Overview
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 / EN
Package documentation
Registry summary
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 verifies the pinned bundle contract, runtime facts, and distribution semantics. The complete README remains in the source repository.
Read the full README on GitHub