# dsh-analyze-image-tool

> 给纯文本 DeepSeek Harness 模型加上识图能力：analyze_image 把图片转发到任意 OpenAI 兼容视觉端点 \| Vision bridge for text-only DSH models

## Metadata

- Author: [@CaseyTso](https://github.com/CaseyTso)
- Repo: <https://github.com/CaseyTso/dsh-analyze-image-tool>
- GitHub: [CaseyTso/dsh-analyze-image-tool](https://github.com/CaseyTso/dsh-analyze-image-tool)
- Stars: 0
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh-plugin`, `multimodal`, `openai-compatible`, `vision`, `vlm`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-18T01:46:53.000Z
- Added: 2026-08-18T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add --allow-build=analyze-image-tool github:CaseyTso/dsh-analyze-image-tool
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-analyze-image-tool](https://deepseek-plugin.org/plugins/CaseyTso/dsh-analyze-image-tool)