Fabio Scarsi fc9534876f fix(search): wire search_skills to SkillRanker embedding cache ... Both paths in search_skills/hybrid_search_skills now go through a shared SkillRanker singleton: - SkillSearchEngine._bm25_phase: previously instantiated a fresh SkillRanker per call, reloading the pickle cache each time. - hybrid_search_skills candidate loop: previously generated embeddings via generate_embedding on every query, ignoring the persistent cache entirely. The persistent pickle at .openspace/skill_embedding_cache/skill_embeddings_v1.pkl is reused across invocations and survives process restarts. Candidates without a stable skill_id are skipped to avoid cache key collisions. On a 28-skill local registry with text-embedding-3-small via OpenRouter, query latency drops from 8-14s to ~300ms after warm-up. Top-1 match identity is preserved on all test queries (score drift <0.001). Cloud candidates that already carry _embedding from the server-side search endpoint are skipped and unchanged.		2026-04-18 11:52:15 +02:00
..
cli	initial commit	2026-03-24 16:03:22 +08:00
__init__.py	initial commit	2026-03-24 16:03:22 +08:00
auth.py	initial commit	2026-03-24 16:03:22 +08:00
client.py	Fix cloud visibility compatibility	2026-04-09 22:36:09 +08:00
embedding.py	initial commit	2026-03-24 16:03:22 +08:00
search.py	fix(search): wire search_skills to SkillRanker embedding cache	2026-04-18 11:52:15 +02:00