hailin c768e2aa53 fix(agent): stricter max_tokens calculation for response length control ... - Reduce tokensPerChar from 2 to 1.8 for more accurate Chinese token estimation - Use min() instead of max() to enforce upper limits on token counts - CHAT: max 200 tokens (was min 256) - SIMPLE_QUERY: max 600 tokens (was min 512) - CLARIFICATION: max 300 tokens (was min 256) - CONFIRMATION: max 400 tokens (was min 384) - DEEP_CONSULTATION: 800-1600 tokens (was 1024-4096) - ACTION_NEEDED: 500-1000 tokens (was 768-2048) This should result in more concise AI responses that better match the intent classifier's suggested length limits. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>		2026-01-23 08:02:34 -08:00
..
conversation-service	fix(agent): stricter max_tokens calculation for response length control	2026-01-23 08:02:34 -08:00
evolution-service	fix(schema): sync ORM entities with database schema	2026-01-23 05:00:38 -08:00
file-service	fix(file-service): specify explicit column types for TypeORM entities	2026-01-10 06:05:36 -08:00
knowledge-service	fix(knowledge): add pgvector transformer for TypeORM embedding columns	2026-01-23 07:12:28 -08:00
payment-service	fix(payment): use PORT env variable instead of PAYMENT_SERVICE_PORT	2026-01-10 02:48:44 -08:00
user-service	fix(health): exclude /health endpoint from API prefix	2026-01-10 02:30:24 -08:00