from functools import lru_cache

from dotenv import load_dotenv
from pydantic import Field
from pydantic_settings import BaseSettings, SettingsConfigDict

# 把 `.env` 显式注入进程环境变量。pydantic-settings 只把 `.env` 读进 Settings 对象，
# **不会**写 `os.environ`；而模型密钥解析（`EnvironmentSecretResolver` 要求 secret_ref
# 形如 `env:VAR`）读的正是 `os.getenv`。两者不打通就会出现"按文档在 .env 里配好密钥、
# 运行时却读不到"，且症状伪装成"没有可用的模型端点"，排查方向被带偏。
# `override=False`：真实进程环境变量优先，`.env` 只作补充（生产用容器注入时不会被覆盖）。
load_dotenv(override=False)


class Settings(BaseSettings):
    app_env: str = "local"
    app_name: str = "jr-agent-platform"
    log_level: str = "INFO"
    timezone: str = "Asia/Shanghai"
    jwt_issuer: str
    jwt_audience: str
    jwt_algorithm: str = "RS256"
    jwt_private_key_path: str = "config/jwt/jwt-private.pem"
    jwt_public_key_path: str = "config/jwt/jwt-public.pem"
    jwt_clock_skew_seconds: int = Field(default=30, ge=0)
    mysql_dsn: str
    mysql_pool_size: int = Field(default=5, ge=1)
    mysql_max_overflow: int = Field(default=10, ge=0)
    mysql_tx_isolation: str = "READ COMMITTED"
    redis_url: str
    redis_connect_timeout_seconds: float = Field(default=2, gt=0)
    # 限流（文档 §3.5 的 429 / §3.6 的 RATE_LIMITED）。默认值刻意宽松：
    # 每用户每接口每分钟 600 次（10 QPS）。取值依据是"本地验收与集成测试的量级"——
    # 两个验收脚本与 tests/integration 里同一身份对同一接口最多几十次调用，
    # 600 留了一个数量级余量，绝不可能误伤；同时 10 QPS 已足以拦住单个客户端
    # 把底座打爆（正常业务交互远低于 1 QPS）。生产按真实容量收紧即可，无需改代码。
    rate_limit_enabled: bool = True
    rate_limit_window_seconds: int = Field(default=60, gt=0)
    rate_limit_max_requests: int = Field(default=600, ge=1)
    rate_limit_key_prefix: str = "jr:rate_limit"
    message_broker_url: str = ""
    message_broker_run_topic: str = "agent.run"
    message_broker_outbox_topic: str = "agent.outbox"
    message_broker_dlq_topic: str = "agent.dlq"
    milvus_uri: str
    milvus_token: str = ""
    milvus_collection: str = "jr_memory"
    neo4j_uri: str
    neo4j_database: str = "neo4j"
    neo4j_username: str = "neo4j"
    neo4j_password: str = ""
    model_router_config_ref: str = "local"
    model_default_endpoint: str = ""
    model_fallback_endpoint: str = ""
    sse_heartbeat_seconds: int = Field(default=15, gt=0)
    sse_chunk_characters: int = Field(default=256, ge=1, le=4096)
    sse_max_connection_seconds: int = Field(default=300, gt=0)
    worker_lease_seconds: int = Field(default=60, gt=0)
    worker_retry_limit: int = Field(default=3, ge=0)
    worker_poll_seconds: float = Field(default=1, gt=0)

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


@lru_cache(maxsize=1)
def get_settings() -> Settings:
    return Settings()  # type: ignore[call-arg]