ForcePilot/backend/package/yuxi/config/app.py

"""应用配置模块。"""

from __future__ import annotations

import os
from pathlib import Path
from typing import Any

import tomli
import tomli_w
from pydantic import BaseModel, Field, PrivateAttr, model_validator

from yuxi.utils.logging_config import logger


class Config(BaseModel):
    """应用配置类。"""

    save_dir: str = Field(default="saves", description="保存目录")
    enable_reranker: bool = Field(default=False, description="是否开启重排序")
    enable_content_guard: bool = Field(default=False, description="是否启用内容审查")
    enable_content_guard_llm: bool = Field(default=False, description="是否启用LLM内容审查")
    default_model: str = Field(
        default="siliconflow-cn:Pro/MiniMaxAI/MiniMax-M2.5",
        description="默认对话模型",
    )
    fast_model: str = Field(
        default="siliconflow-cn:Pro/MiniMaxAI/MiniMax-M2.5",
        description="快速响应模型",
    )
    embed_model: str = Field(
        default="siliconflow-cn:Pro/BAAI/bge-m3",
        description="默认 Embedding 模型",
    )
    reranker: str = Field(
        default="siliconflow-cn:Pro/BAAI/bge-reranker-v2-m3",
        description="默认 Re-Ranker 模型",
    )
    content_guard_llm_model: str = Field(
        default="siliconflow-cn:Pro/MiniMaxAI/MiniMax-M2.5",
        description="内容审查LLM模型",
    )

    default_agent_id: str = Field(default="ChatbotAgent", description="默认智能体ID")

    sandbox_provider: str = Field(default="provisioner", description="沙箱提供者")
    sandbox_provisioner_url: str = Field(default="http://sandbox-provisioner:8002", description="沙箱服务地址")
    sandbox_virtual_path_prefix: str = Field(default="/home/gem/user-data", description="沙箱用户目录前缀")
    sandbox_exec_timeout_seconds: int = Field(default=180, description="沙箱执行超时时间（秒）")
    sandbox_max_output_bytes: int = Field(default=262144, description="沙箱最大输出字节数")
    sandbox_keepalive_interval_seconds: int = Field(default=30, description="沙箱保活间隔")

    enable_ssrf_protection: bool = Field(default=True, description="是否启用 SSRF 防护")
    ssrf_allowed_domains: list[str] = Field(default_factory=list, description="SSRF 域名白名单")
    ssrf_blocked_domains: list[str] = Field(default_factory=list, description="SSRF 域名黑名单")
    ssrf_dns_pinned_ttl: int = Field(default=300, description="SSRF DNS 缓存时间（秒）")

    # === 定时任务调度配置（扁平字段，对齐既有模式，见设计方案 §13） ===
    scheduler_enabled: bool = Field(default=True, description="定时任务总开关")
    scheduler_tick_interval_seconds: int = Field(default=60, description="tick 频率（秒）")
    scheduler_max_consecutive_errors: int = Field(default=5, description="死信阈值")
    scheduler_task_timeout_seconds: int = Field(default=600, description="单任务超时（秒）")
    scheduler_max_payload_size_kb: int = Field(default=64, description="payload 大小上限（KB）")
    scheduler_max_active_tasks_per_owner: int = Field(default=100, description="业务方任务数上限")
    scheduler_stagger_max_seconds: int = Field(default=300, description="整点抖动上限（秒）")
    scheduler_run_log_retention_days: int = Field(default=90, description="run_logs 保留天数")
    scheduler_idempotency_retention_hours: int = Field(default=24, description="幂等记录保留小时数")
    scheduler_min_cron_interval_minutes: int = Field(default=10, description="cron 最小间隔（分钟）")
    scheduler_backoff_schedule: list[int] = Field(
        default_factory=lambda: [10, 30, 120, 600, 3600],
        description="指数退避序列（秒）",
    )

