Skip to content

Enhance model picker #7709

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

Jump to bottom
Merged
aibrahim-oai merged 23 commits into from
Dec 8, 2025
Merged

Enhance model picker #7709

aibrahim-oai merged 23 commits into from
Dec 8, 2025

Conversation

@aibrahim-oai
Copy link
Collaborator

@aibrahim-oai aibrahim-oai commented Dec 7, 2025

External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated "Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.

@chatgpt-codex-connector
Copy link
Contributor

chatgpt-codex-connector bot commented Dec 7, 2025

💡 Codex Review

codex/codex-rs/protocol/src/openai_models.rs

Lines 161 to 165 in 2a9b1e5

upgrade: info.upgrade.as_ref().map(|upgrade_slug| ModelUpgrade {
id: upgrade_slug.clone(),
reasoning_effort_mapping: reasoning_effort_mapping_from_presets(
&info.supported_reasoning_levels,
),

P1 Badge Migration keeps unsupported effort for upgraded models

The ModelUpgrade built from API responses derives reasoning_effort_mapping from the source model’s supported_reasoning_levels instead of the upgrade target. If the backend now returns an upgrade to a model with fewer options (e.g., the new codex-auto-* presets that only expose a single effort), the migration flow in app.rs will carry over the user’s old effort unchanged, persisting a config.model_reasoning_effort the upgrade cannot serve and leading to failed requests after auto-migration. The mapping should be computed from the upgrade model’s supported efforts so the stored effort is clamped to what the target supports.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

@aibrahim-oai aibrahim-oai merged commit 71c75e6 into main Dec 8, 2025
26 checks passed
@aibrahim-oai aibrahim-oai deleted the enhance-model-picker branch December 8, 2025 22:22
@github-actions github-actions bot locked and limited conversation to collaborators Dec 8, 2025
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Reviewers

@pakrym-oai pakrym-oai pakrym-oai approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@aibrahim-oai @pakrym-oai