Browse GitHub Copilot News (216)

Mark Downie covers the April Visual Studio 2026 update, focusing on GitHub Copilot’s new cloud agent workflow, user-level custom agents, and a Debugger Agent that validates fixes against real runtime behavior, plus improvements to C++ agent tools, IntelliSense vs Copilot completion priority, and configurable Copilot shortcuts.

Allison announces that GitHub Copilot Student is removing GPT-5.3-Codex from the model picker, while keeping it available via auto model selection. The post explains this as part of temporary reliability/performance measures and points to documentation on supported models and upcoming usage-based billing changes.

Allison shares a GitHub Changelog update: Copilot cloud agent now starts over 20% faster by using optimized runner environments prebuilt with GitHub Actions custom images, reducing environment startup overhead when Copilot begins work from issues, PRs, or the Agents tab.

Allison announces a billing change for GitHub Copilot code review: starting June 1, 2026, reviews will consume both Copilot AI Credits and (for private repos) GitHub Actions minutes, with guidance on checking usage, budgets, and runner configuration.

Mario Rodriguez announces that GitHub Copilot plans will move to usage-based billing on June 1, 2026, replacing premium request units with GitHub AI Credits based on token usage. The post explains what changes for individuals and organizations, including pooled credits, budget controls, and how Copilot code review also uses GitHub Actions minutes.

Allison announces that GPT-5.5 is rolling out to GitHub Copilot, highlighting improved performance on complex, multi-step agentic coding tasks, plus where you can select it (IDEs, CLI, web, mobile) and what admins need to enable for Business/Enterprise.

Allison announces updates to GitHub Copilot for JetBrains IDEs, including inline agent mode (public preview), improvements to Next Edit Suggestions, and new global/granular auto-approve controls for tool calls like terminal commands and file edits, plus UX and reliability refinements.

The Visual Studio Code Team shares the VS Code 1.118 (Insiders) updates, focused on GitHub Copilot CLI improvements like session-title APIs, session switching keybindings, auto model selection, model badges in chat, and a Copilot CLI SDK change to resolve node-pty via hostRequire.

Allison announces improvements to GitHub Copilot Chat for pull requests, including richer PR context (comments, file changes, commits, reviews) plus new capabilities to review and summarize PRs directly from GitHub surfaces.

Allison announces an update to the GitHub Copilot usage metrics REST API: user-level reports now include a new `used_copilot_cloud_agent` boolean field (matching the Copilot cloud agent rename). The legacy `used_copilot_coding_agent` field remains for backward compatibility until August 1, 2026.

Allison announces an update to GitHub Copilot Chat on github.com that improves debugging when you paste a stack trace. Copilot now recognizes stack traces more reliably and responds with a more structured root-cause analysis, including evidence from code references, confidence level, and suggested fixes.

Linda Li, Maria Naggaga, and Ronak Chokshi introduce Toolboxes in Azure AI Foundry (public preview), a way to centrally curate and govern tool integrations and expose them via a single MCP-compatible endpoint so different agent runtimes can reuse the same tools without per-agent wiring.

Desi Villanueva explains why AI coding agents “forget” work mid-session (context rot and compaction) and introduces auto-memory, a small Python CLI that reads GitHub Copilot CLI’s local SQLite session store to cheaply recall recent files and session details for faster re-orientation.

Microsoft Fabric Blog explains how Model Context Protocol (MCP) enables AI assistants and agents (including GitHub Copilot and Copilot Studio) to discover and operate Microsoft Fabric via new Local (GA) and Remote (preview) MCP servers, covering OneLake operations, API-grounded code generation, and security controls like Entra ID, RBAC, and audit logs.

Ricardo Fiel introduces “Agentic DevOps” as a practical starting point for using AI-powered agents (especially GitHub Copilot agents) across the SDLC, outlining core concepts like chat vs agent execution, local/CLI/cloud agent types, and what comes next in the series.

Kristen Womack announces new Azure Developer CLI (azd) integrations with GitHub Copilot: a Copilot-powered “azd init” flow that scaffolds azure.yaml and infrastructure templates, plus in-terminal AI troubleshooting that can explain, guide, diagnose, and (with approval) fix common Azure deployment errors.

Drew Noakes explains how the C# Dev Kit team replaced C++ Node.js addons with a .NET Native AOT shared library, showing how to build a Node-API (N-API) addon in C# with exported entry points, P/Invoke via LibraryImport, and practical string marshalling between JavaScript and .NET.

Joe Binder explains upcoming changes to GitHub Copilot Individual plans, including paused new sign-ups, tighter token-based usage limits, and adjustments to model availability, with guidance on how to avoid hitting limits in VS Code and Copilot CLI.

Allison announces changes to GitHub Copilot individual plans, including pausing new signups for Pro/Pro+/Student, tightening usage limits with in-product warnings, and removing certain Opus models from Pro (with additional removals planned for Pro+).

Allison announces general availability of Copilot auto model selection in GitHub Copilot CLI, explaining how the CLI dynamically routes requests to different models, shows which model was used, respects admin policies, and how premium request billing works when auto is enabled.