jyh20030112/dsh-visual-plugin 预览 preview

jyh20030112/dsh-visual-plugin

Dsh-visual-plugin。为你的纯文本模型赋予视觉能力:将用户图像转发至任何兼容OpenAI的视觉模型,并在Web UI右侧面板中查看结果。

Project Overview项目介绍

This is a native plugin built exclusively for DeepSeek Harness, adding image and video analysis capabilities to the DSH web interface. It uses DSH’s existing selected vision-capable large language models to process content, so users do not need to configure separate external vision endpoints or manage separate credentials. All analysis results are displayed in a dedicated right-side panel, and it supports uploads for most common image and video formats, with auto-saved analysis history that can be copied with one click anytime you need it.

The typical workflow for this plugin follows a simple, straightforward path. First, you select an existing vision-capable model from within DSH, no extra configuration for the plugin is required. Then you can upload an image directly, the plugin will let the DSH model process it natively, and the result will automatically save to the right panel for you to view or copy. If you upload a video, the plugin will first validate the container format, transcode it to standard H.264, extract relevant keyframes via PySceneDetect, send them to the model for analysis, and even let you play the processed video directly in the right panel.

To use the full video analysis features, you need to install compatible versions of FFmpeg/FFprobe (minimum version 6.1) and PySceneDetect (between version 0.7.1 and 0.8) on your host machine first. The plugin does not automatically download or install these dependencies, but any missing dependencies will not block or break the core image analysis features of the plugin. The plugin is open source under the permissive MIT license, and can be installed with a single DSH plugin command, pre-built packages are already committed so you do not need to build it from source locally on your machine.

这是专为DeepSeek Harness开发的原生视觉插件,为DSH添加了图像与视频分析能力,直接调用DSH已选的支持视觉功能的大模型,无需额外配置第三方视觉端点,分析结果会展示在网页端右侧面板中。支持多种常见图像和视频格式上传,还会自动记录分析历史,每个结果都可以一键复制。

典型工作流程为:用户先在DSH中选中一个支持图像能力的模型,随后上传图像,插件会调用模型原生处理,结果自动存入右侧面板供查看复制;如果上传视频,插件会先验证格式,转码为标准H.264,提取关键帧后再送入模型分析,还支持直接在面板播放处理后的视频。

视频功能需要宿主环境提前安装版本符合要求的FFmpeg/FFprobe(≥6.1)和PySceneDetect(0.7.1≤版本<0.8),插件本身不会自动下载这些依赖,缺失依赖不影响图像功能使用。项目采用MIT许可证开源,可通过DSH的插件命令一行安装,预编译包已提交无需本地构建。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 note1 项提示
  • 16 stars - an early-stage project星标 16,属于早期项目
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add dsh-visual-plugin

把 jyh20030112/dsh-visual-plugin 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-visual-plugin

DeepSeek neon pixel whale

npm version npm downloads GitHub stars MIT license
TypeScript zero runtime deps

Analyze images and videos with DSH's native vision models and inspect the results in a Web UI right panel.

English · 简体中文

A plugin for DeepSeek Harness.

Features

  • Native image understanding — uploaded images stay on DSH's native attachment and model path; the plugin does not configure or call a separate vision model.
  • Copyable image history — the right panel records the current DSH model's final answer beside each image thumbnail, with expandable history and one-click copy.
  • Plugin-owned video upload — accepts MP4, M4V, MOV, AVI, MPG/MPEG, MKV, and WebM only when extension, signature, and FFprobe agree.
  • Scene-aware video analysis — normalizes to H.264/yuv420p MP4, extracts keyframes with PySceneDetect, and sends ordered timestamped images to the current DSH vision model.
  • Right-side panel — switch between image/video views, play normalized videos directly, and stage a selected video in the chat draft.
  • Advanced video settings — tune upload size, storage quota, duration, output size, FPS, CRF, and keyframe count from the plugin settings card.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-diagram 下一个 Next orbis →