    # === Web 搜索配置（扁平字段，见设计方案 §10.1.1） ===
    web_search_provider_chain: list[str] = Field(
        default_factory=lambda: ["searxng", "tavily"],
        description="Web 搜索 Provider 优先级链",
    )
    web_search_searxng_base_url: str = Field(default="http://searxng:8080", description="SearXNG 服务地址")
    web_search_searxng_timeout: int = Field(default=10, description="SearXNG 调用超时（秒）")
    web_search_searxng_engines: list[str] = Field(default_factory=list, description="SearXNG 指定引擎列表（空=使用默认）")
    web_search_searxng_language: str = Field(default="auto", description="SearXNG 搜索语言")
    web_search_searxng_safesearch: int = Field(default=0, description="SearXNG 安全搜索级别（0/1/2）")
    web_search_tavily_api_key: str = Field(default="", description="Tavily API Key（空=读 TAVILY_API_KEY 环境变量）")
    web_search_tavily_timeout: int = Field(default=10, description="Tavily 调用超时（秒）")
    web_search_default_max_results: int = Field(default=5, description="Web 搜索默认结果数")
    web_search_rate_limit_per_minute: int = Field(default=20, description="单 agent Web 搜索每分钟调用上限")

    # === Web 抓取配置（扁平字段，见设计方案 §10.1.2） ===
    crawl4ai_base_url: str = Field(default="http://crawl4ai:11235", description="Crawl4AI 服务地址")
    crawl4ai_timeout: int = Field(default=30, description="Crawl4AI 单页抓取超时（秒）")
    crawl4ai_api_token: str = Field(default="", description="Crawl4AI API Token（预留 JWT 认证）")
    web_crawl_default_max_depth: int = Field(default=2, description="Web 抓取默认递归深度")
    web_crawl_default_max_pages: int = Field(default=20, description="Web 抓取默认最大页数")
    web_crawl_default_concurrency: int = Field(default=5, description="Web 抓取默认并发数")
    web_crawl_domain_whitelist: list[str] = Field(default_factory=list, description="Web 抓取域名白名单（空=允许所有公网域名）")
    web_crawl_respect_robots: bool = Field(default=True, description="Web 抓取是否尊重 robots.txt")
    web_crawl_rate_limit_per_minute: int = Field(default=10, description="单 agent Web 抓取每分钟调用上限")

    _config_file: Path | None = PrivateAttr(default=None)
    _user_modified_fields: set[str] = PrivateAttr(default_factory=set)

    model_config = {"arbitrary_types_allowed": True, "extra": "allow"}

    def __init__(self, **data):
        super().__init__(**data)
        self._setup_paths()
        self._load_user_config()
        self._handle_environment()

    def _setup_paths(self) -> None:
        self._config_file = Path(self.save_dir) / "config" / "base.toml"
        self._config_file.parent.mkdir(parents=True, exist_ok=True)

    def _load_user_config(self) -> None:
        if not self._config_file or not self._config_file.exists():
            logger.info(f"Config file not found, using defaults: {self._config_file}")
            return

        logger.info(f"Loading config from {self._config_file}")
        try:
            with open(self._config_file, "rb") as f:
                user_config = tomli.load(f)

            self._user_modified_fields = set(user_config.keys())

            for key, value in user_config.items():
                if hasattr(self, key):
                    setattr(self, key, value)
                else:
                    logger.warning(f"Unknown config key: {key}")

        except Exception as e:
            logger.error(f"Failed to load config from {self._config_file}: {e}")

    def _handle_environment(self) -> None:
        self.sandbox_provider = (os.getenv("SANDBOX_PROVIDER") or self.sandbox_provider or "provisioner").strip()
        self.sandbox_provisioner_url = (
            os.getenv("SANDBOX_PROVISIONER_URL") or self.sandbox_provisioner_url or "http://sandbox-provisioner:8002"
        ).strip()
        self.sandbox_virtual_path_prefix = (
            os.getenv("SANDBOX_VIRTUAL_PATH_PREFIX") or self.sandbox_virtual_path_prefix or "/home/gem/user-data"
        ).strip()
        self.sandbox_exec_timeout_seconds = int(
            os.getenv("SANDBOX_EXEC_TIMEOUT_SECONDS") or self.sandbox_exec_timeout_seconds or 180
        )
        self.sandbox_max_output_bytes = int(
            os.getenv("SANDBOX_MAX_OUTPUT_BYTES") or self.sandbox_max_output_bytes or 262144
        )
        self.sandbox_keepalive_interval_seconds = int(
            os.getenv("SANDBOX_KEEPALIVE_INTERVAL_SECONDS") or self.sandbox_keepalive_interval_seconds or 30
        )

