dsh-session-export
Run the following command in DeepSeek Harness:
dsh plugin install bwndlct/dsh-session-export
Paste the following prompt into your AI chat to install this plugin:
To install the dsh-session-export plugin in DeepSeek Harness, run the command dsh plugin install bwndlct/dsh-session-export, or get the source from https://github.com/bwndlct/dsh-session-export.
About this plugin
When using DeepSeek Harness (DSH) for complex tasks, session logs are often buried and hard to read or share directly. The dsh-session-export plugin addresses this by exporting the current session's event-sourced log into self-contained Markdown and JSON files, making your conversation records portable, human-readable, and structurally clear.
At its core, this plugin faithfully reproduces the execution order of the session—from user messages and assistant replies to tool calls and results, everything is preserved sequentially. The export uses a stable schema versioning for future compatibility, while a robust design handles unknown events and anomalies without crashing. You can trigger exports anytime via the session_export() tool or with a single slash command in the Web UI, consuming zero model tokens.
Whether you're a DSH developer archiving debug sessions, an AI researcher analyzing conversation patterns, or a team sharing task records for collaboration, dsh-session-export offers reliable support. With zero runtime dependencies and cross-platform safe filenames, the export process integrates seamlessly into your workflow.
Use Cases
- Exporting records for analysis when developers debug complex session flows.
- Sharing complete conversation context and tool call details during team collaboration.
- Archiving important interaction sessions for subsequent review or training data preparation.
Best For
- Developers and engineers using DeepSeek Harness.
- Data scientists or researchers working on AI interaction studies.
- Teams that need to manage and archive records of automated workflows.
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.