test: 清理 backlog——chat_structured 超限检测 + client 上下文管理器

tests/test_inference_client.py

@@ -54,6 +54,24 @@ def test_chat_requires_api_key():
         HttpLLMClient(base_url="https://x", api_key="")
 
 
+def test_client_context_manager_closes_transport():
+    # with 块退出后底层 httpx.Client 应被关闭（释放连接）
+    with HttpLLMClient(
+        base_url="https://api.test.local",
+        api_key="sk-test",
+        transport=httpx.MockTransport(_ok_handler),
+    ) as client:
+        assert isinstance(client, HttpLLMClient)
+        text, _ = client.chat(
+            model="deepseek-chat",
+            messages=[ChatMessage(role="user", content="hi")],
+            temperature=0.2,
+            max_tokens=100,
+        )
+        assert text == "Hello"
+    assert client._client.is_closed is True
+
+
 def test_chat_timeout():
     def slow(request):
         raise httpx.ReadTimeout("slow")