Gate recall on the margin over the runner-up, not just the score

The e5 embedder puts every cosine in one narrow band (0.79-0.89), so the absolute query_min_score gate cannot tell a real hit from a made-up question: any value under the band answers everything, any value above it answers nothing. False recall was 5/5. New gate asks whether one note is clearly the best instead: top1 - top2 > delta. New query_min_margin config knob, default 0.008, read off the sweep in the recall harness. The absolute floor stays as a second check. On the recall fixture with e5: answered 72% -> 68%, false recall 5/5 -> 1/5. Vikunja #359 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 11:50:39 +04:00
parent 34521c30b8
commit 11831c6ace
9 changed files with 237 additions and 50 deletions
@@ -41,6 +41,8 @@
      "lib_path": "/opt/maven/lib/libonnxruntime.so"
    },
    "llm_router": false,
+    "query_min_score": 0.55,
+    "query_min_margin": 0.008,
    "tool_timeout": "30s",
    "tools": [
      { "name": "status",     "cmd": ["systemctl", "status"],         "scope": "homelab", "destructive": false },