yunke/yunke-server/app/config.py

from functools import lru_cache
from pathlib import Path

from pydantic_settings import BaseSettings, SettingsConfigDict


class Settings(BaseSettings):
    """Application settings sourced from environment / .env file."""

    model_config = SettingsConfigDict(
        env_file=".env",
        env_file_encoding="utf-8",
        extra="ignore",
    )

    yunke_base_url: str = "https://crm2.yunkecn.com"
    yunke_username: str = ""
    yunke_password: str = ""
    db_url: str = "mysql+asyncmy://user:pass@localhost:3306/yunke"
    redis_url: str = "redis://localhost:6379/0"
    media_dir: Path = Path("./media")
    # Fernet key for encrypting stored credentials. Required for real runs;
    # empty default lets tests construct Settings without a key.
    encryption_key: str = ""

    # Existing-session creds (optional; bypasses programmatic login — e.g. for
    # validation with a live browser session). Read from .env / environment.
    yk_userid: str = ""
    yk_company: str = ""
    yk_cookie: str = ""
    # Shared bearer token for the viewing API. Empty (default) -> auth DISABLED
    # (we trust the network boundary; this is a local/intranet tool). When set,
    # every API request must present this value via ``Authorization: Bearer
    # <token>`` or ``?token=<token>``. See app/api/auth.py.
    api_token: str = ""

    # --- Anti-risk-control / stealth tuning ---------------------------------
    # These are the knobs that pace automated scraping so it resembles the
    # normal web app. Defaults are deliberately CONSERVATIVE (slow + jittered):
    # roughly one request every ~1.0..1.8s. Loosen these only once we have
    # evidence the CRM tolerates a faster pace. See app.session.yunke_client.
    # Lower bound on seconds between successive upstream requests.
    request_min_interval: float = 1.0
    # Random extra 0..jitter seconds added on top of ``request_min_interval``
    # per request, so the cadence is not a perfectly periodic signature.
    request_jitter: float = 0.8
    # Hard cap on the number of upstream requests a single client may send in
    # one run. 0 = unlimited; >0 = enforce, then raise RequestCapReached.
    max_requests_per_run: int = 0
    # Exponential backoff parameters applied when the CRM signals risk control
    # (HTTP 429 or a 200 body carrying a 风控/限流 marker). Delay for retry N
    # (0-indexed) is ``risk_backoff_base * 2**N`` clamped to ``risk_backoff_max``.
    risk_backoff_base: float = 2.0
    risk_backoff_max: float = 60.0
    # Number of retries attempted after the initial request before giving up.
    risk_backoff_attempts: int = 4


@lru_cache
def get_settings() -> Settings:
    """Return the process-wide Settings singleton."""
    return Settings()