Model-facing `vision` tool for DeepSeek Harness: describe and OCR image files by calling the free Zhipu GLM vision API directly (glm-4v-flash fallback chain), no external CLI required.
Install
# from npm (prebuilt)
dsh plugin --profile web add dsh-vision-free-eyes
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:314857493/dsh-vision#path:/packages/vision-tool
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)的纯文本模型补上免费「眼睛」:一个模型可调用的 vision(image, question) 工具,
直连智谱 GLM 免费视觉 API(glm-4v-flash → glm-4.6v-flash → glm-4.1v-thinking-flash 自动降级链),
不依赖任何外部 CLI。完整说明见仓库根目录的 README。
安装(发布后)
dsh plugin --profile web add dsh-vision-free-eyes
或在 profile 的 cordis.patch.yml 中追加:
- insert:
- id: dsh-vision-free-eyes
name: dsh-vision-free-eyes
前提
- 必须:智谱 GLM 免费 key,环境变量
GLM_API_KEY或ZHIPU_API_KEY(open.bigmodel.cn 注册即得,格式id.secret;Windows 也可setx,插件自动读注册表)。 - 出站 HTTPS 到
open.bigmodel.cn。
使用
告诉模型图片路径即可,例如:"看一下 D:\xxx\screenshot.png"。
可选参数:mode="ocr"(只提取图中文字)、no_cache=true(跳过进程内结果缓存)。
输出为图片内容的文字描述,末尾带 [glm | 耗时ms] 标记。
配置
| config | 默认 | 说明 |
|---|---|---|
apiKeyEnv |
GLM_API_KEY / ZHIPU_API_KEY |
GLM key 的环境变量名(可传数组) |
no_cache |
false |
跳过进程内结果缓存,强制重新请求 |
限制
- 单图 ≤ 15MB;支持 png/jpg/jpeg/webp/gif/bmp。
- 不支持 PDF(
doc模式已移除);图片字节会上传到智谱服务器。
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.