mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
Dragan Spiridonov
a9f7082f15
Closes 11 findings from a post-merge audit of the external embedder endpoint implementation. The "no silent hash fallback" correctness promise was being contradicted by two callers; the connect timeout was actually an idle timeout; the identity probe could be bypassed in several paths; and identity drift across runs was undetectable. All hardened. Critical/High fixes: - sqlite-persistence backfill no longer falls back to hash embeddings when the endpoint is configured; re-raises to protect the HNSW index from non-comparable vectors (was poisoning silently on every endpoint blip). - qe-reasoning-bank.embed() propagates the throw under isUsingEndpoint() instead of silently substituting a hash vector. - EmbedderEndpointClient.embed() now gates on probe() — lazy probe on first use with in-flight dedup so 20+ concurrent embeds share one probe. - Circuit breaker recovery (window expires) clears cached identity so the next embed re-probes — endpoint restarts often coincide with model swaps. - True TCP-connect timeout enforced at the socket layer (was req.setTimeout, which is an idle-after-write timeout — SYN blackholes hung ~75s instead of 5s). - Endpoint identity persisted to memory.db kv_store (_system namespace) — cross- run fingerprint drift now surfaces as a loud warning on next boot. Medium fixes: - encoding_format: 'float' pinned in request; base64 responses fail loud. - TLS knobs (ca, cert, key, rejectUnauthorized, servername) passthrough for self-hosted https endpoints without NODE_TLS_REJECT_UNAUTHORIZED=0. - URL userinfo stripped + warned at parse; redacted from all error messages and logs. - Embedding cache key namespaced by mode (endpoint:<fingerprint>:<text> vs inproc:<text>) — cross-mode collisions structurally impossible. Tests: - 33 unit tests pass (was 23): adds probe-gate, breaker re-probe, connect timeout, DNS failure, concurrent embed dedup, base64 fail-loud, URL redaction, encoding_format wire format. - 6 live integration tests against real llama-server (all-MiniLM-L6-v2.Q8_0.gguf): probe, single embed, batch, lazy probe gate, dim mismatch, 50-input batch. Replaces the prior "9ms in-process fake" with honest numbers (cold 15ms, warm 2ms against localhost llama.cpp). - New tests/integration/embedder-endpoint-llamacpp.test.ts is gated on AQE_LLAMA_EMBED_URL so it skips cleanly in CI without the binary. ADR-097 updated with the per-caller audit table (12 writers verified non-poisoning) and "drop-in for 6 providers" claim softened to "verified against llama-server; OpenAI shape compat expected but unverified" per provider. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Agentic QE v3 Implementation Documentation
This directory contains all implementation documentation, planning, and research for Agentic QE v3.
Directory Structure
implementation/
├── adrs/ # Architecture Decision Records
├── architecture/ # Architecture diagrams & analysis
├── planning/ # Master plans & implementation strategies
├── security/ # Security considerations
└── agents/ # Agent specifications
Document Index
ADRs (Architecture Decision Records)
| Document | Description |
|---|---|
| v3-adrs.md | All 10 ADRs (001-010) master document |
Planning
| Document | Description |
|---|---|
| AQE-V3-MASTER-PLAN.md | Complete v3 master plan with DDD architecture |
Quick Links
- Skills: /.claude/skills/v3-qe-ddd-architecture/
- Agents: /.claude/agents/v3/
- Source (future): /v3/src/ - v3 source code (to be implemented)
Key Concepts
Domain-Driven Design for QE
Agentic QE v3 uses DDD with 6 bounded contexts:
- Test Generation - AI-powered test creation
- Test Execution - Parallel execution and retry
- Coverage Analysis - O(log n) gap detection
- Quality Assessment - Quality gates and metrics
- Defect Intelligence - Prediction and analysis
- Learning Optimization - Pattern learning and transfer
Agent Hierarchy
21 specialized v3 agents organized hierarchically:
- Queen Coordinator (orchestration)
- Test Generation Group (4 agents)
- Quality Gates Group (3 agents)
- Intelligence Group (3 agents)
- Execution Group (3 agents)
- Coverage Group (3 agents)
- Learning Group (4 agents)
Key ADRs
| ADR | Decision |
|---|---|
| ADR-001 | Adopt DDD for QE bounded contexts |
| ADR-002 | Event-driven domain communication |
| ADR-003 | Sublinear O(log n) coverage analysis |
| ADR-004 | Plugin architecture for extensions |
| ADR-005 | AI-first test generation |
Getting Started
# Use v3 DDD skill
Task("Analyze QE architecture",
"Design DDD bounded contexts for quality engineering",
"system-architect")
# Use v3 Queen Coordinator
Task("Orchestrate QE workflow",
"Coordinate full quality engineering workflow",
"v3-qe-queen-coordinator")
# Use v3 Test Architect
Task("Generate tests",
"Create AI-powered test suite for UserService",
"v3-qe-test-architect")
Last Updated: 2026-01-07 Version: 1.0.0