DialogueContextBridge
Run the following command in DeepSeek Harness:
dsh plugin install ShadowQuill/DialogueContextBridge
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install ShadowQuill/DialogueContextBridge in the DeepSeek Harness terminal to install; the source is at https://github.com/ShadowQuill/DialogueContextBridge
About this plugin
Working on long-cycle projects with an LLM—software development, academic research, product design—the biggest friction is rarely model capability but the session boundary. Every new conversation starts from zero: you re-paste context, re-state decisions, re-explain parameter choices. Key details quietly erode across repeated summaries, and project continuity is artificially broken by session walls.
DialogueContextBridge compiles the real consensus reached in a conversation into a structured three-layer snapshot: verbatim key messages, a compressed structured summary, and user preferences keyed for stable reference. One command injects it into a new session, and the AI instantly picks up everything previously established. All data stays on this machine; snapshots are plain-text Markdown you can export, import across devices, optionally encrypt with AES-256-GCM, and even track with built-in version control.
It is built for heavy LLM users who push a single project across many sessions: developers who need the finalized API and parameters intact, researchers who want to preserve ruled-out approaches and their reasoning chains, designers who rely on fixed style constraints. If your workflow is long-cycle, iterative, and context-dense, this plugin removes the cold-start tax from every new conversation.
Screenshots
Use Cases
- Maintaining LLM context continuity across multiple sessions in long-cycle projects
- Packing finalized code, decisions, and parameters into portable snapshots for a new conversation
- Migrating LLM collaboration memory across devices and accounts with optional encryption
Best For
- Engineers using LLMs for long-term software development and iteration
- Professionals advancing academic research or product design across AI-assisted sessions
- Heavy LLM users who need to manage context across sessions and avoid re-explaining background
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.