dsh-vision-bridge
Adds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.
通过已配置的 DSH Provider 或 OpenAI 兼容端点提供图片输入与识别。
How to install
dsh plugin add dsh-vision-bridge About
dsh-vision-bridge DSH 插件：为纯文本模型提供视觉能力，复用 DSH 已添加的 Provider，也支持新增 OpenAI 兼容直连 Provider，**带设置页可视化配置**。 功能 提供 vision_bridge_read_image 工具：手动触发图片识别，返回结构化文本证据（OCR + 布局 + 语义） 粘贴图片时自动接管：上传图片并插入紧凑的一图一 ID 引用（例如 「▧ 图片 #KdAy1D」） **无厂商硬编码**：Provider 与模型列表实时读取 DSH registry **设置页「插件 → 视觉桥接」子菜单**：选择 DSH Provider，或新增自定义 Provider，保存即热生效 **连通性测试**：一键向视觉 API 发送测试图，返回延迟与响应样本 **不注册 wrapper provider**：选择 DSH Provider 时复用其 adapter、凭据和 attachment 通道 安装 bash 方式一：DSH 插件 CLI（自动写入 bundles） dsh plugin --profile web add github:alaxrpg/dsh-vision-bridge 方式二：手动安装 cd ~/.dsh/profiles/web pnpm add github:alaxrpg/dsh-vision-brid…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-28
- Created
- 2026-08-25
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin
Related plugins
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.
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
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.
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.