Remediation Agent

This page outlines the SonarQube Remediation Agent, built to help you fix and manage code issues found by SonarQube.

Beta: The SonarQube Remediation Agent is a Beta feature available with the SonarQube Cloud Team (annual) and Enterprise plans. It's free during beta and will be a paid feature when it moves to General Availability. For terms and conditions, see our legal page about features in Early Access.

Overview

The SonarQube Remediation Agent runs an independent review and analysis to help you fix reliability and maintainability issues found in your latest code. It focuses on issues in your SonarQube Cloud backlog (discovered in your main branch analysis) and on issues found in your latest GitHub pull request (PR).

The agent uses Anthropic's Claude Opus 4.6 to generate fix suggestions in the background and checks that the new code doesn't introduce new issues before offering the suggestion.

After issues from your analysis are assigned, the agent proposes fixes and creates new PRs for your review. You maintain full control—enable it per project, then review and approve code suggestions for each issue.

The SonarQube Remediation Agent can suggest fixes in three ways:

• It can be triggered from a pull request analysis when your quality gate fails.

• It can fix issues from your backlog.

• It can run on an automated schedule, proposing fixes for eligible main branch issues without manual assignment.

Supported languages

The Remediation Agent works with your most common languages (Java, JavaScript/TypeScript, and Python) by providing feedback on maintainability, reliability, and select security issues. In addition, it also offers fix suggestions for Secrets. See the Requirements and limitations article for complete details.

Sharing your code with Sonar

If you use the SonarQube Remediation Agent, the affected code snippet is sent to an LLM to generate a fix suggestion. Sonar verifies suggestions before offering them as a fix. Service agreements with Sonar’s LLMs prevent your code from being used to train those models and it isn’t stored by the LLM provider or any third party.

For terms and conditions, see the Early Access terms in our Legal Documentation.

Setup

To enable and install the agent, see Administer the Remediation Agent.

To understand the agent's behavior and learn how to engage with the agent in your pull request, follow the Pull request fix suggestions and Backlog fix suggestions guides.