Scorp1o117/dsh-tool-vision

Name: Scorp1o117/dsh-tool-vision
Author: Scorp1o117

Plugin插件 Native原生 ⭐ 8 NOASSERTION Vision & Media视觉与多媒体

DeepSeek Harness 外置视觉模型插件

Project Overview项目介绍

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

This is a native DSH plugin that adds external vision model support to DeepSeek Harness, and is part of the DeepSeek Harness Enhancement Suite. It provides an inspect_image tool that can connect to any OpenAI-compatible vision API endpoint, process images from local files or public HTTP URLs, and inject the text description generated by the vision model straight into the DSH agent loop. It also includes an image bridge feature that converts pasted images for text-only models into text hints before they enter the session log. It can be installed via npm or loaded directly from a local file path.

It is targeted at DSH users who need a separate vision endpoint or want to add image processing capabilities to text-only models. The image bridge runs on DSH’s agent/pre-step waterfall, so it can modify the step before it is saved to the durable session log. Older images already saved to the session log from previous versions are automatically repaired lazily on the first pre-step of the next session. Users can whitelist or blacklist which models get direct image blocks, working around common incorrect modality declarations in DSH profiles. It has a built-in master toggle that lets users disable all features without a DSH restart.

The plugin has no additional dependencies outside of the DSH SDK, and works with all major OpenAI-compatible vision models including OpenAI GPT-4o, Qwen-VL, GLM-4V, and local vision models hosted via Ollama. Once registered, it is available on the global tools layer so every agent running in the DSH process can call the inspect_image tool. It includes a dedicated web UI settings section that lets users edit configuration and apply changes hot without restarting DSH. It is released under the open source MIT license, with some core code ported from the existing dsh-vision-router project. Users can configure it via environment variables or directly in their DSH profile patch.

这是专为DeepSeek Harness开发的原生视觉插件，属于DeepSeek Harness增强套件的一部分，为DSH生态补充外部视觉模型能力。核心提供inspect_image工具，可对接任意OpenAI兼容格式的视觉API端点，处理本地文件或网络URL图片，将视觉模型返回的文本描述注入Agent对话循环，还内置图片桥接功能。

适合需要使用独立视觉端点处理图片、给纯文本模型补充视觉能力的DSH用户。插件会在DSH的agent/pre-step阶段将粘贴的图片转换为inspect_image提示，旧会话中已记录的图片也会自动懒修复，可配置仅指定模型直接接收图片块，避开DSH本身配置声明里常见的模态校验问题。

除DSH SDK外无额外依赖，支持OpenAI GPT-4o、通义千问VL、GLM-4V、Ollama本地模型等任意OpenAI兼容端点，全局注册后所有DSH Agent都可调用，带Web UI设置面板，配置修改热更新无需重启，采用MIT许可证开源，可通过npm或本地路径安装加载。

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-tool-vision（Scorp1o117/dsh-tool-vision）
仓库：https://github.com/Scorp1o117/dsh-tool-vision
本站详情页：https://www.yhbd.top/plugins/scorp1o117-dsh-tool-vision/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 NOASSERTION · ⭐ 8 · 最近提交 2026-09-30 · 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 8 stars - very few users, little community feedback星标只有 8，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 desktop add dsh-tool-vision@0.9.7

把 Scorp1o117/dsh-tool-vision 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

29.6 KB · 缓存于 2026-09-30 22:10:39 · 29.6 KB

dsh-tool-vision

Configuration page (DSH 0.2.0-rc.2 and later)

Open Plugins → Installed → dsh-tool-vision from the homepage sidebar to configure and save this plugin. The page uses the official plugins.bundle.config interface, without a duplicate entry in global Settings. Web and Desktop share the page. This version requires DSH 0.2.0-rc.2 or a later 0.2.x host; existing configuration is retained.

GitHub: Scorp1o117/dsh-tool-vision · npm: dsh-tool-vision

Part of the DeepSeek Harness Enhancement Suite — Vision · Soul/Persona · Long-term Memory · Plugin Marketplace.

External vision model for DeepSeek Harness.

DSH 0.1.1 adds native image input for DeepSeek's vision catalog. This plugin remains useful when you want a separate OpenAI-compatible vision endpoint, pixel-level image tools, screenshots, or a text-model bridge. The harness derives every model request strictly from the session log (llm/stream requests must equal the durable derivation — the agent-loop invariant), so the bridge keeps its conversion inside that durable path:

inspect_image tool — sends an image (local file, or http(s) URL) to any OpenAI-compatible /chat/completions endpoint that supports image_url content parts, and returns the vision model's textual answer into the agent loop.
Image bridge (v0.2.1) — pasted images are turned into inspect_image hints before they enter the durable log, on the agent/pre-step waterfall (the one seam where the harness lets a plugin replace the messages of a proposed step). Images already logged by an older version are repaired lazily with a surface replace on the session's first pre-step. Only models listed in multimodalModels receive image blocks directly; a model's declared inputModalities are never consulted, because profiles routinely declare input: [text, image] on text-only models just to pass the harness's prompt-admission check.

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 Scorp1o117/dsh-tool-vision 的 README.md。在 GitHub 查看原文 →