dsh-llm-vision-bridge

{
  "name": "dsh-llm-vision-bridge",
  "owner": "Einskyle",
  "category": "tools",
  "description": "Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.",
  "descriptionZh": "DeepSeek 视觉桥接：注册原生 LLM provider，聊天内粘贴的图片自动由视觉模型（pi-ai/llama.cpp 上的 Qwen3-VL）转成文字描述后交给纯文本 DeepSeek 作答——图片准入、路由与会话压缩全部走 harness 原生机制，带 LRU 描述缓存与 503 重试。",
  "install": "dsh plugin --profile web add dsh-llm-vision-bridge",
  "npm": "dsh-llm-vision-bridge",
  "stars": 1,
  "added": "2026-08-14",
  "source": "registry"
}