# Action planning

> Use task_type act with a target goal to return action-ready spatial guidance.

Source: https://fourechelon.com/docs/action-planning · Machine-readable: https://fourechelon.com/openapi.json · Index: https://fourechelon.com/llms.txt

## task

act

## question

What sequence of moves gets the scene to the goal state?

## required

| Field | Type | Description |
| --- | --- | --- |
| input.goal | object | The target state to reach. |
| input.cad_scene | object | Current scene. point_cloud_scene also works. |
| input.object_id | string | Optional. The object being acted on. |

## returns

| Field | Type | Description |
| --- | --- | --- |
| spatial_action.steps | Ordered actions grounded in scene geometry. |
| spatial_action.constraints | Physical limits each step respects. |
| spatial_action.blocked | Steps that cannot be satisfied, and why. |

## notes

This is a planning service, not a controller. It runs off-device over the network with no real-time or safety guarantee — treat the plan as a proposal your system validates.

## Example

```bash
curl https://fourechelon.com/api/v1/responses \
  -H "Authorization: Bearer $FOUR_ECHELON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rowe-1.0",
    "input": {
      "task_type": "act",
      "goal": { "state": "assembled" },
      "cad_scene": { "schema": "four-cad.cad_scene.v1", "solids": [] }
    }
  }'
```