openai[patch]: support streaming token counts in AzureChatOpenAI (#30494)

When OpenAI originally released `stream_options` to enable token usage
during streaming, it was not supported in AzureOpenAI. It is now
supported.

Like the [OpenAI
SDK](f66d2e6fdc/src/openai/resources/completions.py (L68)),
ChatOpenAI does not return usage metadata during streaming by default
(which adds an extra chunk to the stream). The OpenAI SDK requires users
to pass `stream_options={"include_usage": True}`. ChatOpenAI implements
a convenience argument `stream_usage: Optional[bool]`, and an attribute
`stream_usage: bool = False`.

Here we extend this to AzureChatOpenAI by moving the `stream_usage`
attribute and `stream_usage` kwarg (on `_(a)stream`) from ChatOpenAI to
BaseChatOpenAI.

---

Additional consideration: we must be sensitive to the number of users
using BaseChatOpenAI to interact with other APIs that do not support the
`stream_options` parameter.

Suppose OpenAI in the future updates the default behavior to stream
token usage. Currently, BaseChatOpenAI only passes `stream_options` if
`stream_usage` is True, so there would be no way to disable this new
default behavior.

To address this, we could update the `stream_usage` attribute to
`Optional[bool] = None`, but this is technically a breaking change (as
currently values of False are not passed to the client). IMO: if / when
this change happens, we could accompany it with this update in a minor
bump.

--- 

Related previous PRs:
- https://github.com/langchain-ai/langchain/pull/22628
- https://github.com/langchain-ai/langchain/pull/22854
- https://github.com/langchain-ai/langchain/pull/23552

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>

libs/partners/openai/tests/integration_tests/chat_models/test_azure_standard.py

@@ -3,7 +3,6 @@
 import os
 from typing import Type
 
-import pytest
 from langchain_core.language_models import BaseChatModel
 from langchain_tests.integration_tests import ChatModelIntegrationTests
 
@@ -25,6 +24,7 @@ class TestAzureOpenAIStandard(ChatModelIntegrationTests):
             "model": "gpt-4o-mini",
             "openai_api_version": OPENAI_API_VERSION,
             "azure_endpoint": OPENAI_API_BASE,
+            "stream_usage": True,
         }
 
     @property
@@ -35,10 +35,6 @@ class TestAzureOpenAIStandard(ChatModelIntegrationTests):
     def supports_json_mode(self) -> bool:
         return True
 
-    @pytest.mark.xfail(reason="Not yet supported.")
-    def test_usage_metadata_streaming(self, model: BaseChatModel) -> None:
-        super().test_usage_metadata_streaming(model)
-
 
 class TestAzureOpenAIStandardLegacy(ChatModelIntegrationTests):
     """Test a legacy model."""
@@ -53,12 +49,9 @@ class TestAzureOpenAIStandardLegacy(ChatModelIntegrationTests):
             "deployment_name": os.environ["AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME"],
             "openai_api_version": OPENAI_API_VERSION,
             "azure_endpoint": OPENAI_API_BASE,
+            "stream_usage": True,
         }
 
     @property
     def structured_output_kwargs(self) -> dict:
         return {"method": "function_calling"}
-
-    @pytest.mark.xfail(reason="Not yet supported.")
-    def test_usage_metadata_streaming(self, model: BaseChatModel) -> None:
-        super().test_usage_metadata_streaming(model)