AI Agent Hub
Back to plugins
🖥️

dsh-prompt-history

Client Updated 2026.08.26

Run the following command in DeepSeek Harness:

dsh plugin install Xiaofei-fei/dsh-prompt-history

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

Run dsh plugin install Xiaofei-fei/dsh-prompt-history in your terminal to install this plugin; the source repository is available at https://github.com/Xiaofei-fei/dsh-prompt-history.

About this plugin

The DSH Web input box has long been a plain text field—retrieving your previous prompt meant retyping from memory, and copying a code block required manual selection plus a right-click. dsh-prompt-history brings Linux shell-like input ergonomics into the DSH Web composer: press Up-arrow to recall history with prefix matching, hit Ctrl+R for incremental reverse search, and enjoy terminal-consistent paste and copy behaviors that keep a keyboard-first workflow flowing smoothly.

Beyond arrow-key recall, the plugin offers two copy-and-quote modes (toolbar buttons or auto-copy-on-select), optional cross-session history persistence (up to 200 entries stored locally in the browser), and a draggable Chat TOC that lists every message you have sent so you can jump to any of them in a long conversation. All features are purely UI-level: they produce no session events, make no model requests, and recalled text only enters the input draft until you press Enter.

If you frequently revisit past prompts, copy code snippets, or prefer a terminal-style keyboard workflow in DSH Web, this roughly 12 KB client-side plugin can meaningfully speed up your daily input without any network setup or backend changes.

Use Cases

  • Recall previously sent prompts with arrow-key navigation in long chats
  • Select text from messages or code blocks to copy or quote instantly
  • Jump to any historical message via a draggable chat table of contents

Best For

  • DSH Web users who prefer keyboard-driven workflows
  • Developers who frequently quote or copy code snippets from chat
  • Power users managing long conversation contexts in AI assistants