oil-oil/dsh-vision

Name: oil-oil/dsh-vision
Author: oil-oil

Plugin插件 Native原生 ⭐ 89 MIT Vision & Media视觉与多媒体

DeepSeek Harness的近原生图像理解能力

Project Overview项目介绍

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

dsh-vision is a native plugin built exclusively for DeepSeek Harness that adds native vision passthrough and a vision bridge capability to the platform. To install it, you can use DeepSeek Harness’s built-in plugin manager by running the command npx @deepseek-ai/dsh plugin --profile web add github:oil-oil/dsh-vision in your terminal, then restart Harness to activate it. Once activated, it replaces the official deepseek-official adapter while preserving all existing model catalogs, settings, and user credentials, and adds a dedicated Vision Recognition configuration card to the plugin settings menu.

When you use the plugin, you can paste or drag images into the Harness composer just like you would normally. If your main model natively supports images, the original images are sent directly without any extra preprocessing or OCR. If you are using a text-only main model like the official DeepSeek text model, the plugin will use your configured vision model to analyze the images, then inject the results as context for the main model to generate the final answer. It supports analyzing multiple attached images at once, making it easy to compare images or combine evidence across multiple inputs.

The plugin is released under the open-source MIT License, with no associated costs for personal or commercial use. API keys are stored through Harness’s official credential service, and are write-only in the browser, meaning the plugin can never read them back into any page, chat, or session log. If no cloud vision provider is configured, it falls back to local OCR: macOS uses the built-in system Vision capability, while Linux and Windows require installing Tesseract and matching language data for local OCR. Security is enforced by marking vision output as untrusted, so instructions embedded in images do not gain system access.

dsh-vision 是专为 DeepSeek Harness 开发的原生视觉插件，核心功能是为 DSH 提供原生视觉透传以及视觉桥接能力。当用户选用支持图片输入的主模型时，原始图片会直接发送给模型，无需额外预处理或 OCR。当主模型是仅文本型（例如官方 DeepSeek 模型）时，插件会调用用户独立配置的视觉模型先解析图片内容，再把结果注入上下文供主模型生成最终回答。

用户可以通过 DeepSeek Harness 内置的插件管理器直接安装，安装完成后重启 DSH 即可使用。使用时和原生操作一致，只需要正常粘贴或者拖拽图片到输入框即可。插件适合需要在 DSH 中处理图片内容、但当前选用的主模型不支持原生视觉输入的用户，同时也保留了对原生支持视觉的模型的透传能力，不会改变用户原有的使用流程。

插件采用 MIT 许可证开源，完全免费供个人和商业使用。API 密钥通过 DSH 官方凭证服务存储，在界面中仅可写入不可读取，保障用户的密钥信息安全。如果没有配置云端视觉服务，插件会自动降级到本地方案：macOS 可直接使用系统自带视觉能力，Linux 和 Windows 需要提前安装 Tesseract 和对应语言包才能使用本地 OCR。

View on GitHub在 GitHub 查看

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-vision（oil-oil/dsh-vision）
仓库：https://github.com/oil-oil/dsh-vision
本站详情页：https://www.yhbd.top/plugins/oil-oil-dsh-vision/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 89 · 最近提交 2026-08-18 · 主语言 TypeScript

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 no risk signal found未发现风险信号

This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号（星标、许可证、更新活跃度、清单完整度）

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

npx @deepseek-ai/dsh plugin --profile web add github:oil-oil/dsh-vision

把 oil-oil/dsh-vision 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

5.5 KB · 缓存于 2026-08-23 03:40:50 · 5.5 KB

dsh-vision: native vision passthrough and a vision bridge for DeepSeek Harness

English | 中文

dsh-vision is a plugin for DeepSeek Harness. Vision-capable models keep receiving images natively. When the selected main model is text-only, the plugin asks a separate vision model to observe the original images, then lets the original DeepSeek model produce the final answer.

How it works

Main model	Image path	Final answer
Supports images	Original images are sent directly, without preprocessing or OCR	Current model
`deepseek-official` or another text-only model	A configured vision model observes the original images; its output is injected as untrusted attachment context	DeepSeek
Cloud vision unavailable	Falls back to macOS Vision or Tesseract	DeepSeek

The plugin does not replace the main model selected in Harness. Multiple image attachments are analyzed together, so comparisons and combined evidence work naturally. The user's task is forwarded unchanged instead of being wrapped in a fixed report template.

Install

Use the plugin manager built into DeepSeek Harness:

npx @deepseek-ai/dsh plugin --profile web add github:oil-oil/dsh-vision

Restart Harness, then paste or drag images into the composer as usual. The plugin replaces the official deepseek-official adapter while preserving its model catalog, settings, and credentials. It also adds a Vision Recognition card to Settings → Plugins → Plugin configuration.

DeepSeek Harness is still in Developer Preview. This release supports 0.1.0-rc.6 and 0.1.0-rc.7; its settings-card registration satisfies both the legacy list Slot and the current keyed Slot without relying on private runtime inspection.

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 oil-oil/dsh-vision 的 README.md。在 GitHub 查看原文 →