asepharyana c7f53e4f7e feat(gateway): remove Jev (System One) analyzer, restore LLM-only text moderation ...

Jev (oc/jev-1.13-free via 9router /v1/systemone) added as primary text
analyzer was underperforming. Delete the whole feature:
- jevAnalyzer.ts + its unit & live-smoke tests
- Jev-first branch in textBatchProcessor, restore pure callModerationLLM path
- AI_LLM_JEV_* config vars (zod) and .env.example entries
- @typesafe-ai/sdk dependency (+ lockfile)

Behavior: text moderation is LLM-only again, exactly as before the
Jev feature; AGENTS.md invariant 'LLM is the only judge' holds.

2026-09-24 12:06:36 +07:00

..

batchBudget.test.ts

perf(ai): kontiguitas batch budget + max_tokens dinamis + urutan kronologis RETURNING

2026-08-22 17:19:41 +07:00

batchOutcomeClassifier.test.ts

feat(discord-gateway): use Discord CDN for image analysis, uploader archive-only

2026-08-28 22:07:37 +07:00

cacheBatchLookup.test.ts

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

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

cacheGuards.test.ts

perf(gmw-ai): cache-hit optimization — bare-key Qdrant upsert + hit_count bump

2026-08-25 12:03:47 +07:00

contextEnrichment.test.ts

fix(ai): pertahankan status warn di cache moderasi + bersihkan prompt stale

2026-08-22 16:17:55 +07:00

conversationContext.test.ts

feat(ai-moderation): enrich analysis context with recency, repetition, user history and channel topic

2026-08-10 17:15:33 +07:00

discordImageKeyNormalize.test.ts

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

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

fallbackResultClassifier.test.ts

feat(discord-gateway): use Discord CDN for image analysis, uploader archive-only

2026-08-28 22:07:37 +07:00

imageCacheKey.test.ts

audit(gateway): fix dead /metrics endpoint, raise OOM-prone MemoryMax, trim DB pool

2026-08-16 08:41:54 +07:00

imageResizer.test.ts

audit(gateway): fix dead /metrics endpoint, raise OOM-prone MemoryMax, trim DB pool

2026-08-16 08:41:54 +07:00

llmChunkExtraction.test.ts

feat(gateway): add manual video-watch command for selfbot screen-share capture

2026-09-02 10:12:03 +07:00

llmE2e.test.ts

test: add live-LLM E2E moderation test suite

2026-09-18 21:27:06 +07:00

llmThinkingDisable.test.ts

audit(gateway): fix dead /metrics endpoint, raise OOM-prone MemoryMax, trim DB pool

2026-08-16 08:41:54 +07:00

moderationScoreOptional.test.ts

fix(gateway): make moderation score optional — LLM omits it in media batches

2026-09-02 13:15:05 +07:00

nicknameEnforcement.test.ts

fix(moderation): enforcement safety net — username-only offense never auto-deleted

2026-09-03 20:39:17 +07:00

qdrantEnsure.test.ts

fix(gateway): local infra defaults + qdrant collection retry-on-failure

2026-09-02 12:57:54 +07:00

storedStatusNormalization.test.ts

fix(ai): pertahankan status warn di cache moderasi + bersihkan prompt stale

2026-08-22 16:17:55 +07:00

termGlossary.test.ts

feat(glossary): implement term glossary for LLM moderation with caching and extraction logic

2026-08-12 13:44:52 +07:00

tinyFishSearch.test.ts

feat(gateway): tinyfish web search as fallback when wikipedia misses

2026-09-14 00:44:38 +07:00

visionNoImageSeen.test.ts

chore: migrate AI LLM router from 9router to omniroute

2026-08-28 20:18:48 +07:00

wikipediaSearchQueries.test.ts

feat(gateway): refactor term extraction and scoring logic into textSignals.ts for reuse

2026-08-31 22:59:27 +07:00