iomgaa
d8e8fd8124
Five call sites (QuotaGate entry, RetryMW/EmbeddingClient success and transient-failure settlement) now read effective_est_tokens() instead of est_tokens. Success paths gain an unavailable branch that keeps delta at zero once usage frames may be missing; it has no producer yet, so behaviour is unchanged while the tpm>0 => est_tokens>0 gate still holds.
55 lines
1.9 KiB
Python
55 lines
1.9 KiB
Python
"""限流准入封装: 后端故障必须报错而非放行(降级方向铁律)。
|
|
|
|
非降级设计说明: 缓存/遥测挂 → 静默;限流挂 → 若放行,多 worker 会同时
|
|
失去闸门直接击穿网关,故一律 GovernanceBackendError 上抛。
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
from polygateway.errors import GovernanceBackendError
|
|
|
|
if TYPE_CHECKING:
|
|
from polygateway.ports import Permit, RateLimiter
|
|
from polygateway.types import SourceConfig, SourceStats
|
|
|
|
|
|
class QuotaGate:
|
|
"""RetryMW 面向限流后端的唯一入口;包装一切后端异常。"""
|
|
|
|
def __init__(self, limiter: RateLimiter) -> None:
|
|
self._limiter = limiter
|
|
|
|
async def try_acquire(self, source: SourceConfig) -> Permit | None:
|
|
try:
|
|
return await self._limiter.try_acquire(source.name, source.effective_est_tokens())
|
|
except GovernanceBackendError:
|
|
raise
|
|
except Exception as exc:
|
|
raise GovernanceBackendError(f"限流后端故障(try_acquire): {exc}") from exc
|
|
|
|
async def stats(self, source: SourceConfig) -> SourceStats:
|
|
try:
|
|
return await self._limiter.source_stats(source.name)
|
|
except GovernanceBackendError:
|
|
raise
|
|
except Exception as exc:
|
|
raise GovernanceBackendError(f"限流后端故障(source_stats): {exc}") from exc
|
|
|
|
async def mark_progress(self) -> None:
|
|
try:
|
|
await self._limiter.mark_progress()
|
|
except GovernanceBackendError:
|
|
raise
|
|
except Exception as exc:
|
|
raise GovernanceBackendError(f"限流后端故障(mark_progress): {exc}") from exc
|
|
|
|
async def progress_age_s(self) -> float:
|
|
try:
|
|
return await self._limiter.progress_age_s()
|
|
except GovernanceBackendError:
|
|
raise
|
|
except Exception as exc:
|
|
raise GovernanceBackendError(f"限流后端故障(progress_age_s): {exc}") from exc
|