"""HLE - Humanity's Last Exam.

Official source cais/hle is gated on HF (needs auth); we load the ModelScope
mirror of the identical data via the native raw-file downloader.
"""

from ..sample import Sample
from ..registry import register_dataset
from ..spec import DatasetSpec


@register_dataset(
    DatasetSpec(
        name='hle',
        source='cais/hle',  # ModelScope mirror of the gated HF original
        split='test',
        task_type='qa',
        tags=['knowledge', 'frontier'],
        description="Humanity's Last Exam. Some samples carry an image field (multimodal).",
        params={'hub': 'modelscope'},
    )
)
def hle():
    def to_sample(record: dict) -> Sample:
        return Sample(
            input=record['question'],
            target=str(record['answer']).strip(),
            metadata={
                'id': record.get('id'),
                'answer_type': record.get('answer_type'),
                'category': record.get('category'),
                'raw_subject': record.get('raw_subject'),
                'has_image': bool(record.get('image')),
            },
        )

    return to_sample