DSH Plugin HubDSH 插件市场

huashenglian/dsh-her-eyes

Plugin插件 Native原生 ⭐ 3 MIT Vision & Media视觉与多媒体Data & Analysis数据与分析

一个dsh插件，能让AI自动调用VLM（多模态模型）进行视觉分析。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native VLM image analysis plugin built exclusively for DeepSeek Harness (DSH). It registers a global analyze_image tool that makes image analysis available to every DSH AI session. The plugin supports OpenAI-compatible VLM endpoints for image analysis, with built-in automatic failover between primary and backup endpoints to prevent workflow interruptions. It also adds a multilingual, auto-saving settings page under DSH’s Settings menu, so users can configure VLM parameters without editing raw config files directly. To install, users run a single DSH CLI command, and the self-activating bundle handles the rest with no manual edits needed.

This plugin is designed for DSH users who need to add visual analysis capabilities to their AI workflows. After installation, users can configure primary and backup API endpoints, set a retry count for failure detection, and select VLM models directly through the web settings page. All edits to configuration are saved automatically and take effect immediately, with no need to click a separate save button or restart the DSH web server. If the primary endpoint exceeds the set number of consecutive failures, the plugin automatically switches to the backup endpoint to keep your workflow running smoothly.

The plugin has a few basic requirements to run properly. Users must have the DSH CLI installed with a web profile, and need pnpm available in their system PATH. If pnpm is not available, users can manually complete installation using npx, following the step-by-step alternative instructions provided in the README. Configuration is stored in a dedicated JSON file at ~/.dsh/vlm-vision.json, and uninstalling the plugin does not remove this file, so users can retain their settings if they reinstall later. The plugin is released under the open source MIT license, so it is free to use, modify, and distribute.

这是DeepSeek Harness（DSH）原生的视觉语言模型（VLM）图像分析插件，为DSH全局工具注册了analyze_image分析工具，支持通过OpenAI兼容的VLM API端点分析图像，自带主备端点自动故障转移功能，还在DSH设置界面添加了自动保存的多语言配置页面。安装过程无需手动修改配置文件，仅需一条DSH命令即可完成安装激活。

该插件面向需要在DSH工作流中加入图像分析能力的用户，支持用户在设置页面直接配置主备API端点、重试次数、模型ID等参数，所有修改自动保存即时生效，无需手动点击保存按钮。当主端点连续失败次数超过设定值后，会自动切换到备用端点，保障图像分析任务不中断，且所有标识符都做了唯一前缀处理，不会和其他插件产生冲突。

该插件要求用户已安装带web配置文件的DSH CLI，环境变量PATH中需要有pnpm，若没有pnpm也可使用npx作为替代完成安装。所有配置默认保存在~/.dsh/vlm-vision.json文件中，卸载插件时不会删除该配置文件。插件采用MIT开源许可证，允许用户自由使用、修改和分发源代码。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-her-eyes（huashenglian/dsh-her-eyes）
仓库：https://github.com/huashenglian/dsh-her-eyes
本站详情页：https://www.yhbd.top/plugins/huashenglian-dsh-her-eyes/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 3 · 最近提交 2026-08-13 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 3 stars - very few users, little community feedback星标只有 3，几乎没人在用，遇到问题缺少社区反馈
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 github:huashenglian/dsh-her-eyes

把 huashenglian/dsh-her-eyes 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

4.7 KB · 缓存于 2026-08-23 03:41:56 · 4.7 KB

dsh-her-eyes

English | 中文

A Vision-Language-Model (VLM) analyzer plugin for DeepSeek Harness (dsh). It gives the AI an analyze_image tool backed by primary/backup OpenAI-compatible vision endpoints with automatic failover, and adds an auto-saving Settings → Vision Models (VLM) page (English/中文).

Features

  • analyze_image tool registered on the global tools registry — available in every session.
  • Primary / backup VLM APIs — OpenAI-compatible endpoint + apiKey + model; if the primary fails consecutively beyond the retry count, the AI automatically falls back to the backup.
  • Auto-saving settings page — every edit saves and takes effect immediately; no Save button. Also lets you fetch the model list from the endpoint.
  • Web routes /vlm/config, /vlm/models, /vlm/reset served by the host half.
  • i18n — the settings page follows the harness UI language (English / 中文).

Requirements

  • dsh CLI (DeepSeek Harness) with a web profile installed. Requires pnpm on PATH (or use npx --yes pnpm@<version>).

Install

The plugin is a bundle: it carries its own cordis.patch.yml and self-activates. Installing it is a single command — no manual patch editing in the profile.

# From a local directory
dsh plugin --profile web add ./dsh-her-eyes

# From GitHub
dsh plugin --profile web add github:huashenglian/dsh-her-eyes

# From a packed tarball (pnpm pack / npm pack)
dsh plugin --profile web add ./dsh-her-eyes-1.2.0.tgz

dsh plugin add installs the dependency and appends the bundle to dsh.profile.bundles automatically.

If pnpm is not on PATH, run the equivalent manually:

# in the profile directory (~/.dsh/profiles/web)
npx --yes pnpm@11.7.0 add file:./plugins/dsh-her-eyes

then add "dsh-her-eyes" to the dsh.profile.bundles array in package.json.

Manual placement (alternative)

  1. Put the package under $DSH_HOME/profiles/web/plugins/dsh-her-eyes/.
  2. Add "dsh-her-eyes": "file:./plugins/dsh-her-eyes" to the profile package.json dependencies.
  3. Add "dsh-her-eyes" to the profile dsh.profile.bundles array.
  4. Run pnpm install (or npx --yes pnpm@11.7.0 install), then restart dsh web.

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 →

渲染基于仓库 huashenglian/dsh-her-eyes 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-image-transcription-plugin 下一个 Next knotline →