company-ai-platform/app/core/config/settings.py

import json
from functools import lru_cache
from typing import Annotated, Any

from pydantic import Field, field_validator, model_validator
from pydantic_settings import BaseSettings, NoDecode, SettingsConfigDict

from app.core.constants import (
    ActorValue,
    ConfigErrorDetail,
    DEFAULT_MODEL_PROVIDER,
    DEFAULT_OPENCLAW_ACTION_JSON,
)


class Settings(BaseSettings):
    """Runtime settings loaded from environment variables and `.env`."""

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

    app_name: str = "Company AI Management Platform"
    app_env: str = "local"
    debug: bool = False
    read_only_mode: bool = True
    api_prefix: str = "/api/v1"
    api_key: str | None = None
    api_actor: str = ActorValue.API
    api_keys: list[dict[str, Any]] = Field(default_factory=list)
    audit_api_key: str | None = None
    audit_api_actor: str = ActorValue.AUDITOR
    audit_api_keys: list[dict[str, Any]] = Field(default_factory=list)
    cors_origins: list[str] = Field(default_factory=lambda: ["*"])
    mask_sensitive_responses: bool = True
    masked_response_fields: list[str] = Field(default_factory=list)

    database_url: str = "sqlite:///./company_ai.db"
    legacy_database_url: str | None = None
    legacy_project_query: str | None = None
    legacy_task_query: str | None = None
    legacy_allowed_queries: dict[str, str] = Field(default_factory=dict)
    legacy_project_code_prefix: str = "LEGACY"
    legacy_task_code_prefix: str = "LEGACY-TASK"
    redis_url: str = "redis://127.0.0.1:6379/0"

    feishu_base_url: str = "https://open.feishu.cn/open-apis"
    feishu_app_id: str | None = None
    feishu_app_secret: str | None = None
    feishu_verification_token: str | None = None
    feishu_encrypt_key: str | None = None
    feishu_default_chat_id: str | None = None
    model_provider: str = DEFAULT_MODEL_PROVIDER
    openclaw_base_url: str = "http://127.0.0.1:2070"
    openclaw_http_url: str | None = None
    openclaw_ws_url: str | None = None
    openclaw_api_key: str | None = None
    openclaw_gateway_token: str | None = None
    openclaw_allowed_tools: Annotated[list[str], NoDecode] = Field(default_factory=list)
    openclaw_allowed_actions: Annotated[list[str], NoDecode] = Field(
        default_factory=lambda: [DEFAULT_OPENCLAW_ACTION_JSON]
    )
    hermes_base_url: str = "http://127.0.0.1:2073/v1"
    hermes_api_key: str | None = None
    hermes_model: str = "hermes-agent"
    hermes_session_id: str | None = None
    direct_llm_base_url: str = "https://api.openai.com/v1"
    direct_llm_api_key: str | None = None
    direct_llm_model: str = "gpt-4.1-mini"

    scheduler_enabled: bool = False
    task_queue_enabled: bool = False
    task_queue_always_eager: bool = False
    lifecycle_pipeline_enabled: bool = False
    finance_needs_enabled: bool = False
    market_analysis_enabled: bool = False
    market_data_provider: str = "tushare"
    market_data_base_url: str = "https://api.tushare.pro"
    market_data_token: str | None = None
    market_premarket_cron_hour: int = 8
    market_premarket_cron_minute: int = 30
    market_close_cron_hour: int = 15
    market_close_cron_minute: int = 30
    market_weekly_day_of_week: str = "sun"
    market_weekly_cron_hour: int = 20
    market_weekly_cron_minute: int = 0
    legacy_sync_enabled: bool = False
    celery_result_backend_url: str | None = None
    daily_brief_cron_hour: int = 9
    daily_brief_cron_minute: int = 0
    attendance_summary_cron_hour: int = 18
    attendance_summary_cron_minute: int = 0
    risk_progress_cron_hour: int = 17
    risk_progress_cron_minute: int = 30
    work_daily_cron_hour: int = 18
    work_daily_cron_minute: int = 30
    work_weekly_report_day_of_week: str = "fri"
    work_weekly_cron_hour: int = 18
    work_weekly_cron_minute: int = 45
    weekly_project_report_day_of_week: str = "mon"
    weekly_project_report_cron_hour: int = 9
    weekly_project_report_cron_minute: int = 30
    legacy_project_sync_cron_hour: int = 2
    legacy_project_sync_cron_minute: int = 0
    legacy_task_sync_cron_hour: int = 2
    legacy_task_sync_cron_minute: int = 30
    event_dispatch_enabled: bool = True
    event_dispatch_batch_size: int = 100
    event_dispatch_max_attempts: int = 3
    event_dispatch_retry_delay_seconds: int = 300
    event_dispatch_lock_seconds: int = 300
    event_dispatch_cron_minute: str = "*/5"
    heartbeat_interval_seconds: int = 60
    ai_memory_enabled: bool = True
    ai_memory_auto_write_enabled: bool = True
    ai_memory_recall_limit: int = 5
    ai_memory_auto_write_ttl_days: int = Field(default=90, ge=1, le=3650)
    ai_memory_blocked_content_terms: list[str] = Field(
        default_factory=lambda: [
            "bank account",
            "budget",
            "cash flow",
            "financial statement",
            "id card",
            "payment",
            "salary",
            "成本",
            "付款",
            "工资",
            "收款",
            "现金流",
            "财务",
            "预算",
        ]
    )
    ai_analysis_max_attempts: int = 3
    ai_memory_forbidden_keys: list[str] = Field(
        default_factory=lambda: [
            "authorization",
            "api_key",
            "apikey",
            "access_token",
            "tenant_access_token",
            "token",
            "secret",
            "password",
            "openclaw_gateway_token",
            "hermes_api_key",
            "direct_llm_api_key",
            "market_data_token",
            "feishu_app_secret",
            "feishu_verification_token",
        ]
    )

