feat: record the observability fields end to end through telemetry

src/polygateway/middleware/telemetry.py

@@ -61,6 +61,8 @@ class TelemetryEmitter:
             max_inter_token_ms=response.max_inter_token_ms if response else None,
             cache_hit=False,
             error=error,
+            cached_prompt_tokens=response.cached_prompt_tokens if response else None,
+            model_reported=response.model_reported if response else None,
         )
 
     async def emit_cache_hit(self, *, request: ChatRequest, response: LLMResponse) -> None:
@@ -81,6 +83,10 @@ class TelemetryEmitter:
             max_inter_token_ms=None,
             cache_hit=True,
             error=None,
+            # 决策 B1: 与 model/prompt_tokens 同一口径,原样回放历史值。
+            # 统计供应商缓存命中率必须带 WHERE cache_hit = false,否则重复计数。
+            cached_prompt_tokens=response.cached_prompt_tokens,
+            model_reported=response.model_reported,
         )
 
     async def emit_terminal_failure(
@@ -103,6 +109,8 @@ class TelemetryEmitter:
             max_inter_token_ms=None,
             cache_hit=False,
             error=error,
+            cached_prompt_tokens=None,
+            model_reported=None,
         )
 
     async def _record(
@@ -123,6 +131,8 @@ class TelemetryEmitter:
         max_inter_token_ms: float | None,
         cache_hit: bool,
         error: str | None,
+        cached_prompt_tokens: int | None,
+        model_reported: 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);
@@ -134,7 +144,9 @@ class TelemetryEmitter:
                 # 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)
+                cost = self._pricing.cost(
+                    model, prompt_tokens, completion_tokens, cached_prompt_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)
@@ -158,6 +170,8 @@ class TelemetryEmitter:
                 cache_hit=cache_hit,
                 error=error,
                 cost=cost,
+                cached_prompt_tokens=cached_prompt_tokens,
+                model_reported=model_reported,
             )
         except asyncio.CancelledError:
             raise