Browse GitHub Copilot News (215)

Allison outlines six GitHub Copilot model deprecations scheduled for December 14, 2026, with suggested replacements and guidance for administrators. The changes affect all Copilot experiences, although Claude Haiku 4.5 remains available to individual annual-plan subscribers. Users should update workflows and integrations before the deadline.

Allison announces generally available GitHub Enterprise Server support in the GitHub Copilot app, letting users work with remote repositories, issues, and pull requests. Support requires app version 1.2.0 or later and an initial GitHub.com or GHE.com sign-in. Cloud sessions remain unavailable for GitHub Enterprise Server.

Allison announces general availability of Gemini 4 Hydrogen in GitHub Copilot for paid plans. The model supports agentic coding, tool use, and multistep workflows, with gradual rollout across supported interfaces. The announcement explains usage-based billing at provider list pricing and how Business and Enterprise administrators can control access.

Jakub Oleksy reviews GitHub’s October service disruptions, their causes, and the changes intended to prevent recurrence. The report covers Azure capacity growth, database routing failures, overloaded connections, delayed Actions jobs, and Copilot authentication errors, showing why additional capacity must be paired with stronger isolation and safer recovery procedures.

Andrea Griffiths explains how to package repeatable tasks as agent skills that work across GitHub Copilot and other clients. Using independent verification and analytics pipeline examples, she shows how to separate project context from instructions, share execution paths, and enforce human approvals and CI checks without confusing instructions with permissions.

Praveen Sethuraman announces Bring Your Own Model general availability in Visual Studio 18.12. Developers can connect hosted or local models to Agent Mode without GitHub sign-in, maintain multiple provider configurations, select compatible API formats, and use enterprise proxy settings. Administrators can control access through organizational policy.

Anna Hoffman reviews Microsoft SQL updates released throughout 2026, spanning Azure SQL, SQL Server, Microsoft Fabric, and database tooling. The roundup covers Hyperscale scaling, vector search, recovery and security controls, migration options, Copilot-assisted workflows, database deployment, and driver updates, with availability details and limitations to check before adopting them.

Allison outlines an update that lets enterprise GitHub Apps assign GitHub Copilot seats to users and enterprise teams through enterprise-level seat management APIs. Access requires the new Enterprise Copilot license management fine-grained permission for Apps.

Allison announces general availability of Gemini 4 Carbon in GitHub Copilot for Pro+, Max, Business, and Enterprise users. The model targets complex coding and reasoning tasks, with usage-based billing at provider list pricing. Availability is rolling out gradually, and organization administrators can control access through model policies.

Allison describes how the Microsoft C++ Language Server for GitHub Copilot CLI now automatically generates compilation databases for MSBuild projects. The bundled extractor removes a separate configuration step and reduces setup token usage, while CMake and custom build systems still require a supplied compilation database or a configuration skill.

The .NET Team introduces .NET 11, an STS release with two years of support. The release brings C# 15 union types, runtime and SDK improvements, expanded web and mobile capabilities, and tools for AI applications. The announcement also outlines preview limitations and upgrade requirements as .NET 8 and .NET 9 reach end of support.

Dalia Abo Sheasha introduces the SDK-powered GitHub Copilot Chat experience enabled by default in Visual Studio 2026 version 18.12. The update improves results on C# coding tasks, adds mid-task instructions and live subagent visibility, and supports reusable agent skills. Plan mode and chat exports are still being brought over.

Allison announces Claude Fable 5.2 availability in GitHub Copilot for complex coding tasks. The update covers supported plans and tools, usage-based pricing, administrator enablement, and default retention of prompts and outputs, with temporary zero data retention access available to eligible enterprise customers.

Waldek Mastykarz examines how semantic version labels influence AI coding agents upgrading dependencies. Nearly 1,000 runs using GitHub Copilot CLI show that some models check patch releases less carefully than major releases, even with identical code. The findings support honest versioning and mandatory verification for every dependency update.

Allison outlines updates to GitHub Copilot code review, including API-based settings management across enterprises, organizations, and repositories. The changes also add attribution and source metadata, compact review overviews, AI credit visibility, and reliability fixes. Administrators should note differences in token and GitHub App support across settings endpoints.

Allison explains how the GitHub Copilot impact dashboard now tracks Copilot Chat and VS Code Agents window engagement across nine experiences. Enterprise and organization reports include the same additions, while the renamed Chat-first users cohort, unchanged adoption phases, and reporting rules clarify how to interpret the metrics.

Nick Liffen outlines how GitHub Copilot can support planning, implementation, verification, and production investigation beyond code generation. The guide covers shared project context, parallel tasks, focused pull requests, security checks, and operational evidence, while keeping developers responsible for approving plans, evaluating changes, and deciding what needs to happen next.

Allison summarizes this week’s GitHub Copilot updates, including availability in JetBrains Air and a public preview in Xcode’s built-in coding assistant. Other changes cover pull request merging, conversation context limits, CLI settings, session organization, and VS Code tools for reviewing agent work and scheduling local tasks.

Allison announces general availability of @GitHub in Slack and Teams, letting developers investigate bugs, create issues, implement changes, and open pull requests from conversations. Canvas in Teams supports collaborative review of plans, changes, and previews, while additional updates simplify repository selection and improve conversation reliability and attribution.

Allison outlines new GitHub Copilot usage metrics API fields that show whether developers act on code review feedback. Repository reports now include addressed rates, comment breakdowns, and merged pull requests without subsequent human change requests, with important distinctions around merge-day counting, bot pull requests, and report access.

Allison details new GitHub Copilot usage metrics API fields that identify missing client telemetry and IDE or extension version gaps. Enterprise and organization reports now show affected users and daily counts, with guidance on access permissions, overlapping counts, and interpreting unavailable data.

