PiedPiper911/dsh-workflow-canvas ↗★ 0
@piedpiper911/dsh-workflow-canvas
适用于 DSH 的可视化工作流构建器:基于 React Flow 提供拖拽画布,用于编排工具调用、子智能体及条件分支。
AI 分析
核心用途是通过直观的流程图画布设计和运行复杂的 AI 工作流。适合需要构建多步骤任务、多 Agent 协同或包含复杂逻辑判断的自动化任务的用户。
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PiedPiper911/dsh-workflow-canvas说明文档
阅读完整 README ↗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.
Runhands the steps toctx.workflows;Exportsaves a.workflow.jsonyou 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