AlloyPlane/dsh-eye-vision ↗★ 1
dsh-eye-vision
dsh-eye-vision: give text-only DeepSeek Harness models eyes — image understanding via any OpenAI-compatible multimodal API. Fork of dsh-free-vision with custom-provider fixes and an allowed-directories whitelist.
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AlloyPlane/dsh-eye-vision说明文档
阅读完整 README ↗Configuration
Settings file: ~/.dsh/free-vision.json (same path as upstream for drop-in compatibility):
{
"modelProvider": "custom",
"baseURLs": { "custom": "https://your-api.example.com/v1" },
"modelName": "your-vision-model",
"apiKey": "sk-...",
"allowedDirs": "D:/workspace",
"toolName": "image_understand"
}
Or use environment variables (fallback chain: settings file > env):
| Provider | Key env | Base URL env |
|---|---|---|
| custom | CUSTOM_API_KEY | CUSTOM_BASE_URL + CUSTOM_MODEL_NAME |
| qwen | DASHSCOPE_API_KEY | QWEN_BASE_URL |
| volcengine | VOLCENGINE_API_KEY | VOLCENGINE_BASE_URL |
| siliconflow | SILICONFLOW_API_KEY | SILICONFLOW_BASE_URL |
| zhipu | ZHIPU_API_KEY | ZHIPU_BASE_URL |
| hunyuan | HUNYUAN_API_KEY | HUNYUAN_BASE_URL |
allowedDirs: semicolon/comma-separated extra roots the engine may read images from (default: engine CWD + home directory).
Usage
看图：D:/path/to/screenshot.png
OCR：D:/path/to/document.png
UI 分析：D:/path/to/design.png (task_type: ui)
Tool arguments: image_source (local path / http(s) URL / data URI), prompt, task_type (auto|general|ocr|ui|debug|describe). PNG/JPG/WebP/GIF up to ~10 MB.