dsh-session-link-pro
Run the following command in DeepSeek Harness:
dsh plugin install shenhuanageshei/dsh-session-link-pro
Paste the following prompt into your AI chat to install this plugin:
Install it in DeepSeek Harness by running dsh plugin install shenhuanageshei/dsh-session-link-pro; the full source is available at https://github.com/shenhuanageshei/dsh-session-link-pro .
About this plugin
When you run multiple sessions in DeepSeek Harness to advance different tasks in parallel, those sessions are completely isolated: you cannot see what a neighboring session is doing, cannot hand off a partial conclusion from one session to another, and archiving or reviewing a session means manually scrolling through the UI. dsh-session-link-pro exists to fill that gap, turning parallel session silos into a communicative, traceable collaboration network.
Five core capabilities drive the value: session deep-links let you copy and paste a read-only snapshot into any session; a workspace-level session list shows each session topic, run state, and recent message summary at a glance; session export produces a human-readable Markdown file plus a lossless JSON dump of all events; cross-session messaging distinguishes steer (inject at the current step boundary for a running target) from followup (wake an idle target and immediately trigger an LLM response as a new turn), with source metadata so the receiver can reply directly; and paired channels, established after mutual one-time approval, create bidirectional confirmation-free messaging ideal for iterative auto-testing loops. Received cross-session messages render as a prominent highlighted card so they stand out clearly in the chat stream.
This plugin is best suited for developers who decompose complex workflows across two to five concurrent DSH sessions-searching, summarizing, and coding in parallel-while needing to pass intermediate results, archive final artifacts, or run confirmation-free back-and-forth between specific session pairs. If you work linearly in a single session the benefit is limited, but if you manage multiple parallel sessions and frequently need cross-session collaboration it will measurably reduce context-switching overhead.
Use Cases
- Running several DSH sessions in parallel and sharing intermediate results across them
- Archiving a session by exporting the full conversation to Markdown and JSON
- Two sessions in an iterative debug loop that need confirmation-free bidirectional messaging
Best For
- Workflow developers managing two to five parallel DSH sessions
- Heavy users who relay context across sessions and archive conversations
- Developers who split complex tasks across multiple sessions and need frequent cross-session interaction
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.