dsh-context-management
Run the following command in DeepSeek Harness:
dsh plugin install PlxloYzb/dsh-context-management
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness by running dsh plugin install PlxloYzb/dsh-context-management; the source code is available at https://github.com/PlxloYzb/dsh-context-management.
About this plugin
In DSH multi-profile workflows, the default Basic compression strategy bundled with each preset often falls short of real-world context-window management needs. dsh-context-management fills that gap: it automatically takes over the native Basic compression of every preset in a target profile, replacing the default behaviour with a more flexible mechanism while leaving presets that have no native compression (such as minimal) completely untouched.
The plugin centres on three capabilities. Context window rotation lets you swap conversation windows seamlessly without losing critical context. Reversible compression condenses long histories into summaries while preserving a path to full restoration. History retrieval enables targeted search and reference within already-loaded context. Together they turn context management from passive truncation into active scheduling.
If you are working on DSH 0.1.2-rc.1 with multiple profiles and presets, and you need fine-grained control over context windows, dsh-context-management offers a lightweight, reversible, and low-intrusion layer on top of what DSH already provides.
Use Cases
- Swap conversation windows in long sessions without losing critical context
- Condense verbose history into summaries and restore full context on demand
- Unify and schedule compression across multiple preset profiles
Best For
- Developers working with DSH multi-profile setups
- Users seeking fine-grained context window control
- DSH users wanting to replace the default Basic compression strategy
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.