    @field_validator("cors_origins", mode="before")
    @classmethod
    def parse_cors_origins(cls, value: Any) -> list[str]:
        if isinstance(value, list):
            return [str(item).strip() for item in value if str(item).strip()]
        if value is None:
            return []
        text = str(value).strip()
        if text.startswith("["):
            data = json.loads(text)
            if not isinstance(data, list):
                raise ValueError(ConfigErrorDetail.CORS_ORIGINS_FORMAT)
            return [str(item).strip() for item in data if str(item).strip()]
        return [item.strip() for item in text.split(",") if item.strip()]

    @field_validator(
        "openclaw_allowed_tools",
        "openclaw_allowed_actions",
        "ai_memory_forbidden_keys",
        "ai_memory_blocked_content_terms",
        mode="before",
    )
    @classmethod
    def parse_csv_list(cls, value: str | list[str] | None) -> list[str]:
        if value is None:
            return []
        if isinstance(value, list):
            return [str(item).strip() for item in value if str(item).strip()]
        text = value.strip()
        if not text:
            return []
        if text.startswith("["):
            data = json.loads(text)
            if not isinstance(data, list):
                raise ValueError(ConfigErrorDetail.CORS_ORIGINS_FORMAT)
            return [str(item).strip() for item in data if str(item).strip()]
        return [item.strip() for item in text.split(",") if item.strip()]

    @field_validator("masked_response_fields", mode="before")
    @classmethod
    def parse_masked_response_fields(cls, value: Any) -> list[str]:
        if isinstance(value, list):
            return [str(item).strip() for item in value if str(item).strip()]
        if value is None:
            return []
        text = str(value).strip()
        if not text:
            return []
        if text.startswith("["):
            data = json.loads(text)
            if not isinstance(data, list):
                raise ValueError(ConfigErrorDetail.CORS_ORIGINS_FORMAT)
            return [str(item).strip() for item in data if str(item).strip()]
        return [item.strip() for item in text.split(",") if item.strip()]

    @field_validator("api_keys", "audit_api_keys", mode="before")
    @classmethod
    def parse_service_keys(cls, value: Any) -> list[dict[str, Any]]:
        if value is None or value == "":
            return []
        if isinstance(value, list):
            return [dict(item) for item in value if isinstance(item, dict)]
        if isinstance(value, str):
            data = json.loads(value)
            if not isinstance(data, list):
                raise ValueError(ConfigErrorDetail.SERVICE_KEYS_FORMAT)
            if not all(isinstance(item, dict) for item in data):
                raise ValueError(ConfigErrorDetail.SERVICE_KEYS_FORMAT)
            return [dict(item) for item in data]
        raise ValueError(ConfigErrorDetail.SERVICE_KEYS_FORMAT)

    @field_validator("legacy_allowed_queries", mode="before")
    @classmethod
    def parse_legacy_allowed_queries(cls, value: Any) -> dict[str, str]:
        if value is None or value == "":
            return {}
        if isinstance(value, dict):
            return {str(key): str(item) for key, item in value.items()}
        if isinstance(value, str):
            data = json.loads(value)
            if not isinstance(data, dict):
                raise ValueError(ConfigErrorDetail.LEGACY_ALLOWED_QUERIES_FORMAT)
            return {str(key): str(item) for key, item in data.items()}
        raise ValueError(ConfigErrorDetail.LEGACY_ALLOWED_QUERIES_FORMAT)

    @model_validator(mode="after")
    def validate_production_safety(self) -> "Settings":
        if self.app_env.lower() not in {"prod", "production"}:
            return self
        errors: list[str] = []
        if self.database_url.startswith("sqlite"):
            errors.append("DATABASE_URL must use PostgreSQL in production")
        if not self.api_key and not any(item.get("key") for item in self.api_keys):
            errors.append("API_KEY or API_KEYS is required in production")
        if not self.audit_api_key and not any(
            item.get("key") for item in self.audit_api_keys
        ):
            errors.append("AUDIT_API_KEY or AUDIT_API_KEYS is required in production")
        if "*" in self.cors_origins:
            errors.append("CORS_ORIGINS cannot contain '*' in production")
        if self.debug:
            errors.append("DEBUG must be false in production")
        if errors:
            raise ValueError("; ".join(errors))
        return self


@lru_cache
def get_settings() -> Settings:
    """Return cached application settings."""

    return Settings()