-
Notifications
You must be signed in to change notification settings - Fork 6.9k
Add a workflow for a hardcoded version of models #8118
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.
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
Conversation
|
@codex review this |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
💡 Codex Review
Here are some automated review suggestions for this pull request.
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".
| let token = require_openai_api_key()?; | ||
|
|
||
| let provider = ModelProviderInfo::create_openai_provider(); | ||
| let api_provider = provider.to_api_provider(Some(AuthMode::ChatGPT))?; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Use API key with ChatGPT endpoint fails
This binary always reads OPENAI_API_KEY but then forces AuthMode::ChatGPT, which makes to_api_provider target the ChatGPT backend (https://chatgpt.com/backend-api/codex). Standard OpenAI API keys are not accepted there, so the workflow (which exports OPENAI_API_KEY) will consistently 401 and never update models.json unless the secret is actually a ChatGPT access token. Consider defaulting to the API-key auth mode (or making the auth mode configurable) when you’re using OPENAI_API_KEY.
Useful? React with 👍 / 👎.
|
@codex review this |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
💡 Codex Review
Here are some automated review suggestions for this pull request.
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".
|
@codex review this |
|
@codex review this |
| ) | ||
|
|
||
| url="${base_url%/}/models?client_version=${client_version}" | ||
| curl --fail --show-error --location "${headers[@]}" "${url}" | jq '.' > codex-rs/core/models.json |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
will this leak the key?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
no this doesn't print the headers supposedly
| @@ -0,0 +1,48 @@ | |||
| name: rust-release-prepare | |||
| on: | |||
| workflow_dispatch: | |||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should this run on schedule?
|
Codex Review: Didn't find any major issues. Delightful! ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
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". |
Uh oh!
There was an error while loading. Please reload this page.