DSH插件商店

dsh-llm-vision-bridge

Einskyle

DeepSeek vision bridge for dsh: route image attachments to a vision model (Qwen3-VL via pi-ai/llama.cpp) and continue on a text-only LLM (DeepSeek)

text-llm-vision

shaoqiuyuavailable

Scene-aware vision routing layer for DeepSeek Harness (dsh): decides which engine/backend an image should go to (chat/UI/table/code) before other vision plugins route it. Switch-gated, front-loaded, never touches other plugins' tools. 场景级识图路由层。

dsh-tool-vision-read

Mappedinfo

DSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see images