Browse GitHub Copilot News (209)

Kevin Stubbings explains how GitHub Security Lab’s open-source Taskflow Agent uses targeted LLM “taskflows” to audit Android apps, including how to run the workflows in a Codespace and what kinds of findings to expect. He also walks through two disclosed examples and where AI tends to produce false positives or misjudge severity.

Dan Wahlin introduces a free, open source “GitHub Copilot app for Beginners” course that teaches developers how to run and supervise AI coding agents in the Copilot desktop app, keep parallel work isolated with git worktrees, and validate changes with diffs, tests, previews, and PR checks.

Allison announces general availability of Claude Sonnet 5.5 in GitHub Copilot, including where you can select it (IDEs, Copilot CLI, coding agent, and GitHub clients), how it’s billed under usage-based pricing, and how Business/Enterprise admins can control access via model policy settings.

Allison announces an in-product validator for GitHub Copilot enterprise managed settings that helps admins catch configuration issues (like malformed JSON, unsupported settings, and invalid team mappings) so Copilot policies are enforced correctly across the enterprise.

Allison announces an update to GitHub Copilot repository-level usage metrics that breaks pull request review time into distinct stages, helping teams pinpoint where PRs are getting stuck (waiting for first review, review iteration, or post-approval merge delay).

Kayla Cinnamon explains how to use canvases in the GitHub Copilot app to generate a custom, shared UI (like a kanban board or release checklist) from a plain-English description, then iteratively refine it while the agent updates the same live surface.

Allison announces that GitHub’s agentic autofix can now use Copilot Memory to pull repository-specific context when resolving security alerts, and to store fix patterns as reusable memories for future fixes and other Copilot features.

Allison summarizes the September 21 weekly GitHub Copilot releases, including new model options, a local sandboxing preview in the Copilot app, and feature updates across Slack/Teams, JetBrains IDEs, and VS Code—especially around agent sessions, remote development, and observability.

Allison outlines updates to GitHub Copilot’s Slack and Microsoft Teams integrations, focusing on richer conversation context, better traceability when creating GitHub work, and more control over model selection and repository defaults. The post also summarizes reliability fixes and explains preview availability for Copilot Business and Enterprise.

Josh Black explains how GitHub’s Primer Design System migrated from CSS-in-JS to CSS Modules without breaking production, using feature flags, visual regression testing, and incremental rollouts. The post also covers the follow-on work to eliminate `sx` props and remove `styled-components`, including automation via codemods and Copilot coding agents.

Allison announces a new GitHub Copilot enterprise-wide default policy that controls whether generally available Copilot features and supported client capabilities are enabled, disabled, or delegated to organizations, with a 28-day configuration window before enforcement begins.

Burke Holland argues that chat is often the wrong interface for working with LLMs, and shows how GitHub Copilot app “canvases” provide a more task-oriented surface. He walks through examples like a Connect 4 canvas, a winget UI, and a SQLite UI, then connects the idea to automating agent-driven development workflows.

Allison announces generally available updates to GitHub Copilot code review, adding a dedicated personal settings page and an enterprise-wide default review effort setting for organization-owned repositories.

Alberto Gimeno explains how the GitHub Copilot app was reworked to keep pull request reviews responsive even with million-line diffs and hundreds of inline comments, focusing on virtualization limits, dynamic height measurement, scroll anchoring, and the instrumentation loop used to harden performance.

Allison announces a public preview feature in the GitHub Copilot app that lets teams sandbox local sessions per project to reduce the blast radius of unintended commands. It covers filesystem allow/deny lists, outbound and local network controls, and limiting access to Git and GitHub CLI credentials.

Allison announces OpenTelemetry support in the GitHub Copilot app, letting enterprises export agent activity telemetry to compatible observability tools so teams can trace agent sessions, investigate unexpected behavior, and manage monitoring settings centrally.

Allison announces GitHub Copilot for JetBrains 1.18.0, highlighting new agent-session controls like assisted tool approvals, message re-editing with conversation rewind, shared org skills and instructions, Codex agent plan mode, and more granular MCP tool controls, plus several UX, reliability, and compatibility updates.

Julia Gong, Shengjie Ma, Ben Liggett, and Ulugbek Abdullaev explain how GitHub Copilot’s inline suggestions in VS Code moved to a unified “3-in-1” model that handles completions, near-cursor edits, and longer-distance edits, and how model training and client-side UX changes were tuned together using benchmarks and online flights.

Allison announces faster C++ code intelligence in GitHub Copilot CLI through whole codebase indexing, which builds a persistent symbol index across the entire repository to speed up definitions, references, and symbol search, with notes on how to check progress and disable indexing if needed.

Allison announces that Anthropic’s Claude Opus 5.5 model is now available in GitHub Copilot, including where you can select it, which Copilot plans get access, and how admins can control enablement via model policies and usage-based billing.

