from browseruse_bench.utils import (
    EvaluationModel,
    load_evaluation_model,
    encode_image,
    extract_score_from_response,
    calculate_success,
    normalized_results_file,
)

class EvaluationModel:
    def __init__(
        self,
        model: str = "gpt-4o",
        api_key: str = None,
        base_url: str = None
    )

def generate(
    self,
    messages: List[Dict],
    max_tokens: int = 2048,
    temperature: float = 0.3,
    **kwargs
) -> str

def load_evaluation_model(
    model: str = None,
    api_key: str = None,
    base_url: str = None
) -> EvaluationModel

eval:
  model: gpt-5.4
  api_key: $OPENAI_API_KEY
  base_url: $OPENAI_BASE_URL

def encode_image(
    image: PIL.Image,
    scale_factor: float = 1.0
) -> str

def extract_score_from_response(response: str) -> int

def calculate_success(
    score: int,
    threshold: int = 60
) -> bool

@contextmanager
def normalized_results_file(results_file: Path) -> Generator[Path, None, None]

from browseruse_bench.utils import normalized_results_file

with normalized_results_file(Path("results.json")) as jsonl_path:
    # jsonl_path is guaranteed to be JSONL format
    with open(jsonl_path) as f:
        for line in f:
            record = json.loads(line)