DSH-Multimodal

Plugins in this repository

• dsh-multimodalv0.3.3✓

  DSH multimodal input plugin: route file attachments (images, video, audio, text) through per-preset model chains and feed the results to the session model as prompt tokens. Adds a Multimodal settings page.

  package.json

  package.json

  dsh.bundle.patch

  cordis.patch.yml

  Official core packages (15)

  • @deepseek-ai/cordis^4.0.1shared
  • @deepseek-ai/dsh-agent^0.1.0-rc.6shared
  • @deepseek-ai/dsh-api-remotes^0.1.0-rc.6shared
  • @deepseek-ai/dsh-attachment^0.1.0-rc.6shared
  • @deepseek-ai/dsh-client-connection^0.1.0-rc.6shared
  • @deepseek-ai/dsh-client-locale^0.1.0-rc.6shared
  • @deepseek-ai/dsh-client-runtime^0.1.0-rc.6shared
  • @deepseek-ai/dsh-client-ui-conversation^0.1.0-rc.6shared
  • @deepseek-ai/dsh-client-ui-primitives^0.1.0-rc.6shared
  • @deepseek-ai/dsh-client-ui-slots^0.1.0-rc.6shared
  • @deepseek-ai/dsh-client-web-react^0.1.0-rc.6shared
  • @deepseek-ai/dsh-host-apiproxy^0.1.0-rc.6shared
  • @deepseek-ai/dsh-llm^0.1.0-rc.6shared
  • @deepseek-ai/dsh-settings^0.1.0-rc.6shared
  • @deepseek-ai/schemastery^3.18.1shared

Paths are pinned to commit b0795a47a899

Overview

DSH 多模态输入插件：为不同类型的文件（图片 / 视频 / 音频 / 文本）配置独立的处理模型链，在文件进入会话模型之前，先用预设模型把它处理成 Prompt Tokens（文本），再交给会话模型。插件在 DSH 设置中新增独立的 Multimodal 页面。