dsh-session-pause
Run the following command in DeepSeek Harness:
dsh plugin install watericetangcw/dsh-session-pause
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install the plugin via command: dsh plugin install watericetangcw/dsh-session-pause. Full source code address: https://github.com/watericetangcw/dsh-session-pause.
About this plugin
When working with DeepSeek Harness on extended tasks, users often need to interrupt sessions without losing progress, but native pause functionality may be lacking, forcing restarts or manual state management. The dsh-session-pause plugin addresses this by offering a one-click pause feature that gracefully halts the session at a boundary, persisting all messages, tool calls, and context into the existing JSONL log. This enables seamless resume later—even after restarting DSH or switching machines—making it seem as if the session never paused. Its core capabilities include non-intrusive integration (without modifying DSH code), comprehensive state preservation, and cross-session recovery. It is ideal for users handling complex tool-chain processes or long-running research and development tasks, providing flexible control over workflows.
Use Cases
- Taking a break during complex tool-chain tasks.
- Resuming sessions after restarting DSH.
- Queuing new messages while paused for later processing.
Best For
- Developers managing long-running code execution tasks.
- Researchers conducting multi-step experiments or data analysis.
- Advanced users seeking customization and control over session flows.
Related Plugins
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.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.