dsh-vision-router

仓库内包含的插件

• @deepseek-ai/dsh-vision-routerv0.2.0

  Codex-style image offload for DeepSeek Harness: routes chat-box images to a user-configured vision model and feeds the text description back to a text-only primary model (e.g. deepseek-v4-pro).

  package.json

  package.json

  dsh.bundle.patch

  —

  官方核心包 (6)

  • @deepseek-ai/cordis^4.0.1共享
  • @deepseek-ai/dsh-agent^0.1.0-rc.6共享
  • @deepseek-ai/dsh-attachment^0.0.1-rc.1共享
  • @deepseek-ai/dsh-invariants^0.0.1-rc.1共享
  • @deepseek-ai/dsh-llm^0.0.1-rc.1共享
  • @deepseek-ai/schemastery^3.18.1私有副本

路径固定于提交 0a6443bdcbb0

概览

给 DeepSeek Harness 纯文本模型加视觉：采用codex风格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.