lijian-ui/dsh-vision-toggle ↗★ 0
@lijian-ui/dsh-vision-toggle
Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lijian-ui/dsh-vision-toggle说明文档
阅读完整 README ↗Usage
- Open dsh desktop
- Navigate to Settings → Model Vision (modeled after the other settings sections)
- The section lists every configured model, grouped by provider. Next to each model there is a "Support image" switch:
- On: the model accepts image input; you can now attach images in chat
- Off: the model is text-only
Turning the switch on simply sets that model's
inputto['text', 'image']; turning it off sets it back to['text']. This matches exactly how dsh decides whether a model supports images.