Enabling AI CodeFix at project level

Sonar's AI CodeFix uses a large language model (LLM) to automatically generate AI-driven code fixes for the issues discovered by SonarQube Server. AI CodeFix must be enabled by an Instance Admin and is defined for All projects or for Only selected projects. 

See the Enabling AI CodeFix page for the full details.

Getting AI-generated fix suggestions

SonarQube Cloud's AI CodeFix is an Early Access feature that uses OpenAI’s GPT-4o (recommended) or Anthropic's Claude 3.5 or 3.7 Sonnet to suggest fixes for a select set of rules in Java, JavaScript, TypeScript, Python, C#, and C++. See the Sonar AI CodeFix terms for details about the terms of access. 

To learn more about which rules are eligible for AI CodeFix, please see the list of Rules covered with AI CodeFix.

When an Instance Admin enables AI CodeFix for your project, you can get an AI-generated fix suggestion for eligible issues. To learn how to get fix suggestions in SonarQube Server, see Getting AI-generated fix suggestions. Then use the Open in IDE feature to apply the fix.

If you're using SonarQube for IntelliJ or SonarQube for VS Code and running in connected mode with SonarQUbe Server, it's possible to use AI CodeFix directly in your IDE.

To learn more about which rules are eligible for AI CodeFix, please see the list of Rules covered with AI CodeFix.

Related pages

• Overview of AI features at the project level
• Setting quality standards for AI Code Assurance
• Overview of AI capabilities