Browse GitHub Copilot News (223)

Napalys Klicius explains why migrating Copilot code review to shared Unix-style exploration tools (grep, glob, view) initially increased cost and reduced useful findings, and how rewriting tool instructions to match a reviewer’s diff-first workflow delivered about 20% lower average review cost without hurting quality.

Allison announces an update to GitHub Mobile that adds improved filtering and sorting for GitHub Copilot sessions, helping developers find active, completed, and needs-attention sessions more quickly as their session list grows.

Mika Dumont introduces an interactive upgrade canvas in the GitHub Copilot app that lets teams track a .NET modernization end-to-end, from assessment and planning through execution, code changes, build failures, and final results, with the same upgrade workflow available in Visual Studio, VS Code, and the Copilot CLI.

Allison announces the rollout of OpenAI’s GPT-5.6 model family (Sol, Terra, and Luna) in GitHub Copilot, including what each variant is best suited for, where you can select them, and what admins need to enable for Business and Enterprise plans.

Allison announces a GitHub Copilot Chat feature on github.com that generates a high-level overview of a repository you’re visiting for the first time, summarizing the repo’s purpose, technologies used, and contribution guidelines, with an option to generate a README when one doesn’t exist.

David Pine explains how the .NET Aspire team uses GitHub Agentic Workflows to turn merged product pull requests into SME-reviewed documentation pull requests in a separate repo, while keeping security tight through a “safe-outputs” contract and narrowly scoped GitHub App permissions.

Allison announces enterprise-managed OpenTelemetry export controls for GitHub Copilot in VS Code and Copilot CLI, letting organizations centrally mandate OTLP endpoints, protocols, resource attributes, and capture settings without relying on per-developer OTEL_* environment variables.

Allison announces general availability of device-level deployment for managed GitHub Copilot settings in VS Code and GitHub Copilot CLI, enabling enterprise admins to enforce consistent Copilot governance via MDM, configuration files, or server-managed settings.

Jakub Oleksy’s June 2026 GitHub availability report summarizes six production incidents (including Copilot outages) and the reliability work behind GitHub’s ongoing Azure migration, with concrete mitigations like dependency pinning, stronger config validation, improved traffic blocking, and tighter production access controls.

Allison summarizes the June/early July 2026 Visual Studio Code releases (v1.123–v1.127) focused on GitHub Copilot: integrated browser upgrades for agent-driven web validation, better organization for parallel agent sessions, clearer cost and token visibility, easier model-provider discovery via Marketplace, and more hands-off Autopilot behavior.

Katie Savage announces a free, instructor-led virtual training series starting July 16 that introduces the GitHub Copilot app and its agent-driven workflow, including setup, custom instructions, MCPs, and features like Agent Merge and Canvases for tracking work.

Bruno Borges walks through using GitHub Copilot CLI plus a community Namecheap skill to publish a GitHub Pages site on a custom domain with HTTPS, without manually editing DNS records. The post shows the end-to-end flow: create the repo and site, enable registrar API access, apply the required A/CNAME records, and verify resolution and HTTP health.

Allison announces a GitHub Mobile update that lets developers kick off Copilot cloud agent from a pull request to resolve merge conflicts, helping unblock PRs while away from a desktop workflow.

Allison announces an update to GitHub Mobile that adds live notifications for remote GitHub Copilot CLI sessions, so developers can monitor coding agent progress, see when input is needed, and jump back into session logs from their phone.

Allison announces new GitHub Copilot usage metrics API fields that let enterprises and organizations compare pull request review speed and review-cycle counts across AI adoption phases, helping teams measure how Copilot adoption correlates with code review throughput.

Allison announces updates to GitHub Copilot for JetBrains IDEs, including Codex as a new agent provider (public preview), expanded agent customization features (Hooks and MCP server management), and new controls for approvals, permissions, and debugging across agentic sessions.

Allison announces that Kimi K2.7 Code is now available to GitHub Copilot Business and Copilot Enterprise customers, including how admins can enable it and what to consider before turning on an open-weight model.

Allison announces that GitHub Enterprise Cloud admins can now set per-user AI credit budgets for cost centers directly in the billing UI, matching controls that previously required the REST API.

Allison announces that the GitHub Copilot app is now available across all Copilot plans, enabling agent-driven development from a desktop app on macOS, Windows, and Linux, with support for signing in via GitHub or running sessions using your own model provider key.

Allison announces that the Copilot Billing Preview app will be retired on August 3, 2026, and points teams to GitHub’s built-in billing settings for tracking GitHub Copilot spend, budgets, and AI usage details.

