“ydy0615”
163 lines
7.5 KiB
Python
163 lines
7.5 KiB
Python
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
|
|
speech_tts_model: str
|
|
speech_asr_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
|
|
speech_tts_max_input_chars: int
|
|
speech_asr_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
|
|
speech_tts_input_cost_per_1k_chars: float
|
|
speech_tts_output_cost_per_minute_audio: float
|
|
speech_asr_input_cost_per_mb: 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,http://localhost:5173,http://127.0.0.1:5173",
|
|
)
|
|
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", "Nex-N2-mini-mlx-OptiQ-8bit-MTP")),
|
|
pro_model=_str_env("RISK_PRO_MODEL", os.getenv("PRO_LLM_MODEL", os.getenv("LLM_MODEL", "Nex-N2-mini-mlx-OptiQ-8bit-MTP"))),
|
|
vision_model=_str_env("RISK_VISION_MODEL", os.getenv("VLM_MODEL", "Nex-N2-mini-mlx-OptiQ-8bit-MTP")),
|
|
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", "Nex-N2-mini-mlx-OptiQ-8bit-MTP")),
|
|
speech_tts_model=_str_env("RISK_SPEECH_TTS_MODEL", "Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit"),
|
|
speech_asr_model=_str_env("RISK_SPEECH_ASR_MODEL", "Qwen3-ASR-0.6B-8bit"),
|
|
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", 100 * 1024 * 1024),
|
|
speech_tts_max_input_chars=_int_env("RISK_SPEECH_TTS_MAX_INPUT_CHARS", 4096),
|
|
speech_asr_max_input_bytes=_int_env("RISK_SPEECH_ASR_MAX_INPUT_BYTES", 100 * 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),
|
|
speech_tts_input_cost_per_1k_chars=_float_env("RISK_SPEECH_TTS_INPUT_COST_PER_1K_CHARS", 0.0),
|
|
speech_tts_output_cost_per_minute_audio=_float_env("RISK_SPEECH_TTS_OUTPUT_COST_PER_MINUTE_AUDIO", 0.0),
|
|
speech_asr_input_cost_per_mb=_float_env("RISK_SPEECH_ASR_INPUT_COST_PER_MB", 0.0),
|
|
)
|