dsh-image-router
Digests the images in a prompt with a vision model before admission, so any model — a text-only one included — can read them without the session ever switching models, and adds a describe_image tool for image paths.
在准入前把提示词里的图片换成视觉模型的文字分析,因此任何模型(包括纯文本模型)都能读图且会话不切换模型;另提供 describe_image 工具处理图片路径。
How to install
dsh plugin add dsh-image-router About
dsh-image-router [!IMPORTANT] **当前版本 0.4.4,已发布到 npm,适配 DSH 0.1.5-rc.1+(已在 0.1.5-rc.1 上真机验证)。** 若你装到的是更早的 0.1.0,那是本插件的第一个(已废弃的)构建,会让「设置 → 模型」页加载失败 —— 用 dsh plugin --profile web add dsh-image-router@latest 直接装最新版即可。 图片在进入会话之前,先由你指定的视觉模型转成文字 —— <b>你的会话模型自始至终不变</b>,模型选择器也不会跳。<br /><br /> 你贴一张截图,问「这个报错怎么修」 ↓ 插件在「提示词准入」之前拦下这次提示词 qwen-token-plan-cn / qwen3.8-flash ← 一次旁路调用(不改会话路由、不写 model/selection) ↓ 分析结果替换掉图片,成为提示词里的一段文字 你原本选定的模型(GUI 里显示的那个)继续作答 📑 目录 ⚡ 一分钟安装 ✨ 功能一览 🖼️ 它长什么样 🧭 给视觉模型的两种方式 🔐 安全 · ⚠️ 已知限制 · 🖥️ 兼容性 🛠️ 开发与测试 · 🤝 参与贡献 🔍 审计与排查(折叠) · ⚙️ 配置项(折叠) · 🧩 工作原理(折叠) ⚡ 一分钟安装 **前置**:已装好 DSH(d…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-09-12
- Created
- 2026-09-12
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh-plugin, image-router, vision
Related plugins
dsh-comfyui
fandc520/dsh-comfyui
Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.
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.
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
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.