Add Mistral provider support#638
Conversation
|
** Tested both API fallback and AI Studio web usage flow locally. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 67a2194b52
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".
|
Thanks again for contributing Mistral support here, @stamsam. Since this PR was opened, Mistral support has landed through the newer #607 path and is now on main, so this branch is effectively superseded. I’m going to close this one to keep the queue tidy, but I really appreciate you helping push Mistral support forward. |
2 participants
Summary
Adds Mistral as a new provider in CodexBar with a hybrid fetch strategy:
webmode uses the Mistral AI Studio billing endpoint when a browser session is availableapimode falls back toMISTRAL_API_KEYfor model discovery and API-only statusautoprefers web billing and falls back gracefully to the public APIWhat’s Included
Notes
Mistral’s documented public API does not currently expose the billing/usage totals needed for full quota cards, so real usage totals come from the logged-in AI Studio web session. The provider keeps API-key support for fallback and CLI use.
Verification
CodexBarCLICodexBarScreenshots
Live usage in the menu card and the Mistral settings flow:
