dsh-vidfetch
dsh-vidfetch — 一个用于下载视频的 DeepSeek Harness 插件。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:anaksunamu/dsh-vidfetch#b836f458fe67456917e2a4df5511390a2a06a7eeVidfetch 以 dsh-vidfetch 发布，当前版本为 0.1.0。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 your DeepSeek Harness agent the ability to download a video straight from a URL.
Registers a single tool, fetch_video, that the model can call to download the main video from any URL.
ok plus the list of files it wrote. Or a short error cause if the URL is unsupported.dir somewhere writable.dsh plugin --profile web add dsh-vidfetch
From this repository:
git clone https://github.com/anaksunamu/dsh-vidfetch.git
npm install --prefix ./dsh-vidfetch
npm run build --prefix ./dsh-vidfetc
dsh plugin --profile web add ./dsh-vidfetch
The model calls fetch_video with two required parameters:
| Parameter | Type | Description |
|---|---|---|
url | string | The URL where the video is located. |
dir | string | Output directory for the downloaded file. |
Example call the agent makes:
{ "url": "https://example.com/watch/abc123", "dir": "~/downloads" }
Output:
{ "message": "ok", "files": ["downloads/video.mp4"] }
On failure, message contains a short error cause and files is empty:
{ "message": "Unsupported URL", "files": [] }
0.1.1-rc.x line.^22.19.0 || >=24.0.0.Clear the risk explicitly before trusting an agent tool:
dir the model supplies (default: current working directory if empty). The model decides the path — point dir at a sandboxed or scratch folder if you don't want arbitrary writes.yt-dlp process per call; it inherits the host's environment.0.1.1-rc.x.