github-copilot

On November 5, 2026 Microsoft added a Windows Arm64 migration scenario to the GitHub Copilot upgrade agent. Here is what the blockers look like in a real .NET project, what the agent can and cannot verify, and how to check the result yourself.

Copilot Fusion, generally available since October 28, 2026, is a runtime model router that picks a model and an execution pattern (Single, Cascade, or Critique) per prompt. Here is how the three patterns work, what Fusion Standard, High, and Max cost you in AI credits, how to lock the effort level with managed-settings.json, and the gotchas the docs bury.

ACP (Agent Client Protocol, v1) connects an editor to a coding agent; MCP (spec 2026-07-28) connects an agent to tools. They sit on opposite sides of the agent and are used together: ACP's session/new even carries the MCP servers the agent should start. Here is the feature matrix, the wire flow, and a working agent and client checked against @agentclientprotocol/sdk 2.4.0.

MXC is Microsoft's MIT-licensed SDK for running untrusted code, including model output, plugins and tools, under one deny-by-default policy that it maps to Seatbelt on macOS, bubblewrap on Linux and ProcessContainer on Windows. Here is what MXC SDK 1.0.1 and schema 1.0.0 actually define, how Copilot CLI hands it a policy per process, and what stays outside the box.

A guard hook that crashes or times out lets the dangerous command through in most coding agents. Fail closed for pre-action guards, fail open for everything else, and make the script fail closed by itself because Copilot, Codex and Gemini CLI treat a timeout as allow. Compared on Claude Code 2.1.295+, Cursor hooks, Copilot CLI 1.0.105, Codex and Gemini CLI, with a portable guard script.

Turn on the local sandbox for everyday Copilot CLI work, move to a cloud sandbox when the code or the task should never touch your laptop, and use a dev container when the team needs the same reproducible toolchain. Compared on Copilot CLI 1.0.104: what each boundary isolates, what it leaks, what it costs, and how to stack them.

Use /fleet for a one-off parallel task in your terminal, a dynamic workflow when the same multi-agent process has to run the same way twice, and GitHub Agentic Workflows when that process runs unattended on repository events. Compared on Copilot CLI 1.0.103 and gh-aw v0.93.6: who plans the split, limits, resume, permissions, write safety and billing.

Run /sandbox policy <command> to see what the sandbox blocked, then grant the path or host it needs, update Copilot CLI to 1.0.103 for the localhost, proxy and Linux fixes, and only bypass a command on purpose.

Turn on GitHub Copilot computer use in Copilot CLI and the Copilot app on macOS and Windows, grant the macOS Accessibility and Screen Recording permissions, approve apps per session or always, write prompts that keep the agent read-only, and lock it down with deny rules and the features.computerUse managed setting.

Request a GitHub Copilot code review from a script with the REST requested_reviewers endpoint, the GraphQL requestReviewsByLogin mutation, or gh pr edit, then control whether it runs at Lite or Balanced effort. Covers the bot login, the effort precedence chain, why the per-request effort field announced on October 2, 2026 is not in the published schemas yet, and how to read the effort that actually ran.