mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
Dragan Spiridonov
53ee377aec
Full remediation of docs/analysis/SYSTEM-INTEGRITY-AUDIT-2026-07-04.md's P0-P2 findings, tracked in docs/plans/SYSTEM-INTEGRITY-REMEDIATION-GOAP-PLAN-2026-07-04.md. Highlights: - Dream engine: real pattern creation on insight apply, error/outcome concept nodes from real ADR-110 data, and a follow-up fix ensuring the concept refresh actually runs on the real automatic path (not just via test wrappers); persistTaskOutcome now genuinely promotes pending insights instead of blindly incrementing an applied counter - Witness chain: Ed25519 signing wired via persistent key directory, archival/append-after-archival bug fixed, CI verification gate added - Mincut: real event-bus wiring (was a no-op stub) and scaffold-vertex detection fixes - GOAP: real domain-API dispatch executor replacing the always-mock one - SONA: EWC++ cold-start deadlock fixed via independent request-count persistence - ADR-110 pattern-nulls wired into the real production capture path - Daemon/snapshot visibility, TTL unit bugs, and 8 ADRs re-statused with additive verification notes Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Agentic QE v3 Documentation
Welcome to Agentic QE v3 - a complete architectural reimagining with Domain-Driven Design, 12 bounded contexts, 47+ specialized agents, and AI-first quality engineering.
What's New in v3
| Feature | v2 | v3 |
|---|---|---|
| Architecture | Flat structure | 12 DDD bounded contexts |
| Agents | 22 QE agents | 47+ specialized agents |
| Communication | Direct calls | Event-driven |
| Coverage Analysis | O(n) | O(log n) with HNSW |
| Learning | Per-agent | Unified cross-domain |
| Coordination | Manual | Hierarchical auto-coordination |
Quick Links
Getting Started
Architecture
Domains (12 Bounded Contexts)
- Domain Index
- Test Generation
- Test Execution
- Coverage Analysis
- Quality Assessment
- Defect Intelligence
- Code Intelligence
- Requirements Validation
- Security Compliance
- Contract Testing
- Visual Accessibility
- Chaos Resilience
- Learning Optimization
Agents
Reference
Key Metrics
| Metric | Target |
|---|---|
| Coverage analysis | O(log n) - 100x faster |
| Generated test validity | >80% |
| Defect prediction accuracy | >85% |
| Max concurrent agents | 15 |
| Sprint improvement | 15%/sprint |
Version
- Current: v3.0.0-alpha
- Architecture: 12 DDD Bounded Contexts
- Agents: 47+ (71 definitions)
- Skills: 21 v3-specific skills
- Protocols: 6 coordination protocols