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).

tests/unit/test_client.py

@@ -144,6 +144,66 @@ class TestChatEndToEnd:
                 await client.chat([{"role": "user", "content": "hi"}], structured="json")
 
 
+class TestGenerationMsClient:
+    """裸生成时间的 client 级口径(1.3.7 批次 C2/F)。
+
+    `_ScriptedGenClockTransport` 在每次 transport 调用内推进注入钟,
+    使"时间花在哪"可断言(同 test_backpressure.ClockAdvancingTransport 范式)。
+    """
+
+    _MSG = [{"role": "user", "content": "hi"}]
+
+    async def test_generation_ms_structured_last_round_wins(self):
+        """结构化重问覆盖而非累加: 首轮坏 JSON 推进 1s,重问轮推进 0.25s → 250。
+
+        推进量取二进制可精确表示值: int 截断下非精确值会因浮点误差少 1ms。
+        """
+        from pydantic import BaseModel
+
+        class Answer(BaseModel):
+            answer: int
+
+        clock = _StatsClock()
+        transport = _ScriptedGenClockTransport(
+            [_ok("not json at all"), _ok('{"answer": 1}')], [1.0, 0.25], clock
+        )
+        async with _client(transport=transport, structured_max_retries=1, now=clock) as client:
+            resp = await client.chat(self._MSG, structured=Answer)
+        assert resp.content == '{"answer": 1}' and len(transport.calls) == 2
+        assert resp.call_stats is not None
+        assert resp.call_stats.attempts == 2
+        assert resp.call_stats.generation_ms == 250
+
+    async def test_cache_hit_generation_ms_zero(self):
+        """缓存命中不产生 transport 调用: generation_ms 恒 0(0 是实测,非"未知")。"""
+        client = _client(cache=InMemoryCache(), cache_namespace="proj", cache_ttl_s=3600)
+        async with client:
+            first = await client.chat(self._MSG)
+            second = await client.chat(self._MSG)
+        assert first.cache_hit is False and second.cache_hit is True
+        assert second.call_stats is not None
+        assert second.call_stats.generation_ms == 0
+        assert second.call_stats.attempts == 0
+
+
+class _ScriptedGenClockTransport:
+    """脚本化假 transport: 每次成功调用在返回前按脚本推进注入钟(批次 C2/F)。"""
+
+    def __init__(self, results, advances, clock):
+        self._results = list(results)
+        self._advances = list(advances)
+        self._clock = clock
+        self.calls = []
+
+    async def complete(
+        self, *, messages, source, stream, overlay, call_id, reasoning_effort, first_token_event
+    ):
+        self.calls.append(call_id)
+        result = self._results.pop(0)
+        self._clock.advance(self._advances.pop(0))
+        return result
+
+
 class TestSamplingOverlay:
     """调用级采样参数入口(issue #4 Task 3)。"""