DSH Plugins Marketplace

DSH Plugins

Plugins

/

dsh-pro-vision

l

dsh-pro-vision

Manifest valid1

DSH plugin: let DeepSeek-V4-Pro use V4-Flash-Vision-Exp for attached images. Install: dsh plugin --profile web add github:lasdrder0705/dsh-pro-vision

hasBundlePatch

dsh-pro-vision

中文 · English

DeepSeek-V4-Pro 是纯文本模型。这个插件在不切换主模型的前提下,把会话里的图片交给 deepseek-v4-flash-vision-exp 识图,再把说明交给 Pro。

A DeepSeek Harness plugin that lets V4-Pro use V4-Flash-Vision-Exp for attached images.

纯 JavaScript,无原生依赖,macOS / Windows / Linux 同一条安装命令。


中文

安装

Mac / Windows 同一条命令(Web 界面):

dsh plugin --profile web add github:lasdrder0705/dsh-pro-vision

然后重启 dsh web

Windows 若直接运行报错,给仓库地址加上引号,或改用 npx:

dsh plugin --profile web add "github:lasdrder0705/dsh-pro-vision"
npx @deepseek-ai/dsh plugin --profile web add github:lasdrder0705/dsh-pro-vision

本仓库没有构建脚本,一般不需要 allowBuilds

卸载:

dsh plugin --profile web remove dsh-pro-vision

让 Pro 能贴图

安装后,在 $DSH_HOME/settings.yaml 里给 Pro 声明图片输入(否则界面会按纯文本拒绝贴图):

llm-deepseek:
  models:
    - id: deepseek-v4-pro
      name: DeepSeek-V4-Pro
      inputModalities: [text, image]

设置是动态的,下一轮对话就会生效。真正发给 Pro 的请求里,图片会被替换成 Flash Vision 的文字说明。

行为

  1. Web UI / read_image 可以把图片交给 Pro。
  2. 插件先调用 deepseek-v4-flash-vision-exp 识图。
  3. 把说明写成 [Image N] ... 再发给 Pro。
  4. 同一张附件在进程内会缓存,后续轮次不再重复识图。

直接选用 deepseek-v4-flash-vision-exp 时插件不会插手。

配置

可选,写在 profile 的 cordis.patch.yml

- id: dsh-pro-vision
  config:
    provider: deepseek-official
    visionModel: deepseek-v4-flash-vision-exp
    textModels:
      - deepseek-v4-pro
    maxVisionTokens: 8192
    visionReasoningEffort: high

English

Install

Same command on Mac and Windows (web profile):

dsh plugin --profile web add github:lasdrder0705/dsh-pro-vision

Restart dsh web.

On Windows, quote the spec or use npx if the unquoted form fails:

dsh plugin --profile web add "github:lasdrder0705/dsh-pro-vision"
npx @deepseek-ai/dsh plugin --profile web add github:lasdrder0705/dsh-pro-vision

No native build. Uninstall with dsh plugin --profile web remove dsh-pro-vision.

Allow Pro to accept images

In $DSH_HOME/settings.yaml:

llm-deepseek:
  models:
    - id: deepseek-v4-pro
      name: DeepSeek-V4-Pro
      inputModalities: [text, image]

The plugin still strips images before they reach the Pro API and replaces them with Flash Vision captions.

Comments

Loading…

From the same category

archify

by tt-a1i

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

Workflow & AutomationTools & CapabilitiesManifest valid

69.8k

3.5k/wk

MIT

JavaScript

Sep 22, 2026

dsh plugin --profile web add @tt-a1i/archify-dsh

DeepSeek Harness plugin for Reactive Resume: bridges your resumes and job applications into a Harness session over MCP.

Tools & CapabilitiesManifest valid

41.7k

251/wk

MIT

Aug 24, 2026

dsh plugin --profile web add dsh-plugin-reactive-resume

by Tencent

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Development & InfrastructureTools & CapabilitiesManifest valid

28.9k

831/wk

NOASSERTION

Go

Sep 22, 2026

dsh plugin --profile web add @wxg-prc-cpg/dsh-weknora

by anywhere-labs

为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」,桌面本身也是「插件」。

Tools & CapabilitiesManifest valid

28.5k

170/wk

MIT

TypeScript

Sep 22, 2026

dsh plugin --profile web add dsh-plugin-desktop

by titanwings

Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill).

Tools & Capabilities

25k

MIT

TypeScript

Sep 22, 2026

Index only — not installable

by Nagi-ovo

Enhancement suite for Gemini, AI Studio, Claude & ChatGPT — plus a prompt manager for any websites, DeepSeek Harness included. / 面向 Gemini、AI Studio、Claude 与 ChatGPT 的增强套件;其中的提示词管理器可用于任意网站,如 DeepSeek

Tools & Capabilities

20.1k

GPL-3.0

TypeScript

Sep 21, 2026

Index only — not installable