dsh-vision-bridge
Routes images to a vision model of your choice - auto-rewrite, explicit tools, or hybrid - so a text-only chat model does not fail a turn that contains a picture.
将图片交给所选的视觉模型处理（自动改写、显式工具或混合模式），使纯文本聊天模型也能处理包含图片的对话。
How to install
dsh plugin add @goodandready/dsh-vision-bridge About
dsh-vision-bridge **Universal vision bridge** for DeepSeek Harness (dsh) — a self-contained replacement for dsh-vision-router. When the chat model has **no vision** (e.g. deepseek-v4-flash) and a message contains an image, the image never reaches the text-only model. Instead, the plugin picks **how** to handle it — depending on the configured **mode**: **hybrid** (default) — auto-rewrite image blocks into text descriptions using a vision model; tools stay available for explicit follow-ups. **llm** — auto-rewrite via vision model only (the text-only model never sees raw images); tools remain ca…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-27
- Created
- 2026-08-18
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh, dsh-plugin
Related plugins
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
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.
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.
dsh-deepseek-vision
siegfly/dsh-deepseek-vision
A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.