dsh-btw
Run the following command in DeepSeek Harness:
dsh plugin install XiaoWind/dsh-btw
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install XiaoWind/dsh-btw in DeepSeek Harness to install this plugin. The full source is hosted at https://github.com/XiaoWind/dsh-btw. Restart the Web app after installation.
About this plugin
The most frustrating moment during a long agent run is not the error—it is suddenly remembering a critical detail while the agent is mid-turn, where interrupting means starting over. dsh-btw solves exactly that: a single /btw command queues your note without interrupting, cancelling, or restarting the in-progress turn.
The semantics are deliberately restrained: the note is appended as an ordinary user message to the next-turn queue, so the current turn completes exactly as planned; multiple /btw notes are delivered in strict FIFO order; once delivered, a note leaves no trace—no persistence, no replay after a restart. There are no configuration knobs. Install, restart the Web process, and you are done.
If you regularly collaborate with a DSH agent on multi-step tasks and find yourself thinking, wait, I need to tell it one more thing while waiting for output, this is the plugin that exists for that moment.
Use Cases
- Remembering an extra detail while the agent is mid-way through a multi-step task
- Wanting to adjust course during a long output without cancelling the current turn
- Queuing multiple follow-up notes that should arrive in submission order on the next turn
Best For
- Developers who run multi-step tasks with a DSH agent
- Collab users who frequently have follow-up thoughts while waiting for agent output
- Heavy users who prioritize an uninterrupted agent workflow
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.