Skills Plugins MCP Prompt Model 导航 博客 资讯 我的中心
会话与消息 #dsh-plugin#dsh#deepseek#deepseek-harness#learning#local-first

dsh-explain

学习模式:把已完成工作里的概念讲清楚并安排轻量复习(开发中)。

dsh-external @dsh-external ⬇ 2 ★ 11 main

安装

dsh plugin --profile web add github:dsh-external/dsh-explain
下载安装清单

需要可复现安装时,可在仓库后追加 #commit 固定提交。

学习模式:把已完成工作里的概念讲清楚并安排轻量复习(开发中)。

该插件未提供要点说明,请参考仓库 README。

dsh-plugindshdeepseekdeepseek-harnesslearninglocal-first
  1. 安装并启动 DeepSeek Harness:npx @deepseek-ai/dsh web
  2. 在终端执行上面的安装命令(CLI 会解析插件并核验来源)
  3. 用 dsh plugins list 确认已安装,必要时重启 Harness 生效

插件以当前 dsh 进程的权限运行,安装时可能执行代码。请先通读仓库源码与许可证,确认无破坏性命令与越权访问;本站只做索引,不对第三方插件安全性作担保。

代码仓库github.com/dsh-external/dsh-explain
许可证MIT
主要语言main
下载量2
GitHub 星标11
最近推送2026-09-15
收录日期2026-09-19
分类会话与消息

事实信息来自公开插件目录快照(2026-10-03),介绍文案由本站再加工。

以下为插件仓库 README 全文(原始内容,由公开目录抓取整理)。

English · 简体中文

  [图片: dsh-explain — turn everyday work into a private, continuous learning loop]

  [图片: DSH 0.1.6-alpha.1]

  [图片: CI]

  [图片: Latest release]

  [图片: Local first]

  [图片: MIT License]

  Quick start ·
  Watch the full demo ·
  Privacy model ·
  Reproduce the recording

`dsh-explain` is a learning-mode plugin for [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness). It turns useful concepts from completed work into structured explanations, schedules lightweight reviews, and lets you inspect or correct what it learns about you.

The primary agent stays untouched. Explain uses its own model calls, scheduler, context, and local SQLite database.

## See the learning loop

![A real DSH Web flow that captures a completed answer, reviews a concept, corrects a learner preference, and exports local data](https://raw.githubusercontent.com/yuezengwu/dsh-explain/main/docs/assets/dsh-explain-demo.gif)

The 28-second preview runs against real assembled DSH Web `0.1.2-rc.1` with deterministic, private fixture data. [Watch the higher-quality MP4](https://raw.githubusercontent.com/yuezengwu/dsh-explain/main/docs/assets/dsh-explain-demo.mp4) or read the [recording contract](https://github.com/yuezengwu/dsh-explain/blob/main/docs/DEMO.md).

| Capture | Review | Adapt |
|---|---|---|
| Turn a finalized answer or selected text into an editable `/explain` draft. Nothing submits automatically. | Revisit due concepts through recall, application, and distinction questions. | Inspect explanation preferences and topic familiarity, then correct or forget an inference. |

## Quick start

The current development and installation baseline is DSH `0.1.6-alpha.1`, published on 2026-09-15 and available through npm `alpha`. npm `next` remains `0.1.5-rc.2` and `latest` remains `0.1.5-rc.1`; all seven previously verified hosts remain supported. Pin the version explicitly; see the [compatibility contract](https://github.com/yuezengwu/dsh-explain/blob/main/docs/COMPATIBILITY.md) for exact source revisions, asynchronous Session history reads, and verification.

```sh
npx @deepseek-ai/dsh@0.1.6-alpha.1 plugin --profile web add github:yuezengwu/dsh-explain#v0.3.0
npx @deepseek-ai/dsh@0.1.6-alpha.1 --profile web
```

Open **Settings → Learning**, choose an auxiliary provider and model, enable learning mode, and save. Explain observes only future completed top-level turns; it does not scan existing history.

Git-hosted plugins build during installation. If pnpm requests build approval, add the printed `dsh-explain` entry to the profile's `pnpm-workspace.yaml`, then repeat the install command. For automated runs that should not open a browser, start DSH with `--no-open`.

> The commands pin Explain [v0.3.0](https://github.com/yuezengwu/dsh-explain/releases/tag/v0.3.0). Omit `#v0.3.0` only when you want the current `main` branch.

## Start from the work itself

| Entry point | What happens |
|---|---|
| `/explain ` | Requests an explanation using the current session as bounded source context. |
| **Explain selected text** | Creates an editable `/explain --selection …` draft from visible text. |
| **Learn from this answer** | Creates an editable draft tied to the exact finalized assistant turn. |
| Automatic evaluation | May add one useful explanation after an eligible turn, within your configured budget. |
| `/review` | Opens or resumes a local review round in the Learning tab. |

Each explanation answers three practical questions: **What is it? Why does it matter here? What is the common pitfall?** Choose **Got it** to close the card, or **Not yet** for a different explanation.

