Large Language Models (LLMs)-powered code review automation has the potential to transform code review workflows. Despite the advances of LLM-powered code review comment generation approaches, several practical challenges remain for designing enterprise-grade code review automation tools. In particular, this paper aims at answering the practical question: how can we design a review-guided, context-aware, quality-checked code review comment generation without fine-tuning? In this paper, we present RovoDev Code Reviewer, an enterprise-grade LLM-based code review automation tool designed and deployed at scale within Atlassian's development ecosystem with seamless integration into Atlassian's Bitbucket. Through the offline, online, user feedback evaluations over a one-year period, we conclude that RovoDev Code Reviewer is effective in generating code review comments that could lead to code resolution for 38.70% (i.e., comments that triggered code changes in the subsequent commits); and offers the promise of accelerating feedback cycles (i.e., decreasing the PR cycle time by 30.8%), alleviating reviewer workload (i.e., reducing the number of human-written comments by 35.6%), and improving overall software quality (i.e., finding errors with actionable suggestions).

翻译：基于大语言模型（LLMs）的代码审查自动化有潜力变革代码审查工作流。尽管基于大语言模型的代码审查意见生成方法取得了进展，但设计企业级代码审查自动化工具仍面临若干实际挑战。具体而言，本文旨在回答一个实际问题：如何在不进行微调的情况下，设计一种基于审查引导、上下文感知且经过质量检查的代码审查意见生成方法？本文介绍了 RovoDev 代码审查器，这是一个企业级、基于大语言模型的代码审查自动化工具，在 Atlassian 开发生态系统内大规模设计并部署，并与 Atlassian 的 Bitbucket 无缝集成。通过为期一年的离线评估、在线评估和用户反馈评估，我们得出结论：RovoDev 代码审查器能有效生成代码审查意见，其中 38.70% 的意见可促成代码问题解决（即，触发了后续提交中的代码变更）；并且有望加速反馈周期（即，将 PR 周期时间缩短 30.8%）、减轻审查者工作量（即，减少 35.6% 的人工编写意见）、并提升整体软件质量（即，发现错误并提供可操作建议）。