        if self.sandbox_provider.lower() != "provisioner":
            raise ValueError("Only sandbox_provider=provisioner is supported.")
        if not self.sandbox_provisioner_url:
            raise ValueError("SANDBOX_PROVISIONER_URL is required when sandbox provider is provisioner.")
        if not self.sandbox_virtual_path_prefix.startswith("/"):
            self.sandbox_virtual_path_prefix = f"/{self.sandbox_virtual_path_prefix}"

        # SSRF 环境变量覆盖（兼容 YUXI_URL_WHITELIST）
        ssrf_env = os.getenv("YUXI_URL_WHITELIST", "")
        if ssrf_env:
            self.ssrf_allowed_domains = [d.strip() for d in ssrf_env.split(",") if d.strip()]

        # === scheduler 环境变量覆盖（对齐既有三段式写法，见设计方案 §13） ===
        self.scheduler_enabled = (
            os.getenv("SCHEDULER_ENABLED", "true").lower() in ("true", "1", "yes")
        )
        self.scheduler_tick_interval_seconds = int(
            os.getenv("SCHEDULER_TICK_INTERVAL_SECONDS") or self.scheduler_tick_interval_seconds or 60
        )
        self.scheduler_max_consecutive_errors = int(
            os.getenv("SCHEDULER_MAX_CONSECUTIVE_ERRORS") or self.scheduler_max_consecutive_errors or 5
        )
        self.scheduler_task_timeout_seconds = int(
            os.getenv("SCHEDULER_TASK_TIMEOUT_SECONDS") or self.scheduler_task_timeout_seconds or 600
        )
        self.scheduler_max_payload_size_kb = int(
            os.getenv("SCHEDULER_MAX_PAYLOAD_SIZE_KB") or self.scheduler_max_payload_size_kb or 64
        )
        self.scheduler_max_active_tasks_per_owner = int(
            os.getenv("SCHEDULER_MAX_ACTIVE_TASKS_PER_OWNER")
            or self.scheduler_max_active_tasks_per_owner
            or 100
        )
        self.scheduler_stagger_max_seconds = int(
            os.getenv("SCHEDULER_STAGGER_MAX_SECONDS") or self.scheduler_stagger_max_seconds or 300
        )
        self.scheduler_run_log_retention_days = int(
            os.getenv("SCHEDULER_RUN_LOG_RETENTION_DAYS") or self.scheduler_run_log_retention_days or 90
        )
        self.scheduler_idempotency_retention_hours = int(
            os.getenv("SCHEDULER_IDEMPOTENCY_RETENTION_HOURS")
            or self.scheduler_idempotency_retention_hours
            or 24
        )
        self.scheduler_min_cron_interval_minutes = int(
            os.getenv("SCHEDULER_MIN_CRON_INTERVAL_MINUTES")
            or self.scheduler_min_cron_interval_minutes
            or 10
        )

        # === Web 搜索环境变量覆盖 ===
        self.web_search_searxng_base_url = (
            os.getenv("WEB_SEARCH_SEARXNG_BASE_URL") or self.web_search_searxng_base_url
        )
        self.web_search_searxng_timeout = int(
            os.getenv("WEB_SEARCH_SEARXNG_TIMEOUT") or self.web_search_searxng_timeout
        )
        self.web_search_searxng_language = (
            os.getenv("WEB_SEARCH_SEARXNG_LANGUAGE") or self.web_search_searxng_language
        )
        self.web_search_searxng_safesearch = int(
            os.getenv("WEB_SEARCH_SEARXNG_SAFESEARCH") or self.web_search_searxng_safesearch
        )
        self.web_search_tavily_api_key = (
            os.getenv("TAVILY_API_KEY") or self.web_search_tavily_api_key
        )
        self.web_search_tavily_timeout = int(
            os.getenv("WEB_SEARCH_TAVILY_TIMEOUT") or self.web_search_tavily_timeout
        )

