GitHub Weekly: Copilot Coding Agent Levels Up, Enterprise AI Gets Real Governance

GitHub Doubles Down on Agentic Workflows If you blinked this week, you missed five major updates to GitHub's agent ecosystem. Model selection for Copilot coding agent. Self-review before PRs. Built-in security scanning. Enterprise AI controls going GA. And GitHub Actions finally killing the double-zip artifact problem. Let's break down what actually matters. Copilot Coding Agent Gets Model Selection The Copilot coding agent now lets you pick your model. Before this, every background task ran on a single default model—you couldn't pay for a beefier model for complex refactors or drop down to something faster for routine work. Now you can. The Agents panel includes a model picker. Use a faster model for straightforward tasks like adding unit tests. Upgrade to a more capable model when you're dealing with gnarly refactors or integration tests that need real edge cases. Or leave it on auto and let GitHub choose. Model selection is live for Copilot Pro and Pro+ users now, with Business and