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
S
Description
Bete Discord moderation watcher
29 MiB
Languages
TypeScript 95.8%
CSS 1.4%
Shell 1%
Nix 0.9%
PLpgSQL 0.5%
Other 0.4%