AI Agent Hub
Back to plugins
🖥️

dsh-plugin-model-switcher

Client Updated 2026.08.21

Run the following command in DeepSeek Harness:

dsh plugin install Mrlilili/dsh-plugin-model-switcher

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install Mrlilili/dsh-plugin-model-switcher in your DSH shell to install this plugin; the source code is available at https://github.com/Mrlilili/dsh-plugin-model-switcher. Restart DSH after installation to activate the shortcuts.

About this plugin

Switching models or adjusting reasoning effort in DSH usually means reaching for the mouse and clicking through dropdowns — an easy way to break your flow. dsh-plugin-model-switcher condenses these two high-frequency actions into keyboard shortcuts, so you can swap models or tune reasoning depth without lifting your hands off the keyboard.

Press Ctrl+Shift+M (Cmd+Shift+M on macOS) to cycle through the models available under your current provider, or Ctrl+Shift+R to step through the reasoning-effort levels (off → low → high → max → off). A brief toast notification in the bottom-right corner confirms each switch, so you always know which model or effort level is active.

This plugin is a great fit for developers who work with multiple model providers simultaneously, compare outputs across models on the fly, or want to dial reasoning depth up or down depending on task complexity — all without leaving the keyboard.

Use Cases

  • Rapidly cycle among models from different providers to compare output quality
  • Adjust reasoning effort levels on the fly based on task complexity
  • Stay fully keyboard-driven and avoid the context-break of mouse-driven dropdowns

Best For

  • Developers who juggle multiple model providers and switch frequently
  • Heavy DSH users who prefer a keyboard-driven workflow
  • Prompt engineers who want fine-grained control over reasoning depth