Skip to content

fix: skip temperature for goose-gpt-5 model #5311

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
lifeizhou-ap merged 2 commits into from
Oct 22, 2025
Merged

fix: skip temperature for goose-gpt-5 model #5311

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
238fb00
skip temperature for goose-gpt-5 model
lifeizhou-ap Oct 22, 2025
e95c806
updated comments
lifeizhou-ap Oct 22, 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
2 changes: 1 addition & 1 deletion crates/goose/src/providers/formats/databricks.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -625,7 +625,7 @@ pub fn create_request(
}
}

// o1 models use max_completion_tokens instead of max_tokens
// open ai reasoning models use max_completion_tokens instead of max_tokens
Copy link
Collaborator

@DOsinga DOsinga Oct 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we need this at all? in fact shouldn't we just check whether we have max_tokens in there and if not check if there is max_completion_tokens in there?

Copy link
Contributor Author

@lifeizhou-ap lifeizhou-ap Oct 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

By reading the open ai doc here, max_token is deprecated.

We may have a separate PR to use max_completion_tokens and test it.

if let Some(tokens) = model_config.max_tokens {
let key = if is_openai_reasoning_model {
"max_completion_tokens"
Expand Down
Loading