feat: add opt-in cross-source hedged requests for chat
This commit is contained in:
@@ -19,7 +19,7 @@ from typing import TYPE_CHECKING, Any, Literal
|
||||
from polygateway.backends.memory.breaker import InMemoryGate
|
||||
from polygateway.backends.memory.cache import InMemoryCache
|
||||
from polygateway.backends.memory.limiter import InMemoryLimiter
|
||||
from polygateway.config import GatewaySettings
|
||||
from polygateway.config import GatewaySettings, check_hedge_assembly
|
||||
from polygateway.deadline import ensure_call_deadline, with_call_deadline
|
||||
from polygateway.errors import PolyGatewayError
|
||||
from polygateway.middleware.base import compose
|
||||
@@ -237,6 +237,8 @@ class GatewayClient:
|
||||
structured_escalation: StructuredOutputStrategy | None = None,
|
||||
structured_max_retries: int = 1,
|
||||
call_deadline_s: float | None = None,
|
||||
hedge_after_s: float | None = None,
|
||||
hedge_max_extra: int = 1,
|
||||
now: Any = time.monotonic,
|
||||
sleep: Any = asyncio.sleep,
|
||||
rng: Any = random.random,
|
||||
@@ -245,6 +247,15 @@ class GatewayClient:
|
||||
self._call_deadline_s = ensure_call_deadline(
|
||||
call_deadline_s, "GatewayClient(call_deadline_s=...)"
|
||||
)
|
||||
# 对冲守卫与 GatewaySettings 共用同一份(issue #24 H4): 直接构造这条路
|
||||
# 不经过 settings,值域/交叉守卫若只挂在 settings 上就会被它绕过
|
||||
self._hedge_after_s = check_hedge_assembly(
|
||||
hedge_after_s=hedge_after_s,
|
||||
hedge_max_extra=hedge_max_extra,
|
||||
sources=sources,
|
||||
call_deadline_s=self._call_deadline_s,
|
||||
origin="GatewayClient(hedge_after_s=...)",
|
||||
)
|
||||
emitter = (
|
||||
TelemetryEmitter(telemetry, scope=scope, pricing=pricing, text_cap=text_cap)
|
||||
if telemetry is not None
|
||||
@@ -267,6 +278,8 @@ class GatewayClient:
|
||||
ceiling=float(max([64, *(s.max_concurrency for s in sources if s.max_concurrency)]))
|
||||
),
|
||||
emitter=emitter,
|
||||
# max_extra 不下传(issue #24 H5): v1 编排固定单路对冲,无消费者
|
||||
hedge_after_s=self._hedge_after_s,
|
||||
now=now,
|
||||
sleep=sleep,
|
||||
rng=rng,
|
||||
@@ -509,6 +522,8 @@ class GatewayClient:
|
||||
structured_escalation=escalation,
|
||||
structured_max_retries=settings.structured_max_retries,
|
||||
call_deadline_s=settings.call_deadline_s,
|
||||
hedge_after_s=settings.hedge_after_s,
|
||||
hedge_max_extra=settings.hedge_max_extra,
|
||||
)
|
||||
_mark_owned_components(client, limiter=limiter, breaker=breaker, telemetry=telemetry)
|
||||
client._owns_cache = cache is None # 缓存后端可以是 None(backend=none),helper 会跳过
|
||||
|
||||
Reference in New Issue
Block a user