        # === Web 抓取环境变量覆盖 ===
        self.crawl4ai_base_url = (
            os.getenv("CRAWL4AI_BASE_URL") or self.crawl4ai_base_url
        )
        self.crawl4ai_timeout = int(
            os.getenv("CRAWL4AI_TIMEOUT") or self.crawl4ai_timeout
        )
        self.crawl4ai_api_token = (
            os.getenv("CRAWL4AI_API_TOKEN") or self.crawl4ai_api_token
        )

    @model_validator(mode="after")
    def _validate_web_search_crawl_config(self):
        """校验 web_search 与 web_crawl 配置合法性。"""
        valid_providers = {"searxng", "tavily"}
        for provider in self.web_search_provider_chain:
            if provider not in valid_providers:
                raise ValueError(
                    f"web_search_provider_chain 含未知 Provider 名: {provider}，"
                    f"合法值: {valid_providers}"
                )
        if not 1 <= self.web_search_default_max_results <= 10:
            raise ValueError("web_search_default_max_results 必须在 [1, 10] 范围内")
        if not 1 <= self.web_crawl_default_max_depth <= 3:
            raise ValueError("web_crawl_default_max_depth 必须在 [1, 3] 范围内")
        if not 1 <= self.web_crawl_default_max_pages <= 100:
            raise ValueError("web_crawl_default_max_pages 必须在 [1, 100] 范围内")
        return self

    def save(self) -> None:
        if not self._config_file:
            logger.warning("Config file path not set")
            return

        logger.info(f"Saving config to {self._config_file}")
        default_config = Config.model_construct()
        user_modified = {}
        for field_name, field_info in self.model_fields.items():
            if field_info.exclude:
                continue
            current_value = getattr(self, field_name)
            default_value = getattr(default_config, field_name)
            if current_value != default_value:
                user_modified[field_name] = current_value

        try:
            with open(self._config_file, "wb") as f:
                tomli_w.dump(user_modified, f)
            logger.info(f"Config saved to {self._config_file}")
        except Exception as e:
            logger.error(f"Failed to save config to {self._config_file}: {e}")

    def dump_config(self) -> dict[str, Any]:
        config_dict = self.model_dump()
        # 敏感字段脱敏
        sensitive_keys = {"web_search_tavily_api_key", "crawl4ai_api_token"}
        for key in sensitive_keys:
            if key in config_dict and config_dict[key]:
                config_dict[key] = "***"
        fields_info = {}
        for field_name, field_info in Config.model_fields.items():
            if field_info.exclude:
                continue
            fields_info[field_name] = {
                "des": field_info.description,
                "default": field_info.default,
                "type": field_info.annotation.__name__
                if hasattr(field_info.annotation, "__name__")
                else str(field_info.annotation),
                "exclude": field_info.exclude if hasattr(field_info, "exclude") else False,
            }
        config_dict["_config_items"] = fields_info
        return config_dict

    def update(self, other: dict[str, Any]) -> None:
        for key, value in other.items():
            if hasattr(self, key):
                setattr(self, key, value)
            else:
                logger.warning(f"Unknown config key: {key}")

    def get_ssrf_policy(self):
        """根据配置生成 SSRF 策略。"""
        from yuxi.utils.net_security import SSRFPolicy

        return SSRFPolicy(
            allowed_domains=self.ssrf_allowed_domains,
            blocked_domains=self.ssrf_blocked_domains,
            dns_pinned_ttl=self.ssrf_dns_pinned_ttl,
        )


config = Config()