Aaron Powell walks through diagnosing a production hang in a C# app by capturing a memory dump and analyzing it in Visual Studio, using Parallel Stacks to spot thread-pool saturation and then using GitHub Copilot to help interpret what the dump is showing.

Allison announces that OpenAI’s GPT-6 Sol and GPT-6 Luna are now available as model choices in GitHub Copilot, alongside GPT-6 Astra. The update covers what each model is optimized for, where you can select them, how they’re billed, and how admins can control access via model policy settings.

Allison announces that Grok 4.7 (xAI’s reasoning model) is rolling out in GitHub Copilot, including where developers can select it, which Copilot plans get access, and how admins can control availability via model policy and default model enablement settings.

Waldek Mastykarz explains why a model’s published knowledge cutoff date doesn’t reliably predict whether it can do real work with a specific developer product, and shows how workload-based evaluations give a more accurate signal when building and testing AI coding agents and extensions.

Allison announces generally available improvements to GitHub Copilot code review, including a clearer pull request overview that tracks findings across review iterations, smarter auto-resolution of Copilot comments, and generated commit titles/descriptions when accepting eligible batches of suggestions.

Allison summarizes the September 14 weekly GitHub Copilot updates, including improvements to Copilot code review, new auto model selection tiers, admin controls and usage metrics for Business/Enterprise, a Sentry canvas in the Copilot app, and new agent workflow features in VS Code.

Allison announces that several AI models will be deprecated across GitHub Copilot experiences on October 19, 2026, and outlines which replacement models to use plus how Copilot Business and Enterprise admins can enable alternatives via model policies.

Allison announces updates to GitHub Copilot’s impact dashboard and reporting APIs, adding 28-day feature engagement metrics so enterprise and organization admins can see which Copilot experiences are being used regularly and where enablement may be needed.

Allison announces expanded GitHub Copilot CLI reporting in the Copilot usage metrics API, adding agentic activity metrics for skills, custom agents, MCP servers, slash commands, and plugins, plus guidance on how counts are calculated and who can access the reports.

Stephen Toub breaks down how GitHub rewrote the Copilot agent runtime from a TypeScript/Node.js/V8 stack into a production Rust runtime, largely using Copilot agents. He explains the architectural drivers (in-process hosting, lower memory, better startup), the incremental port strategy, interop layers, regression patterns, and the measured performance gains.

Allison announces general availability of Copilot budget increase requests, letting members request additional AI credits when they hit their limit and enabling org/enterprise owners and billing managers to approve, adjust, or deny requests directly from GitHub settings under usage-based billing.

Julia Gong, Ben Liggett, and Ulugbek Abdullaev explain how GitHub Copilot’s inline suggestions in VS Code moved from three separate models (completions, next edit suggestions, and long-distance edits) to a unified “3-in-1” approach, including the diff-patch output format, training strategy, and evaluation methods used to ship it.

Allison announces a public preview feature where GitHub Copilot suggests allowed values while admins define repository custom properties, helping organizations build consistent governance metadata that can be used to scope rulesets across large fleets of repositories.

Aaron Powell shows how to baseline and then raise unit test coverage in the Interview Coach app using Visual Studio’s code coverage tooling and GitHub Copilot’s Test Agent, moving from targeted tests for a single class to solution-wide analysis and test generation.

Justin Yoo walks through a sample “Interview Coach” app that uses the GitHub Copilot SDK as an agent runtime (outside the editor) to run an interview workflow: ingest a resume, ask behavioral/technical questions, store session context, and generate end-of-interview feedback using MCP tools and Agent Framework handoffs.

Mariyaali announces the general availability of the SQL DW operations skill for Microsoft Fabric Data Warehouse, which lets teams use natural-language prompts (for example via GitHub Copilot CLI) to run bounded, read-only diagnostics and get structured findings, evidence, and recommended next steps for common warehouse incidents.

Allison announces new configuration tiers for GitHub Copilot auto model selection—efficiency, balance, and intelligence—so teams can control how Copilot trades off cost, response quality, and response time per prompt, with billing based on the model selected.

Allison announces new generally available GitHub Copilot usage metrics that track activity in the dedicated VS Code Agents window, including both aggregate (enterprise/org) and per-user fields for 1-day and 28-day reporting periods.

Allison announces improvements to GitHub Copilot code review, including automatic resolution of addressed review comments, smarter commit message suggestions when applying Copilot fixes, and deeper review analysis using Copilot SDK shell tools plus an ensemble approach for Lite reviews.

Tomoko Tanaka shows how her team turned event marketing runbooks into “ops as code” using GitHub Issues, GitHub Actions, and GitHub Copilot. The post breaks down the repo patterns (issue forms, labels, skills in Markdown, and a DRY_RUN switch) that automate setup, daily screening, and post-event reporting with guardrails.