from __future__ import annotations

import os
from collections.abc import Mapping
from dataclasses import dataclass

DEFAULT_DIVERGENCE_TOLERANCE = 0.0
DEFAULT_EMBEDDING_MODEL = "text-embedding-3-small"
DEFAULT_TOP_K = 5

ENABLED_ENV = "SKILL_AUTHORING_ENABLED"
DIVERGENCE_TOLERANCE_ENV = "SKILL_DIVERGENCE_TOLERANCE"
EMBEDDING_MODEL_ENV = "SKILL_EMBEDDING_MODEL"
TOP_K_ENV = "SKILL_RETRIEVAL_TOP_K"


@dataclass(frozen=True)
class SkillAuthoringConfig:
    enabled: bool = False
    divergence_tolerance: float = DEFAULT_DIVERGENCE_TOLERANCE
    embedding_model: str = DEFAULT_EMBEDDING_MODEL
    top_k: int = DEFAULT_TOP_K


def load_config(env: Mapping[str, str] | None = None) -> SkillAuthoringConfig:
    values = env or os.environ
    return SkillAuthoringConfig(
        enabled=_parse_bool(values.get(ENABLED_ENV), default=False),
        divergence_tolerance=_parse_float(
            values.get(DIVERGENCE_TOLERANCE_ENV),
            default=DEFAULT_DIVERGENCE_TOLERANCE,
        ),
        embedding_model=values.get(EMBEDDING_MODEL_ENV) or DEFAULT_EMBEDDING_MODEL,
        top_k=_parse_int(values.get(TOP_K_ENV), default=DEFAULT_TOP_K),
    )


def _parse_bool(value: str | None, *, default: bool) -> bool:
    if value is None:
        return default
    return value.strip().lower() in {"1", "true", "yes", "on", "enabled"}


def _parse_float(value: str | None, *, default: float) -> float:
    if value is None:
        return default
    try:
        parsed = float(value)
    except ValueError:
        return default
    return parsed if parsed >= 0 else default


def _parse_int(value: str | None, *, default: int) -> int:
    if value is None:
        return default
    try:
        parsed = int(value)
    except ValueError:
        return default
    return parsed if parsed > 0 else default