memoryweave/go/internal/storage
小唯 72cbf73583 feat: P0 recall fallback + P2 trust scoring for graph edges
P0: When bge-embed/IPC recall fails, fall back to graph.db keyword search (FallbackTextSearch) instead of 500 error. Response includes X-Fallback: graph header.

P2: Add trust_score, retrieval_count, helpful_count columns to graph_edges table. New POST /api/v1/graph/edge/feedback endpoint. UpdateEdgeTrustScores batch calculation.
2026-07-02 00:22:28 +08:00
..
bench_test.go
cooccur.go
embedder.go storage/embedder: 支持 MODEL_NAME 环境变量指定 embedding 模型 2026-06-06 18:22:40 +08:00
graph_cache.go feat: P0 recall fallback + P2 trust scoring for graph edges 2026-07-02 00:22:28 +08:00
lancedb.go G7.1+G7.2: skill persistence + crystallize API 2026-06-02 00:01:59 +08:00
lancedb_ipc.go fix G7 E3: crystallize路由路径+GetSkillCandidates通过Rust IPC查LanceDB 2026-06-02 04:19:58 +08:00
memvector.go G7.1+G7.2: skill persistence + crystallize API 2026-06-02 00:01:59 +08:00
recall.go feat: add freshness field to memory lifecycle 2026-06-15 10:39:15 +08:00
redis.go G7.1: skill persistence - BayesianSkillManager Redis + CRUD API 2026-06-01 23:44:36 +08:00
reranker.go
searchcache.go G8: Restore+ListBackups 端点;G9: SearchCache 双级缓存(内存+Redis L2) 2026-06-02 11:43:34 +08:00
sqlite.go G7.1+G7.2: skill persistence + crystallize API 2026-06-02 00:01:59 +08:00
sqlite_mem.go fix: add clusters_found/noise_points/quality_score to consolidate API response 2026-06-08 10:35:10 +08:00