dsh plugin --profile web add github:niuniuaba/dsh-subagent-vision
dsh plugin --profile web add git+https://github.com/niuniuaba/dsh-subagent-vision.git
dsh plugin --profile web add /path/to/plugins/dsh-subagent-vision
Plugins in this repository
dsh-subagent-visionv0.1.4✓
dsh bundle: subagent_vision — delegate image reading to a vision-capable model from a text-only session, plus paste-to-path so pasted images reach the subagent as file paths.
A DeepSeek Harness bundle plugin that lets a text-only main agent (DeepSeek) read images in the same session — no model switching, no second session, no copy-paste. When a task needs vision, the main agent delegates to a fresh subagent routed to a vision-capable model you pick in the settings (configured under Settings Models, chosen under Settings 视觉处理模型; the factory default is qwen3.8-max — see Configure), and the child's text result is merged back. The image itself never reaches the main mode
Repository check result
Results are bound to the listed commit and cover only static checks run by this registry. The Evidence Score measures reviewable information; it is not a compatibility percentage or a security guarantee.