openai / openai/codex

Support /model in codex desktop app for non-OpenAI provider

Open
#44,024 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

app bug custom-model
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of the Codex App are you using (From “About Codex” dialog)?

26.901.31953

What subscription do you have?

API

What platform is your computer?

macOS

What issue are you seeing?

/model (and shortcut ctrl+shift+m) only shows up if requiresAuth is true. That's derived from the codex app-server requiresOpenaiAuth. Our setup uses bifrost proxy as a gateway for OpenAI API access so we define a custom provider in our config.toml. Thus, requiresOpenaiAuth is false and I can't use /model in app.

I believe /model has nothing to do with openai auth. It works with any third-party models. Can we drop this if requiresAuth branch in the desktop app? Thanks!

What steps can reproduce the bug?

See above. I attached a screenshot for the missing /model below.

Image
What is the expected behavior?

No response

Additional information

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start in the Codex desktop app where the /model command and Ctrl+Shift+M shortcut are gated by requiresAuth, then trace how app-server's requiresOpenaiAuth is derived for custom providers in config.toml. Done means /model is available with the reported Bifrost-backed non-OpenAI provider while existing OpenAI-auth behavior remains intact.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
desktop
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
68/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.