The art of simplicity

In my earlier posts about the GitHub Copilot CLI , I already introduced the /compact command, a slash command that summarizes your conversation history to free up context space, letting you keep working in the same session without losing momentum. Well, good news! It's no longer CLI-only. The February 2026 release of VS Code brings /compact directly into the editor, and it's part of a much broader story about making agents actually usable for the kind of long, messy, real-world tasks developers deal with every day. The Context Window problem Here's what happens without context compaction: you start an agent session, ask it to dig into a complex feature, go back and forth a few times, and eventually the conversation grows so large that the model starts losing the thread, or the session simply stops. You're forced to start over, re-explain everything, and lose all the accumulated understanding the agent had built up. Context compaction solves this by summarizing...

If you've spent any time working with GitHub Copilot in agent mode, you've probably hit that frustrating moment: the agent does something unexpected, picks the wrong tool, ignores a prompt file, or just… takes forever, and you have no idea why. Until recently, your only recourse was the raw Chat Debug view : useful, but dense, and not exactly designed for quick diagnosis. That changes with the Agent Debug Log panel, available in preview as of VS Code 1.110. What it is The Agent Debug Log panel shows a chronological event log of everything that happens during a chat session, including tool calls, LLM requests, prompt file discovery, and errors. Think of it as a structured, human-readable trace of your agent's entire thought process, rendered right inside VS Code. It replaces the old Diagnostics chat action with a richer, more detailed view, and is particularly valuable as your agent setups grow in complexity; custom instructions, multiple prompt files, MCP servers, and...

Verifying frontend changes always meant a mental context switch: write code, alt-tab to a browser, poke around in DevTools, switch back. Even with a decent dev server, the loop was still manual — and for AI agents, it was essentially broken. Agents could write unit tests for logic, but verifying whether a button actually renders, whether a dialog triggers, or whether a layout holds up? That required a human in the loop. I first tried to tackle this problem by using the Playwright or Chrome Dev-Tools MCP server, but with the February 2026 release of VS Code (1.110) , that changes. Agents can now open, interact with, and inspect your running application directly inside VS Code's integrated browser — closing the development loop without any manual hand-off. How it works When browser agent tools are enabled, Copilot gains access to a set of tools that let it read and interact with pages in the integrated browser. As the agent interacts with the page, it sees updates to page co...

A few weeks ago I wrote about Copilot Memory in VS Code - the GitHub-hosted system that lets Copilot learn repository-specific insights across agents. Since then, VS Code has shipped a second, complementary memory system: the Memory tool . These two systems solve related but distinct problems, and understanding both helps you get the most out of Copilot in your daily workflow. What is the Memory Tool? The Memory tool is a built-in agent capability that stores notes locally on your machine . Unlike Copilot Memory, which lives on GitHub's servers and requires a GitHub repo to function, the Memory tool writes plain files to your local filesystem and reads them back at the start of each session. You enable or disable it with the github.copilot.chat.tools.memory.enabled setting. It's on by default. Three memory scopes VSCode organizes memories into three scopes: Scope Persists across sessions Persists across workspaces Good for ...

If you've ever been mid-session with Copilot and thought "I want to try a completely different approach, but I don't want to lose everything I've built up here" — the new /fork command is exactly what you've been waiting for. Shipped in the February 2026 release of VS Code, /fork lets you branch a chat session into a new, fully independent thread — complete with the full conversation history — so you can explore an alternative direction without touching the original. The problem it solves Until now, exploring multiple design options or implementation strategies with Copilot meant one of two things: Start a new session — losing all the context you've already established. Stay in the same session — making your conversation messy and hard to track. Neither is great. Especially for larger tasks where the agent has already built up a useful mental model of your codebase, intent, and constraints. How to use /fork There are two ways to ...

I was working on a refactoring using VS Code the other day when I noticed something I hadn't seen before: a tiny bar chart quietly living in the status bar, tracking my AI vs. manual typing usage over the last 24 hours. It's called AI Statistics, and it shipped in VS Code 1.103. To enable it, open settings and search for "AI stats" — flip the checkbox, and a small gauge appears in the bottom-right of your status bar. Hover over it and you get a breakdown: how much of your recent code came from AI completions versus your own keystrokes. On the surface it sounds like a novelty. But I found myself actually pausing when I saw the numbers. It reframed something I hadn't really thought about consciously: not whether AI coding tools are good or bad, but just how much I'm actually leaning on them day to day. That visibility is weirdly valuable. It's the kind of data point that makes you more intentional — maybe you lean in harder on AI for boilerplate an...

