DSH Plugin HubDSH 插件市场

yepyeel/dsh-vision

Plugin插件 Native原生 ⭐ 2 MIT Vision & Media视觉与多媒体

提供dsh中deepseek v4等无法识图的模型一双眼睛

Project Overview项目介绍

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

This is a native profile bundle plugin built exclusively for DeepSeek Harness, designed to add vision support to text-only large language models that do not natively handle image inputs. These text-only models include DeepSeek V4 Flash, DeepSeek V4 Pro, and any other model that omits image from its declared input modalities. When a user request includes image attachments that the current selected model cannot process, the plugin generates text descriptions for the images, replaces the image blocks with those descriptions only in the request sent to the model, and keeps the original images intact in the session log and user interface.

The plugin supports three distinct operating modes that users can configure in the DeepSeek Harness settings menu under the Vision Recognition section. The default automatic mode walks through all added image-capable models in provider registration order and uses the first one that succeeds at generating a description. If no image-capable model is available or all attempts fail, it falls back to system OCR for text extraction. Users can also choose to specify a single image-capable model, which will not fall back to other models or OCR if it fails, or use only system OCR if no image-capable models are available.

To install this plugin, you need to have a working DeepSeek Harness installation with the dsh CLI available on your system PATH. After cloning the repository to your local machine, you can run the command dsh plugin --profile web add . from the project directory to install it, then restart dsh web to load the plugin and its settings page. For OCR functionality, macOS and Windows do not require any extra dependencies, while other platforms need Tesseract OCR installed and added to the system PATH. The plugin is released under the permissive MIT open source license, and has documented limitations that users should review before use.

这是一个专为 DeepSeek Harness 开发的原生配置包插件，作用是让不支持图像输入的纯文本大模型（比如 DeepSeek V4 Flash、DeepSeek V4 Pro 这类）也能处理带图片的请求。当用户请求包含图片，而当前选用的模型无法识别图片时，插件会调用已添加的 vision 模型或者系统 OCR 对图片生成描述，仅在发送给模型的请求中用描述替换图片区块，会话日志和界面都会保留原始图片。

本插件支持三种工作模式：默认自动模式会按已添加模型的注册顺序，优先选择第一个可用的带图像能力的模型生成描述，生成失败后会自动回退到系统 OCR；用户也可以指定特定的带图像能力的模型，这种模式下失败后不回退；如果没有可用的 vision 模型，也可以直接使用系统 OCR。它适合只有纯文本模型配额、又需要偶尔处理图片请求的 DeepSeek Harness 用户。

使用本插件需要先安装 DeepSeek Harness，并且环境变量中配置好 dsh CLI 工具。OCR 功能在 macOS 和 Windows 系统不需要额外依赖，其他平台需要安装 Tesseract 并将其加入环境变量。本插件采用 MIT 开源许可证，存在一些使用限制：仅会选择声明了支持图像输入的模型，指定模型模式下失败直接关闭，系统 OCR 仅提取文本不做场景描述。

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-vision（yepyeel/dsh-vision）
仓库：https://github.com/yepyeel/dsh-vision
本站详情页：https://www.yhbd.top/plugins/yepyeel-dsh-vision/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-08-17 · 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 2 stars - very few users, little community feedback星标只有 2，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:yepyeel/dsh-vision

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

READMEREADME

3.5 KB · 缓存于 2026-08-25 04:53:48 · 3.5 KB

dsh-vision

English | 中文

A DeepSeek Harness profile bundle that gives text-only models (DeepSeek V4 Flash, DeepSeek V4 Pro, and any other route whose inputModalities omit image) working vision.

When a request contains image attachments and the target model cannot see them, the plugin describes each image and replaces the image blocks with that text for the provider call only. The session log and the UI keep the original images.

Requirements

  • A DeepSeek Harness installation with the dsh CLI available on your PATH.
  • For vision-model description: at least one already-added model that declares image in its inputModalities.
  • For the OCR fallback: macOS (Vision framework) and Windows (Windows.Media.Ocr) need nothing extra; other platforms need Tesseract installed and on the PATH.

Behaviour

  1. Auto (default) — walk already-added models that declare image input, in provider registration order, and use the first one that succeeds. If none are available, fall back to system OCR.
  2. Specified model — use only the vision model chosen in Settings. Failures are not retried and never fall back to another model or OCR.
  3. Auto + no vision model — system OCR:
    • macOS: Vision framework
    • Windows: Windows.Media.Ocr
    • any platform: Tesseract if installed

Descriptions are cached per attachment + model (or OCR) for the life of the process so later turns do not re-pay the vision call.

Settings

Open Settings → 视觉识别:

  • Auto — first available vision model, then system OCR.
  • 指定识图模型 — pick one already-added image-capable model. No fallback.

The same values live in $DSH_HOME/settings.yaml under dsh-vision:.

Install

From this directory:

dsh plugin --profile web add .

Restart dsh web so the new bundle layer and the client settings page load.

To remove:

dsh plugin --profile web remove dsh-vision

How it works

The fix has two layers:

  1. Declare capability — on startup the host row augments the current text-only model's inputModalities with image (by wrapping ctx.llm.resolveModelInfo). The session.prompt / session.selectModel image-admission gates therefore stop rejecting image messages with "model does not support images", and the read_image tool becomes available to text-only models too.
  2. Rewrite — the host row listens on the llm/stream waterfall. When a rewrite is needed the plugin builds a new request (images replaced by descriptions) and calls ctx.llm.stream again. The nested call targets a vision-capable model, so the interceptor lets it through. Frozen agent-loop requests are never mutated.

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

Related相关推荐

← 上一个 Prev dsh-task-stack 下一个 Next DeepSeek-Harness-Desktop →