dsh-playwright-cli:把 Playwright CLI 接进 DSH 的 agent loop
dsh-playwright-cli 是 DSH 智能体的 Host-only 插件,旨在将 Playwright CLI 常用操作封装为 agent 可调用的工具,实现自动化测试流程。该插件提供四项核心功能:`playwright_version` 探测本地 CLI 状态;`playwright_install` 自动安装浏览器及缺失的测试依赖;`playwright_test` 运行测试套件,支持多种参数配置;`playwright_show_report` 生成并返回 HTML 报告的路由或文件路径。 插件基于 DSH 的 shell 执行器运行,继承其沙箱策略、超时控制及环境变量配置,
Read Moredsh-layered-memory:DSH 跨会话长期记忆插件
dsh-layered-memory 是 DeepSeek Harness (DSH) 的跨会话长期记忆插件,采用 MIT 授权,旨在解决会话结束后上下文丢失问题。该插件将验证过的事实、任务经验和环境信息持久化存储于磁盘,支持跨会话检索。 核心功能包括 L1-L3 分层记忆、命名空间隔离、BM25 全文检索、内容去重及跨命名空间经验提升。插件提供 14 个记忆工具,如 `memory_write`(强制证据验证)、`memory_search`、`memory_index` 等,支持渐进式工具暴露。一致性维护依赖查重、手动更新及合并候选,系统不自动检测矛盾,且严禁物理丢弃已验证事实,仅允许压缩
Read Moredsh-teacher:DSH 插件,把智能体变成苏格拉底式教师
dsh-teacher 是一个基于 DSH 生态的插件化教学工具,旨在将传统的“直接讲解”转变为“苏格拉底式提问引导”。该插件从 Markdown 问题集加载课程,并持久化存储于 SQLite 中。其核心策略是“只问不答”,通过隐藏答案键引导用户思考,同时在会话中实时记录“知识缺口”。 该插件集成 FSRS-5 间隔重复算法,对到期的知识缺口进行按需重测,实现跨会话的长期记忆巩固。此外,它提供无需 LLM 参与的即时测验弹窗(支持多选和填空),测验结束后由 LLM 进行评分和错误点的苏格拉底式复盘。Web 客户端支持查看题库、缺口面板及状态。 安装需 DSH rc.6+ 及 Node ≥ 22
Read MoreConnect OpenMAIC Classroom to DeepSeek Harness with dsh-openmaic
### 版本1(正式技术文档风格): DSH-OpenMAIC is maintained by THU-MAIC from Tsinghua University. It integrates OpenMAIC with DeepSeek Harness: a single request can generate a usable classroom link, and the slides, interactive components and teaching cards written by the intelligent agent can be rendered in real time within the conversation. This article verifies the installation commands, four tools, Socratic skills and configuration items against the catalog page and GitHub repository. ### 版本2(更贴合开源项目介绍口吻): Maintained by THU-MAIC of Tsinghua University, DSH-OpenMAIC connects OpenMAIC to DeepSeek Harness. With it, one single prompt can spawn a fully functional classroom link, and the slides, interactive widgets and teaching flashcards generated by the AI agent can be rendered on-site right in the chat interface. This paper cross-checks the installation commands, four core tools, Socratic questioning skills and configuration items against the project catalog page and GitHub repository.
Read More