BREAKING CHANGE: Network policies are now permissive by default
Previously, all agents had restrictive domain whitelisting enabled by
default (blockUnknownDomains: true), which blocked access to:
- Multi-model router's 8+ LLM providers (only Anthropic was allowed)
- Arbitrary websites needed for QE testing purposes
Changes:
- Default policies now use blockUnknownDomains: false (permissive)
- Rate limiting still applies for protection
- Audit logging enabled by default for visibility
- Added LLM_PROVIDER_DOMAINS constant with 15 provider domains
- Added createRestrictivePolicy() for opt-in security when needed
- Added enableRestrictiveModeGlobally() for secure deployments
For security-sensitive deployments, use:
```typescript
// Option 1: Per-agent restrictive policy
const policy = createRestrictivePolicy('qe-test-generator', ['custom.api.com']);
manager.registerPolicy(policy);
// Option 2: Global restrictive mode
enableRestrictiveModeGlobally();
```
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Major Features:
- Nervous System Integration: BTSP learning, HDC memory, circadian cycling,
global workspace attention - all QE agents now benefit automatically
- Supabase Cloud Persistence: HybridPersistenceProvider with local-first
storage and background cloud sync, full CLI commands (aqe supabase)
- Migration Support: Transfer local SQLite data to Supabase cloud
Changes:
- BaseAgent: Auto-initializes nervous system components
- Persistence: New IPersistenceProvider interface with adapters
- CLI: Added supabase subcommands (setup, test, status, sync, schema)
- Version bump to 2.8.1 across all files
Tests:
- 41 nervous system integration tests (all passing)
- BaseAgent.nervous-system.test.ts validates HDC, BTSP, workspace
Closes#188 (MCP tool handlers implemented in previous commit)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Comprehensive 6-phase plan to transform web dashboard into a compute
contribution platform based on analysis of ruvector/edge-net:
- Phase 1: Zustand state management migration
- Phase 2: Credit economy system
- Phase 3: WASM task execution
- Phase 4: Cryptographic identity
- Phase 5: Enhanced UI with HeroUI
- Phase 6: Backend infrastructure
Related: #186🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add comprehensive use cases guide explaining dashboard limitations
- Fix P2P connection bug: connect to discovered peers, not random IDs
- Add webapp package.json with Vite/React dependencies for dev server
The dashboard is for monitoring and pattern sharing, NOT local code
generation. Local QE work requires CLI or VS Code Extension due to
browser sandbox restrictions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
VS Code Extension Fixes:
- Fix @ruvector/edge missing in VSIX by updating .vscodeignore
- Add fallback mode in EdgeAgentService for when WASM unavailable
- Complete fallback implementation with brute-force cosine search
Marketplace Publishing Assets:
- Add README.md with features, commands, settings documentation
- Add CHANGELOG.md with version history (0.1.0, 0.2.0)
- Add LICENSE (MIT)
- Add 128x128 PNG icon with gradient design
- Add icon and galleryBanner to package.json
Documentation:
- Add vscode-extension-publishing.md guide with step-by-step instructions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
### Added
- C4 diagram builders for context, container, and component levels
- ProjectMetadataAnalyzer for system type inference from package.json/docker-compose
- ExternalSystemDetector for database, API, cache, and queue detection
- ComponentBoundaryAnalyzer for layer and relationship mapping
- CLI commands: `aqe kg c4-context`, `aqe kg c4-container`, `aqe kg c4-component`
- CodeIntelligenceAgent c4-diagrams capability
- 22 unit tests for C4 diagram builders
### Changed
- MermaidGenerator with static C4 generation methods
- Type consolidation in src/code-intelligence/inference/types.ts
- Standardized ComponentRelationship to use sourceId/targetId
- Updated qe-code-intelligence.md with C4 capabilities and examples
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
## 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>
- Update README.md: 19 → 21 QE agents, add token reduction benefit
- Add link to benchmark results in quickstart guide
- Highlight 80% token reduction as key feature
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
## Wave 1: Database Foundation
- Add SQL schema for code_chunks, code_entities, entity_relationships
- Use RuVector 768-dim embeddings (not pgvector)
- Implement hybrid_code_search function (BM25 + vector)
- Add pg_trgm extension for full-text search
- Create setup scripts for Ollama/nomic-embed-text
