vulnerabilities` - Detailed analysis\n\n---\n\n## Tool Naming Convention\nAll tools follow: `mcp__agentic_qe__<tool_name>`\n\nExample: `mcp__agentic_qe__test_generate_enhanced`\n";
 export declare const SERVER_NAME = "agentic-qe";
-export declare const SERVER_VERSION = "2.3.0";
+export declare const SERVER_VERSION = "2.3.2";
 /**
  * Get formatted server info for MCP initialization
  */

package/dist/mcp/server-instructions.js

@@ -119,7 +119,7 @@ All tools follow: \`mcp__agentic_qe__<tool_name>\`
 Example: \`mcp__agentic_qe__test_generate_enhanced\`
 `;
 exports.SERVER_NAME = 'agentic-qe';
-exports.SERVER_VERSION = '2.3.0';
+exports.SERVER_VERSION = '2.3.2';
 /**
  * Get formatted server info for MCP initialization
  */

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-qe",
-  "version": "2.3.0",
+  "version": "2.3.2",
   "description": "Agentic Quality Engineering Fleet System - AI-driven quality management platform with 41 QE skills, learning, pattern reuse, ML-based flaky detection, Multi-Model Router (70-81% cost savings), streaming progress updates, 84 MCP tools with lazy loading (87% context reduction), and native TypeScript hooks",
   "main": "dist/cli/index.js",
   "types": "dist/cli/index.d.ts",
@@ -139,7 +139,7 @@
     "openai": "^6.9.1",
     "ora": "^5.4.1",
     "playwright": "^1.57.0",
-    "ruvector": "^0.1.24",
+    "ruvector": "0.1.24",
     "uuid": "^11.0.5",
     "winston": "^3.18.3",
     "ws": "^8.18.3",