Skip to content

Fix #1559: Handle empty choices array in LiteLLM model (same as PR #935) #1981

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 4 commits into from
Oct 24, 2025
+25 −11
Merged

Fix #1559: Handle empty choices array in LiteLLM model (same as PR #935) #1981

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a4d59a9
Fix #1559: Handle empty choices array in LiteLLM model
Oct 22, 2025
6aca0aa
Fix linting error: line too long
Oct 22, 2025
a8e2c78
Refactor: simplify items initialization with ternary expression
Oct 22, 2025
a8c8b03
Refine defensive checks based on code review feedback
Oct 24, 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
36 changes: 25 additions & 11 deletions src/agents/extensions/models/litellm_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,18 +110,26 @@ async def get_response(
prompt=prompt,
)

assert isinstance(response.choices[0], litellm.types.utils.Choices)
message: litellm.types.utils.Message | None = None
first_choice: litellm.types.utils.Choices | None = None
if response.choices and len(response.choices) > 0:
choice = response.choices[0]
if isinstance(choice, litellm.types.utils.Choices):
first_choice = choice
message = first_choice.message

if _debug.DONT_LOG_MODEL_DATA:
logger.debug("Received model response")
else:
logger.debug(
f"""LLM resp:\n{
json.dumps(
response.choices[0].message.model_dump(), indent=2, ensure_ascii=False
)
}\n"""
)
if message is not None:
logger.debug(
f"""LLM resp:\n{
json.dumps(message.model_dump(), indent=2, ensure_ascii=False)
}\n"""
)
else:
finish_reason = first_choice.finish_reason if first_choice else "-"
logger.debug(f"LLM resp had no message. finish_reason: {finish_reason}")

if hasattr(response, "usage"):
response_usage = response.usage
Expand Down Expand Up @@ -152,14 +160,20 @@ async def get_response(
logger.warning("No usage information returned from Litellm")

if tracing.include_data():
span_generation.span_data.output = [response.choices[0].message.model_dump()]
span_generation.span_data.output = (
[message.model_dump()] if message is not None else []
)
span_generation.span_data.usage = {
"input_tokens": usage.input_tokens,
"output_tokens": usage.output_tokens,
}

items = Converter.message_to_output_items(
LitellmConverter.convert_message_to_openai(response.choices[0].message)
items = (
Converter.message_to_output_items(
LitellmConverter.convert_message_to_openai(message)
)
if message is not None
else []
)

return ModelResponse(
Expand Down