dsh-query-jump
Run the following command in DeepSeek Harness:
dsh plugin install SocFeng/dsh-query-jump
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, please execute the command: dsh plugin install SocFeng/dsh-query-jump. Source: https://github.com/SocFeng/dsh-query-jump
About this plugin
When using DeepSeek Harness for extensive conversations, users often forget their previous specific queries, making it tedious to manually sift through hundreds of messages to find a particular topic. The dsh-query-jump plugin addresses this by adding a subtle, light-colored short line to the right edge of the chat area. Hovering over it reveals a list of your actual questions with timestamps, helping you quickly establish a timeline. Clicking a list item smoothly scrolls to the corresponding message bubble, with the currently active item highlighted. Whether you are reviewing historical context or repositioning key nodes, this lightweight tool significantly improves reading and interaction efficiency in long sessions, making memory retrieval effortless.
Use Cases
- Quickly locate historical questions in super long conversations
- Review conversation timeline to clarify context
- Click list items to smoothly jump to specific messages
Best For
- Users who need to frequently review historical questions
- Developers handling long and complex tasks
- People who want to improve long session reading efficiency
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.