dsh-workspace-history
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
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.