## Wave 2: Multi-Language Parser
- Implement TreeSitterParser with 5 language support
- Add language-specific extractors (TS, Python, Go, Rust, JS)
- Implement incremental parsing with tree caching
- Create comprehensive test suite with fixtures
## Architecture Decision
- Defer Apache AGE to v2 (see ADR-002)
- Use SQL tables for graph relationships
- Rationale: Lower complexity, team familiarity, sufficient for v1
Closes#159, Closes#160🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 0.5: Universal RuVector Integration (v2.5.9)
## Agent Architecture Migration
- **CoverageAnalyzerAgent**: Migrated from EventEmitter to extend BaseAgent
- Full RuVector integration with HybridRouter support
- Implements abstract methods: initializeComponents(), performTask(), loadKnowledge(), cleanup()
- New getCoverageStatus() method for agent-specific status
- Configuration via CoverageAnalyzerConfig extending BaseAgentConfig
- **QualityGateAgent**: Migrated from EventEmitter to extend BaseAgent
- Full RuVector integration with HybridRouter support
- Implements abstract methods: initializeComponents(), performTask(), loadKnowledge(), cleanup()
- New getQualityGateStatus() method for agent-specific status
- Configuration via QualityGateConfig extending BaseAgentConfig
## RuVector Methods Now Available on All Agents
All QE agents now inherit these methods from BaseAgent:
- hasRuVectorCache() - Check if RuVector GNN cache is enabled
- getRuVectorMetrics() - Get GNN/LoRA/cache performance metrics
- getCacheHitRate() - Get cache hit rate (0-1)
- getRoutingStats() - Get routing decisions and latency statistics
- forceRuVectorLearn() - Trigger LoRA learning consolidation
- getCostSavingsReport() - Get cost savings from caching
- getLLMStats() - Get LLM provider status including RuVector
## Other Changes
- Updated QEAgentFactory to use new single-config constructor pattern
- Added 6 RuVector MCP tools for external integration
- Updated verification script - All 6 tests pass
- Added BaseAgent.RuVector.test.ts unit tests
- Added ruvector-agent-usage.ts example
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Restores 225 report files that were previously removed in cleanup.
These reports are present in upstream main and should be preserved.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This PR adds a comprehensive suite of 10+ n8n workflow testing agents:
Core Agents:
- N8nWorkflowExecutorAgent: Execute workflows with data validation
- N8nPerformanceTesterAgent: Load/stress testing with metrics
- N8nChaosTesterAgent: Fault injection with N8nTestHarness
- N8nBDDScenarioTesterAgent: Cucumber-style BDD testing
- N8nSecurityAuditorAgent: 40+ secret patterns, runtime leak detection
- N8nExpressionValidatorAgent: Safe expression validation (no eval)
- N8nIntegrationTestAgent: Real API connectivity testing
- N8nTriggerTestAgent: Webhook testing with correct URL patterns
- N8nComplianceValidatorAgent: GDPR/HIPAA/SOC2/PCI-DSS checks
- N8nMonitoringValidatorAgent: SLA compliance and metrics
Key Features:
- Runtime execution is DEFAULT (not opt-in)
- Real workflow execution, not just static analysis
- Proper n8n webhook URL patterns (/webhook/<path>, /webhook-test/<workflowId>/<path>)
- Safe expression evaluation using pattern matching (no unsafe eval)
- Dual authentication support (API key + session fallback)
- Graceful fallback with warnings if execution fails
⚠️ IMPORTANT: These agents need to be tested against a real n8n instance
before marking them as final. See docs/guides/n8n-real-instance-setup.md
for setup instructions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove Audi Q3/Sportback references from test files
- Update scan-comprehensive.ts with generic examples
- Update video-vision-analyzer.ts with generic vehicle example
- Delete docs/accessibility/ folder with brand-specific content
- Update enhancement plan with generic test references
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update agent description to emphasize copy-paste ready fixes
- Document video frame analysis workflow using Claude Code native vision
- Add comprehensive WebVTT caption generation for WCAG 1.2.x compliance
- Include audio descriptions for blind/visually impaired users
- Add Audi Q3 Sportback video accessibility test artifacts:
- 10 extracted frames from walkaround video
- English and German WebVTT captions
- Detailed audio descriptions
- WCAG compliance audit report
Key developer benefits:
- Every violation includes ready-to-use code fixes
- Video accessibility content generated automatically
- Context-aware ARIA labels (not generic suggestions)
- Zero-cost video analysis via Claude vision or Ollama
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Profa