perf(ai-moderation): naikkan cache hit dgn guard akurasi

Browse Source

- Fase-1 exact-cache lookup: N query serial -> SATU query ANY($1::text[])
- Global reuse utk bare key legacy, HANYA verdict non-actionable
  (clean/flagless/action=none, conf>=0.85, umur<=72h) — flagged/warn
  tetap context-scoped
- Semantic cache dua-band: clean band 0.92 default, actionable tetap
  0.97; di antara band -> LLM (fail-open ke akurasi)
- hit_count kini di-increment (bulk UPDATE per batch) -> hit-rate terukur
- Cache hasil wikipediaSearch di Redis (6h, hanya hasil non-kosong)
- Memoize fetchUrlSafely utk type=text (LRU 30m + in-flight dedupe)
- makeImageCacheKey strip query CDN Discord (?ex/is/hm, format/width)
  -> attachment sama = satu key vision, skip re-download+re-vision

Spec: .hermes/plans/2026-08-24-ai-analysis-cache-optimization.md
Tests: +33 (cacheGuards, discordImageKeyNormalize, cacheBatchLookup)

...

This commit is contained in:

asepharyana

2026-08-24 18:51:23 +07:00

parent 440ec41da8

commit 1accfd9390

11 changed files with 1297 additions and 112 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

.hermes/plans/2026-08-24_135602-gmw-fe-constellation-rombak.md

+205

File diff suppressed because one or more lines are too long