mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
4f88b7cb3f
Fix MCP persistence pipeline so test_outcomes and coverage_sessions receive data from live tool calls. Add Priority 2 instrumentation: routing tier tags, HNSW/FTS5 search latency, token tracker auto-save, and pipeline step timers. Collect baseline snapshots for all Tier 3 metrics. Key changes: - Fix handler-factory Step 5d: wire recordDomainFeedback into feedback loop - Add getQualityFeedbackLoop singleton for cross-module access - Graceful degradation for optional native modules (FlashAttention, DecisionTransformer) - Add experience embedding computation on capture - Add model_tier column to routing_outcomes with tier inference - Add performance.now() timing to HNSW search and FTS5 searchFTS - Activate TokenMetricsCollector DB persistence and auto-save on init - Add per-step latencies to TestSchedulingPipeline result - WAL checkpoint in brain-checkpoint before RVF export - Baseline docs and JSON for Tier 3 benchmark comparison Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>