This empirical study investigates how state-of-the-art Large Language Models (LLMs) can automatically resolve code issues identified by SonarQube, a widely used static analysis tool. As automated maintenance becomes more common, combining AI models with rule-based analysis offers a promising approach to improving code quality. We compare six LLMs, including GPT-4o, Gemini 2.0 Flash, Claude 3 Opus, Mistral Large, Grok 3, and Deep-Seek V3, in performing automated code repair. Using a unified prompt strategy, SonarQube issues are mapped into structured prompts, and LLM-generated fixes replace affected functions in the source code. We evaluate repairs based on syntactic correctness, reduction in SonarQube reported issues, and introduce the Static Repair Success Rate (SRSR), a strict metric that measures the proportion of syntactically valid repairs that resolve all original issues without introducing new ones, followed by a semantic analysis to assess whether the repaired code preserved the intended program behavior. Overall, the average reduction in SonarQube-reported issues, calculated across all models and projects, was about 36.02%. The best result for a single project was achieved by the Grok 3 model, which reduced issues by 71.54%. These findings suggest that LLMs can enhance automated refactoring and help reduce static analysis–reported issues. They offer insights for integrating AI into development workflows, helping companies streamline maintenance, reduce technical debt, and sustain high code quality.

With Python's ascension as a dominant program-ming language, particularly in the fields of artificial intelligence and data science, the need for comprehensive datasets focusing on software quality within Python projects has become increasingly noticeable. This study introduces a detailed dataset designed to address this gap, enriching academic resources in software engineering. The dataset encompasses a wide array of software quality metrics on up to 80 projects, including 51.765.853 Sonar-Qube issues, 268.506 SonarQube code quality metrics, 11.915 software refactoring records, and 155.127 pairs of bug-inducing and bug-fixing commits, along with 863.931 GitHub issue tracker entries. This extensive collection serves as a versatile tool for various research activities, enabling analysis of the relationships between technical debt and software refactorings, correlations be-tween refactoring processes and bug resolution, and their overall impact on software maintainability and reliability. By offering a comprehensive and multifaceted dataset, this study significantly contributes to understanding and improving software quality in Python projects.