dsh-deepseek-vision
A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.
视觉语言网关：注册支持图片输入的 DeepSeek provider 路由，图片先由可配置 VL 模型（默认 Qwen-VL）描述成文字再发送。
How to install
dsh plugin add dsh-deepseek-vision About
dsh-deepseek-vision **安装：** dsh plugin --profile web add dsh-deepseek-vision **dsh-deepseek-vision 是给 DeepSeek Harness 的视觉语言网关插件。** 纯文本的 DeepSeek 编程模型 通过一个"网关"provider 路由获得贴图能力：图片先由可配置的视觉模型（默认 Qwen-VL） 逐字描述成文字，再交给 DeepSeek 继续写代码。官方仓库零改动、跨机器安装不锁官方版本。 同类方案里它是**最薄的桥**：不注入 agent 工具、不经过第三方中转、不依赖本地模型。 English | 中文 目录 亮点 为什么选它 快速开始 效果 工作原理 配置 使用 安装 版本对齐 开发 边界与注意 FAQ 许可 亮点 **贴图即用，不用换模型：** 注册独立路由 deepseek-vision（显示名 *DeepSeek + Vision*）， 真实声明 inputModalities: ['text','image']——聊天窗贴图、tool-fs read_image、浏览器 截图工具全部放行。 **每张图只描述一次：** 按 attachmentId 进程内 LRU 缓存，重试、上下文压缩、后续轮次 复用同一份描述，不重复计费。 **会话不变量保持：** 原始图片仍持…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 9
- mo. downloads
- 3.5K
- Last push
- 2026-09-11
- Created
- 2026-08-15
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- coding-agent, deepseek, deepseek-harness, dsh, dsh-plugin, llm-gateway, multimodal, plugin, qwen-vl, vision-language
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.