Cc Workflow AI Editor

• Call get_workflow_schema via cc-workflow-studio MCP server
• Call get_current_workflow via cc-workflow-studio MCP server
• Ask the user what to create or modify
• Generate workflow JSON: use built-in sub-agents (builtInType: explore/plan/general-purpose) by default. Only call list_available_agents when the user explicitly asks to use an existing custom sub-agent.
• Apply changes via cc-workflow-studio MCP server:
• New workflow or structural changes (add/remove nodes/connections): use apply_workflow
• Partial updates to existing nodes (change name, position, or data): use update_nodes (more token-efficient)
• Fix errors if any
• Ask for feedback, repeat from step 4

Group Node

Group nodes are visual containers for organizing related nodes on the canvas. They do NOT affect workflow execution.

Rules

• Group nodes have type: "group" and require data.label (display name)
• Group nodes must have style: { width, height } to define their visual area
• Group nodes CANNOT have connections (no edges to/from group nodes)
• To place a node inside a group, set the child node's parentId to the group's id
• Child node position is relative to the group's top-left corner (not the canvas origin)
• The name field on group nodes is not validated (can be empty or omitted)

Example

{
  "nodes": [
    {
      "id": "group-1",
      "type": "group",
      "name": "",
      "position": { "x": 100, "y": 100 },
      "style": { "width": 400, "height": 300 },
      "data": { "label": "Data Processing" }
    },
    {
      "id": "node-1",
      "type": "subAgent",
      "name": "fetch-data",
      "parentId": "group-1",
      "position": { "x": 50, "y": 50 },
      "data": { "description": "Fetch data from API", "outputPorts": 1 }
    }
  ]
}