GXX182/dsh-vision-bridge

Name: GXX182/dsh-vision-bridge
Author: GXX182

Desktop桌面端 Native原生 ⭐ 4 MIT Vision & Media视觉与多媒体 Notifications & Remote通知与远程 Sessions & Context会话与上下文

DeepSeek Harness 插件，用于将会话图像桥接到可插拔的视觉 API，同时保持 DeepSeek 作为主要模型。

Project Overview项目介绍

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

dsh-vision-bridge is a native plugin for DeepSeek Harness that adds image understanding capabilities to text-first models. Users can install it directly from GitHub by running dsh plugin --profile web add "github:GXX182/dsh-vision-bridge#semver:*" to get the latest stable release, or build it from a local checkout after running npm install and npm run build for local development. It adds a small glasses toggle next to eligible text-only models, keeps the original Harness model list intact, delegates all image analysis to a user-configured separate vision provider, and never sends image blocks directly to the upstream text model.

Once installed, users just need to toggle the glasses switch on for their desired text model, then select the model and attach an image to ask a visual question just like they would with any other prompt. The preference is stored locally in the Harness client, so you won’t need to re-enable it every time you use the model. The plugin supports multiple vision provider formats, including Gemini-native, OpenAI-compatible and Anthropic-compatible APIs, and users can add, remove, or switch between different providers directly in the Harness settings menu. It is built for DeepSeek Harness users who want to add image capabilities to their preferred text-first models without switching to another vision-capable model.

This plugin requires DeepSeek Harness version 0.1.0-rc.5 or a newer compatible 0.1.x release, and Node.js version 22.19 or higher, or Node 24 and above to run correctly. Users need to have at least one valid API key for a vision-capable LLM endpoint to use this plugin, and the default out-of-the-box configuration after installation uses Google’s Gemini API with the gemini-3.6-flash model. It is released under the permissive open-source MIT license, and has a few documented known limitations listed in the project README: it does not support remote image URLs, only inline image bytes, and it does not independently verify the accuracy of analysis results from the vision provider.

dsh-vision-bridge 是专为 DeepSeek Harness 开发的原生插件，用于给原本仅支持文本输入的大模型添加图像理解能力。该插件通过 DSH 的命令行工具即可安装，支持从 GitHub 直接拉取最新版本，也支持从本地检出代码后编译安装。它会在符合条件的模型旁添加一个眼镜形状的开关控件，不会重复创建新的模型分组，保持 Harness 原有模型列表整洁不变，并将图像分析委托给独立配置的视觉提供商。

用户只需给符合条件的文本模型开启视觉桥接开关，选择模型后附加图片提问即可正常使用，偏好设置会自动保存在本地 Harness 客户端，不会触发模型刷新或切换。插件支持 Gemini 原生、OpenAI 兼容、Anthropic 兼容多种 API 格式，用户可以在设置中添加、切换、删除不同的视觉提供商配置。适合需要让自己常用的文本大模型获得图像理解能力，又不想切换模型的 DeepSeek Harness 用户使用。

该插件要求 DeepSeek Harness 版本在 0.1.0-rc.5 及以上的 0.1.x 版本，Node.js 需要 22.19 以上或 24 及以上版本，用户需要至少拥有一个支持图像的模型 API 密钥。采用 MIT 许可证开源，默认配置使用 Gemini 的 API 密钥和 gemini-3.6-flash 模型。已知限制包括不支持远程图片 URL，仅支持内联图片字节，不会独立验证分析结论的正确性。

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-bridge（GXX182/dsh-vision-bridge）
仓库：https://github.com/GXX182/dsh-vision-bridge
本站详情页：https://www.yhbd.top/plugins/gxx182-dsh-vision-bridge/
本站登记：类型 client · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 4 · 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 2 warnings2 项注意

Only 4 stars - very few users, little community feedback星标只有 4，几乎没人在用，遇到问题缺少社区反馈
Desktop client: installation downloads an executable - verify the publisher and checksums桌面客户端：安装会下载可执行文件，请核对发布者与校验和

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:GXX182/dsh-vision-bridge#semver:*"

把 GXX182/dsh-vision-bridge 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

8.2 KB · 缓存于 2026-08-23 03:42:03 · 8.2 KB

Vision Bridge glasses icon

dsh-vision-bridge

_{A vision layer for text-first models in DeepSeek Harness}

简体中文 · Install · Configure · Security

dsh-vision-bridge is an installable DeepSeek Harness bundle that adds image understanding to text-first model routes. It preserves the Harness model list, adds a small glasses control to eligible models, and delegates image analysis to a separately configured vision provider.

The plugin supports Gemini-native, OpenAI-compatible Chat Completions/Responses, and Anthropic-compatible Messages APIs. The selected vision provider returns bounded text analysis; image blocks are never forwarded directly to the active upstream model.

Highlights

One model list: Vision Bridge no longer appears as a duplicated provider group.
Per-model glasses toggle: Gray means the bridge preference is off; blue means it is on.
Selection stays explicit: Clicking the glasses only changes the preference. Clicking the model name selects the model and applies that preference.
Persistent without model churn: Glasses preferences are remembered in the Harness web client without triggering a model switch or model-directory refresh.
Clear service provenance: Hover the glasses to see the active vision provider and model.
Multiple vision providers: Add, switch, and delete isolated provider profiles from Settings.
Native-vision aware: Models that already advertise image input do not receive a bridge toggle.
Reasoning UI preserved: The original Harness reasoning-effort menu remains unchanged.

Model selector behavior

Control	Result
Gray glasses	Vision Bridge is disabled for that model.
Blue glasses	Vision Bridge is enabled for that model.
Click glasses	Toggle and remember the preference only; the selected model does not change.
Click model name/row	Select the model. Blue routes through Vision Bridge; gray uses the normal upstream route.
Hover glasses	Show the vision provider and model that will perform image understanding.

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 GXX182/dsh-vision-bridge 的 README.md。在 GitHub 查看原文 →