PiedPiper911/dsh-workflow-canvas

Name: PiedPiper911/dsh-workflow-canvas
Author: PiedPiper911

Plugin插件 Native原生 ⭐ 4 Subagents & Orchestration子代理与编排

PiedPiper911 的 DSH 插件 — dsh-workflow-canvas

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

dsh-workflow-canvas is a native plugin built exclusively for DeepSeek Harness (DSH), designed to provide a visual drag-and-drop interface for building custom DSH workflows. It leverages the React Flow library for interactive node drawing and Zustand for lightweight state management, letting users drag and drop nodes to arrange tool calls, sub-agent tasks, and conditional branching logic. Installing the plugin is straightforward: users only need to run the command dsh plugin add @piedpiper911/dsh-workflow-canvas in their terminal to add it to their running DSH instance. It directly integrates with DSH's built-in ctx.workflows execution engine once installed.

The plugin offers five core node types: Trigger for workflow entry, Tool for single tool calls, Agent for delegating tasks to a sub-agent, Condition for conditional branching, and Output for formatting final results. To build a workflow, users drag nodes from the toolbar onto the canvas, connect them with edges to map out the process flow. Once the graph is complete, the plugin automatically compiles it into an ordered step list that matches the exact format DSH's workflow engine requires. This tool is ideal for DSH users who prefer visual workflow design over manually writing workflow configuration files.

After building the workflow, users can run it directly in DSH or export it as a .workflow.json file for later reloading and editing. The plugin uses a transport-agnostic data model, so the canvas is just a view layer over plain JSON workflow specifications, making it compatible with any DSH workflow provider. It is released under the permissive MIT license, so it is free to use, modify, and redistribute. For developers who want to contribute or modify the plugin, the development process uses npm, with commands to run a local demo or build the production package.

dsh-workflow-canvas 是一款专为 DeepSeek Harness (DSH) 开发的原生可视化工作流构建插件。它允许用户通过拖拽节点的方式，编排工具调用、子代理任务和条件分支，最终生成符合 DSH 工作流引擎要求的有序步骤列表，可直接通过 DSH 内置引擎运行。用户只需要在命令行执行 dsh plugin add @piedpiper911/dsh-workflow-canvas 即可一键完成安装。

该插件共支持五种节点类型，分别是工作流触发入口节点、单工具调用节点、子代理任务节点、条件分支节点和结果输出节点。用户先在画布上拖拽所需节点，连接节点形成流程图，插件会自动将流程图编译为 DSH 工作流引擎可识别的有序步骤列表。它适合需要可视化编排多步骤代理任务、不想手动编写工作流配置的 DSH 进阶用户使用。

该插件基于 React Flow 和 Zustand 开发，采用 MIT 开源许可，完全免费供个人和商用。它输出的工作流是标准 JSON 格式，可导出保存后再次加载编辑，数据模型传输无关，可兼容任意 DSH 工作流提供者。如果开发者需要对其进行二次开发，可以按照官方步骤安装依赖、启动本地调试，编译完成后即可打包使用。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-workflow-canvas（PiedPiper911/dsh-workflow-canvas）
仓库：https://github.com/PiedPiper911/dsh-workflow-canvas
本站详情页：https://www.yhbd.top/plugins/piedpiper911-dsh-workflow-canvas/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证未声明 · ⭐ 4 · 最近提交 2026-08-17 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 2 warnings2 项注意

No license declared - all rights reserved by default; ask the author before commercial use or redistribution未声明开源许可证 —— 默认「保留所有权利」，商用或再分发前先问作者
Only 4 stars - very few users, little community feedback星标只有 4，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin add @piedpiper911/dsh-workflow-canvas

把 PiedPiper911/dsh-workflow-canvas 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

1.4 KB · 缓存于 2026-08-27 05:42:05 · 1.4 KB

dsh-workflow-canvas 🧭

Visual workflow builder for DeepSeek Harness (DSH). Drag and drop nodes to orchestrate tool calls, sub-agents, and conditional branches into a workflow that runs through DSH's ctx.workflows engine. Powered by React Flow (xyflow) and Zustand.

Install

dsh plugin add @piedpiper911/dsh-workflow-canvas

Node types

Node	What it does
▶ Trigger	Workflow entry point (a prompt).
⚙ Tool	A single tool call (e.g. `video_frames`, `bash`).
🤖 Agent	Delegate a step to a sub-agent with its own prompt.
◇ Condition	Branch on an expression (then/else edges).
✓ Output	Terminal result template.

How it works

Build a graph on the canvas: drag nodes from the toolbar, connect them with edges.
The store compiles the graph into an ordered step list (breadth-first from triggers, conditions become branches) — this is the exact shape DSH's workflow engine consumes.
Run hands the steps to ctx.workflows; Export saves a .workflow.json you can reload later.

The data model is deliberately transport-agnostic: the canvas is a view over a plain-JSON workflow spec, so it composes with any DSH workflow provider.

Development

npm ci
npm run dev        # standalone demo at :5173
npm run build      # tsc + vite build

License

MIT

渲染基于仓库 PiedPiper911/dsh-workflow-canvas 的 README.md。在 GitHub 查看原文 →