AI Coding Tools Roundup: Copilot Gets Computer Use and Dynamic Workflows as Claude Code Ships 2.1.288

GitHub led the news this week. Copilot can now interact with desktop apps through computer use, it gained dynamic workflows for orchestrating agents, and several models were retired. Claude Code also shipped version 2.1.288, listed in the Claude Code changelog.

Copilot Computer Use: Agents That Click and Type

Per the GitHub changelog, computer use is in public preview for the Copilot CLI and desktop app on macOS and Windows. Copilot can read app content, click controls, enter text, press keys, scroll and drag, including in legacy software that has no API or command line. You stay in control: Copilot asks for approval before controlling apps, macOS needs Accessibility and Screen Recording permissions, and organizations can disable the feature.

• CLI: run /computer on to enable, /computer show for status, /computer off to disable.
• Copilot app: Settings > Computer Use, then toggle it on.

Dynamic Workflows in Copilot CLI and the Copilot App

The dynamic workflows announcement describes a way to define how a task is carried out by combining automated steps with one or more agents. Workflows can run commands and call external services, run independent tasks in parallel, pass structured results between stages, pause for user input and let agents verify findings. Good fits include release validation, parallel review of changed files and codebase pattern detection. The feature is in public preview on all Copilot plans, and in the CLI you must enable experimental mode with the --experimental flag or /experimental on.

Model Deprecations and Code Review Changes

On October 2 GitHub deprecated four models: Gemini 3.5 Flash and Gemini 3.6 Flash (replaced by Gemini 3.8 Flash), Kimi K2.7 Code (replaced by Kimi K3) and Claude Opus 4.7 (replaced by Claude Opus 5.5). Enterprise admins should enable the replacement models in Copilot settings. Separately, Copilot code review now has REST and GraphQL API support, with a selectable effort level, and Balanced became the default effort level from September 28. People who chose Lite keep that setting.

Claude Code 2.1.288

Version 2.1.288 (see the GitHub releases) adds $.ui.selection() so mods can capture transcript selections in fullscreen mode, plus built-in gh api support in cloud sessions without the GitHub CLI installed, and a fix for control characters being transmitted incorrectly. It builds on the Mods system introduced in 2.1.287, which we covered in the October 2 roundup.

Codex, Copilot CLI and OpenCode

OpenAI Codex is on 0.162.0 alpha builds on the Codex releases page, with no detailed notes yet, so stay on the latest stable build for now. Copilot CLI is in its 1.0.92 pre-release series (see Copilot CLI releases), adding a pre-conversation Ctrl+E environment picker, network bypass prompts for sandboxed shell commands and MCP reconnect fixes. The OpenCode changelog shows no new release in the last day.

What It Means for Developers

• If you pin Copilot models in workflows or integrations, move off the retired ones now.
• Treat computer use as a preview: keep approvals on and test on non-critical apps first.
• Teams scripting code review can now call it by API; check the effort level your tooling expects.
• Claude Code users should update to 2.1.288, especially for cloud sessions that rely on gh api.

Resources & References

• GitHub Copilot changelog
• Claude Code changelog
• OpenAI Codex releases on GitHub
• OpenCode changelog
• GitHub Copilot CLI releases