hailin db8617dda8 refactor(agents): remove per-intent hard truncation, keep 2000-char safety net ... Hard-coded INTENT_MAX_ANSWER_LENGTH limits caused mid-sentence truncation and content loss. Length control now relies on prompt + schema description + LLM-Judge (3 layers). Only a 2000-char safety net remains for extreme edge cases. Also simplified followUp: non-question followUp is now always appended (prevents model content split from silently dropping text). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-07 10:32:53 -08:00
..
conversation-service	refactor(agents): remove per-intent hard truncation, keep 2000-char safety net	2026-02-07 10:32:53 -08:00
docling-service	fix(docling): align volume mount with HF default cache path	2026-02-07 07:38:28 -08:00
evolution-service	fix(analytics): handle statDate as string from database	2026-01-26 08:40:09 -08:00
file-service	fix(files): replace MinIO presigned URLs with API proxy + base64 for Claude	2026-02-07 04:49:39 -08:00
knowledge-service	feat(knowledge): add Docling document parsing microservice	2026-02-07 05:24:10 -08:00
payment-service	fix(tenant): use TenantContextModule.forRoot() for global tenant context	2026-01-26 04:31:56 -08:00
user-service	fix(nginx): fix admin location try_files path and add multi-tenancy migrations	2026-01-26 07:46:52 -08:00