Waldek Mastykarz shares results from running 150 agent tasks comparing Claude Sonnet 4.6 vs Sonnet 5 inside GitHub Copilot Chat in VS Code, showing how “cheaper per token” can still mean higher costs, higher variance, and worse output quality depending on the workload.

The VS Code Team shares results from a two-week production experiment with OpenAI that tuned the GPT-5.5 system prompt used by the VS Code coding harness. It explains the prompt variants tested, the metrics used to judge quality vs speed/cost, and why the winning prompt became the new default.

Allison details three changes to the GitHub Copilot usage metrics API that improve reporting completeness for Copilot CLI activity, IDE identification, and AI credit attribution—helping orgs and enterprises get more reliable usage and consumption data from the REST API.

Allison announces the July 31, 2026 deprecation of Gemini 2.5 Pro and Gemini 3 Flash across GitHub Copilot experiences, and explains what Copilot Enterprise admins and teams need to change to keep using supported models.

Allison announces that GitHub Copilot CLI can now authenticate in GitHub Actions using the built-in GITHUB_TOKEN, removing the need to manage long-lived personal access tokens. The post also explains the required Copilot policy and workflow permission, plus options for tracking and controlling organization-billed AI credit spend.

Allison announces a public preview for streaming GitHub Copilot agent session data in GitHub Enterprise Cloud, giving enterprises visibility into prompts, responses, and tool calls via a streaming endpoint or a REST API, with Microsoft Purview supported as a streaming destination.

Allison announces AI credit pools for GitHub cost centers, letting enterprises cap how much of their monthly included Copilot AI credits each cost center can consume via the REST API, helping keep spend allocation aligned with the licenses assigned to each group.

Allison explains how enterprise admins can make GitHub Copilot’s auto model selection the default for new conversations by setting `model` to `auto` in enterprise managed settings, while still allowing users to switch models per conversation.

Allison announces general availability of enterprise managed-settings.json for GitHub Enterprise Cloud, letting admins centrally enforce Copilot client configuration (like allowed marketplaces, enabled plugins, and model selection) via a file stored in a .github-private repo and applied to VS Code and Copilot CLI.

Allison announces a new Copilot CLI plugin for the Microsoft C++ Language Server, including a setup skill that generates and maintains compile_commands.json for better C++ semantic features across CMake, MSBuild, and custom build systems.

Allison announces general availability of Kimi K2.7 Code in GitHub Copilot, the first open-weight model offered in the Copilot model picker, including where it’s available, how it rolls out across plans, and what admins need to enable for Business and Enterprise.

Allison announces general availability of Copilot vision, which lets developers attach images and PDFs to GitHub Copilot Chat prompts so Copilot can reason about visual context alongside code, across VS Code, github.com, and the Copilot CLI.

Allison announces a public preview feature for Copilot CLI and the GitHub Copilot SDK that lets you cap AI credit usage per session, helping teams control spend during interactive work and unattended scripted runs.

Allison announces general availability of browser tools for GitHub Copilot in VS Code, enabling Copilot agents to drive a real browser to navigate and test live web apps, capture page content and console errors, and run scripted flows, with privacy defaults and enterprise controls.

Mark Russinovich introduces Azure Chaos Studio Workspaces (public preview) and explains how scenario-based chaos engineering helps teams prove real application resilience on Azure by simulating common outage patterns—like zone loss, DNS failure, database failover, and messaging disruption—then reviewing structured drill reports correlated with Azure Monitor signals.

Allison announces an update to Copilot CLI where Auto model selection routes each request to an appropriate model based on task needs and real-time reliability signals, with billing tied to the selected model’s multiplier and a discount for paid subscribers using Auto.

The Visual Studio Code Team highlights early changes in VS Code 1.128 (Insiders), including enterprise policy support for OpenTelemetry settings and updates to AI model configuration and credentials when using Copilot-related agent features.

Allison announces general availability of Anthropic’s Claude Sonnet 5 in GitHub Copilot, including where it can be selected (IDE, CLI, and GitHub surfaces), how it’s billed under usage-based pricing, and how Business/Enterprise admins can enable it via model policy settings with Zero Data Retention.

Jan Krivanek and Yuliia Kovalova show how to run MCP-powered MSBuild binlog diagnostics inside GitHub Actions so failed PR builds get an automated root-cause comment (with inline suggestions) without anyone downloading logs. They also catalog new Binlog MCP tools and share evaluation data on quality, time, and token usage.

Mark Downie covers the June Visual Studio update, focusing on GitHub Copilot usage tracking (token-based metering with alerts), new trust validation for MCP servers, and the general availability of the Copilot modernization agent for C++ MSVC upgrades.