feat(llm): migrate model calls to LangChain ChatOpenAI

test/services/test_stream_retry_cleanup.py

@@ -1,7 +1,7 @@
 import asyncio
 from contextlib import aclosing
 from types import SimpleNamespace
-from unittest.mock import AsyncMock
+from unittest.mock import AsyncMock, Mock
 
 import pytest
 
@@ -69,16 +69,16 @@ async def test_timeout_covers_whole_attempt_and_retries_are_bounded(stream):
         async def generate(self):
             await asyncio.Future()
             yield None
-        async def close(self): self.closed = True
-    async def create(**kwargs):
-        if stream:
-            response = HangingResponse()
-            responses.append(response)
-            return response
+        async def aclose(self): self.closed = True
+    async def invoke(*args, **kwargs):
         await asyncio.Future()
+    def create_stream(*args, **kwargs):
+        response = HangingResponse()
+        responses.append(response)
+        return response
     llm = OpenAILLMService(model='m', api_key='audit', timeout_seconds=0.01, max_retries=2)
-    call = AsyncMock(side_effect=create)
-    llm._client = SimpleNamespace(chat=SimpleNamespace(completions=SimpleNamespace(create=call)))
+    call = Mock(side_effect=create_stream) if stream else AsyncMock(side_effect=invoke)
+    llm._client = SimpleNamespace(astream=call) if stream else SimpleNamespace(ainvoke=call)
     llm._retry_delay = AsyncMock()
     # 先加载 SDK 错误类；外层看门狗不测模块惰性导入耗时。
     assert llm._retryable(TimeoutError())
@@ -89,6 +89,6 @@ async def test_timeout_covers_whole_attempt_and_retries_are_bounded(stream):
                 async for _ in llm.stream_tokens('system', 'user'): pass
             else:
                 await llm.complete('system', 'user')
-    assert call.await_count == 3
+    assert call.call_count == 3
     assert llm._retry_delay.await_count == 2
     assert all(response.closed for response in responses)