Cleanup

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

Refactor without changing behavior. Return only Python code.

def normalize_records_01(records):
    out = []
    for i in range(len(records)):
        r = records[i]
        if r.get('name') is not None:
            name = r.get('name').strip().lower()
            if name != '':
                out.append({'name': name, 'active': bool(r.get('active', False))})
    return out

{
  "expected_contains": [
    "for record in records",
    "strip().lower()",
    "return out"
  ]
}