MythEclipse 0eee7b9390 fix: cap AI batch size and split failed batches ...

Reduce effective AI batch size so streaming requests finish before timeout. Keep token-based batching but cap each request to 80 messages or about 9k content tokens, and recursively split failed batches instead of marking the whole batch failed.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-14 04:48:20 +07:00

..

aiAnalyzer.ts

fix: cap AI batch size and split failed batches

2026-05-14 04:48:20 +07:00

attachmentUploader.ts

refactor: replace Database type with SqliteDatabase in moderation modules

2026-05-13 19:47:44 +07:00

backlogSync.ts

feat: add API endpoint for syncing selected channel backlog

2026-05-14 04:02:25 +07:00

messageCapture.ts

fix: remove Picser upload, use Discord URLs directly

2026-05-14 03:51:48 +07:00

messageMetadata.ts

feat(moderation): implement backlog message synchronization and enhance message metadata handling

2026-05-13 21:04:45 +07:00

messageStore.ts

feat: add warn category for minor rule violations

2026-05-14 04:23:11 +07:00

types.ts

feat: add warn category for minor rule violations

2026-05-14 04:23:11 +07:00