fix(llm): Anthropic 结构化输出记真实 usage——修计费记 0 成本（CR-H3）

packages/llm_gateway/ww_llm_gateway/adapters/anthropic.py

@@ -46,7 +46,9 @@ class AnthropicClient(Protocol):
 
 
 class StructuredAnthropic(Protocol):
-    async def create(self, *, response_model: type[BaseModel], **kwargs: Any) -> BaseModel: ...
+    async def create_with_completion(
+        self, *, response_model: type[BaseModel], **kwargs: Any
+    ) -> tuple[BaseModel, Any]: ...
 
 
 def _is_transient(exc: Exception) -> bool:
@@ -115,7 +117,7 @@ class AnthropicAdapter:
             # 注入客户端是 `AnthropicClient` Protocol（保留测试替身缝），
             # 但 instructor.from_anthropic 只重载真实 SDK 的具体类型；
             # 本适配器异步 → 转 `AsyncAnthropic` 选中 AsyncInstructor 重载，
-            # 返回的 AsyncInstructor 鸭子匹配 StructuredAnthropic。
+            # 返回的 AsyncInstructor 鸭子匹配 StructuredAnthropic（含 create_with_completion）。
             async_client = cast("AsyncAnthropic", self._client)
             self._structured_client = cast(
                 "StructuredAnthropic", instructor.from_anthropic(async_client)
@@ -156,9 +158,11 @@ class AnthropicAdapter:
         system = _system_blocks(req)
         if system:
             kwargs["system"] = system
-        parsed = await self._structured().create(response_model=req.output_schema, **kwargs)
-        # instructor.from_anthropic 默认不回 raw usage（按名隐藏）；usage 经流/text 路径覆盖。
-        usage = ProviderUsage(input_tokens=0, output_tokens=0)
+        parsed, raw = await self._structured().create_with_completion(
+            response_model=req.output_schema, **kwargs
+        )
+        # 从 raw completion 提取真实 usage（记账真源，§4.8）；不再硬编码零（CR-H3）。
+        usage = _usage_from(getattr(raw, "usage", None))
         return ProviderResult(text=parsed.model_dump_json(), usage=usage, parsed=parsed)
 
     async def stream(self, req: LlmRequest, model: str) -> AsyncIterator[StreamChunk]: