dsh-local-vision
DeepSeek Harness 插件：一个可由模型调用的 local_vision 工具，通过 Ollama 使用本地视觉模型描述图像。不使用云服务，图像不会离开本机。提供两个级别：快速（文本/颜色/摘要）和详细（完整描述）。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-local-vision@0.2.1Local Vision 以 dsh-local-vision 发布，当前版本为 0.2.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Give a text-only DeepSeek Harness agent local "eyes". This plugin registers a
model-callable local_vision tool that describes an image using a local
vision model through Ollama. The image never leaves your
machine — no cloud, no uploads, no API keys.
Ollama running (default http://localhost:11434).
At least one vision-capable model pulled, e.g.:
ollama pull qwen2.5vl:3b # small, fast — text / colors / summary
ollama pull gemma4:12b-it-qat # larger — thorough description
# from npm (recommended)
npm install -g @deepseek-ai/dsh
dsh plugin --profile web add dsh-local-vision
# or from this repository (use `file:` so @deepseek-ai/dsh-tools resolves)
dsh plugin --profile web add file:/path/to/deepseek-harness-plugins/dsh-local-vision
Restart the DSH session so the new bundle is composed. The package then appears
in Settings → Plugins → Plugin list and the tool local_vision is available.
local_vision(image: "/abs/path/screenshot.png", mode: "fast")
local_vision(image: "/abs/path/mockup.png", mode: "detailed", prompt: "Describe the navigation and buttons")
local_vision(image: "screen", mode: "detailed") # capture the current display (macOS screencapture)
mode | intent | default model |
|---|---|---|
fast | transcribe visible text, name dominant colors, one-line summary | qwen2.5vl:3b |
detailed | full factual description: layout, UI elements, all text, colors, state | gemma4:12b-it-qat |
| Param | Type | Notes |
|---|---|---|
image | string (required) | Absolute path to a PNG/JPEG/WebP/GIF, or the literal screen. |
mode | "fast" | "detailed" | Defaults to fast. |
prompt | string | Optional focused question. Defaults per mode. |
model | string | Optional override of the Ollama model id for this call. |
Optional, at $DSH_HOME/local-vision.json (default ~/.dsh/local-vision.json):
{
"host": "http://localhost:11434",
"models": { "fast": "qwen2.5vl:3b", "detailed": "gemma4:12b-it-qat" },
"temperature": 0.1,
"timeoutMs": 300000
}
All keys are optional; defaults are shown above. The plugin sends the image to
Ollama's OpenAI-compatible /v1/chat/completions endpoint as a base64 data URI.
image: "screen" requires macOS and Screen Recording permission for the terminal.