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

packages/llm_gateway/tests/test_new_adapters.py

@@ -164,6 +164,51 @@ async def test_gemini_structured_output() -> None:
     assert "config" in models.last_kwargs
 
 
+async def test_anthropic_structured_output_threads_usage() -> None:
+    # 结构化输出必须记真实 usage（CR-H3）：instructor 的 create_with_completion 回
+    # (parsed, raw)，raw.usage 带真实 token 数；网关据此记账（§4.8）。
+    class _RawUsage:
+        input_tokens = 120
+        output_tokens = 80
+        cache_read_input_tokens = 30
+
+    class _Raw:
+        usage = _RawUsage()
+
+    class _FakeStructured:
+        def __init__(self) -> None:
+            self.last_kwargs: dict[str, Any] = {}
+
+        async def create_with_completion(
+            self, *, response_model: type[BaseModel], **kwargs: Any
+        ) -> tuple[BaseModel, Any]:
+            self.last_kwargs = kwargs
+            return response_model(score=7), _Raw()
+
+        # 修前路径调 `.create`（仅回 parsed）——保留它，令 RED 是值不符（0!=120）
+        # 而非 AttributeError，坐实旧代码硬编码零 usage 的缺陷。
+        async def create(self, *, response_model: type[BaseModel], **kwargs: Any) -> BaseModel:
+            return response_model(score=7)
+
+    fake = _FakeStructured()
+    client = _FakeAnthropicClient(_FakeAnthropicMessages("", 0, 0, 0))
+    adapter = AnthropicAdapter("anthropic", client, structured_client=fake)
+    req = LlmRequest(
+        tier="analyst",
+        input="打分",
+        output_schema=Out,
+        scope=Scope(user_id=uuid.UUID(int=1)),
+    )
+
+    result = await adapter.complete(req, "claude-3-5-sonnet")
+
+    assert isinstance(result.parsed, Out)
+    assert result.parsed.score == 7
+    assert result.usage.input_tokens == 120
+    assert result.usage.output_tokens == 80
+    assert result.usage.cache_read_tokens == 30
+
+
 async def test_anthropic_stream_yields_text_then_usage() -> None:
     class _StreamEvent:
         def __init__(self, **kw: Any) -> None: