hailin ba83e433d3 feat: enable OpenAI Realtime STT for streaming speech recognition ... Switch from batch STT (gpt-4o-transcribe via /audio/transcriptions) to streaming Realtime API (WebSocket). This eliminates the ~2s batch upload+process latency per utterance. Also updated nginx proxy on 67.223.119.33 to support WebSocket upgrade for /v1/realtime endpoint. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-01 07:49:25 -08:00
..
agent-service	fix: increase body parser limit to 50mb for large PDF uploads	2026-02-28 05:35:43 -08:00
audit-service	fix: release QueryRunner connections to prevent pool exhaustion	2026-02-23 15:55:06 -08:00
auth-service	feat: complete tenant member management (CRUD + delete tenant)	2026-02-26 10:00:09 -08:00
comm-service	fix: release QueryRunner connections to prevent pool exhaustion	2026-02-23 15:55:06 -08:00
inventory-service	fix: set tenantId when creating credentials in inventory-service	2026-02-26 10:52:14 -08:00
monitor-service	fix: release QueryRunner connections to prevent pool exhaustion	2026-02-23 15:55:06 -08:00
ops-service	fix: release QueryRunner connections to prevent pool exhaustion	2026-02-23 15:55:06 -08:00
voice-agent	feat: enable OpenAI Realtime STT for streaming speech recognition	2026-03-01 07:49:25 -08:00
voice-service	fix: use livekit-api package for voice-service token endpoint	2026-02-28 09:49:11 -08:00