John Miller announces general availability of the Microsoft Foundry extension for Azure Developer CLI and walks through creating, testing, evaluating, and deploying hosted agents. The guide keeps agent and resource configuration alongside application code, explains remote builds, and shows how to reuse deployment and evaluation settings in CI/CD pipelines.

Mika Dumont explains how the GitHub Copilot upgrade agent helps migrate .NET applications from Windows x64 or x86 to Windows Arm64. It identifies compatibility blockers, proposes a migration plan, and updates code and project settings, while developers review changes and validate runtime behavior on matching hardware.

Waldek Mastykarz examines five GitHub Copilot runs that produced working Dev Proxy CI scripts but concealed fragile workarounds and unintended network changes. He shows how reading agent trajectories reveals gaps in documentation, CLI help, defaults, and product capabilities that evaluation scores miss, and how to validate fixes.

Baiju Meswani, Emma Ning, and Tianlei Wu explain how to run Qwen3.8-27B through Foundry Local and connect it to GitHub Copilot. They cover NVIDIA hardware requirements, inference optimizations, setup steps, and the trade-offs between private, offline coding assistance and the stronger reasoning capabilities of advanced cloud models.

Nick Zhu explains the upcoming end of GitHub Copilot support for JetBrains IDEs version 2025.2.x. The minimum supported version will become 2025.3.x, with 2026.2 or later recommended. Existing plugins are expected to keep working, but affected IDE versions will stop receiving new features, fixes, and performance improvements.

Karthik Vijayan, Jennifer Zhu, Youyou Wang explain how mixed-precision quantization, speculative decoding, and bounded KV caches enable MAI-Code-1.1-Flash to run locally through GitHub Copilot on RTX Spark PCs. Their measurements show the trade-offs between coding quality, memory footprint, and long-context responsiveness within a fixed device budget.

Allison announces the public preview of GitHub Copilot in Xcode’s built-in coding assistant, starting with Xcode 27.3 beta. The integration supports all Copilot plans and requires macOS Tahoe 26.6 or later. The existing GitHub Copilot for Xcode extension remains available as a separate option.

Allison explains how the GitHub Copilot usage metrics API now separates local BYOK and enterprise custom model usage from Copilot-hosted models. The update adds user-level and aggregate reporting without changing existing totals, with important limitations around client telemetry, token counts, model names, and historical data.

Hang Wang, Jun Han, and Ji Dong introduce GitHub Copilot as a built-in agent in JetBrains Air, with local and cloud task execution. They explain how to get started, enable native Next Edit Suggestions, and choose between Air’s streamlined access and the fuller capabilities of the GitHub Copilot plugin.

Richard Lander explains how NuGet packages can carry version-matched agent skills alongside library binaries. He demonstrates tools for discovering and copying those skills into repositories, compares package delivery with Git-based approaches, and discusses model evaluation, token costs, and the security implications of agents consuming package documentation.

tompeplow demonstrates how OneLake supports agent-driven data engineering through hosted MCP servers, endpoint discovery, and shortcuts. Using GitHub Copilot, the examples explore mirrored databases, document permissions, combine external data in a Lakehouse, and run SQL and Spark analytics while working within existing access permissions.

Yun Jung Choi explains how six specialized Azure plugins extend AI-agent workflows for AKS troubleshooting, cost analysis, Advisor recommendations, graph queries, Azure Local, and Foundry IQ knowledge bases. The guide includes example prompts, installation commands for supported clients, and approval requirements for resource changes and disruptive operations.

Alex Perrault explores how Arnis turns OpenStreetMap data into Minecraft worlds and how its sole maintainer, Louis Erbkamm, uses GitHub Copilot to investigate bugs and review contributions. Copilot sub-agents help examine sensitive parts of the codebase and suggest corner cases for regression testing.

Allison announces GitHub Copilot support in JetBrains Air, enabling local and cloud coding tasks through the Agent Client Protocol. The update supports parallel sessions and in-context review using existing Copilot subscriptions, with isolated cloud execution and limitations around plan selection, usage visibility, and administrative spending controls.

Waldek Mastykarz examines whether naming a workspace folder ‘eval’ changes GitHub Copilot CLI behavior. Across about 900 runs with four models, the name increased agents’ suspicion that they were being tested without producing statistically significant behavioral differences. The analysis explains the experiment’s controls, limitations, and practical guidance for evaluation harnesses.

nareshvenkat introduces Project Osmos, a data engineering agent for Microsoft Fabric that investigates datasets, executes PySpark, and validates results. Persistent, shared tasks retain project context while teams define operating boundaries, review evidence, and guide changes. Tasks can be initiated through GitHub Copilot CLI, Claude Code, or Codex.

LeeBenjamin introduces the generally available Govern experience in Microsoft Fabric’s OneLake catalog and the new Govern Skills collection. Together, they provide centralized estate insights, policy controls, and AI-assisted governance checks, with evidence-based recommendations and confirmation before sensitive changes through tools such as GitHub Copilot.

Satya Nadella outlines GitHub updates announced at Universe, including Copilot Fusion performance and cost claims, a unified Copilot harness in Foundry, and Copilot Projects for coordinating multiple agents across repositories. The post also notes plans to expand GitHub capacity and strengthen its architecture.

Jeff Hollan, Viswajeeet Balaji, and Anthony Chu introduce the Microsoft Copilot harness public preview in Foundry Agent Service and generally available resilience for hosted agents. They demonstrate reusable skills and declarative deployment, explain recovery responsibilities and preview limitations, and outline consumption-based runtime billing beginning December 1, 2026.