"""evalharness.eval -- the evaluation layer.

Pipeline: extract -> score -> aggregate, all plugin-driven.

    from evalharness.eval import evaluate, get_eval
    from evalharness import get_dataset

    ds = get_dataset('gsm8k')
    report = evaluate(ds, predictions)      # recipe auto-resolved by dataset name
    report.save('gsm8k.report.json')

Four scoring paradigms: text-compare (implemented), llm-judge (wired via
runner judge= once ModelAdapter exists), execution & env-reward (slots raise
LayerNotReady until sandbox/agent layers land).
"""

from .aggregator import AGGREGATOR_REGISTRY, get_aggregator, register_aggregator
from .extractor import EXTRACTOR_REGISTRY, get_extractor, make_extractor, register_extractor
from .recipe import EVAL_REGISTRY, EvalRecipe, JudgeConfig, get_eval, list_evals, register_eval
from .record import EvalReport, SampleResult
from .registry import EvalRegistry
from .runner import evaluate
from .scorer import SCORER_REGISTRY, LayerNotReady, ScoreContext, get_scorer, register_scorer

__all__ = [
    'evaluate', 'EvalRecipe', 'JudgeConfig', 'get_eval', 'list_evals', 'register_eval',
    'EvalReport', 'SampleResult', 'LayerNotReady', 'ScoreContext',
    'EXTRACTOR_REGISTRY', 'SCORER_REGISTRY', 'AGGREGATOR_REGISTRY', 'EvalRegistry',
    'register_extractor', 'get_extractor', 'make_extractor',
    'register_scorer', 'get_scorer', 'register_aggregator', 'get_aggregator',
]


def _discover_builtin_recipes() -> None:
    """Import every recipe module under ./recipes (import = register)."""
    import importlib
    import pkgutil
    from pathlib import Path

    pkg_dir = Path(__file__).parent / 'recipes'
    if not pkg_dir.exists():
        return
    for info in pkgutil.iter_modules([str(pkg_dir)]):
        importlib.import_module(f'{__name__}.recipes.{info.name}')


_discover_builtin_recipes()