6 Commits

Author	SHA1	Message	Date
john	6d48480b1c	Improve cross_device MemFuse recall with source tags and recallContext. ... Auto-enable device/location prefixes for cross_device scenarios, thread question_device into keyword and embedding paths, and boost lexical scores from source-tag tokens. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-02 14:12:48 +08:00
john	fb3a442e73	Improve MemFuse recall via hybrid ranking and candidate generation. ... Add RRF fusion with English word-level lexical scoring, tiered keyword fetch, and vector margin expansion (0.15/200) to fix pre-rank truncation; wire DashScope embedding bench path and update baseline to 28.8% recall@20. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-02 13:41:12 +08:00
john	2c0d903ecf	Improve pgvector keyword recall ranking without changing hybrid sort. ... Rank ILIKE matches by lexical coverage instead of recency and attach lexical scores to keyword rows so MemFuseBench candidate recall rises sharply while Chinese hybrid ordering stays unchanged. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-02 10:01:42 +08:00
john	dcf83e9b6f	fix(memory-v2): improve pgvector recall and WeChat memory injection ... Add keyword fallback and dedupe for pgvector resolve, score personal vs episodic memories by relevance, record WeChat recall product events, and disable broken chatrecall on Postgres session storage. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-01 22:26:47 +08:00
john	d52aab8ab0	fix(memory): add bounded hybrid recall	2026-07-22 11:15:00 +08:00
john	20116b161f	Merge Memory V2 runtime facade	2026-07-03 09:46:03 +08:00