Merge pull request #112 from openai/pr112

Fix streaming in chat completions

Author: rm-openai

src/agents/models/openai_chatcompletions.py

@@ -51,8 +51,10 @@
     ResponseOutputText,
     ResponseRefusalDeltaEvent,
     ResponseTextDeltaEvent,
+    ResponseUsage,
 )
 from openai.types.responses.response_input_param import FunctionCallOutput, ItemReference, Message
+from openai.types.responses.response_usage import OutputTokensDetails
 
 from .. import _debug
 from ..agent_output import AgentOutputSchema
@@ -405,7 +407,23 @@ async def stream_response(
             for function_call in state.function_calls.values():
                 outputs.append(function_call)
 
-            final_response = response.model_copy(update={"output": outputs, "usage": usage})
+            final_response = response.model_copy()
+            final_response.output = outputs
+            final_response.usage = (
+                ResponseUsage(
+                    input_tokens=usage.prompt_tokens,
+                    output_tokens=usage.completion_tokens,
+                    total_tokens=usage.total_tokens,
+                    output_tokens_details=OutputTokensDetails(
+                        reasoning_tokens=usage.completion_tokens_details.reasoning_tokens
+                        if usage.completion_tokens_details
+                        and usage.completion_tokens_details.reasoning_tokens
+                        else 0
+                    ),
+                )
+                if usage
+                else None
+            )
 
             yield ResponseCompletedEvent(
                 response=final_response,

tests/test_openai_chatcompletions_stream.py

@@ -107,6 +107,11 @@ async def patched_fetch_response(self, *args, **kwargs):
     assert isinstance(completed_resp.output[0].content[0], ResponseOutputText)
     assert completed_resp.output[0].content[0].text == "Hello"
 
+    assert completed_resp.usage, "usage should not be None"
+    assert completed_resp.usage.input_tokens == 7
+    assert completed_resp.usage.output_tokens == 5
+    assert completed_resp.usage.total_tokens == 12
+
 
 @pytest.mark.allow_call_model_methods
 @pytest.mark.asyncio