"""SWE-bench Verified (official source: princeton-nlp/SWE-bench_Verified)."""

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


@register_dataset(
    DatasetSpec(
        name='swe_bench_verified',
        source='princeton-nlp/SWE-bench_Verified',  # official: https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified
        split='test',
        task_type='agent',
        tags=['code', 'agent', 'swe'],
        requires=['docker'],
        description='SWE-bench Verified; per-instance docker image carried in Sample.sandbox.',
    )
)
def swe_bench_verified():
    def to_sample(record: dict) -> Sample:
        instance_id = record['instance_id']
        return Sample(
            input=record['problem_statement'],
            target=record['patch'],  # gold patch (for oracle/oracle-check only)
            sandbox=SandboxSpec(image=f'sweb.eval.x86_64.{instance_id}'),  # official image naming
            metadata={
                'instance_id': instance_id,
                'repo': record['repo'],
                'base_commit': record['base_commit'],
                'test_patch': record['test_patch'],
                'FAIL_TO_PASS': record['FAIL_TO_PASS'],
                'PASS_TO_PASS': record['PASS_TO_PASS'],
                'environment_setup_commit': record.get('environment_setup_commit'),
                'difficulty': record.get('difficulty'),
            },
        )

    return to_sample