asepharyana bcb563ea7f feat(vision): route multimodal analysis to dedicated NVIDIA direct endpoint ...

- config: add AI_LLM_VISION_BASE_URL + AI_LLM_VISION_API_KEY (separate from text router)
- llmClient: llmVision() now calls dedicated vision endpoint when configured
  (axios POST to integrate.api.nvidia.com, model nvidia/nemotron-3-nano-omni-30b-a3b-reasoning,
  reasoning_budget 16384, non-stream), falls back to router combo otherwise
- keeps text/moderation on omniroute, vision on NVIDIA direct

2026-08-15 14:31:53 +07:00

..

config

feat(vision): route multimodal analysis to dedicated NVIDIA direct endpoint

2026-08-15 14:31:53 +07:00

database

feat(glossary): persist resolved definitions in Postgres + harden live SearXNG lookups

2026-08-12 14:22:22 +07:00

discord

refactor: split monolith into 3 microservices (frontend, backend, discord-gateway)

2026-06-01 21:44:29 +07:00

errors

refactor: break monorepo into 3 standalone services (gateway, backend, frontend)

2026-07-30 11:50:48 +07:00

logger

refactor: break monorepo into 3 standalone services (gateway, backend, frontend)

2026-07-30 11:50:48 +07:00

utils

fix(goLive): retry VIDEO(op12)/SPEAKING(op5) opcodes until ws OPEN — broken shared-screen video

2026-08-13 01:44:40 +07:00

index.ts

refactor: break monorepo into 3 standalone services (gateway, backend, frontend)

2026-07-30 11:50:48 +07:00

moderation-types.ts

feat(ai-moderation): reset offensive nickname instead of deleting message

2026-08-10 11:48:27 +07:00

redis-channels.ts

feat(media): loop mode + high-quality OggOpus music playback

2026-08-07 14:53:37 +07:00

uploader.ts

refactor: break monorepo into 3 standalone services (gateway, backend, frontend)

2026-07-30 11:50:48 +07:00