Skip to content

fix: copy extra_kwargs to prevent litellm from polluting metadata #1610

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 29, 2025
Merged

fix: copy extra_kwargs to prevent litellm from polluting metadata #1610

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1074614
fix: copy extra_kwargs to prevent litellm from pollute metadata
zhowzeng Aug 29, 2025
b876b45
refactor: use copy rather than deepcopy
zhowzeng Aug 29, 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
3 changes: 2 additions & 1 deletion src/agents/extensions/models/litellm_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
import json
import time
from collections.abc import AsyncIterator
from copy import deepcopy
from typing import Any, Literal, cast, overload

from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails
Expand Down Expand Up @@ -329,7 +330,7 @@ async def _fetch_response(
extra_headers={**HEADERS, **(model_settings.extra_headers or {})},
api_key=self.api_key,
base_url=self.base_url,
**extra_kwargs,
**deepcopy(extra_kwargs),
)

if isinstance(ret, litellm.types.utils.ModelResponse):
Expand Down