Skip to content

fix: override verbosity for gpt-5-codex #6007

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 8 commits into from
Oct 31, 2025
+7 −5
Merged

fix: override verbosity for gpt-5-codex #6007

Changes from 6 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
987c9ff
override
aibrahim-oai Oct 31, 2025
7f810f3
override
aibrahim-oai Oct 31, 2025
739cdc3
override
aibrahim-oai Oct 31, 2025
2622e69
override
aibrahim-oai Oct 31, 2025
a0da842
support verbostty
aibrahim-oai Oct 31, 2025
69abc31
support verbostty
aibrahim-oai Oct 31, 2025
5d9428a
support verbostty
aibrahim-oai Oct 31, 2025
daa2ba8
support verbostty
aibrahim-oai Oct 31, 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 codex-rs/core/src/model_family.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,7 +160,7 @@ pub fn find_family_for_model(slug: &str) -> Option<ModelFamily> {
reasoning_summary_format: ReasoningSummaryFormat::Experimental,
base_instructions: GPT_5_CODEX_INSTRUCTIONS.to_string(),
apply_patch_tool_type: Some(ApplyPatchToolType::Freeform),
support_verbosity: true,
support_verbosity: false,
Copy link
Contributor

@chatgpt-codex-connector chatgpt-codex-connector bot Oct 31, 2025

Choose a reason for hiding this comment

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

P1 Badge Avoid spurious verbosity warnings

Setting support_verbosity to false for gpt-5-codex routes every call into the else branch in core/src/client.rs (lines 216-223). That branch unconditionally emits a warn! about model_verbosity being set, even when self.config.model_verbosity is None (the default for most users). As a result, every request against gpt-5-codex will now log a misleading warning. This regression was not present before this change (the branch was never taken), so we should either keep support_verbosity true and clamp values, or make the warning conditional on model_verbosity actually being set.

Useful? React with 👍 / 👎.

Copy link
Contributor

@chatgpt-codex-connector chatgpt-codex-connector bot Oct 31, 2025

Choose a reason for hiding this comment

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

P1 Badge Avoid spurious verbosity warning

Turning support_verbosity off for gpt-5-codex causes stream_responses to take the warning branch in core/src/client.rs line 216 on every call. Because the default Config leaves model_verbosity as None, we now emit warn!("model_verbosity is set but ignored…") even when the user never configured it. gpt-5-codex is our default model, so this introduces a new, user-visible warning on every request. This regression didn’t exist before flipping the flag; we either need to keep support_verbosity true or update the warning path to only fire when the option is actually set.

Useful? React with 👍 / 👎.

)
} else if slug.starts_with("gpt-5") {
model_family!(
Expand Down
Loading