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)

src/polygateway/middleware/retry.py

@@ -246,12 +246,20 @@ class RetryMW:
                 await self._admission.on_no_runnable(gate_rejections, reasons, clock)
                 continue
             async with clock.attempting() as attempt:
-                outcome = await self._attempt(request, *picked, reasons, attempt_fails)
+                # 每轮一个 sink: 裸生成时间由编排裁定归属(T2 单路 = 成功那轮;
+                # T3 对冲 = 赢家那一路),`_attempt` 只负责把本次 transport 耗时投进来
+                generation_sink: list[int] = []
+                outcome = await self._attempt(
+                    request, *picked, reasons, attempt_fails, generation_sink=generation_sink
+                )
                 rate_limited = _is_rate_limited(outcome)
                 if rate_limited:
                     # 免了重试预算就得进 stall 账,否则这段耗时无人治理(见 StallClock)
                     attempt.refund()
             if isinstance(outcome, LLMResponse):
+                # 与 register_attempt 同款 None 守卫: 库内现场构造的请求跳过登记
+                if request.call_context is not None:
+                    request.call_context.record_generation(generation_sink[0], accumulate=False)
                 return outcome
             if not rate_limited:
                 fails += 1
@@ -275,6 +283,8 @@ class RetryMW:
         entry: GateDecision,
         reasons: dict[str, str],
         attempt_fails: dict[str, int],
+        *,
+        generation_sink: list[int],
     ) -> LLMResponse | _Failed:
         call_id = str(uuid.uuid4())
         started = self._now()
@@ -288,6 +298,10 @@ class RetryMW:
         if request.call_context is not None:
             request.call_context.register_attempt()
         try:
+            # 裸生成时间(1.3.7 H8): 计时只包 transport 调用本身,起点紧贴调用前、
+            # 终点为返回后首句(中间无 await);取消落进来时 transport 未返回,不计。
+            # 与该链路 total_latency_ms 同一只注入钟,差值(波动开销)才有意义
+            gen_started = self._now()
             result = await self._transport.complete(
                 messages=request.messages,
                 source=source,
@@ -300,6 +314,7 @@ class RetryMW:
                 # T3 对冲编排接线前恒为 None: 调用方不观测首 token(计划 §3.1)
                 first_token_event=None,
             )
+            generation_sink.append(int((self._now() - gen_started) * 1000))
             if result.usage_source == "unavailable":
                 # 用量不可得时按入场预扣量结算(delta==0),否则押金会被整笔退回,
                 # 对"从不返回 usage 帧"的源等于 TPM 闸失效(设计 §3.2 #9)

src/polygateway/ocr.py

@@ -395,11 +395,16 @@ class OcrClient:
         # layout 的 POST + ZIP GET 在同一次 `_invoke` 内,故这里只登记 **1** 次
         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);
+            # layout 的 POST + ZIP GET 在同一次 `_invoke` 内,属同一段生成耗时
+            gen_started = self._now()
             result = await self._invoke(kind, image, source, call_id)
+            gen_ms = int((self._now() - gen_started) * 1000)
             await self._record_quietly(self._breaker.record_success(entry))
             await self._record_quietly(self._quota.mark_progress())
             self._feed_outcome(source.name, ok=True)
             latency_ms = int((self._now() - started) * 1000)
+            context.record_generation(gen_ms, accumulate=False)
             await self._emit(
                 kind,
                 operation,

src/polygateway/types.py

@@ -317,23 +317,42 @@ class CallStats:
     含缓存 IO、退避等待、准入等待、重问、分批与内联记账。
     "总耗时减最后一次尝试耗时"**不等于**纯等待(含其他本地工作)。"""
 
+    hedges: int = 0
+    """本次逻辑调用实际并发发出的对冲路数(触发但准入失败静默不计);1.3.6 及以前恒 0。"""
+    generation_ms: int = 0
+    """裸生成时间: 赢家/成功那次 transport 调用的墙钟时长(口径见设计 §4.5 H8)。"""
+    hedge_won: bool = False
+    """赢家是否为对冲路;无对冲恒 False。"""
+
 
 class _CallContext:
     """私有可变逻辑调用上下文: 只持计数、单调时钟与终态去重位,不做 I/O。
 
-    **每调用一个实例**的单任务对象: chat 重试、结构化重问、embedding 分批
-    都在同一任务内串行推进,故计数无需锁。**严禁提升为 client 实例属性**
+    **每逻辑调用一个实例**,可多任务并发登记(对冲);全部方法无 await,
+    事件循环内任务安全。**严禁提升为 client 实例属性**
     ——那会让同一 client 的并发调用互相串掉计数与逻辑 ID(库铁律"纯 asyncio 中立"、
     VT `evolve_llm = llm` 教训的同一形态)。
     """
 
-    __slots__ = ("_attempts", "_now", "_started", "_terminal_claimed", "logical_call_id")
+    __slots__ = (
+        "_attempts",
+        "_generation_ms",
+        "_hedge_won",
+        "_hedges",
+        "_now",
+        "_started",
+        "_terminal_claimed",
+        "logical_call_id",
+    )
 
     def __init__(self, *, now: Callable[[], float]) -> None:
         self.logical_call_id = str(uuid.uuid4())
         self._now = now
         self._started = now()
         self._attempts = 0
+        self._generation_ms = 0
+        self._hedges = 0
+        self._hedge_won = False
         self._terminal_claimed = False
 
     def register_attempt(self) -> None:
@@ -344,12 +363,24 @@ class _CallContext:
         """
         self._attempts += 1
 
