dsh-vision-mix

DeepSeek Harness Other Low risk

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

把文本、识图和生图 API 组合成一个 Mix 模型并按对话内容自动路由：纯文本走聊天模型，用户图片和 Agent 截图走识图模型，后续可继续追问同一张图；还支持图片生成与编辑及会话级调用记录。

How to install

DeepSeek Harness dsh plugin add dsh-vision-mix

About

Vision Mix Vision Mix 是 DeepSeek Harness 的视觉增强插件。它把文本模型、视觉模型和可选的图片生成 API 组合成一个 Mix 模型，让原本不支持图片的 Agent 能识别上传图片、理解网页截图、持续追问图片内容，并生成或编辑图片。模型的 Base URL、协议和 API Key 仍由 DSH 的“设置 → 模型”统一管理。Vision Mix 只引用已经配置好的 Provider，不复制凭据。三分钟上手 1. 安装在 DeepSeek Harness 仓库目录执行： powershell pnpm dsh plugin --profile web add dsh-vision-mix 启动 Web： powershell pnpm dsh web 安装后的正常启动不需要 --patch。 2. 配置准备使用的模型打开“设置 → 模型”，配置至少两个模型： | 用途 | 要求 | 示例 | |---|---|---| | 基础模型 | 能处理文本、推理和工具调用 | deepseek-chat、deepseek-v4-pro | | 识图模型 | 中转站实际支持 OpenAI/Anthropic 图片消息 | gpt-5.6-sol、其他视觉模型 | 识图和基础模型可以来自同一个 Provider，也可以分别使用不同中转站。如果还要生…

GitHub ↗

Recommendation signals

61 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

61 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ npm ↗ Homepage ↗ Report issue ↗

Basic safety check

Findings: None
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics: deepseek-harness, dsh-plugin, gpt-image-2, image-generation, multimodal, vision

Related plugins

DeepSeek HarnessClaude CodeCodex

Score92

modlens

liustack/modlens

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

☆ 4.0K ↓ 106.1K Other ↗

DeepSeek Harness Featured

Score72

dsh-web

zhu1090093659/dsh-web-ui/tree/main/packages/dsh-tool-describe-image

A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.

☆ 8.0K ↓ – Other ↗

DeepSeek Harness

Score70

dsh-vision-router

ysr666/dsh-vision-router

Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.

☆ 1.1K ↓ 66.0K Other ↗

DeepSeek Harness

Score67

dsh-vision-toolkit

Anionex/dsh-vision-toolkit

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.

☆ 883 ↓ 42.3K Other ↗