import os from dataclasses import dataclass def _bool_env(name: str, default: bool) -> bool: value = os.getenv(name) if value is None: return default return value.strip().lower() in {"1", "true", "yes", "on"} def _int_env(name: str, default: int) -> int: try: return int(os.getenv(name, str(default))) except (TypeError, ValueError): return default def _float_env(name: str, default: float) -> float: try: return float(os.getenv(name, str(default))) except (TypeError, ValueError): return default def _str_env(name: str, default: str) -> str: value = os.getenv(name) if value is None: return default return value.strip() or default def _optional_env(name: str) -> str | None: value = os.getenv(name) if value is None: return None value = value.strip() return value or None @dataclass(frozen=True) class RiskConfig: cors_allow_origins: tuple[str, ...] session_cookie_name: str session_cookie_secure: bool session_cookie_samesite: str session_cookie_domain: str | None session_cookie_max_age: int session_cookie_path: str session_rotation_seconds: int api_window_seconds: int api_soft_limit_per_window: int api_hard_limit_per_window: int llm_window_seconds: int llm_soft_limit_per_window: int llm_hard_limit_per_window: int session_concurrency_limit: int global_concurrency_limit: int daily_budget_global_usd: float daily_budget_session_usd: float daily_budget_ip_usd: float single_request_max_cost_usd: float delay_step_ms: int delay_cap_ms: int model_circuit_breaker_failures: int model_circuit_ttl_seconds: int enforce_redis_fail_closed: bool completion_model: str pro_model: str vision_model: str completion_max_input_chars: int completion_max_output_tokens: int completion_temperature: float pro_max_input_chars: int pro_max_output_tokens: int pro_temperature: float web_search_model: str web_search_max_input_chars: int web_search_max_output_tokens: int web_search_temperature: float compress_max_input_chars: int compress_max_output_tokens: int ocr_max_input_bytes: int completion_input_cost_per_1k: float completion_output_cost_per_1k: float pro_input_cost_per_1k: float pro_output_cost_per_1k: float vision_input_cost_per_1k: float vision_output_cost_per_1k: float def load_risk_config() -> RiskConfig: raw_origins = _str_env( "CORS_ALLOW_ORIGINS", "https://chat.imageteach.tech,http://localhost:8080,http://127.0.0.1:8080", ) cors_allow_origins = tuple( origin.strip() for origin in raw_origins.split(",") if origin.strip() ) return RiskConfig( cors_allow_origins=cors_allow_origins, session_cookie_name=_str_env("SESSION_COOKIE_NAME", "llm_anonymous_session"), session_cookie_secure=_bool_env("SESSION_COOKIE_SECURE", True), session_cookie_samesite=_str_env("SESSION_COOKIE_SAMESITE", "none"), session_cookie_domain=_optional_env("SESSION_COOKIE_DOMAIN"), session_cookie_max_age=_int_env("SESSION_COOKIE_MAX_AGE_SECONDS", 60 * 60 * 24 * 30), session_cookie_path=_str_env("SESSION_COOKIE_PATH", "/"), session_rotation_seconds=_int_env("SESSION_ROTATION_SECONDS", 60 * 60 * 24), api_window_seconds=_int_env("RISK_API_WINDOW_SECONDS", 60), api_soft_limit_per_window=_int_env("RISK_API_SOFT_LIMIT", 90), api_hard_limit_per_window=_int_env("RISK_API_HARD_LIMIT", 180), llm_window_seconds=_int_env("RISK_LLM_WINDOW_SECONDS", 600), llm_soft_limit_per_window=_int_env("RISK_LLM_SOFT_LIMIT", 8), llm_hard_limit_per_window=_int_env("RISK_LLM_HARD_LIMIT", 16), session_concurrency_limit=_int_env("RISK_SESSION_CONCURRENCY_LIMIT", 2), global_concurrency_limit=_int_env("RISK_GLOBAL_CONCURRENCY_LIMIT", 12), daily_budget_global_usd=_float_env("RISK_DAILY_BUDGET_GLOBAL_USD", 20.0), daily_budget_session_usd=_float_env("RISK_DAILY_BUDGET_SESSION_USD", 2.0), daily_budget_ip_usd=_float_env("RISK_DAILY_BUDGET_IP_USD", 5.0), single_request_max_cost_usd=_float_env("RISK_SINGLE_REQUEST_MAX_COST_USD", 0.8), delay_step_ms=_int_env("RISK_DELAY_STEP_MS", 2500), delay_cap_ms=_int_env("RISK_DELAY_CAP_MS", 30000), model_circuit_breaker_failures=_int_env("RISK_MODEL_CIRCUIT_FAILURES", 8), model_circuit_ttl_seconds=_int_env("RISK_MODEL_CIRCUIT_TTL_SECONDS", 300), enforce_redis_fail_closed=_bool_env("RISK_ENFORCE_REDIS_FAIL_CLOSED", False), completion_model=_str_env("RISK_COMPLETION_MODEL", os.getenv("LLM_MODEL", "gpt-4.1-mini")), pro_model=_str_env("RISK_PRO_MODEL", os.getenv("PRO_LLM_MODEL", os.getenv("LLM_MODEL", "gpt-4.1"))), vision_model=_str_env("RISK_VISION_MODEL", os.getenv("VLM_MODEL", "gpt-4.1-mini")), completion_max_input_chars=_int_env("RISK_COMPLETION_MAX_INPUT_CHARS", 24000), completion_max_output_tokens=_int_env("RISK_COMPLETION_MAX_OUTPUT_TOKENS", 768), completion_temperature=_float_env("RISK_COMPLETION_TEMPERATURE", 0.4), pro_max_input_chars=_int_env("RISK_PRO_MAX_INPUT_CHARS", 48000), pro_max_output_tokens=_int_env("RISK_PRO_MAX_OUTPUT_TOKENS", 2048), pro_temperature=_float_env("RISK_PRO_TEMPERATURE", 0.6), web_search_model=_str_env("RISK_WEB_SEARCH_MODEL", os.getenv("LLM_MODEL", "gpt-4.1-mini")), web_search_max_input_chars=_int_env("RISK_WEB_SEARCH_MAX_INPUT_CHARS", 128000), web_search_max_output_tokens=_int_env("RISK_WEB_SEARCH_MAX_OUTPUT_TOKENS", 4096), web_search_temperature=_float_env("RISK_WEB_SEARCH_TEMPERATURE", 0.4), compress_max_input_chars=_int_env("RISK_COMPRESS_MAX_INPUT_CHARS", 128000), compress_max_output_tokens=_int_env("RISK_COMPRESS_MAX_OUTPUT_TOKENS", 1536), ocr_max_input_bytes=_int_env("RISK_OCR_MAX_INPUT_BYTES", 10 * 1024 * 1024), completion_input_cost_per_1k=_float_env("RISK_COMPLETION_INPUT_COST_PER_1K", 0.0004), completion_output_cost_per_1k=_float_env("RISK_COMPLETION_OUTPUT_COST_PER_1K", 0.0016), pro_input_cost_per_1k=_float_env("RISK_PRO_INPUT_COST_PER_1K", 0.003), pro_output_cost_per_1k=_float_env("RISK_PRO_OUTPUT_COST_PER_1K", 0.012), vision_input_cost_per_1k=_float_env("RISK_VISION_INPUT_COST_PER_1K", 0.0008), vision_output_cost_per_1k=_float_env("RISK_VISION_OUTPUT_COST_PER_1K", 0.0024), )