149c922bac
feat(v3): add Vibium browser automation integration with real E2E testing
...
- Add VibiumClientImpl wrapper for browser automation via WebDriver BiDi
- Integrate axe-core for real accessibility testing in browser context
- Add multi-viewport screenshot capture service
- Implement visual regression testing with baseline comparison
- Create E2E test runner service with user flow generation
- Add real integration tests (no mocks) with CI environment detection
- Update visual-accessibility domain with browser mode support
- Add npm script test:integration:browser for real browser tests
- Bump version to 3.0.0-alpha.32
Key files:
- src/integrations/vibium/client.ts - Browser automation client
- src/domains/visual-accessibility/services/axe-core-integration.ts
- src/domains/test-execution/services/e2e-runner.ts
- tests/integrations/vibium/vibium-real.test.ts - NO MOCKS tests
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-19 09:24:43 +00:00
e8b2ae6094
feat(v3): add TinyDancer routing, consensus engine, and documentation updates
...
Major Features:
- TinyDancer 3-tier model routing (ADR-026): Haiku/Sonnet/Opus based on complexity
- Multi-model consensus engine with Byzantine fault tolerance
- Claim verifier service for agent work validation
- Code intelligence metric collectors (LOC, test counts)
- Fleet integration with init wizard
Documentation:
- Update README with 50 agents (43 main + 7 subagents)
- Add TinyDancer, Dream cycles, Consensus sections
- Remove unverified performance claims (keep 166x MCP verified)
- Create v2-vs-v3 comparison document
- Add reference docs for AQE fleet and Claude Flow
Testing:
- Add consensus engine unit tests
- Add queen-tinydancer wiring integration tests
- Add security-consensus wiring tests
- Add claim verifier integration tests
- Add fleet integration tests
Bump version to 3.0.0-alpha.28
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-18 17:33:22 +00:00
fd2f37eaa0
fix(v3): update README claims and init hooks to use correct package name
...
Changes:
- Fix README.md agent counts (48 QE agents = 41 main + 7 subagents)
- Fix README.md skill counts (15 QE-specific skills)
- Fix v3/README.md agent counts (47 → 48)
- Fix init-wizard.ts hooks from 'npx @agentic-qe/v3' to 'npx agentic-qe'
- Complete v2 → v2/ folder reorganization (54 items moved)
- Update root package.json to point to v3 as main version
Verified claims:
- 48 QE agents (41 main + 7 TDD subagents)
- 15 QE-specific skills
- 12 DDD bounded contexts
- ~5,600+ tests
- HNSW, ReasoningBank, Queen Coordinator features exist
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-17 18:03:40 +00:00
0a7a1c8b09
feat(release): v2.6.2 - Phase 2 LLM Independence & Cost Optimization
...
## Added
- ML-Based Complexity Classification with 4-level task analysis
- Model Capability Registry with 25+ December 2025 models
- Claude Opus 4.5, DeepSeek R1/V3, GPT-5, Gemini 2.5 Pro
- Cost Optimization Strategies (PromptCompressor, Caching, Batching)
- HybridRouter integration with complexity-based model selection
## Changed
- README.md Quick Start section (user-focused, no version numbers)
- .env.example rewritten for Phase 2 features
- CONTRIBUTORS.md updated with @fndlalit's n8n contribution (#151 )
## Fixed
- HybridRouter RuVector test isolation
- Compression benchmarks with honest expectations (2-8% vs false 50%)
## New Tests
- ComplexityClassifier, ModelCapabilityRegistry, CompressionBenchmark
- HybridRouter integration, model selection, and cost tracking tests
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-24 15:24:41 +00:00
9fd235d2e6
feat(phase-1): complete LLM Independence Phase 1 implementation
...
Phase 1.1 - OllamaProvider:
- Add OllamaProvider with all 13 ILLMProvider methods
- Add unit and integration tests for OllamaProvider
- Integrate with LLMProviderFactory auto-detection
Phase 1.2 - Agent Abstraction:
- Add IAgentLLM interface for provider-independent LLM access
- Add AgentLLMAdapter bridging ILLMProvider to IAgentLLM
- Update BaseAgent with getAgentLLM() method
- Migrate 4 LLM-active agents: TestGenerator, CoverageAnalyzer,
CodeIntelligence, N8nBase
- 15 n8n agents inherit capability via N8nBaseAgent
- 17 algorithmic agents work without LLM by design
Phase 1.3 - Configuration:
- Add ProviderConfig types and ConfigLoader
- Add CLI providers commands (list, status, switch, test)
- Add example provider configurations
Documentation:
- Update implementation plan with accurate agent categorization
- Add usage examples for IAgentLLM patterns
- Add provider guides and research documents
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-24 11:19:04 +00:00
ab86895b33
feat(agents): add CodeIntelligenceAgent for knowledge graph code understanding
...
