CODE REVIEW

Codex cloud now reviews GitLab merge requests and runs @codex tasks in beta on all ChatGPT plans. Setup for GitLab.com and Self-Managed 19.0+.

Codex's Code Review plugin opens GitHub PRs in the desktop and web app, runs a private Codex review, and lets you choose which findings to post.

Railway preview environments for agent pull requests: an isolated copy of your whole stack for every PR, so you verify agent changes by running them.

Build an AI pull request reviewer on Railway: a webhook service runs OpenCode headless on every PR diff and posts findings as a review, never touching the code.

Diffs vs whole files for code editing agents: a paper finds full-file generation beating diff edits on Flutter/Dart tasks. The lesson: route by task locality.

Linear's 2026 data shows coding agents tripled weekly PRs for connected teams, yet total product-development time rose. What it means for engineering leads.

Vibe maintenance for AI-generated pull requests: Steve Yegge's workflow to automate triage, let agents repair good ideas, and keep maintainer taste in charge.

GitHub stacked pull requests are in public preview: how stacks split one large change into small, reviewable PRs with one-click merge and a gh-stack skill.

LLM agents resolve real Java merge conflicts more often than structured merge tools in a calibrated ConflictBench study. Their edge is coverage: tools abstain.

PAIChecker finds 13.6% of SWE-bench Verified instances pair a PR with an issue it does not resolve, penalizing agents that solve the stated problem.

Best AI code review tools in 2026: CodeRabbit, DeepSource, Greptile, SonarQube and Copilot code review compared on pricing, platform support and security.

Fable 5 posts an 80.3% SWE-Bench Pro score and costs 2x Opus 4.8 - here is the task-profile scoring guide that tells you when the premium pays off.

The rsync Claude debate shows why teams need reproducible defect forensics before AI attribution becomes a public blame machine.

Permissions, logs, and rollback for AI coding agents work best as one system. A run ledger and practical allow, ask, and deny policy for agents that edit code.

AI code review is the new bottleneck as coding agents outpace reviewers. Build review systems around reproduction, small diffs, tests and receipts.

Over-editing is when AI coding agents make huge diffs for tiny fixes. Why models do it, why tests miss it, and how to keep agent edits minimal.