fix: harden the observability fields against the verifier findings

src/polygateway/pricing.py

@@ -99,7 +99,8 @@ class PricingTable:
                 logger.warning("pricing 表无 model {!r} 的单价,cost 记 None", model)
             return None
         billed_input = prompt_tokens / 1_000_000 * price.input_per_1m
-        if price.cached_input_per_1m is not None and cached_prompt_tokens:
+        # 负数按"无命中"处理: cost() 是公共方法,不能假定调用方已过 transport 的校验
+        if price.cached_input_per_1m is not None and (cached_prompt_tokens or 0) > 0:
             cached = self._clamp_cached(model, prompt_tokens, cached_prompt_tokens)
             billed_input = (prompt_tokens - cached) / 1_000_000 * price.input_per_1m + (
                 cached / 1_000_000 * price.cached_input_per_1m

src/polygateway/transports/openai_compat.py

@@ -45,9 +45,12 @@ def _sse_delta(chunk: dict[str, Any], usage_sink: dict[str, Any]) -> tuple[bool,
     """从 chunk 提取增量: (True, content) 或 (False, reasoning);usage 帧旁路进 sink。"""
     if chunk.get("usage"):
         usage_sink["usage"] = chunk["usage"]
-    if "model" not in usage_sink and chunk.get("model") is not None:
-        # 首次写入即固定: 末帧的异常值不得覆盖首帧报的真实版本(issue #3)
-        usage_sink["model"] = chunk["model"]
+    if "model" not in usage_sink:
+        # 首个**有效**值即固定: 末帧的异常值不得覆盖它;但首帧报空串也不能锁死
+        # sink——否则后续真实版本会丢(issue #3)
+        reported = _coerce_model_reported(chunk.get("model"))
+        if reported is not None:
+            usage_sink["model"] = reported
     choices = chunk.get("choices") or []
     if not choices:
         return None