Thanks to visit codestin.com
Credit goes to github.com

Skip to content

fix(openai): handle async response api input and outputs #1301

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 2 commits into from
Aug 18, 2025
Merged

fix(openai): handle async response api input and outputs #1301

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b95c79
fix(openai): handle async response api input and outputs
hassiebp Aug 18, 2025
c61b70b
fix parsed_completion_tokens
hassiebp Aug 18, 2025
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
17 changes: 15 additions & 2 deletions langfuse/openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -391,7 +391,7 @@ def _get_langfuse_data_from_kwargs(resource: OpenAiDefinition, kwargs: Any) -> A

if resource.type == "completion":
prompt = kwargs.get("prompt", None)
elif resource.object == "Responses":
elif resource.object == "Responses" or resource.object == "AsyncResponses":
prompt = kwargs.get("input", None)
elif resource.type == "chat":
prompt = _extract_chat_prompt(kwargs)
Expand All @@ -408,6 +408,12 @@ def _get_langfuse_data_from_kwargs(resource: OpenAiDefinition, kwargs: Any) -> A
else float("inf")
)

parsed_max_completion_tokens = (
kwargs.get("max_completion_tokens", None)
if not isinstance(kwargs.get("max_completion_tokens", float("inf")), NotGiven)
else None
)

parsed_top_p = (
kwargs.get("top_p", 1)
if not isinstance(kwargs.get("top_p", 1), NotGiven)
Expand Down Expand Up @@ -441,6 +447,11 @@ def _get_langfuse_data_from_kwargs(resource: OpenAiDefinition, kwargs: Any) -> A
"frequency_penalty": parsed_frequency_penalty,
"presence_penalty": parsed_presence_penalty,
}

if parsed_max_completion_tokens is not None:
modelParameters.pop("max_tokens", None)
modelParameters["max_completion_tokens"] = parsed_max_completion_tokens

if parsed_n is not None and parsed_n > 1:
modelParameters["n"] = parsed_n

Expand Down Expand Up @@ -672,7 +683,7 @@ def _get_langfuse_data_from_default_response(

completion = choice.text if _is_openai_v1() else choice.get("text", None)

elif resource.object == "Responses":
elif resource.object == "Responses" or resource.object == "AsyncResponses":
output = response.get("output", {})

if not isinstance(output, list):
Expand Down Expand Up @@ -922,6 +933,7 @@ def _finalize(self) -> None:
model, completion, usage, metadata = (
_extract_streamed_response_api_response(self.items)
if self.resource.object == "Responses"
or self.resource.object == "AsyncResponses"
else _extract_streamed_openai_response(self.resource, self.items)
)

Expand Down Expand Up @@ -992,6 +1004,7 @@ async def _finalize(self) -> None:
model, completion, usage, metadata = (
_extract_streamed_response_api_response(self.items)
if self.resource.object == "Responses"
or self.resource.object == "AsyncResponses"
else _extract_streamed_openai_response(self.resource, self.items)
)

Expand Down
Loading