lolipop-1x1/dsh-you-should-know ↗★ 0
dsh-you-should-know
在任务中提醒用户理解重要事实与方案取舍 适合需要决策提醒的DSH用户,在任务中自动提示关键事实与方案取舍。
安装
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lolipop-1x1/dsh-you-should-know说明文档
阅读完整 README ↗Usage
Automatic observation is enabled by default, and the observer follows the main session model. Existing saved settings are preserved. Start a task normally; short tasks usually do not reach a check, and a note is not guaranteed on every turn.
| Action | Result |
|---|---|
| Learn more | View the reason and impact; reuse an existing explanation in the same language when available |
| Knew this already / Understood | Save the topic to reduce repeated notes |
| Chat in main session | Insert the note and explanation only when there is no draft or attachment; you send it |
| Dismiss | Close the note and briefly offer feedback options |
| Minimize / Open note | Change the panel display without submitting feedback or marking the topic as understood |
Notes help you understand a task. They are not fact checks or execution reviews: they may miss important details or be inaccurate. Bring a note into the main session when you want to discuss it further.
Usage and data
Automatic observation makes extra model calls, even when no note appears. The plugin currently uses full conversation context without trimming or an extra summarization call. Disable observation, increase the interval, or set a per-turn limit to control extra calls. Expanding a note makes a separate model request when no usable explanation exists. Cancellation does not guarantee that remote billing stops.
Requests use the model services already configured in Harness. When you select an independent observer model, full context is sent to that model's provider. The plugin does not store its own API keys, add telemetry, or upload feedback externally.
Notes, explanations, topics, and required interaction state are saved in the Harness storage domain; the host manages the path and backend. Full request snapshots stay in memory only. Prompts ask the model not to repeat credentials or personal information in notes, but this does not remove such information from the full context sent to the model.