Skip to content

feat(llm): support baseurls for llm providers#9684

Open
perfectra1n wants to merge 1 commit into
mainfrom
feat/implement-baseurls-for-providers
Open

feat(llm): support baseurls for llm providers#9684
perfectra1n wants to merge 1 commit into
mainfrom
feat/implement-baseurls-for-providers

Conversation

@perfectra1n
Copy link
Copy Markdown
Member

@perfectra1n perfectra1n commented May 10, 2026

Closes #9725

@dosubot dosubot Bot added the size:M This PR changes 30-99 lines, ignoring generated files. label May 10, 2026
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request introduces the ability to override the default API base URL for LLM providers (Anthropic, OpenAI, and Google Gemini). This is achieved by adding a "Base URL" field to the provider configuration modal in the client, updating the server-side provider interfaces and factories to support an optional baseURL, and passing this value to the respective AI SDKs. New unit tests were also added for each provider to ensure the base URL is correctly handled. I have no feedback to provide.

@perfectra1n
Copy link
Copy Markdown
Member Author

This would also help for all of the "please also support provider X" instances, as many providers have a "OpenAI compatible" endpoint, so they could just set the OpenAI provider's base URL to whatever they wanted intead of adding a whole other provider...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:M This PR changes 30-99 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add llama.cpp support for local AI integration

2 participants