中文

← Back to list

dsh-vision-plugin

DeepSeek Harness Other Low risk

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).

让纯文本模型也能看图：发图自动用视觉模型描述（默认提示词），描述不足时对话模型自动生成更具体的提示词重新解析；系统模型/自定义双模式 + GUI 可视化配置、Key 脱敏安全、针对 DSH 0.1.0-rc.6 的宿主小补丁（见仓库 README）。

How to install

DeepSeek Harness dsh plugin add dsh-vision-plugin

About

👁️ dsh-vision-plugin — DSH 视觉理解插件 给 DeepSeek Harness（DSH）装上"眼睛"：**纯文本模型（如 deepseek-v4-flash）也能处理图片**——发图后自动用视觉模型生成描述，文本模型基于描述回答；描述不足时自动生成更具体的提示词重新解析。配置全程 GUI 可视化、保存即生效。 ⚠️ 社区项目，非 DeepSeek 官方。已在 DSH 0.1.0-rc.6（Desktop）实测。 > 📦 v1.0.0 ｜ MIT License ｜ Windows + PowerShell 安装 ｜ 支持 desktop / web / headless profile --- ✨ 特性 🖼️ **发图自动接管**：对话模型收到图片不再被拒绝——用**默认提示词**调视觉模型生成描述，文本模型基于描述回答 🔁 **迭代式视觉解析**：描述不足时，对话模型**自动生成更具体的提示词调用 view_image 重新解析**（可省略 image 参数复用会话最近上传的图片） 🧩 **两种连接模式**： **系统模型**：自动检测 DSH 已启用且支持视觉的模型（Xiaomi / OpenCode Zen Go 等），复用系统 API Key，**零配置** **自定义模型**：手动填 OpenAI 兼容端点（URL + Key + 模型…

GitHub ↗

Recommendation signals

49 Tool quality · Based on stars, downloads, maintenance, security and docs
– User interest · Adjusted by in-site views, install copies and download clicks
49 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
MIT
Language
TypeScript
GitHub stars
0
mo. downloads
–
Last push
2026-08-17
Created
2026-08-17

Links

GitHub ↗ npm ↗ Homepage ↗ Report issue ↗

Basic safety check

Findings
None
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin

Related plugins

DeepSeek HarnessClaude CodeCodex New
Score73

modlens

liustack/modlens

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

☆ 2.7K ↓ – Other ↗
DeepSeek Harness New
Score68

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.

☆ 562 ↓ 2.7K Other ↗
DeepSeek Harness New
Score68

dsh-vision-toolkit

Anionex/dsh-vision-toolkit

Vision tasks for text-only models: intent-aware image Q&A, long-screenshot OCR, UI reproduction, grounding, and pixel diff.

☆ 588 ↓ – Other ↗
DeepSeek Harness New
Score67

dsh-vision

linenxi-ctrl/dsh-vision

External vision plugin for DeepSeek Harness: whale-button config panel, image recognition with auto-reply, and agent screenshot/recognize tools.

☆ 12 ↓ 910 Other ↗