PROJECT TOPICS

项目标签

dsh-plugin

PROJECT README

README

Browser-local audio/video tools for DeepSeek Harness (DSH), powered by FFmpeg.wasm.

No uploads, no servers — every operation runs in your browser via WebAssembly.

dsh plugin add @piedpiper911/dsh-video-tools

Tool	What it does
`video_info`	Probe a video's duration, resolution, and codecs without transcoding.
`video_frames`	Extract evenly-spaced frames as JPEGs, or a single frame at a timestamp.
`image_compress`	Recompress an image to JPEG at a target width to shrink it for vision models.
`video_to_gif`	Convert a video clip to an animated GIF (two-pass palette optimization).

1. upload the video → workspace
2. video_frames { input: "demo.mp4", count: 4 }
3. describe what you see in each frame

One shared FFmpeg instance is lazily loaded on first use and reused for the whole session — the ~30 MB core downloads exactly once.
All I/O happens in FFmpeg's in-memory virtual filesystem; nothing touches disk.
Tool arguments are validated with the DSH schema DSL (defineTool), so the model only ever sees well-formed inputs.

npm ci
npm run build      # tsc → lib/
npm test           # vitest

MIT

CLASSIFICATION EVIDENCE

项目类型待识别

功能分类其他

规则置信度低

系统优先读取 GitHub Topics，再与站内分类词典和词根规则比对。当前命中：无有效分类标签。