feat(llm): migrate model calls to LangChain ChatOpenAI

test/agent/test_llm_stream_tokens.py

@@ -6,7 +6,9 @@ mock 客户端返回 token 事件流；验证消息构造与 complete 一致、
 
 import asyncio
 from types import SimpleNamespace
-from unittest.mock import AsyncMock
+from unittest.mock import Mock
+
+from langchain_core.messages import AIMessageChunk
 
 import httpx
 import pytest
@@ -22,9 +24,7 @@ from src.agent.llm import (
 
 
 def _event(content):
-    return SimpleNamespace(
-        choices=[SimpleNamespace(delta=SimpleNamespace(content=content))]
-    )
+    return AIMessageChunk(content=content)
 
 
 def _service_with_stream(events):
@@ -44,10 +44,8 @@ def _service_with_stream(events):
             for item in self._items:
                 yield item
 
-    create = AsyncMock(return_value=_Stream(events))
-    llm._client = SimpleNamespace(
-        chat=SimpleNamespace(completions=SimpleNamespace(create=create))
-    )
+    create = Mock(return_value=_Stream(events))
+    llm._client = SimpleNamespace(astream=create)
     return llm, create
 
 
@@ -60,13 +58,11 @@ async def test_stream_tokens_yields_incrementally_and_forwards_kwargs():
     ]
     assert tokens == ["你", "好"]      # 空 delta 被跳过
 
-    kwargs = create.call_args.kwargs
-    assert kwargs["model"] == "test-model"
-    assert kwargs["stream"] is True
-    assert kwargs["temperature"] == 0
-    assert kwargs["extra_body"]["reasoning_effort"] == "none"    # extra_body 透传
-    assert kwargs["messages"][0] == {"role": "system", "content": "系统"}
-    assert kwargs["messages"][-1] == {"role": "user", "content": "输入"}
+    messages = create.call_args.args[0]
+    assert messages[0] == {"role": "system", "content": "系统"}
+    assert messages[1] == {"role": "assistant", "content": "h"}
+    assert messages[-1] == {"role": "user", "content": "输入"}
+    assert create.call_args.kwargs["config"]["run_name"] == "llm.stream"
 
 
 @pytest.mark.asyncio
@@ -107,10 +103,8 @@ async def test_stream_tokens_times_out_on_stale_stream():
             yield _event("好")
 
     llm = OpenAILLMService(model="m", api_key="k", timeout_seconds=0.2)
-    create = AsyncMock(return_value=_HangingStream())
-    llm._client = SimpleNamespace(
-        chat=SimpleNamespace(completions=SimpleNamespace(create=create))
-    )
+    create = Mock(return_value=_HangingStream())
+    llm._client = SimpleNamespace(astream=create)
     tokens = []
     with pytest.raises(LLMTimeoutError):
         async for token in llm.stream_tokens("系统", "输入"):