Research, experiments, and implementation notes filed under copilot.
Copilot CLI Local Model Discovery Makes BYOK Less Awkward
GitHub Copilot CLI can now discover supported Ollama models from the model picker, but local model routing still needs clear privacy and capability checks.
Copilot Dynamic Workflows Make Agent Runs More Repeatable
GitHub Copilot dynamic workflows put multi-agent orchestration into reusable code, with limits, checkpoints, and resumable runs.
Copilot Local Sandboxing Makes Agent Permissions Concrete
GitHub Copilot app local sandboxing turns agent permissions into per-project policy, which is the right default shape for developer machines.
GitHub Copilot Auto Gets Cost And Quality Tiers
GitHub Copilot auto model selection now has efficiency, balance, and intelligence tiers, giving teams a practical way to steer cost, latency, and quality without picking a model for...
GitHub Copilot Code Review Gets Closer to Real CI
GitHub Copilot code review now uses broader shell tools and an ensemble of agents in Lite reviews, which makes AI review more useful but also worth treating like...
VS Code Agent Host Makes Coding Sessions Less Tied To One Window
VS Code 1.134 moves agent sessions toward a dedicated Agent Host process, making long-running coding work easier to share, resume, and run near the workspace.
What Agent Plugins 1.0 Gets Right About Portable Tooling
A closer look at the portable packaging layer for skills, commands, hooks, and MCP configuration.