dsh-task-kanban:面向 DSH web 的任务看板插件

DSH 插件 `dsh-task-kanban` 旨在 DSH Web 主界面中实现从需求到代码合并的全流程自动化管理。该插件将自然语言需求细化为串行执行的 Phase 计划,并在独立的 `git worktree` 中严格单并发执行,全部完成后自动合入主分支并清理工作区,解决多会话切换与状态追踪难题。核心功能包括五泳道看板(需求、队列、运行中、已完成、已合并),支持通过 Skill 驱动需求细化,具备队列 FIFO 执行、任务状态可视化及停止重试机制。用户可通过 npm 或本地源码安装,并在插件配置中调整并行 Worker 数、模型及推理强度。该插件适合希望将智能体任务流程化、自动化管理的

Read More
dsh-kanban: A Task Kanban Plugin for DeepSeek Harness Web UI

dsh-kanban is a task board plugin designed specifically for the DeepSeek Harness (DSH) Web UI, aiming to enhance the task management experience through a sidebar without replacing the host application. The plugin organizes Harness sessions into a five-column view: Inbox, Ready, Running, Blocked, and Done. Among these, the Running, Blocked, and Done states are automatically derived from live sessions, while idle sessions can be manually categorized into Inbox or Ready, with manual placements saved in the browser's local storage. Core features include viewing session status via the `/kanban` entry point, organizing pending tasks, and creating new tasks directly from the board using the Harness runtime, ensuring seamless integration with the host

Read More
DPH Task Board (@dph/taskboard): Adding a Status Dashboard to DeepSeek Harness Sessions

The DPH Task Board (@dph/taskboard) is a DeepSeek Harness community plugin designed to transform multi-session management into a visualized four-column status board (Todo, In Progress, In Review, Done). This plugin treats sessions as cards, supporting drag-and-drop categorization, attaching notes, priorities, and tags, along with search, JSON export for backup, and import functionality. It is deeply integrated into the Harness sidebar, allowing configuration of the model, reasoning intensity, and grouping when creating new sessions, and it displays the real-time running status of sessions via a "processing" breathing light. Data is primarily stored in the browser's localStorage, while the host side persists the board state to a local JSON file, enabling agents to directly read and analyze current work progress. The installation process requires a Node.js 18+ environment and goes through the deployment script.

Read More