## Review, then correct the model

Concepts marked **Got it** enter a local spaced-review schedule. **Learning → Today's review** selects up to three due concepts. Each concept advances from recall to application to distinction after successful answers; an unsuccessful answer repeats that skill next time. The auxiliary model evaluates each answer as **Mastered**, **Partial**, or **Forgotten** and schedules the next review at a deterministic interval. Partial or forgotten concepts are treated as learning again and can receive a new explanation; an active explanation pauses that concept's quiz.

**Learning → Learning overview** exposes the current judgments about explanation length, structure, examples, terminology, and topic familiarity—with confidence and source links. You can correct an inference, forget it, or set an explicit preference. Precedence is fixed and visible: **explicit preference → user correction → model inference**.

## One learning thread, many sessions

- Every `$DSH_HOME` owns exactly one Explain learning thread; resumes and forks never copy it.
- Every source session has at most one explanation awaiting feedback.
- One global scheduler serializes explanations, reviews, autonomous evaluation, rephrases, and compaction.
- Autonomous evaluation has a persistent rolling 24-hour budget, configurable in Settings.
- Rephrasing still works if a source session is later deleted because only a bounded source summary is retained.

## Local-first by design

| Data | Behavior |
|---|---|
| Learning thread | Stored in `$DSH_HOME/dsh-explain/v1/thread.sqlite`. |
| Enablement and model settings | Stored through DSH settings in `$DSH_HOME/settings.yaml`. |
| Source material | Reduced to bounded capsules; rephrasing retains at most a 2,000-character restricted summary. |
| Global learning context | Sent with bounded source text to the configured auxiliary provider. Local storage does not imply offline model inference. |
| Export | A versioned local backup excludes private source summaries and filters common credential/path formats in public text. Arbitrary private prose may remain; review before sharing. |
| Clear | A typed `CLEAR` confirmation atomically removes learned content while preserving runtime settings and the active budget window. |

Explain uses first-party DSH conversation, composer, assistant-action, and settings extension points. It does not require patches to DSH or other plugins.

## Compatibility and verification

| Check | Current result |
|---|---|
| DSH compatibility | `0.1.6-alpha.1` published packages; `0.1.2-rc.1`, `0.1.3-alpha.1`, `0.1.3-alpha.2`, `0.1.5-alpha.1`, `0.1.5-alpha.2`, `0.1.5-rc.1`, `0.1.5-rc.2`, `0.1.6-alpha.1` assembled source |
| Unit and integration | 84 tests on each source version |
| Assembled DSH Web | 7 scenarios per source version |
| Explain-owned shortcuts | 3 M6 scenarios |
| Production package | Build and pack dry-run |
| Real auxiliary model | DSH `0.1.6-alpha.1` + `deepseek-flash`: explanation, rephrase, corrected preference, correct/incorrect review, exact-answer command, export and clear |

See the [acceptance matrix](https://github.com/yuezengwu/dsh-explain/blob/main/docs/ACCEPTANCE.md) for coverage and the [2026-09-15 real-model acceptance](https://github.com/yuezengwu/dsh-explain/blob/main/docs/REAL_MODEL_ACCEPTANCE.md) for the current model route, sample, screenshots, and test limits. DSH remains a developer preview; Explain follows its current public API line instead of retaining compatibility layers for private-preview packages.

## Local development

The default development install uses published `0.1.6-alpha.1` API packages, with a version-scoped repair for their [missing store runtime dependencies](https://github.com/yuezengwu/dsh-explain/blob/main/docs/COMPATIBILITY.md#发布包依赖修复). Assembled-Web tests accept a built DSH checkout for any of the eight versions above. The existing demo recording remains on `0.1.2-rc.1`:

```sh
pnpm install
DSH_SOURCE_DIR=/absolute/path/to/dsh pnpm dsh:link
DSH_SOURCE_DIR=/absolute/path/to/dsh pnpm dsh:link:check
pnpm typecheck
pnpm test
DSH_SOURCE_DIR=/absolute/path/to/dsh pnpm test:web
DSH_SOURCE_DIR=/absolute/path/to/dsh pnpm test:m6
pnpm build
```

Install this checkout directly for manual development:

```sh
dsh plugin --profile web add /absolute/path/to/dsh-explain
dsh --profile web --dump-config
dsh --profile web
```

## Documentation

| Document | Purpose |
|---|---|
| [Demo production](https://github.com/yuezengwu/dsh-explain/blob/main/docs/DEMO.md) | Storyboard, privacy contract, commands, assets, and artwork provenance. |
| [Product requirements](https://github.com/yuezengwu/dsh-explain/blob/main/docs/PRD.md) | User model, scope, policies, and acceptance criteria. |
| [Architecture](https://github.com/yuezengwu/dsh-explain/blob/main/docs/ARCHITECTURE.md) | Persistence, scheduling, RPC, UI integration, and failure behavior. |
| [Acceptance matrix](https://github.com/yuezengwu/dsh-explain/blob/main/docs/ACCEPTANCE.md) | Automated and real-flow evidence. |
| [Iteration plan](https://github.com/yuezengwu/dsh-explain/blob/main/docs/NEXT.md) | Completed milestones and follow-up sequencing. |

## License

[MIT](LICENSE)

数据来源:公开的 DeepSeek Harness 插件目录与各插件 GitHub 仓库。本站为独立第三方目录,与 DeepSeek、幻方(High-Flyer)及插件作者均无隶属或背书关系。

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。