label_ai_service/app/core/config.py

import os
from functools import lru_cache
from pathlib import Path
from typing import Any

import yaml
from dotenv import load_dotenv

load_dotenv()

# Maps environment variable names to nested YAML key paths
_ENV_OVERRIDES: dict[str, list[str]] = {
    "DASHSCOPE_API_KEY": ["dashscope", "api_key"],
    "DASHSCOPE_BASE_URL": ["dashscope", "base_url"],
    "DASHSCOPE_FINE_TUNE_BASE_URL": ["dashscope", "fine_tune_base_url"],
    "ZHIPUAI_API_KEY": ["zhipuai", "api_key"],
    "STORAGE_ACCESS_KEY": ["storage", "access_key"],
    "STORAGE_SECRET_KEY": ["storage", "secret_key"],
    "STORAGE_ENDPOINT": ["storage", "endpoint"],
    "BACKEND_CALLBACK_URL": ["backend", "callback_url"],
    "LOG_LEVEL": ["server", "log_level"],
    "MAX_VIDEO_SIZE_MB": ["video", "max_file_size_mb"],
}

_CONFIG_PATH = Path(__file__).parent.parent.parent / "config.yaml"


def _set_nested(cfg: dict, keys: list[str], value: Any) -> None:
    for key in keys[:-1]:
        cfg = cfg.setdefault(key, {})
    # Coerce numeric env vars
    try:
        value = int(value)
    except (TypeError, ValueError):
        pass
    cfg[keys[-1]] = value


@lru_cache(maxsize=1)
def get_config() -> dict:
    with open(_CONFIG_PATH, "r", encoding="utf-8") as f:
        cfg: dict = yaml.safe_load(f)

    for env_var, key_path in _ENV_OVERRIDES.items():
        value = os.environ.get(env_var)
        if value is not None:
            _set_nested(cfg, key_path, value)

    return cfg