fix: void the cost of rows whose usage is unavailable

失败尝试与终态失败行的 usage_source 由 estimated 改 unavailable(用量确实
不可得),并在 TelemetryEmitter 的成本换算里为 unavailable 短路记 NULL。
短路刻意插在 cache_hit 分支之后: 缓存命中未产生新调用,0.0 是事实而非未知。
附 OCR 成功行的防回归钉(仍为 measured、settle 恒 0,设计 §3.3 剔出决定)。

src/polygateway/middleware/telemetry.py

@@ -44,7 +44,7 @@ class TelemetryEmitter:
         response: LLMResponse | None,
         error: str | None,
     ) -> None:
-        """逐次尝试记录(RetryMW 调用);失败尝试 usage 按 estimated 记 0。"""
+        """逐次尝试记录(RetryMW 调用);失败尝试无用量可言,记 0 并标 unavailable。"""
         await self._record(
             request=request,
             call_id=call_id,
@@ -55,7 +55,7 @@ class TelemetryEmitter:
             thinking=response.thinking if response else "",
             prompt_tokens=response.prompt_tokens if response else 0,
             completion_tokens=response.completion_tokens if response else 0,
-            usage_source=response.usage_source if response else "estimated",
+            usage_source=response.usage_source if response else "unavailable",
             latency_ms=latency_ms,
             ttft_ms=response.ttft_ms if response else None,
             max_inter_token_ms=response.max_inter_token_ms if response else None,
@@ -97,7 +97,7 @@ class TelemetryEmitter:
             thinking="",
             prompt_tokens=0,
             completion_tokens=0,
-            usage_source="estimated",
+            usage_source="unavailable",
             latency_ms=latency_ms,
             ttft_ms=None,
             max_inter_token_ms=None,
@@ -129,6 +129,10 @@ class TelemetryEmitter:
             # 失败/终态行 None;未注入价格表 = 恒 None(M1 现状)
             if cache_hit:
                 cost: float | None = 0.0
+            elif usage_source == "unavailable":
+                # 用量不可得: 宁可算不出成本,也不算错成本(解耦设计 §3.1 不变式)。
+                # 必须排在 cache_hit 之后——缓存命中未产生新调用,0.0 是事实而非未知
+                cost = None
             elif error is None and model and self._pricing is not None:
                 cost = self._pricing.cost(model, prompt_tokens, completion_tokens)
             else: