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).

src/polygateway/embedding.py

@@ -370,7 +370,11 @@ class EmbeddingClient:
         # 登记在 transport 调用**之前**(同 RetryMW): 失败与取消的尝试也真的发出去了
         context.register_attempt()
         try:
+            # 裸生成时间(1.3.7 H8): 计时只包 transport 调用本身(同 RetryMW 口径),
+            # 与本链路 total_latency_ms 同一只注入钟;分批累加在成功分支登记
+            gen_started = self._now()
             result = await self._transport.embed(texts=batch, source=source, call_id=call_id)
+            gen_ms = int((self._now() - gen_started) * 1000)
             if self._expected_dim is not None and result.dim != self._expected_dim:
                 raise ResultInvalidError(
                     f"{source.name} 维度 {result.dim} 不符期望 {self._expected_dim}",
@@ -384,6 +388,7 @@ class EmbeddingClient:
                 actual = result.prompt_tokens
             # 真实 usage 恰为 0 也是已知事实, 后续取消不得改写成 est
             settlement_known = True
+            context.record_generation(gen_ms, accumulate=True)
             await self._record_quietly(self._breaker.record_success(entry))
             await self._record_quietly(self._quota.mark_progress())
             latency_ms = int((self._now() - started) * 1000)