feat: add pricing table and cost calculation in telemetry emitter

src/polygateway/middleware/telemetry.py

@@ -23,14 +23,16 @@ if TYPE_CHECKING:
     from collections.abc import Callable
 
     from polygateway.ports import CallNext, TelemetryRecorder
+    from polygateway.pricing import PricingTable
     from polygateway.types import ChatRequest, LLMResponse, SourceConfig
 
 
 class TelemetryEmitter:
     """从请求与结果组装 18 字段并写入 recorder;一切写失败降级 warning。"""
 
-    def __init__(self, recorder: TelemetryRecorder) -> None:
+    def __init__(self, recorder: TelemetryRecorder, *, pricing: PricingTable | None = None) -> None:
         self._recorder = recorder
+        self._pricing = pricing
 
     async def emit_attempt(
         self,
@@ -123,6 +125,14 @@ class TelemetryEmitter:
         error: str | None,
     ) -> None:
         try:
+            # 成本换算(M2 §6): 成功行按单价换算;缓存命中 0.0(未产生新调用);
+            # 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 error is None and model and self._pricing is not None:
+                cost = self._pricing.cost(model, prompt_tokens, completion_tokens)
+            else:
+                cost = None
             # messages 落库前多模态摘要,与缓存 key 共用同一函数(VT R12)
             messages_json = json.dumps(digest_messages(request.messages), ensure_ascii=False)
             await self._recorder.record_llm_call(
@@ -143,7 +153,7 @@ class TelemetryEmitter:
                 max_inter_token_ms=max_inter_token_ms,
                 cache_hit=cache_hit,
                 error=error,
-                cost=None,  # M1 无 pricing;M2 换算后填充
+                cost=cost,
             )
         except asyncio.CancelledError:
             raise