Skip to content

fix: add NVIDIA API compatibility for minimax-M2 model #9001

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

Closed
wants to merge 2 commits into from
Closed

fix: add NVIDIA API compatibility for minimax-M2 model #9001

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0878604
fix: add NVIDIA API compatibility for minimax-M2 model
roomote Nov 3, 2025
ff2ec78
refactor: make NVIDIA API hostname detection more specific
roomote Nov 3, 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
17 changes: 15 additions & 2 deletions src/api/providers/openai.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,13 +156,14 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
}

const isGrokXAI = this._isGrokXAI(this.options.openAiBaseUrl)
const isNvidiaApi = this._isNvidiaApi(this.options.openAiBaseUrl)

const requestOptions: OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming = {
model: modelId,
temperature: this.options.modelTemperature ?? (deepseekReasoner ? DEEP_SEEK_DEFAULT_TEMPERATURE : 0),
messages: convertedMessages,
stream: true as const,
...(isGrokXAI ? {} : { stream_options: { include_usage: true } }),
...(isGrokXAI || isNvidiaApi ? {} : { stream_options: { include_usage: true } }),
...(reasoning && reasoning),
}

Expand Down Expand Up @@ -317,6 +318,8 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
if (this.options.openAiStreamingEnabled ?? true) {
const isGrokXAI = this._isGrokXAI(this.options.openAiBaseUrl)

const isNvidiaApi = this._isNvidiaApi(this.options.openAiBaseUrl)

const requestOptions: OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming = {
model: modelId,
messages: [
Expand All @@ -327,7 +330,7 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
...convertToOpenAiMessages(messages),
],
stream: true,
...(isGrokXAI ? {} : { stream_options: { include_usage: true } }),
...(isGrokXAI || isNvidiaApi ? {} : { stream_options: { include_usage: true } }),
reasoning_effort: modelInfo.reasoningEffort as "low" | "medium" | "high" | undefined,
temperature: undefined,
}
Expand Down Expand Up @@ -423,6 +426,16 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
return urlHost.endsWith(".services.ai.azure.com")
}

private _isNvidiaApi(baseUrl?: string): boolean {
const urlHost = this._getUrlHost(baseUrl)
// NVIDIA API endpoints for AI models
return (
urlHost === "integrate.api.nvidia.com" ||
urlHost === "build.nvidia.com" ||
urlHost.endsWith(".api.nvidia.com")
)
}
Comment on lines +429 to +437
Copy link
Author

@roomote roomote bot Nov 3, 2025

Choose a reason for hiding this comment

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

The new NVIDIA API detection functionality lacks test coverage. Similar to the existing Grok xAI tests (lines 527-565 in the test file), this change should include tests that verify: (1) _isNvidiaApi() correctly identifies NVIDIA endpoints, (2) stream_options is excluded when using NVIDIA API in both streaming and non-streaming modes, and (3) the behavior works correctly with O3 family models. Without tests, future changes could inadvertently break this compatibility fix.


/**
* Adds max_completion_tokens to the request body if needed based on provider configuration
* Note: max_tokens is deprecated in favor of max_completion_tokens as per OpenAI documentation
Expand Down