"""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',
        gen_config={'temperature': 0.0, 'max_tokens': 32768},
        task_type='agent',
        tags=['code', 'agent', 'swe'],
        requires=['docker'],
        description='SWE-bench Verified; per-instance docker image carried in Sample.sandbox.',
    )
)
def _record_to_sample(record: dict) -> Sample:
    instance_id = record['instance_id']
    # EXACT Docker Hub naming (verified by es's pull state: 500/500):
    # swebench/sweb.eval.x86_64.{instance_id.lower() with __->_1776_}:latest
    # -- per-instance images ARE published under the swebench/ namespace
    img = ('swebench/sweb.eval.x86_64.'
           + instance_id.lower().replace('__', '_1776_') + ':latest')
    return Sample(
        input=record['problem_statement'],
        target=record['patch'],  # gold patch (for oracle/oracle-check only)
        sandbox=SandboxSpec(image=img),
        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'),
            'version': record.get('version'),   # official MAP_REPO_VERSION_TO_SPECS key
            'patch': record.get('patch'),
            'hints_text': record.get('hints_text'),
            'created_at': record.get('created_at'),
        },
    )

    return to_sample