bcb563ea7f2faa2729427553e71d715dfd19f5fc
- 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
Description
Bete Discord moderation watcher
27 MiB
Languages
TypeScript
96.9%
Nix
1.2%
Shell
0.9%
CSS
0.5%
PLpgSQL
0.5%