Skip to content

fix: websearch E2E preventing reasoning token loops #167

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

Open
blefo wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: websearch E2E preventing reasoning token loops #167

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
413f937
feat: update system instructions and reduce temperature for web searc…
blefo Nov 14, 2025
31f09d0
Increase timeout for /responses post request
blefo Nov 14, 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
4 changes: 2 additions & 2 deletions tests/e2e/test_chat_completions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -801,15 +801,15 @@ def test_web_search(client, model, high_web_search_rate_limit):
messages=[
{
"role": "system",
"content": "You are a helpful assistant that provides accurate and up-to-date information.",
"content": "You are a helpful assistant that provides accurate and up-to-date information. Answer in 10 words maximum and do not reason.",
},
{
"role": "user",
"content": "Who won the Roland Garros Open in 2024? Just reply with the winner's name.",
},
],
extra_body={"web_search": True},
temperature=0.2,
temperature=0.01,
max_tokens=150,
)

Expand Down
4 changes: 2 additions & 2 deletions tests/e2e/test_chat_completions_http.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -908,15 +908,15 @@ def test_web_search(client, model, high_web_search_rate_limit):
"messages": [
{
"role": "system",
"content": "You are a helpful assistant that provides accurate and up-to-date information.",
"content": "You are a helpful assistant that provides accurate and up-to-date information. Answer in 10 words maximum and do not reason.",
},
{
"role": "user",
"content": "Who won the Roland Garros Open in 2024? Just reply with the winner's name.",
},
],
"extra_body": {"web_search": True},
"temperature": 0.2,
"temperature": 0.01,
"max_tokens": 150,
}

Expand Down
4 changes: 2 additions & 2 deletions tests/e2e/test_responses.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -709,9 +709,9 @@ def test_web_search(client, model, high_web_search_rate_limit):
response = client.responses.create(
model=model,
input="Who won the Roland Garros Open in 2024? Just reply with the winner's name.",
instructions="You are a helpful assistant that provides accurate and up-to-date information.",
instructions="You are a helpful assistant that provides accurate and up-to-date information. Answer in 10 words maximum and do not reason.",
extra_body={"web_search": True},
temperature=0.2,
temperature=0.01,
)

assert response is not None, "Response should not be None"
Expand Down
3 changes: 1 addition & 2 deletions tests/e2e/test_responses_http.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -813,9 +813,8 @@ def test_web_search(client, model, high_web_search_rate_limit):
"model": model,
"input": "Who won the Roland Garros Open in 2024? Just reply with the winner's name.",
"instructions": "You are a helpful assistant that provides accurate and up-to-date information. Answer in 10 words maximum and do not reason.",
"temperature": 0.2,
"max_output_tokens": 15000,
"extra_body": {"web_search": True},
"temperature": 0.01,
}

response = client.post("/responses", json=payload, timeout=180)
Expand Down
Loading