AI Agent Hub
Back to plugins
🧠

dsh-workspace-history

Memory Updated 2026.09.01

Run the following command in DeepSeek Harness:

dsh plugin install joao-paulo-santos/dsh-workspace-history

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

Clone the source from https://github.com/joao-paulo-santos/dsh-workspace-history into your DeepSeek Harness plugins folder alongside its dependencies, then restart the harness to activate the plugin.

About this plugin

When handling long conversations in DeepSeek Harness, context compaction is inevitable, yet the resulting summary vanishes from the chat stream once generated, leaving no way to revisit it later. dsh-workspace-history solves this by journaling every auto-compaction or manual /compact summary as a timestamped Markdown file in the session workspace, building a complete chronological timeline for each project.

In practice, journal files are named by Unix timestamp, so a simple ls reads as a project timeline and a glob pattern isolates one session. With dsh-workspace-overview installed, a History subtab appears in the Workspace Overview: the left panel lists summaries newest-first and the right panel renders the selected entry as Markdown, loading one at a time. A per-session toggle controls whether history is saved, and failure diagnostics are written to .diag.log.

This plugin is well suited for DSH users who frequently trigger context compaction, need to audit summary quality after the fact, or compare summaries across rounds, especially when running multiple concurrent sessions in the same workspace and want per-session history isolation.

Use Cases

  • Review every compaction summary in chronological order after a long session
  • Isolate compaction history per session when running multiple concurrent sessions in one workspace
  • Audit compaction quality and compare summaries across rounds to catch lost context

Best For

  • DSH users who frequently trigger context compaction and need to audit summaries afterward
  • Developers managing multiple concurrent sessions in the same workspace
  • Teams that value context quality and require traceable compaction records