DSH Plugin HubDSH 插件市场
chenkezhen480/dsh-multimodal 预览 preview

chenkezhen480/dsh-multimodal

Plugin插件 Native原生 ⭐ 3 Apache-2.0 Vision & Media视觉与多媒体

我正在为您翻译，请稍等。

Project Overview项目介绍

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

This is a native multimodal image processing plugin built exclusively for DeepSeek Harness (DSH). It provides three core tools: image_recognize, image_generate, and vision_providers, all of which call external API models configured by the deployer. No models are bundled with the plugin by default, and any tool invocation without a properly configured model will throw a clear, actionable error instead of failing silently. To install the plugin locally, you must have pnpm available on your system PATH, check out the repository, run pnpm install and pnpm run build to compile the source code before adding it to your DSH profile.

The plugin supports multiple input formats for image recognition, including local file paths, HTTP URLs, and base64 data URIs, with a 25MiB size cap for inline local images. It can handle various tasks from describing image content, OCR, and reading charts, to generating new images from text or editing existing images. Generated images are saved to disk by default, and the built-in static server exposes them as absolute HTTP URLs that render correctly in DSH's web GUI via Markdown. Users can configure multiple providers, and each tool call can select a specific provider, defaulting to the first matching entry if none is specified.

The plugin has several known limitations that users should be aware of before first use. Local images are capped at 25MiB, so larger files need to be compressed or hosted via a public URL. DashScope image-to-image tasks require a public URL for the source image, as local paths and data URIs are not supported. After installing or upgrading the plugin, you must open a new DSH session because existing sessions do not pick up new or updated tools. The plugin is released under the open-source Apache-2.0 license, allowing free use, modification, and distribution.

这是专为DeepSeek Harness（DSH）开发的原生多模态图像处理插件，提供图像识别、图像生成两类工具，支持调用用户配置的外部多模态大模型API完成任务。插件本身不捆绑任何模型，未配置模型调用时会给出清晰可操作的错误提示，不会静默失败，保证使用流程透明可控。

用户可以通过配置不同类型的视觉和图像生成模型提供者，实现图像内容分析、OCR识别、文生图、图生图等多种多模态任务。支持本地文件、在线URL等多种输入格式，生成的图像会自动保存到指定目录，并通过内置静态服务提供可渲染的链接，适合需要在DSH中扩展多模态能力的开发者和普通用户。

安装需要pnpm位于系统PATH中，需要先本地构建检出代码，再通过DSH插件命令添加到个人配置文件，重启DSH并新建会话后即可使用。插件存在一些已知限制，比如本地图片大小上限为25MB，采用Apache-2.0开源协议，用户可以自由使用和修改源码。

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-multimodal（chenkezhen480/dsh-multimodal）
仓库：https://github.com/chenkezhen480/dsh-multimodal
本站详情页：https://www.yhbd.top/plugins/chenkezhen480-dsh-multimodal/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 3 · 最近提交 2026-08-17 · 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 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:chenkezhen480/dsh-multimodal

把 chenkezhen480/dsh-multimodal 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

11.4 KB · 缓存于 2026-08-25 04:53:49 · 11.4 KB

dsh-plugin-multimodal

English | 中文

Image recognition and image generation for DeepSeek Harness (dsh-plugin, a Cordis plugin).

The plugin is just tools: image_recognize, image_generate, and vision_providers call whichever external API models the deployer declares — vision via multimodal chat/completions; image generation via OpenAI-compatible images/generations or the Aliyun DashScope native async-task protocol. No model is bundled or defaulted — a tool invoked without a configured model fails with a clear, actionable error. It never guesses and never fails silently.

Demo

Image recognition Image generation
Image recognition demo Image generation demo

Features

  • image_recognize — analyze an image (local path / http(s) URL / data URI) through a configured vision model: describe, OCR, read charts/screenshots, review content, …
    • Local files are inlined as base64 data URIs (25 MiB cap)
    • prompt (what to ask), max_tokens / temperature, per-call provider selection
  • image_generate — generate or transform an image through a configured image model, save it to disk, and return its file path plus a Web-renderable URL when the static server is enabled
    • Text-to-image: OpenAI-compatible images/generations (prefers b64_json, falls back to URL download), or protocol: dashscope-native for the DashScope async task API (submit → poll → download), needed when an OpenAI-compatible gateway exposes no image routes (some Aliyun deployments)
    • Image-to-image: pass an image argument (source image) to generate from it (edit / variant / style transfer). OpenAI-compatible endpoints use the image field; DashScope native uses base_image_url
    • Watermark-free by default: OpenAI-compatible requests carry watermark: false (Doubao Seedream etc. support it; endpoints rejecting the param are retried without it). Set watermark: true on the provider to keep the vendor's mark
    • Inline in the Web chat: a built-in static server (default 127.0.0.1:3081) exposes generated images as absolute http(s) URLs; the tool returns Markdown ![](https://github.com/chenkezhen480/dsh-multimodal/blob/HEAD/url) lines the model can paste into its reply so the GUI renders them (the GUI's Markdown renderer allows only absolute http(s) image URLs — local paths, relative links and data URIs never render; the harness webserver serves no arbitrary files, and writing into the frontend dist directory does not work, tested)
    • Real-format extensions: base64 payloads get their extension from the magic bytes (PNG/JPEG/WebP/GIF) so Content-Type matches the content
    • size (e.g. 1024x1024), n (1–4, auto-suffixed filenames), output_path (directory or file)
    • Default save location: <caller workspace>/generated/, timestamped filenames
  • vision_providers — list every configured external model (id, kind, model, endpoint, apiKey status) so the model can pick a provider id
  • Multiple models — the providers list accepts any number of entries; each tool call may select one via provider, defaulting to the first of the matching kind
  • Not configured → clear error — no provider of the kind, unknown provider id, empty apiBase, model, or apiKey all raise actionable Chinese errors when the tool is called; missing connection settings never prevent DSH Web from starting

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 chenkezhen480/dsh-multimodal 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-plugin-dev-guide 下一个 Next claude2dsh →