浅念
6880ff1b97
后端: - POST /api/auth/login:admin 账密(Settings 默认 admin/admin123, ADMIN_USER/ADMIN_PASSWORD 可覆盖)换取共享 api_token,免 token 中间件 - 防爆破:同 IP 15min 窗口内 5 次失败锁 15min(429),成功登录清零 - 错误信息统一「用户名或密码错误」(防用户名枚举) - 测试 7 个新增(TDD),全量 500 绿 前端: - LoginView + 路由守卫(未登录跳 /login,回跳 redirect) - axios 请求拦截器自动带 Bearer;401 清登录态回登录页 - 媒体直链统一 mediaUrl() 带 ?token=(img/audio 标签发不了 header), 替换 4 处裸拼;downloadBlob 手动带头 - isLoggedIn 按 key 存在判定 — 后端鉴权关闭时空 token 不锁死登录页 - MainLayout 侧栏底部退出登录 compose:两份编排透传 ADMIN_USER/ADMIN_PASSWORD(默认 admin/admin123) Co-Authored-By: Claude Code <noreply@anthropic.com>
89 lines
4.1 KiB
Python
89 lines
4.1 KiB
Python
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 = ""
|
|
|
|
# Username/password for the SPA login page (``POST /api/auth/login``).
|
|
# On success the login hands out the ``api_token`` above so the SPA can
|
|
# act as a Bearer client; defaults keep local dev zero-config. Change both
|
|
# in prod via ADMIN_USER / ADMIN_PASSWORD.
|
|
admin_user: str = "admin"
|
|
admin_password: str = "admin123"
|
|
|
|
# Comma-separated list of allowed CORS origins for the viewing API. Empty
|
|
# (default) -> only the dev fallback (``http://localhost:5173``) is allowed;
|
|
# set ``CORS_ORIGINS=https://app.example.com`` in prod to lock cross-origin
|
|
# access down to explicit origins. Never ``*`` (wildcard + credentialed APIs
|
|
# are an open door; we accept no credentials but still restrict origins to
|
|
# avoid reflecting arbitrary attacker-controlled origins in ``Acces-Control-
|
|
# Allow-Origin``).
|
|
cors_origins: str = ""
|
|
|
|
# --- Anti-risk-control / stealth tuning ---------------------------------
|
|
# Tuned 2026-08-11 after triggering 风控 during a heavy session (~500+
|
|
# consecutive requests across groups/WA/voice-clips/SMS in ~1 hour).
|
|
# The previous defaults (1.0s + 0.8s jitter = ~1.0..1.8s cadence) were
|
|
# fast enough to trigger 云客's volume-based risk control when many
|
|
# entities are synced back-to-back. New strategy: slower base cadence +
|
|
# larger jitter (human-like irregularity) + hard per-run cap + longer
|
|
# backoff with more retries (patience over aggression).
|
|
# See app.session.yunke_client for the implementation.
|
|
|
|
# Lower bound on seconds between successive upstream requests.
|
|
# 2.0s base — roughly mimics a human clicking through pages (not a bot
|
|
# hammering at 1 req/s). Combined with jitter this gives ~2.0..4.5s cadence.
|
|
request_min_interval: float = 2.0
|
|
# Random extra 0..jitter seconds. Large jitter (2.5s) ensures the cadence
|
|
# is highly irregular — no periodic signature for 云客 to fingerprint.
|
|
request_jitter: float = 2.5
|
|
# Hard cap: 300 requests per run (~10 minutes at 2s avg). Prevents a
|
|
# runaway sync from hammering 云客 for hours. 0 = unlimited (only for
|
|
# manual debugging). A daily `sync --entity all` will likely need multiple
|
|
# runs (or increase this cap) — by design, to stay under 风控 radar.
|
|
max_requests_per_run: int = 300
|
|
# Exponential backoff: start at 5s, double each retry, cap at 120s.
|
|
# More patient than the old 2s/60s/4 — gives 云客 time to cool down.
|
|
risk_backoff_base: float = 5.0
|
|
risk_backoff_max: float = 120.0
|
|
# 6 retries (was 4) — more chances to recover before giving up.
|
|
# Total worst-case backoff: 5+10+20+40+80+120 = 275s (~4.6 min) before
|
|
# the final attempt; generous recovery window.
|
|
risk_backoff_attempts: int = 6
|
|
|
|
|
|
@lru_cache
|
|
def get_settings() -> Settings:
|
|
"""Return the process-wide Settings singleton."""
|
|
return Settings()
|