"""Execution / agent benchmarks. Recipes exist now; scorers raise LayerNotReady
until the sandbox & agent layers land (interfaces are stable)."""

from ..recipe import EvalRecipe, register_eval


@register_eval('humaneval')
def humaneval():
    return EvalRecipe(
        name='humaneval',
        extract='code_block',
        scorers={'pass@1': 'execution'},
        aggregators={'pass@1': 'pass_at_k'},
        description='HumanEval; sandbox test execution, pass@k.',
    )


@register_eval('bigcodebench')
def bigcodebench():
    return EvalRecipe(
        name='bigcodebench',
        extract='code_block',
        scorers={'pass@1': 'execution'},
        aggregators={'pass@1': 'pass_at_k'},
        description='BigCodeBench; sandbox test execution with libs, pass@k.',
    )


@register_eval('live_code_bench')
def live_code_bench():
    return EvalRecipe(
        name='live_code_bench',
        extract='code_block',
        scorers={'pass@1': 'execution'},
        aggregators={'pass@1': 'pass_at_k'},
        description='LiveCodeBench; hidden tests, pass@k.',
    )


@register_eval('swe_bench_verified')
def swe_bench_verified():
    return EvalRecipe(
        name='swe_bench_verified',
        extract='identity',          # a patch, not an answer
        scorers={'resolved': 'env_reward'},
        description='SWE-bench Verified; docker env, FAIL_TO_PASS/PASS_TO_PASS.',
    )


@register_eval('tau2_bench')
def tau2_bench():
    return EvalRecipe(
        name='tau2_bench',
        extract='identity',
        scorers={'acc': 'env_reward'},
        description='tau2-bench; user-simulated dialog, environment reward.',
    )


@register_eval('bfcl_v3')
def bfcl_v3():
    return EvalRecipe(
        name='bfcl_v3',
        extract='identity',
        scorers={'acc': 'execution'},  # AST check for most categories; exec for executable ones
        aggregators={'acc': 'weighted_group_avg'},  # group_key = test_category
        description='BFCL v3; AST/exec per category, weighted category average.',
    )


@register_eval('general_fc')
def general_fc():
    return EvalRecipe(
        name='general_fc',
        extract='identity',
        scorers={'acc': 'execution'},
        description='General function calling; tool-call comparison.',
    )