Please provide clarification for contradictions in the documentation regarding the json prompt format

[vwiessner]

Your documentation regarding the format of the json that is to be provided as the prompt is contracting itself:

https://github.com/ideogram-oss/ideogram4/blob/main/docs/prompting.md has examples like this

Example: warm sunset palette

{
  "high_level_description": "A lone sailboat on calm water at sunset.",
  "style_description": {
   "aesthetics": "serene, warm, golden hour",
    "lighting": "golden hour backlighting, warm atmospheric haze",
    "photo": "wide angle, f/8, long exposure",
    "medium": "photograph",
    "color_palette": ["#FF6B35", "#F7C59F", "#004E89", "#1A659E", "#2B2D42"]
  },
  "compositional_deconstruction": {
    "background": "A calm ocean stretching to a low horizon, sky washed in orange and pink with thin wisps of cloud.",
    "elements": [
      {"type": "obj", "desc": "A single sailboat with a white triangular sail, silhouetted against the setting sun."}
    ]
  }
}

https://github.com/ideogram-oss/ideogram4/blob/main/src/ideogram4/magic_prompt_system_prompts/v1.txt however declares

OUTPUT CONTRACT — exactly three top-level keys, in this order:

{"aspect_ratio":"W:H","high_level_description":"...","compositional_deconstruction":{"background":"...","elements":[ ... ]}}

Which one is correct?