Remove Temp

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 square(x):
    result = x * x
    return result

{
  "expected_contains": [
    "return x * x",
    "return x*x"
  ]
}