中文

← Back to list

dsh-vision-solution

DeepSeek Harness Other Low risk

Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.

为 DSH 纯文本模型补充视觉能力：识图技能（图片理解/OCR/文档解析，竞速池→自定义通道→本地）+ 幂等宿主补丁，让图片消息能送达模型侧。

How to install

DeepSeek Harness dsh plugin add github:br1nosense/dsh-vision-solution

About

dsh-vision-solution **让 DeepSeek Harness (DSH) 里的纯文本模型（如 DeepSeek）也能发送并识别图片。** 本项目把两个东西整合成一个自包含方案： 1. **识图技能** — ds-vision-skill（v0.5.1，MIT）：图片/截图/PDF/OCR 的统一路由与识别，输出标准 JSON 交给主模型继续推理。 2. **宿主补丁** — vision-patch（幂等补丁引擎）：移除 DSH 对"纯文本模型 + 图片"的拦截，让图片消息能送达到模型侧。 装上即用：**纯文本模型发图不再被拒，图片自动交给视觉 API 识别。** --- 为什么需要它 很多编码/推理 Agent 是纯文本模型（例如通过火山方舟托管的 DeepSeek 系列）。它们本身没有视觉能力，而且 DSH 会在两处直接拒绝图片消息： 发送图片时：Model "xxx" does not support image input. 切换到纯文本模型但会话已含图片时：does not accept image input... 本项目通过**宿主补丁**移除这两处拒绝，并把图片以"带本地路径的占位文本"（[图片附件：xxx，本地路径：...]）送给模型；模型据此调用识图技能里的 vision-router.ps1，把图片交给**火山方舟 doubao-seed-…

GitHub ↗

Recommendation signals

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

Meta

License
NOASSERTION
Language
PowerShell
GitHub stars
0
mo. downloads
–
Last push
2026-08-17
Created
2026-08-14

Links

GitHub ↗ Report issue ↗

Basic safety check

Findings
curated 收录但无 npm 包/安装命令
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
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).

☆ 2.8K ↓ – Other ↗
DeepSeek Harness New
Score69

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.

☆ 630 ↓ 2.7K Other ↗
DeepSeek Harness New
Score69

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.

☆ 616 ↓ – 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 ↗