"""swe_bench_verified_agentic: same data as swe_bench_verified, agentic bench. Separate bench name so both variants coexist (single-turn oracle vs multi-turn agent); source/split/fields identical — the difference lives in the recipe (env loop + official harness scoring) and config.""" from ..registry import register_dataset from ..spec import DatasetSpec @register_dataset( DatasetSpec( name='swe_bench_verified_agentic', source='princeton-nlp/SWE-bench_Verified', split='test', task_type='agent', tags=['code', 'agent', 'swe'], requires=['docker'], description='SWE-bench Verified (agentic): multi-turn bash agent in ' 'the per-instance /testbed container.', ) ) def swe_bench_verified_agentic(): from .swe_bench_verified import _record_to_sample return _record_to_sample