If you've ever found yourself repeatedly correcting GitHub Copilot with the same preferences or re-explaining your team's coding standards in every chat session, the January 2026 release of VS Code brings a possible solution: Copilot Memory . What Is Copilot Memory? Copilot Memory is a new feature that allows GitHub Copilot to remember important context across your coding sessions. Think of it as giving your AI assistant a notebook where it can jot down your preferences, team conventions, and project-specific guidelines—and actually refer back to them later. Released as a preview feature in VS Code version 1.109 (January 2026), Copilot Memory changes how you interact with AI-powered coding assistance by making your conversations with Copilot persistent and personalized. How it works The magic of Copilot Memory happens through a new memory tool that's integrated directly into VS Code's chat interface. Here's how it works: Intelligent detection Copilot a...

If you're using GitHub Copilot in Visual Studio Code, there's a powerful new feature that can save you time and make your AI-powered development workflow more efficient: the /init command. This slash command provides a quick way to set up custom instructions for your workspace or adapt your existing instructions to the specific project context, helping you establish consistent coding practices and AI responses across your projects. What is the /init command? The /init command is a chat slash command in VSCode that helps you quickly prime your workspace with custom instructions for GitHub Copilot. When you type /init in the chat input box, it automatically generates a .github/copilot-instructions.md file tailored to your workspace. Think of it as a quick-start wizard for setting up AI guidelines that will influence how Copilot generates code and handles development tasks throughout your project. How to use the /init command? Using the /init command is straightforw...

I regularly switch between multiple IDEs, mostly VS Code and Visual Studio but sometimes also Rider or Cursor. One of the Visual Studio features I miss when using VS Code is the support for HTTP files. What if I told you that there is a way to use HTTP files in VS Code? Enter the REST Client extension for Visual Studio Code, a lightweight, powerful tool that lets you test APIs without ever leaving your editor. What is the REST client extension? Similar to the HTTP support in Visual Studio, the REST Client extension allows you to send HTTP requests and view responses directly in VS Code. It's minimal, scriptable, and integrates seamlessly into your existing workflow. It offers the same functionality as in Visual Studio and more:   .http and .rest file extensions support Syntax highlight (Request and Response)         Auto completion for method, url, header, custom/system variables, mime types and so on Comments (line ...

If you're working with Git repositories in Visual Studio Code, you might occasionally need to checkout a specific tag—perhaps to review a previous release, test an older version, or understand how the codebase looked at a particular milestone. While VSCode's built-in Git integration is powerful, checking out tags wasn't immediately obvious to me. Let me walk you through the process. What are Git tags? Before diving in, a quick refresher: Git tags are references that point to specific commits in your repository's history. They're commonly used to mark release points (like v1.0.0, v2.1.3, etc.). Unlike branches, tags are meant to be immutable snapshots of your code at a particular moment in time. Checkout a Git tag in VS Code Method 1: Using the Command Palette The quickest way to checkout a tag in VSCode is through the Command Palette: Open the Command Palette by pressing Ctrl+Shift+P (Windows/Linux) or Cmd+Shift+P (Mac) Type "Git: Checko...

At GitHub Universe, GitHub announced that you can use OpenAI Codex with your existing GitHub Copilot Pro+ subscription. Therefore we first need to install the OpenAI Codex extension and sign in with GitHub Copilot. Installation & configuration You can directly install the extension from the extensions or through the Agent sessions view: After the installation has completed, you need to sign in. You can either use your ChatGPT account or your (existing) GitHub Copilot subscription. Once signed in, we have an extra chat window available: There are a few things we can configure here: Environment: Local workspace: The agent will interact with your local machine and VSCode workspace. Connect Codex Web: Send the chat to the ChatGPT web interface. Send to cloud: The agent will operate in a sandboxed cloud environment.   Chat Mode (called approval modes in OpenAI Codex): Chat: Regular chat, doesn’t do any changes directly. ...