Skip to content

fix: transform x-ai error response to open-ai format #1250

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

Merged
merged 2 commits into from
Aug 1, 2025
Merged

fix: transform x-ai error response to open-ai format #1250

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
755949b
fix: transform x-ai error response to open-ai format
b4s36t4 Jul 29, 2025
8dfe74c
chore: remove unused import
b4s36t4 Jul 29, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 31 additions & 3 deletions src/providers/x-ai/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,15 +8,43 @@ import {
responseTransformers,
} from '../open-ai-base';

interface XAIErrorResponse {
error:
| {
message: string;
code: string;
param: string | null;
type: string | null;
}
| string;
code?: string;
}

const xAIResponseTransform = <T>(response: T) => {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🛠️ Code Refactor

Issue: The function lacks documentation explaining its purpose and behavior.
Fix: Add JSDoc comments to explain the function's purpose and return value.
Impact: Improves code maintainability and makes it easier for other developers to understand the transformation logic.

Suggested change
const xAIResponseTransform = <T>(response: T) => {
/**
* Transforms X-AI error responses to match the OpenAI error format
* for consistent error handling across providers.
* @param response The original response from X-AI
* @returns Transformed response in OpenAI-compatible format or the original response if not an error
*/
const xAIResponseTransform = <T>(response: T) => {

let _response = response as XAIErrorResponse;
if ('error' in _response) {
return {
error: {
message: _response.error as string,
code: _response.code ?? null,
param: null,
type: null,
},
provider: X_AI,
};
}
return response;
Comment on lines +24 to +36
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🐛 Bug Fix

Issue: The error handling doesn't properly handle the case when the error property is an object rather than a string, despite the interface defining it as potentially being an object.
Fix: Add proper type checking and handle both string and object error formats.
Impact: Prevents potential runtime errors when X-AI returns an error object instead of a string.

Suggested change
let _response = response as XAIErrorResponse;
if ('error' in _response) {
return {
error: {
message: _response.error as string,
code: _response.code ?? null,
param: null,
type: null,
},
provider: X_AI,
};
}
return response;
let _response = response as XAIErrorResponse;
if ('error' in _response) {
return {
error: {
message: typeof _response.error === 'string'
? _response.error
: _response.error?.message ?? 'Unknown error',
code: _response.code ?? _response.error?.code ?? null,
param: _response.error?.param ?? null,
type: _response.error?.type ?? null,
},
provider: X_AI,
};
}
return response;

};

const XAIConfig: ProviderConfigs = {
chatComplete: chatCompleteParams([], { model: 'grok-beta' }),
complete: completeParams([], { model: 'grok-beta' }),
embed: embedParams([], { model: 'v1' }),
api: XAIAPIConfig,
responseTransforms: responseTransformers(X_AI, {
chatComplete: true,
complete: true,
embed: true,
chatComplete: xAIResponseTransform,
complete: xAIResponseTransform,
embed: xAIResponseTransform,
}),
};

Expand Down