1.8 KiB
1.8 KiB
| id | type | title | tags | importance | confidence | created | updated | relations | |||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ab3ffc18-1707-42ff-ad7e-bffb16f6fdef | insight | Auto-edge implementation: design analysis findings and fixes |
|
0.7 | 0.8 | 2026-03-01T04:12:45.563773+00:00 | 2026-03-01T04:13:13.331186+00:00 |
|
Auto-edge Implementation: Design Analysis Findings and Fixes
Issues Found and Fixed
-
Similarity threshold bypass — keyword-only results lack a
"similarity"key, soif similarity is not Nonealways short-circuited the threshold check. Fixed by requiring tag overlap for the keyword-only path instead. -
Backwards description arrow — The
→in the edge description could point the wrong direction when a heuristic reversed from/to. Fixed by building the description string after direction resolution. -
Wasted slice slots —
[:AUTO_EDGE_MAX]slice happened before threshold filtering, consuming slots on results that would later be rejected. Fixed by filter-then-slice ordering. -
Weak recall query — Title-only recall gave weak signal. Fixed by concatenating tags into the query string.
Deferred Issues (Not Fixed This Session)
- Git commit batching in
relate()(issue #2) - Semantic recall surfacing dormant memories (issue #3)