dsh-vision-router

给 DeepSeek Harness 纯文本模型加视觉：聊天框拖图自动分流给用户配置的视觉模型转文字，v4 不切换模型即可识图。 Vision for text-only DSH models: routes chat-box images to a user-configured vision model and returns text descriptions, deepseek-v4-pro reads images without switching.

Star

7-day growth

Contributors

Language

TypeScript

Updated

2026-08-16

Not an installable plugin package

The package.json declares no dsh.bundle, so even once installed into a profile it is never assembled. It may be an index list, documentation, a standalone app, or still in development — check the repo README for how to use it.

Share card

Drop it into your README — it links back to this page.

Badge (inline)

[![dshfind](https://dshfind.com/api/badge/nlqh7/dsh-vision-router)](https://dshfind.com/en/plugins/nlqh7/dsh-vision-router?ref=badge)

Card (440×200)

[![dshfind](https://dshfind.com/api/card/nlqh7/dsh-vision-router)](https://dshfind.com/en/plugins/nlqh7/dsh-vision-router?ref=badge)

#codex-style #image #multimodal #vision