{
  "1": {
    "class_type": "SimpleText",
    "inputs": {
      "input_text": "Model response:\n```json\n{\"scene\":{\"subject\":\"warehouse robot\",\"action\":\"moving a blue crate\"}}\n```"
    }
  },
  "2": {
    "class_type": "VLMJSONExtract",
    "inputs": {
      "text": [
        "1",
        0
      ],
      "path": "$.scene.action",
      "output_format": "Text",
      "if_missing": "Error",
      "default_value": ""
    }
  },
  "3": {
    "class_type": "VLMTextTemplate",
    "inputs": {
      "template": "{instruction}\n\nObserved action: {text1}",
      "variables_json": "{\"instruction\":\"Write one concise video-generation prompt.\"}",
      "missing_values": "Error",
      "text1": [
        "2",
        0
      ]
    }
  },
  "4": {
    "class_type": "VLMTextClean",
    "inputs": {
      "text": [
        "3",
        0
      ],
      "unicode_normalization": "NFC",
      "whitespace": "Normalize line endings",
      "trim_edges": true,
      "remove_outer_markdown_fence": false,
      "deduplicate_lines": false,
      "max_characters": 0
    }
  },
  "5": {
    "class_type": "ViewText",
    "inputs": {
      "text": [
        "4",
        0
      ]
    }
  }
}