fix: apply the non-productive stall budget to the embedding loop

The embedding loop shares the wall-clock entered_at and the same stall
verdict, so it failed the same way through a different path: one timed-out
attempt, then any round with no runnable source, and _on_no_runnable
declared the scope dead. Issue #8 only recorded the chat path; the
regression test pins this one.

src/polygateway/embedding.py

@@ -39,7 +39,7 @@ from polygateway.errors import (
 )
 from polygateway.middleware.breaker import BreakerGate
 from polygateway.middleware.ratelimit import QuotaGate
-from polygateway.middleware.retry import _failure_reason, backoff_delay
+from polygateway.middleware.retry import StallClock, _failure_reason, backoff_delay
 from polygateway.middleware.telemetry import TelemetryEmitter
 from polygateway.sources import SourceCooldownMemo
 from polygateway.types import (
@@ -179,13 +179,15 @@ class EmbeddingClient:
     ) -> _BatchOutcome:
         fails = 0
         reasons: dict[str, str] = {}
-        entered_at = self._now()
+        # 只计非生产性等待(issue #8): 真实尝试由重试预算治理,不重复烧 stall 预算
+        clock = StallClock(self._now)
         while True:
             picked, gate_rejections = await self._pick_runnable(reasons)
             if picked is None:
-                await self._on_no_runnable(gate_rejections, reasons, entered_at)
+                await self._on_no_runnable(gate_rejections, reasons, clock)
                 continue
-            outcome = await self._attempt(batch, *picked, reasons, session_id, parent_call_id)
+            async with clock.attempting():
+                outcome = await self._attempt(batch, *picked, reasons, session_id, parent_call_id)
             if isinstance(outcome, _BatchOutcome):
                 return outcome
             fails += 1
@@ -228,7 +230,7 @@ class EmbeddingClient:
         return None, gate_rejections
 
     async def _on_no_runnable(
-        self, gate_rejections: int, reasons: dict[str, str], entered_at: float
+        self, gate_rejections: int, reasons: dict[str, str], clock: StallClock
     ) -> None:
         if gate_rejections == len(self._sources):
             names = tuple(s.name for s in self._sources)
@@ -245,7 +247,7 @@ class EmbeddingClient:
                 per_source_reasons=reasons,
             )
         stall = self._bp.stall_window_s
-        if self._now() - entered_at > stall and await self._quota.progress_age_s() > stall:
+        if clock.stalled_s() > stall and await self._quota.progress_age_s() > stall:
             names = tuple(s.name for s in self._sources)
             raise AllSourcesExhausted(
                 scope=self._scope,