GitHub added organization-level billing and access controls for Copilot code review, letting organization owners bill reviews from licensed members to the organization's cost center instead of consumi…
ReviewBench, an open benchmark for AI code review tools, models the language, repository size, and size distribution of real pull requests and uses a multi-source golden set with a consistent evaluati…
GitHub launched ReviewBench, an open benchmark for AI code review agents built on 219 pull requests from 187 public open source repositories across 19 languages, modeled after an analysis of 103.9 mil…
GitHub added a `pull_request_review_times` array to its enterprise and organization repository-level Copilot usage metrics reports, breaking pull request review time into three stages: ready-for-revie…
GitHub's agentic autofix now uses Copilot Memory, available in public preview, to review existing memories for context when resolving security alerts and to store each fix pattern as a memory for futu…
GitHub's Copilot code review now automatically resolves comments once a developer pushes a commit addressing them and generates smart commit messages when its autofix suggestions are applied, the comp…
GitHub announced that Copilot code review now supports pull requests authored by bots, including Copilot cloud agent, and very large pull requests, removing the previous 300-file or 20,000-line limit.…
GitHub's Copilot code review performance declined after swapping in shared CLI tools (grep, glob, view) due to poorly adapted instructions, but rewriting those instructions for pull request review wor…