test: pin the expiry window and close settlement review gaps

src/polygateway/client.py

@@ -634,6 +634,7 @@ async def gather_bounded[T](aws: Iterable[Awaitable[T]], *, concurrency: int) ->
     """有界并发 gather(D5 便利函数,替代 VT 手搓 semaphore+gather 样板)。
 
     语义与 `asyncio.gather` 默认一致: 结果保序、首个异常上抛;仅增加并发上限。
+    期限计时从每次调用真正开始执行起算,信号量排队时长不在 `call_deadline_s` 之内。
     """
     if concurrency < 1:
         raise ValueError("concurrency 必须 ≥ 1")

src/polygateway/deadline.py

@@ -65,7 +65,7 @@ async def with_call_deadline[T](aw: Awaitable[T], *, deadline_s: float | None, s
     # 体内(含清理路径)自抛的 TimeoutError 的**身份**,唯一可靠的区分依据
     inner_timeout: BaseException | None = None
     # 先建对象再进上下文: `as cm` 只在 `__aenter__` 返回后才绑定, 而 except 块无条件
-    # 读 `cm`——进入阶段一旦异常就会变成 NameError 掩盖真实错误
+    # 读 `cm`——进入阶段一旦抛 TimeoutError 就会变成 NameError 掩盖真实错误
     cm = asyncio.timeout(deadline_s)
     try:
         async with cm:

tests/unit/test_deadline.py

@@ -5,6 +5,7 @@
 """
 
 import asyncio
+import time
 
 import pytest
 
@@ -124,14 +125,23 @@ async def test_narrow_success_returns_value_without_pending_cancellation():
 
 
 async def test_domain_error_inside_window_propagates():
+    """计时器已触发但取消尚未投递的窗口内,体内先抛领域异常 → 原样上抛,期限静默让位。
+
+    忙等超过期限: 计时器回调已在 loop 上触发,但任务不挂起取消就投递不进来,
+    此刻体内同步抛出的领域异常必须原样逃逸(设计 §5.2 形态四)。
+    """
+
     class BoomError(RuntimeError):
         pass
 
     async def body():
+        end = time.monotonic() + 0.1
+        while time.monotonic() < end:
+            pass
         raise BoomError("boom")
 
     with pytest.raises(BoomError):
-        await with_call_deadline(body(), deadline_s=0.05, scope="llm")
+        await with_call_deadline(body(), deadline_s=0.02, scope="llm")
 
 
 async def test_none_deadline_takes_the_legacy_path():

tests/unit/test_embedding.py

@@ -700,7 +700,7 @@ class TestEmbedCallDeadline:
         elapsed = loop.time() - started
         assert exc.value.scope == "embed"
         # 按批计的话 20 批全都能跑完(根本不会抛),共享一份则跑不到头
-        assert 2 <= len(transport.calls) < 20
+        assert 1 <= len(transport.calls) < 20
         assert elapsed < 20 * 0.05, f"总时长疑似随批数放大: {elapsed}s"
 
     async def test_empty_input_is_exempt_from_the_deadline(self):

tests/unit/test_retry.py

@@ -585,6 +585,22 @@ class TestCancellationSettlement:
         await mw(_REQ)
         assert (await limiter.source_stats("a")).tpm_used == 0
 
+    async def test_circuit_open_rejection_settles_zero_end_to_end(self):
+        """S1 端到端: 开路拒绝的 pick 预扣后按 0 结算, 不给 tpm_used 增加任何量。"""
+        clock = FakeClock()
+        script = [TransientError(str(i)) for i in range(9)]
+        mw, limiter, *_ = _harness(
+            [_src("a", max_concurrency=1, tpm=10000, est_tokens=400)],
+            script,
+            clock=clock,
+            max_attempts=99,
+        )
+        # 3 次瞬时失败后 a 开路 → 第 4 次 pick 被拒绝
+        with pytest.raises(CircuitOpenError):
+            await mw(_REQ)
+        # 三次瞬时失败各保留 est = 1200; 开路那次 pick 若漏了 settle(0) 会再 +400
+        assert (await limiter.source_stats("a")).tpm_used == 1200
+
 
 class TestCancellation:
     async def test_cancel_mid_flight_releases_permit(self):