# dsh-vision-bridge

> DeepSeek Harness 多模态视觉桥（dsh-vision-bridge）：贴图经 llm/stream 自动转 VL 文字描述（解决 UNSUPPORTED_CONTENT）+ view_image/ocr_image 主动视觉工具 + 原生多模态路由自动跳过（rc.7）；零依赖。Vision bridge for text-only DeepSeek models.

## Metadata

- Author: [@DreamRift](https://github.com/DreamRift)
- Repo: <https://github.com/DreamRift/dsh-vision-bridge>
- GitHub: [DreamRift/dsh-vision-bridge](https://github.com/DreamRift/dsh-vision-bridge)
- Stars: 0
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `dashscope`, `deepseek-harness`, `dsh`, `dsh-plugin`, `llm`, `multimodal`, `ocr`, `qwen-vl`, `vision`, `vision-language-model`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-18T12:38:08.000Z
- Added: 2026-08-18T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add github:DreamRift/dsh-vision-bridge
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-vision-bridge](https://deepseek-plugin.org/plugins/DreamRift/dsh-vision-bridge)