Refactor-Boolean-Flag-Options

The model receives the prompt (and optional system message). The run uses scorer rubric_json_metrics with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.

Return JSON only with keys plan, refactor, tests. A function renderReport(data, true, false, true) uses three boolean flags for PDF mode, redaction, and debug output. Refactor the API to improve readability without changing behavior.

{
  "metrics": {
    "intent": {
      "checks": [
        {
          "contains": [
            "boolean flags"
          ]
        },
        {
          "contains": [
            "options object"
          ]
        },
        {
          "contains": [
            "readability"
          ]
        }
      ]
    },
    "visible": {
      "checks": [
        {
          "contains": [
            "PDF mode"
          ]
        },
        {
          "contains": [
            "redaction"
          ]
        },
        {
          "contains": [
            "debug output"
          ]
        }
      ]
    },
    "hidden": {
      "checks": [
        {
          "contains": [
            "same behavior"
          ]
        },
        {
          "contains": [
            "tests"
          ]
        },
        {
          "contains": [
            "backward compatibility"
          ]
        }
      ]
    }
  }
}