# dsh-vision-bridge

> Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????

## Metadata

- Author: [@ximengxiaolan](https://github.com/ximengxiaolan)
- Repo: <https://github.com/ximengxiaolan/dsh-vision-bridge>
- GitHub: [ximengxiaolan/dsh-vision-bridge](https://github.com/ximengxiaolan/dsh-vision-bridge)
- Stars: 3
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh`, `dsh-plugin`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-14T08:30:21.000Z
- Added: 2026-08-14T00:00:00.000Z

## Install

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