xsl
9e7a886863
多 agent 并行批次的协调提交（消除全部共享文件冲突面）： - 迁移 0004：id_session + ob_event 两表（T3/T4 用，任务不再写迁移） - ORM：UserSession / ObEvent；错误码：九个新码（40xxx/60006，含 meta） - 配置：四档 tiers / refresh TTL / 任务奖励注册表 / 埋点上限 / COS 直传全套 - 骨架：packages/analytics + packages/storage + events/uploads 空路由（已注册） - deps：AnalyticsServiceDep / StorageServiceDep；DailyBudgetGuard 接收 tiers - uv add cos-python-sdk-v5；import-linter/CI/Makefile 纳入两个新包
125 lines
4.6 KiB
Python
125 lines
4.6 KiB
Python
"""Global daily cost circuit breaker (架构文档 §13「必须设置的三道成本闸门」).
|
|
|
|
Gate 1 in §13 is described as "某功能超预算自动降级，并告警". Alerting alone is
|
|
not enough: the failure modes that blow up AI spend (retry storms, a cache-key
|
|
bug, someone scripting the API) all produce cost faster than a human can react
|
|
to a page. So this is an *enforcement* point, not a notification: once the
|
|
platform-wide daily spend crosses the threshold, non-critical scenes are
|
|
rejected outright.
|
|
|
|
Critical scenes (e.g. content moderation follow-ups, paid-path completions)
|
|
opt out via ``SceneConfig.critical`` so that a budget overrun degrades the
|
|
product instead of breaking it.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from datetime import UTC, datetime, timedelta, timezone
|
|
from decimal import Decimal
|
|
from typing import Protocol, runtime_checkable
|
|
|
|
from packages.llm.errors import DailyBudgetExceededError
|
|
|
|
_DAY_SECONDS = 60 * 60 * 24
|
|
|
|
|
|
@runtime_checkable
|
|
class CostCounter(Protocol):
|
|
"""Atomic accumulating counter. Redis in production, dict in tests."""
|
|
|
|
async def incr(self, key: str, amount: Decimal, ttl_seconds: int) -> Decimal: ...
|
|
|
|
async def get(self, key: str) -> Decimal: ...
|
|
|
|
|
|
class InMemoryCostCounter:
|
|
"""Process-local counter. Correct only for a single process — tests only."""
|
|
|
|
def __init__(self) -> None:
|
|
self._values: dict[str, Decimal] = {}
|
|
|
|
async def incr(self, key: str, amount: Decimal, ttl_seconds: int) -> Decimal:
|
|
self._values[key] = self._values.get(key, Decimal("0")) + amount
|
|
return self._values[key]
|
|
|
|
async def get(self, key: str) -> Decimal:
|
|
return self._values.get(key, Decimal("0"))
|
|
|
|
|
|
class RedisCostCounter:
|
|
"""Cross-process counter backed by ``INCRBYFLOAT`` + a rolling TTL."""
|
|
|
|
def __init__(self, redis: object) -> None:
|
|
self._redis = redis
|
|
|
|
async def incr(self, key: str, amount: Decimal, ttl_seconds: int) -> Decimal:
|
|
pipe = self._redis.pipeline() # type: ignore[attr-defined]
|
|
pipe.incrbyfloat(key, float(amount))
|
|
pipe.expire(key, ttl_seconds)
|
|
results = await pipe.execute()
|
|
return Decimal(str(results[0]))
|
|
|
|
async def get(self, key: str) -> Decimal:
|
|
value = await self._redis.get(key) # type: ignore[attr-defined]
|
|
return Decimal(str(value)) if value is not None else Decimal("0")
|
|
|
|
|
|
class DailyBudgetGuard:
|
|
"""Hard platform-wide daily AI budget."""
|
|
|
|
def __init__(
|
|
self,
|
|
counter: CostCounter,
|
|
*,
|
|
daily_budget_cents: Decimal,
|
|
enabled: bool = True,
|
|
key_prefix: str = "llm:cost:daily",
|
|
tz_offset_hours: int = 8,
|
|
clock: object | None = None,
|
|
tiers: list[dict[str, object]] | None = None,
|
|
) -> None:
|
|
self._counter = counter
|
|
self._budget = daily_budget_cents
|
|
self._enabled = enabled
|
|
self._key_prefix = key_prefix
|
|
self._tz = timezone(timedelta(hours=tz_offset_hours))
|
|
self._clock = clock
|
|
# 四档分级降级的配置（架构 §13.3 / T-P1-25b）。T1 任务实现判定逻辑；
|
|
# 这里先接收配置，使 deps 装配层不必随后再改。None = 使用内置默认四档。
|
|
self._tiers_config = tiers
|
|
|
|
@property
|
|
def enabled(self) -> bool:
|
|
return self._enabled
|
|
|
|
@property
|
|
def budget_cents(self) -> Decimal:
|
|
return self._budget
|
|
|
|
def _now(self) -> datetime:
|
|
if self._clock is not None:
|
|
return self._clock() # type: ignore[operator,no-any-return]
|
|
return datetime.now(UTC)
|
|
|
|
def current_key(self) -> str:
|
|
"""Budget day boundary follows UTC+8, consistent with FR-BILL-01."""
|
|
local = self._now().astimezone(self._tz)
|
|
return f"{self._key_prefix}:{local:%Y-%m-%d}"
|
|
|
|
async def spent_today(self) -> Decimal:
|
|
return await self._counter.get(self.current_key())
|
|
|
|
async def ensure_within_budget(self, *, scene: str, critical: bool = False) -> None:
|
|
"""Raise :class:`DailyBudgetExceededError` for non-critical scenes over budget."""
|
|
if not self._enabled or critical:
|
|
return
|
|
spent = await self.spent_today()
|
|
if spent >= self._budget:
|
|
raise DailyBudgetExceededError(str(spent), str(self._budget), scene)
|
|
|
|
async def add_cost(self, cost_cents: Decimal) -> Decimal:
|
|
"""Accumulate spend. Called after every provider attempt, success or not."""
|
|
if not self._enabled or cost_cents <= 0:
|
|
return await self.spent_today() if self._enabled else Decimal("0")
|
|
return await self._counter.incr(self.current_key(), cost_cents, _DAY_SECONDS)
|