Add native inference with encrypted secrets #381
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![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: c013a1ae51
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".
| if (customModelOverride) { | ||
| model = customModelOverride; | ||
| if (bodyData && typeof bodyData === "object" && "model" in bodyData) { | ||
| bodyData = { ...bodyData, model: customModelOverride }; | ||
|
|
There was a problem hiding this comment.
The new custom_system_prompt metadata is only applied inside the if (customModelOverride) block. That means configuring a system prompt alone (without also setting custom_model) is silently ignored, even though the schema adds custom_system_prompt as a standalone option. If a user supplies only custom_system_prompt, requests will proceed without the intended prompt injection. Consider applying the prompt logic whenever custom_system_prompt is set, regardless of custom_model.
Useful? React with 👍 / 👎.
1 participant
No description provided.