+    def record_generation(self, elapsed_ms: int, *, accumulate: bool) -> None:
+        """chat/OCR 覆盖(结构化重问最后一轮为准);embedding 分批累加。"""
+        self._generation_ms = self._generation_ms + elapsed_ms if accumulate else elapsed_ms
+
+    def register_hedge(self, *, hedge_won: bool) -> None:
+        """对冲路实际发出即计数;赢家裁定后一次性登记。"""
+        self._hedges += 1
+        self._hedge_won = hedge_won
+
     def snapshot(self) -> CallStats:
         """同步冻结当前快照;**绝不 await**,可多次调用。"""
         return CallStats(
             logical_call_id=self.logical_call_id,
             attempts=self._attempts,
             total_latency_ms=int((self._now() - self._started) * 1000),
+            hedges=self._hedges,
+            generation_ms=self._generation_ms,
+            hedge_won=self._hedge_won,
         )
 
     def claim_terminal(self) -> bool:

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)。"""
 

tests/unit/test_embedding.py

@@ -319,6 +319,20 @@ class TestEmbedBatching:
         assert resp.cost is None
 
 
+class TestEmbedGenerationMs:
+    """裸生成时间按批累加(1.3.7 H8): generation_ms = 各批 transport 耗时之和。"""
+
+    async def test_generation_ms_sums_batch_transports(self):
+        # 0.25s 为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
+        clock = FakeClock()
+        transport = _ClockAdvancingEmbedTransport([(0.25, "ok"), (0.25, "ok")], clock)
+        client, _ = _embed_client([_src()], [], transport=transport, now=clock)
+        resp = await client.embed(["a", "bb", "ccc", "dddd"])
+        assert resp.call_stats is not None
+        assert resp.call_stats.attempts == 2
+        assert resp.call_stats.generation_ms == 500
+
+
 class TestEmbedPostProcess:
     async def test_normalize_l2(self):
         raw = EmbeddingTransportResult(

tests/unit/test_ocr_client.py

@@ -196,6 +196,21 @@ class TestSuccessPaths:
             await client.parse_layout(b"")
 
 
+class TestOcrGenerationMs:
+    """OCR 裸生成时间单次覆盖(1.3.7 H8): 计时只包 transport 调用本身。"""
+
+    async def test_generation_ms_single_transport_call(self):
+        # 0.5s 为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
+        clock = FakeClock()
+        transport = ClockAdvancingOcrTransport([(0.5, "text")], clock)
+        client, _, _ = _client([_src()], [], now=clock, transport=transport)
+        r = await client.recognize_text(b"jpg")
+        assert r.text == "LINE-1"
+        assert r.call_stats is not None
+        assert r.call_stats.attempts == 1
+        assert r.call_stats.generation_ms == 500
+
+
 class TestFailover:
     async def test_transient_retries_with_backoff(self):
         sleeps = []

tests/unit/test_retry.py

@@ -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)。
 

tests/unit/test_types.py

@@ -622,6 +622,55 @@ class TestCallStatsAndContext:
         with pytest.raises(dataclasses.FrozenInstanceError):
             stats.attempts = 3
 
+    def test_callstats_hedge_fields_default(self):
+        """1.3.7 三字段全带默认值: 仅旧三参数构造不炸,无对冲恒 0/0/False。"""
+        from polygateway.types import CallStats
+
+        stats = CallStats(logical_call_id="lc-1", attempts=2, total_latency_ms=15)
+        assert stats.hedges == 0
+        assert stats.generation_ms == 0
+        assert stats.hedge_won is False
+        explicit = CallStats(
+            logical_call_id="lc-2",
+            attempts=2,
+            total_latency_ms=15,
+            hedges=1,
+            generation_ms=42,
+            hedge_won=True,
+        )
+        assert (explicit.hedges, explicit.generation_ms, explicit.hedge_won) == (1, 42, True)
+
+    def test_callcontext_record_generation_overwrite_and_accumulate(self):
+        """chat/OCR 覆盖(结构化重问最后一轮为准);embedding 分批累加。"""
+        from polygateway.types import _CallContext
+
+        ctx = _CallContext(now=_FakeMonotonic())
+        ctx.record_generation(100, accumulate=False)
+        ctx.record_generation(30, accumulate=False)
+        assert ctx.snapshot().generation_ms == 30
+        ctx.record_generation(50, accumulate=True)
+        assert ctx.snapshot().generation_ms == 80
+
+    def test_callcontext_register_hedge_counts(self):
+        """对冲路实际发出即计数;赢家裁定后一次性登记赢家身份。"""
+        from polygateway.types import _CallContext
+
+        ctx = _CallContext(now=_FakeMonotonic())
+        ctx.register_hedge(hedge_won=False)
+        ctx.register_hedge(hedge_won=True)
+        stats = ctx.snapshot()
+        assert stats.hedges == 2 and stats.hedge_won is True
+
+    def test_snapshot_includes_hedge_fields(self):
+        """快照把三字段带出: 裸生成时间与对冲计数不停留在内部状态里。"""
+        from polygateway.types import _CallContext
+
+        ctx = _CallContext(now=_FakeMonotonic())
+        ctx.record_generation(200, accumulate=False)
+        ctx.register_hedge(hedge_won=True)
+        stats = ctx.snapshot()
+        assert (stats.hedges, stats.generation_ms, stats.hedge_won) == (1, 200, True)
+
     def test_context_counts_attempts_and_freezes_elapsed(self):
         """快照是同步冻结的时间切片: 登记两次尝试后耗时按注入钟折算成毫秒。"""
         from polygateway.types import _CallContext