feat(llm): migrate model calls to LangChain ChatOpenAI

test/services/test_field_commit_and_retry.py

@@ -2,11 +2,13 @@ import asyncio
 import json
 from contextlib import aclosing
 from types import SimpleNamespace
-from unittest.mock import AsyncMock
+from unittest.mock import AsyncMock, Mock
 
 import httpx
 import pytest
-from openai import AsyncOpenAI
+from langchain_core.messages import AIMessageChunk
+
+from src.agent.chat_model import ManagedChatOpenAI
 
 from src.agent.llm import LLMAPIError, LLMRateLimitError, OpenAILLMService
 from src.agent.prompts import SINGLE_CONFIRM, render_prompt
@@ -72,7 +74,10 @@ async def test_commit_is_not_lost_when_consumer_closes_after_graph_completes():
 async def test_factory_disables_sdk_retries():
     llm = OpenAILLMService(model='m', api_key='audit')
     try:
-        assert llm._get_client().max_retries == 0
+        model = llm._get_client()
+        assert model.max_retries == 0
+        assert model.root_async_client.max_retries == 0
+        assert model.root_client.max_retries == 0
     finally:
         await llm.aclose()
 
@@ -101,8 +106,13 @@ async def test_actual_http_attempt_count_is_not_multiplied_by_sdk(stream, status
         return completion(stream)
     llm = OpenAILLMService(model='m', api_key='audit', max_retries=3,
                           extra_body={'reasoning_effort': 'none'})
-    llm._client = AsyncOpenAI(api_key='audit', base_url='http://audit/v1', max_retries=0,
-                             http_client=httpx.AsyncClient(transport=httpx.MockTransport(handler)))
+    llm._client = ManagedChatOpenAI(
+        model='m', api_key='audit', base_url='http://audit/v1', max_retries=0,
+        use_responses_api=False, stream_usage=False, temperature=None,
+        extra_body={'reasoning_effort': 'none'},
+        http_client=httpx.Client(trust_env=False),
+        http_async_client=httpx.AsyncClient(transport=httpx.MockTransport(handler)),
+    )
     llm._retry_delay = AsyncMock()
     try:
         result = ''.join([t async for t in llm.stream_tokens('system', 'user')]) if stream else await llm.complete('system', 'user')
@@ -120,19 +130,19 @@ async def test_stream_failure_after_first_token_closes_response_without_retry():
         def __init__(self): self.closed = False
         def __aiter__(self): return self.generate()
         async def generate(self):
-            yield SimpleNamespace(choices=[SimpleNamespace(delta=SimpleNamespace(content='partial'))])
+            yield AIMessageChunk(content='partial')
             raise OSError('broken socket')
-        async def close(self): self.closed = True
+        async def aclose(self): self.closed = True
     response = Response()
-    create = AsyncMock(return_value=response)
+    create = Mock(return_value=response)
     llm = OpenAILLMService(model='m', api_key='audit')
-    llm._client = SimpleNamespace(chat=SimpleNamespace(completions=SimpleNamespace(create=create)))
+    llm._client = SimpleNamespace(astream=create)
     tokens = []
     with pytest.raises(LLMAPIError):
         async for token in llm.stream_tokens('system', 'user'):
             tokens.append(token)
     assert tokens == ['partial']
-    assert create.await_count == 1
+    assert create.call_count == 1
     assert response.closed
 
 
@@ -145,8 +155,12 @@ async def test_retry_budget_exhaustion_is_exact(stream):
         return httpx.Response(429, json={'error': {'message': 'retry'}})
     llm = OpenAILLMService(model='m', api_key='audit', max_retries=2)
     llm._retry_delay = AsyncMock()
-    llm._client = AsyncOpenAI(api_key='audit', base_url='http://audit/v1', max_retries=0,
-                             http_client=httpx.AsyncClient(transport=httpx.MockTransport(handler)))
+    llm._client = ManagedChatOpenAI(
+        model='m', api_key='audit', base_url='http://audit/v1', max_retries=0,
+        use_responses_api=False, stream_usage=False, temperature=None,
+        http_client=httpx.Client(trust_env=False),
+        http_async_client=httpx.AsyncClient(transport=httpx.MockTransport(handler)),
+    )
     try:
         with pytest.raises(LLMRateLimitError):
             if stream: