dsh-vision-bridge
Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.
输入框贴图自动识别：由 OpenAI 兼容视觉模型转成文字描述后，再交给纯文本 DeepSeek 模型处理。
How to install
dsh plugin add dsh-vision-bridge About
dsh-vision-bridge 让纯文本模型（DeepSeek V4 / V4-Flash）在对话里"看见"图片：**在输入框直接粘贴图片并发送，插件自动调用一个 OpenAI 兼容的视觉模型（VLM）把图片识别成文字描述，再把描述喂给 DeepSeek 继续处理。** 会话中图片照常显示；只有发给模型的内容变成文字。 原理 DSH 对纯文本模型会在提交时拒绝图片（MODEL_DOES_NOT_SUPPORT_IMAGES）。本插件打通两个官方扩展点： 1. **准入放行**：给 ctx.llm.resolveModelInfo 打补丁，声明当前模型支持 image 输入，让图片附件能进入会话。 2. **发模型前转换**：包装 llm.streamWithRegistration，每次请求发往模型前扫描所有消息中的图片块，调用配置的 VLM 生成文字描述，替换成： [用户附上的图片已由视觉模型自动识别（qwen-vl-max）] <描述内容> 如果路由到的模型**原生支持图片**，则放行原图、不做转换。 安装 sh 前置：dsh CLI 与 pnpm dsh plugin --profile web add dsh-vision-bridge 或从 git 安装： dsh plugin --profile web add https://github.com/<your-na…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 2
- mo. downloads
- 315
- Last push
- 2026-08-14
- Created
- 2026-08-14
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh, dsh-plugin
Related plugins
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-web
zhu1090093659/dsh-web-ui/tree/main/packages/dsh-tool-describe-image
A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.
dsh-vision-router
ysr666/dsh-vision-router
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
Anionex/dsh-vision-toolkit
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.