Skip to content

Fix streaming in chat completions #112

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 13, 2025
Merged

Fix streaming in chat completions #112

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 19 additions & 1 deletion src/agents/models/openai_chatcompletions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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,
Expand Down
5 changes: 5 additions & 0 deletions tests/test_openai_chatcompletions_stream.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down