Wave 6 completion - Code Intelligence agent integration:
New Files:
- src/agents/CodeIntelligenceAgent.ts: Full TypeScript implementation
- Extends BaseAgent with code intelligence capabilities
- Task types: index, search, context, graph, stats, incremental-update
- Public API: quickSearch(), getFormattedFileContext(), getFormattedQueryContext()
- Factory registration for QEAgentFactory
- .claude/agents/qe-code-intelligence.md: Agent definition for Claude Code
- Learning protocol with MCP tools
- Memory namespace configuration
- Usage patterns and examples
- docs/guides/code-intelligence-quickstart.md: User documentation
- Prerequisites (Ollama, RuVector PostgreSQL)
- Usage options (CLI, Task tool, programmatic API)
- Configuration and troubleshooting
Updates:
- src/types/index.ts: Added CODE_INTELLIGENCE to QEAgentType enum
- src/agents/index.ts: Export and factory case for CodeIntelligenceAgent
- docs/reference/agents.md: Added agent reference (now 21 QE agents)
- CLAUDE.md: Updated agent count and added guide link
Capabilities:
- Tree-sitter multi-language parsing (TypeScript, Python, Go, Rust, JS)
- Ollama nomic-embed-text embeddings (768 dimensions)
- Hybrid search (BM25 + Vector with RRF fusion)
- Knowledge graph with entity relationships
- 80% token reduction through intelligent context building
- Mermaid diagram generation
- Incremental indexing with git change detection
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-22 11:45:45 +00:00
60eb9609a1
chore(release): bump version to v2.5.7
...
## Changes
- Add 15 n8n workflow testing agents (contributed by @fndlalit)
- Add 5 n8n testing skills to QE skill patterns
- Update aqe init to copy n8n agent directory
- Update documentation with n8n agent reference
- Bump version in all required files
## Files Updated
- package.json, package-lock.json (version 2.5.7)
- README.md (version badge, n8n agents line, 46 skills)
- CHANGELOG.md (v2.5.7 section)
- CLAUDE.md (agent/skill counts)
- docs/reference/agents.md (n8n section)
- docs/reference/skills.md (n8n skills)
- src/cli/init/agents.ts (n8n directory copying)
- src/cli/init/skills.ts (n8n skill patterns)
- src/mcp/server-instructions.ts (SERVER_VERSION)
- src/core/memory/HNSWVectorMemory.ts (version)
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-17 11:51:56 +00:00
e4fa6e0fc4
docs: add AccessibilityAllyAgent to v2.5.0 + update agent counts (19→20)
...
## Changes
### AccessibilityAllyAgent Documentation (PR #129 )
- Added to CHANGELOG.md with full feature list
- Added to docs/reference/agents.md
- Added to .agentic-qe/docs/agents.md
- Added to README.md agent tables
### Agent Count Updates (19 → 20)
Updated all references to reflect new AccessibilityAllyAgent:
- CLAUDE.md (20 QE Agents, 20 main + 11 subagents)
- README.md (20 Specialized Agents, 31 total)
- docs/reference/agents.md
- .agentic-qe/docs/agents.md, skills.md, usage.md
- src/cli/init/agents.ts, claude-config.ts, database-init.ts
- src/learning/baselines/*.ts
- src/telemetry/instrumentation/*.ts
Contributed by: @fndlalit (PR #129 )
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-13 18:14:53 +00:00
d7455132bf
docs: update agent/skill counts and improve README
...
- Update agent count from 18 to 19 (added qx-partner)
- Update skill count references to 41 (was inconsistent 37/38/39)
- Add Self-Learning System section to README explaining RL algorithms
- Add Why AQE? section with Problem-Solution table
- Remove outdated What's New and Roadmap sections from README
- Fix flaky detection accuracy claim from 100% to 90%+
- Remove unverified SWE-Bench and token reduction claims
- Add qx-partner to agents list in skills and manifest
- Update all user-facing docs with correct counts
- Add docs/PERFORMANCE.md for verified benchmarks
Files updated:
- README.md, CLAUDE.md, FUNDING.md
- docs/reference/{agents,skills,usage}.md
- .agentic-qe/docs/{agents,skills,usage}.md
- .claude/skills/agentic-quality-engineering/SKILL.md
- .claude/skills/cicd-pipeline-qe-orchestrator/README.md
- .claude/skills/skills-manifest.json
- src/cli/init/{agents,database-init}.ts
- src/telemetry/instrumentation/{agent,index}.ts
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-06 21:12:40 +00:00
32ba2ec280
feat(mcp): complete legacy tool removal and deprecation warnings (Issue #115 )
...
