CORE CONCEPTS

Structured output

Rowe returns typed output objects for tasks such as fit checks, placement, stability, prediction, reconstruction, action, and optimization. Four Cad consumes reasoning_scene.v2 inside those outputs to render objects, relation lines, collision volumes, support patches, measurements, issue regions, fit results, comparisons, geometry changes, and grounded text.

Response fields

Responses include typed outputs, usage metadata, and a request id.

idstring

Unique response id.

objectstring

The object type. Usually response.

modelstring

The model that generated the response.

outputarray

Typed spatial outputs for the requested task.

usageobject

Input spatial tokens, output spatial tokens, projected input cost, projected output cost, and total estimated cost.

request_idstring

Request id for support and debugging.

Terminal

{
  "id": "resp_4e1f45c7ebd1",
  "object": "response",
  "model": "rowe-1.0",
  "output": [
    {
      "type": "fit_result",
      "data": {
        "feasible": false,
        "confidence": 0.2862,
        "explanation": "Transformer multimodal model predicts fit feasibility=false.",
        "reasoning_scene": {
          "schema_version": "reasoning_scene.v2",
          "scene_id": "four-cad-analysis",
          "task_type": "fit",
          "objects": [],
          "relations": [],
          "overlays": [],
          "measurements": [],
          "reasoning_steps": [],
          "suggested_changes": [],
          "issue_regions": [],
          "fit_results": [],
          "comparison_results": [],
          "geometry_changes": [],
          "text_explanation": "The highlighted geometry shows why the fit check failed."
        }
      }
    }
  ],
  "usage": {
    "input_tokens": 42,
    "output_tokens": 29,
    "estimated_input_cost_usd": 0.000003,
    "estimated_output_cost_usd": 0.000003,
    "estimated_cost_usd": 0.000006
  },
  "request_id": "req_..."
}