AI Agent Hub
Back to plugins
🧠

dsh-session-import

Memory Updated 2026.09.12

Run the following command in DeepSeek Harness:

dsh plugin install kinyokun/dsh-session-import

Paste the following prompt into your AI chat to install this plugin:

Install the plugin in DeepSeek Harness by running dsh plugin install kinyokun/dsh-session-import; source code is available at https://github.com/kinyokun/dsh-session-import.

About this plugin

Once a DSH conversation is exported, it is usually just a pile of JSONL files and scattered attachments. Copying them to a new machine does not let you keep chatting, and the sub-session hierarchy, model settings, and system prompts are all lost. dsh-session-import turns that into a single step: on the new-session page, click Import Conversation, pick a ZIP or raw JSONL, preview the validation report, choose a target workspace, and the entire session tree lands as one resumable conversation.

The plugin writes, validates, and closes sessions through the official DSH SessionHandle, preserving history messages, system prompts, model state, Agent presets, and parent-child relationships among sub-sessions. Image and file attachments are verified by SHA-256 before their references are restored; raw JSONL imports require the target DSH to already hold the attachment bytes. On any anomaly the plugin unmounts the root session and moves the created directory into a recovery area, and a finished import can be safely rolled back with a dry-run preview.

Ideal for developers and power users who migrate DSH conversations across machines, back up session history regularly, or want to pick up previous work seamlessly on a fresh DSH instance.

Use Cases

  • Migrate local DSH conversations to a new machine or workspace
  • Resume conversations seamlessly on a fresh DSH instance after export
  • Periodically back up DSH session history for disaster recovery or audit

Best For

  • Developers sharing DSH conversations across multiple machines
  • Power users needing regular session history backups
  • Users wanting to continue previous work on a fresh DSH instance