"""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()