Registers a `deepseek-vision` provider route: the Web GUI accepts pasted images and transcribes them to text via the free Zhipu GLM vision API before delegating to the DeepSeek adapter.
Install
# from npm (prebuilt)
dsh plugin --profile web add dsh-vision-proxy-route
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:314857493/dsh-vision#path:/packages/vision-route
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time. Only install sources you trust, and pin a commit (github:owner/repo#sha).
README
给 DeepSeek Harness(DSH)注册一个 deepseek-vision 路由:声明图像输入(inputModalities: ['text','image']),
粘贴到 Web GUI 的图片在请求流里被免费的智谱 GLM 视觉模型(glm-4v-flash 降级链)转译成文字,再委派给真正的
DeepSeek 适配器。完整说明见仓库根目录的 README。
安装(发布后)
dsh plugin --profile web add dsh-vision-proxy-route
或在 profile 的 cordis.patch.yml 中追加:
- insert:
- id: dsh-vision-proxy-route
name: dsh-vision-proxy-route
前提
- DSH
0.1.0-rc.5/rc.6(依赖ctx.llm.registerAdapter/registration(provider).adapter/resolveModel.inputModalities/ctx.attachments.readImage这些插件缝) - 智谱 GLM 免费 key:环境变量
GLM_API_KEY或ZHIPU_API_KEY(Windows 也可setx GLM_API_KEY "id.secret",插件自动读注册表)
使用
模型选择器切到「DeepSeek + 自动识图」,直接粘贴图片/截图并附带问题即可;转译失败会替换为 [图片转译失败: ...] 文本,对话不卡死。
Links
More in this category
liustack/modlens★ 2723
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
Anionex/dsh-vision-toolkit★ 604
Vision tasks for text-only models: intent-aware image Q&A, long-screenshot OCR, UI reproduction, grounding, and pixel diff.
ysr666/dsh-vision-router★ 593
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.
linenxi-ctrl/dsh-vision★ 12
External vision plugin for DeepSeek Harness: whale-button config panel, image recognition with auto-reply, and agent screenshot/recognize tools.
Flyvhidbwo/dsh-vision-proxy★ 10
DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed to text via any OpenAI-compatible VLM before reaching the text-only DeepSeek — a keyed fast path (default qwen3.7-flash; DashScope/Zhipu/OpenRouter or any OpenAI-compatible endpoint) with your own key, or local Ollama auto-detected with zero config.
jyh20030112/dsh-visual-plugin★ 9
Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.