Phase 1 Track A - Legacy Removal (COMPLETE):
- Delete 17 legacy handler files (10,433 lines removed)
- Remove legacy tool definitions from tools.ts (100→84 tools)
- Clean up TOOL_NAMES constant
- Update index.ts exports for all affected modules
- Fix server.ts imports
Handlers Deleted:
- src/mcp/handlers/test-generate.ts
- src/mcp/handlers/quality-analyze.ts
- src/mcp/handlers/predict-defects.ts
- src/mcp/handlers/optimize-tests.ts
- src/mcp/handlers/quality/* (5 files)
- src/mcp/handlers/prediction/regression-risk-analyze.ts
- src/mcp/handlers/analysis/performanceBenchmarkRun.ts
- src/mcp/handlers/analysis/performance-benchmark-run-handler.ts
- src/mcp/handlers/advanced/requirements-validate.ts
- src/mcp/handlers/advanced/requirements-generate-bdd.ts
- src/mcp/handlers/security/validate-auth.ts
- src/mcp/handlers/security/check-authz.ts
- src/mcp/handlers/security/scan-dependencies.ts
Phase 4 - Documentation (COMPLETE):
- Add deprecation warnings to kept legacy handlers
- Create migration guide at docs/migration/issue-115-tool-optimization.md
- Update docs/reference/agents.md with tool discovery system
- Update docs/reference/usage.md with lazy loading examples
Metrics:
- Tool count: 100+ → 84 (16% reduction)
- Context reduction: 87% via lazy loading
- Lines removed: 10,433
Closes #115
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-12-06 10:14:40 +00:00
346438f0de
Release v2.0.0: Claude 4.5 Optimization, QUIC Transport, 29 Agent Compaction ( #100 )
...
* SwarmMemoryManager Refactoring Plan
* fix: add missing directories to npm package (v1.9.3)
Added templates/, .claude/helpers/, and docs/reference/ to package.json
files array. These were missing from the npm distribution, causing
`aqe init` to fail with "Template file not found" errors.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
* checkpoint improvements
* fix: critical memory/learning system fixes for v1.9.4
## Critical Fixes
- Vector embeddings now stored correctly (was storing NULL)
- SQL parameter style fixed for agentdb's SqlJsDatabase wrapper
- HNSW index schema mismatch resolved with pattern_id column
- Hooks now save to correct database (.agentic-qe/agentdb.db)
## New Features
- Added 5 SwarmMemoryManager methods for learning data retrieval:
- getBestAction() - Q-learning best action selection
- getRecentLearningExperiences() - Recent experience retrieval
- getLearningExperiencesByTaskType() - Task-filtered experiences
- getHighRewardExperiences() - Successful experience extraction
- getLearningStats() - Aggregate learning statistics
- Added comprehensive integration test for memory/learning loop
- Added RuVector pattern store integration (experimental)
## Technical Details
- Vector embeddings: 384 dimensions × 4 bytes = 1,536 bytes per pattern
- All 12 integration tests pass
- HNSW index: 150x faster vector search enabled
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
* fix: move ARM64-only ruvector packages to optionalDependencies
Fixes CI failures caused by platform-specific dependencies:
- @ruvector/node-linux-arm64-gnu (ARM64 only)
- ruvector-core-linux-arm64-gnu (ARM64 only)
These packages caused npm ci to fail on x64 CI runners with:
"EBADPLATFORM - wanted linux/arm64, current linux/x64"
Solution: Move ARM64 packages to optionalDependencies and add
x64 variants for cross-platform compatibility.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
* chore: regenerate package-lock.json with x64 ruvector packages
Updates lockfile to include optional x64 platform packages for
CI compatibility:
- @ruvector/node-linux-x64-gnu@0.1.17
- ruvector-core-linux-x64-gnu@0.1.15
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
* fix: replace fake QUIC with proper implementation and clean up skills manifest
QUIC Transport:
- Remove fake HTTP/2-based QUICTransport.ts that pretended to be QUIC
- Add proper QUIC implementation via Rust/WASM (@agentic-flow/quic-wasm)
- Add WebSocket fallback transport for when WASM unavailable
- Add dedicated type declarations for optional WASM module
- Features: 0-RTT connection, stream multiplexing, TLS 1.3 built-in
Skills Manifest:
- Rewrite skills-manifest.json with only QE skills (41 skills)
- Remove Claude Flow platform skills (agentdb-*, flow-nexus-*, github-*, etc.)
- Organize into proper categories: qe-core, testing-methodologies, etc.
