概览
dsh-image-vision
Seamless image understanding for DeepSeek Harness: lets pure-text models read pasted/dropped images and Feishu/Lark images via a configurable vision model, without touching the host.
README / ZH
插件文档
目录摘要
Seamless image understanding for DeepSeek Harness: lets pure-text models read pasted/dropped images and Feishu/Lark images via a configurable vision model, without touching the host.
dsh.pub 核对固定版本的组合包契约、运行时事实与分发语义；完整 README 请查看源仓库。
在 GitHub 阅读完整 README