feat: expose bare generation time and hedge flags in CallStats

CallStats gains hedges/generation_ms/hedge_won (all defaulted, appended
after total_latency_ms); _CallContext counts them via record_generation
(overwrite for chat/OCR, accumulate for embedding batches) and
register_hedge, and snapshot carries them out. All three _attempt
implementations time only the transport call itself on the same injected
clock as total_latency_ms; the chat sink is recorded by the orchestrator
so hedge winner attribution stays with T3. Hedge counters stay 0/False
until the T3 orchestration lands.

Red-green evidence: tests/outputs/137/t2/ (10 new tests AttributeError
red, then green; full unit+contracts 1621 passed).
This commit is contained in:
2026-09-10 13:28:51 -04:00
parent 0a6d6225db
commit 463eca380d
9 changed files with 283 additions and 6 deletions
+85 -2
View File
@@ -93,6 +93,39 @@ class FakeTransport:
return action
class _GenClockTransport:
"""委托 FakeTransport 的薄包装: 每次调用返回前按脚本推进注入钟(1.3.7 批次 C)。
generation_ms 的口径是"只计 transport 调用本身",故推进必须发生在被包
transport 内部;退避耗时由用例自带的 sleep 闭包推进,与本包装无关。
"""
def __init__(self, script, advances, clock):
self._inner = FakeTransport(script)
self._advances = list(advances)
self._clock = clock
@property
def calls(self):
return self._inner.calls
async def complete(
self, *, messages, source, stream, overlay, call_id, reasoning_effort, first_token_event
):
advance = self._advances.pop(0)
result = await self._inner.complete(
messages=messages,
source=source,
stream=stream,
overlay=overlay,
call_id=call_id,
reasoning_effort=reasoning_effort,
first_token_event=first_token_event,
)
self._clock.advance(advance)
return result
class HangingGate(InMemoryGate):
"""在指定记账写回处永久挂起的门控: 把"取消落在某个 await 上"变成确定性事件。
@@ -141,6 +174,8 @@ def _harness(
selector=None,
pacer=None,
gate=None,
transport=None,
sleep=None,
):
clock = clock or FakeClock()
limiter = InMemoryLimiter(
@@ -151,8 +186,8 @@ def _harness(
now=clock,
)
gate = gate if gate is not None else InMemoryGate(config=_BREAKER, now=clock)
transport = FakeTransport(script)
sleep = FakeSleep()
transport = transport if transport is not None else FakeTransport(script)
sleep = sleep if sleep is not None else FakeSleep()
mw = RetryMW(
scope="llm",
sources=sources,
@@ -916,6 +951,54 @@ class TestRateLimitPushback:
assert len(transport.calls) == 3
class TestGenerationMs:
"""裸生成时间(1.3.7 H8): 只计 transport 调用本身,不含退避/准入/遥测收尾。"""
def _ctx(self, clock):
from polygateway.types import _CallContext
return _CallContext(now=clock)
async def test_generation_ms_excludes_backoff_and_admission(self):
"""[Transient, ok] 脚本: 退避推进 5s、成功次 transport 推进 0.25s。
generation_ms 恒等于成功次 transport 的 250ms;若口径混入了退避,
它会涨到 5250ms 量级——与 total_latency_ms 的下界断言互为对偶。
推进量取二进制可精确表示值(0.25/5.0): int 截断下 0.2 之类会因浮点
误差落到 199,断言随之抖动(同 test_types 既有用例只用 1.5/2.0 的惯例)。
"""
clock = FakeClock()
async def advancing_sleep(seconds):
clock.advance(seconds)
transport = _GenClockTransport(
[TransientError("boom", source_name="a"), _ok()], [0.0, 0.25], clock
)
mw, *_ = _harness(
[_src("a")],
[],
clock=clock,
transport=transport,
sleep=advancing_sleep,
rng=lambda: 2.0, # backoff = 2.0 * (0.5 + 2.0) = 5.0s
)
ctx = self._ctx(clock)
resp = await mw(dataclasses.replace(_REQ, call_context=ctx))
assert resp.content == "ok" and len(transport.calls) == 2
stats = ctx.snapshot()
assert stats.generation_ms == 250
assert stats.total_latency_ms >= 5250
async def test_generation_ms_zero_hedge_flags_without_hedging(self):
"""无对冲时 hedges/hedge_won 恒 0/False(对冲登记是 T3 的事)。"""
mw, *_ = _harness([_src("a")], [_ok()])
ctx = self._ctx(FakeClock())
await mw(dataclasses.replace(_REQ, call_context=ctx))
stats = ctx.snapshot()
assert stats.hedges == 0 and stats.hedge_won is False
class TestLogicalAttemptCounting:
"""尝试登记在 transport 调用**之前**(1.3.5 设计 §4)。