Bug Fixes:
- Fix UnifiedMemoryCoordinator.ts TypeScript errors
- Use Logger.getInstance() instead of private constructor
- Use swarmMemory.query() instead of non-existent list() method
- Use correct close() method signatures for backends
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
* feat: add QX Partner agent, compact subagents, fix CLAUDE.md dynamic counts
- Add QX Partner agent for Quality Experience analysis combining QA + UX perspectives
- Compact 9 subagent definitions to ~80 lines each (88% reduction)
- Fix CLAUDE.md template to dynamically count agents (including subagents) and skills
- Move CLAUDE.md creation after parallel phases for accurate counts
- Remove 'Production-Ready' claim from README and CHANGELOG
- Clean up backup files and move docs to proper directory
Initialization now correctly reports:
- 31 QE Agents (20 main + 11 subagents)
- 53 QE Skills
- 8 Slash Commands
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
---------
Co-authored-by: Claude <noreply@anthropic.com >
2025-12-02 11:31:30 +01:00
4a58796e83
feat: Add sherlock-review QE skill for evidence-based investigation
...
Add new evidence-based investigative code review skill using Holmesian
deductive reasoning. Focuses on determining what actually happened versus
what was claimed through systematic observation and logical deduction.
New Skill: sherlock-review
- Evidence collection framework and templates
- Deductive reasoning methodology
- Investigation process for bug fixes, features, and performance claims
- Holmesian principles applied to quality engineering
- Integration with existing QE agents (code-reviewer, security-auditor, etc.)
Documentation Updates:
- Updated skill count: 37 → 38 specialized QE skills
- Updated Phase 3: 3 → 4 advanced QE skills
- Added sherlock-review to all documentation (README, CLAUDE.md, skills.md)
- Updated aqe init command to install sherlock-review
- Updated package.json description
Files Changed:
- .claude/skills/sherlock-review/SKILL.md (new, 19.7 KB)
- src/cli/commands/init.ts (added to QE_FLEET_SKILLS array)
- docs/reference/skills.md (Phase 3 section)
- README.md (skill counts and Phase 3 list)
- CLAUDE.md (Quick Reference sections)
- CHANGELOG.md ([Unreleased] section)
- package.json (description)
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-16 08:11:02 +00:00
fb45e5e763
chore: release v1.6.1 - Advanced QE Skills Phase 3
...
## New Features
### 3 New Advanced QE Skills
- six-thinking-hats: Edward de Bono's methodology for comprehensive testing analysis
- brutal-honesty-review: Unvarnished technical criticism for code/test quality
- cicd-pipeline-qe-orchestrator: Complete CI/CD quality orchestration (5 phases, 3 workflows)
### Skills Library Growth
- Phase 1: 18 skills (Original Quality Engineering)
- Phase 2: 16 skills (Expanded QE Library)
- Phase 3: 3 skills (Advanced Quality Engineering) ⭐ NEW
- Total: 37 specialized QE skills (up from 34)
## Changes
### Documentation Updates (10 files)
- CHANGELOG.md: v1.6.1 release notes with comprehensive details
- README.md: Updated version badge, skills count (34→37)
- CLAUDE.md: Updated skills count and names in quick reference
- package.json: Version 1.6.0→1.6.1, description updated
- docs/reference/skills.md: Added Phase 3 section
- docs/reference/usage.md: Updated skills count
- src/cli/commands/init-claude-md-template.ts: New condensed template generator
- CI/CD orchestrator files: Updated all references to 37 skills
### Code Updates
- src/cli/commands/init.ts: Added 3 skills to QE_FLEET_SKILLS array
- Updated validation to check for 37 skills (was 34)
- Updated all documentation comments
### New Files (8 files)
- .claude/skills/six-thinking-hats/SKILL.md (1,215 lines)
- .claude/skills/brutal-honesty-review/SKILL.md (725 lines)
- .claude/skills/cicd-pipeline-qe-orchestrator/SKILL.md (510 lines)
- .claude/skills/cicd-pipeline-qe-orchestrator/README.md (290 lines)
- resources/workflows/microservice-pipeline.md (372 lines)
- resources/workflows/monolith-pipeline.md (389 lines)
- resources/workflows/mobile-pipeline.md (497 lines)
- src/cli/commands/init-claude-md-template.ts (99 lines)
## Testing
- ✅ Build: Compiled successfully with no TypeScript errors
- ✅ Init: `aqe init --yes` successfully copies all 37 skills
- ✅ Verification: All 3 new skill directories created with valid SKILL.md
- ✅ CLAUDE.md: Correctly reports "37 QE Skills" with new skill names
- ✅ Lint: No new linting issues introduced
- ✅ Unit Tests: 898 passed, no new failures related to v1.6.1
## Impact
- Skills Coverage: 95%+ of modern QE practices with advanced frameworks
- CI/CD Integration: Complete pipeline orchestration commit→production
- Critical Thinking: Cognitive frameworks for better testing decisions
- Quality Standards: Brutal honesty approach for technical excellence
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-13 15:57:52 +00:00
Profa