GitHub has paused new Copilot Pro, Pro+, and Student sign-ups after agentic workflows pushed compute demand beyond the old plan structure. The sharper signal is economic: token-based session and weekly limits now matter separately from premium request counts.
GitHub is making third-party coding agents less static: Claude and Codex users on github.com can now choose among 4 Anthropic models and 3 OpenAI models when they launch a task. That matters because model choice changes latency, spend, and code quality far more than a small UI toggle suggests.
GitHub is turning Copilot compliance from slideware into deployable policy: US and EU data residency now covers all generally available Copilot features, and US government deployments get FedRAMP Moderate infrastructure. The practical catch is cost, with data-resident requests priced at a 1.1x model multiplier.
Long-running CLI agent work no longer has to stay pinned to one screen. GitHub's new <code>copilot --remote</code> feature mirrors a live session to the web or GitHub Mobile, where you can send follow-up commands, switch modes, and handle approvals from another device.
One of the ugliest pull-request stalls just became a button. GitHub says its new Fix with Copilot flow can resolve merge conflicts, re-check build and tests, and push the repaired branch from a cloud-based development environment.
GitHub has expanded Copilot cloud agent on GitHub Mobile beyond pull request review. Developers can now ask the agent to research a codebase, draft an implementation plan, edit on a branch, review diffs, and open a pull request from a phone when ready.
GitHub put the Copilot SDK into public preview on April 2, 2026, exposing the same runtime behind Copilot cloud agent and Copilot CLI. The SDK ships across five languages with tool use, streaming, permissions, OpenTelemetry, and BYOK support.
GitHub’s April 8 changelog for Visual Studio Code summarizes Copilot releases v1.111 through v1.115 and shows a stronger shift toward autonomous agent workflows. Key additions include Autopilot in public preview, integrated browser debugging, multimodal chat inputs, and a unified editor for instructions, agents, skills, and plugins.
GitHub used X on April 11, 2026 to highlight an internal workflow that lets AI do the repetitive accessibility triage work while humans validate fixes. The important part is not just the tooling stack, but the operational result: faster routing, tighter feedback loops, and measurable reductions in backlog and resolution time.
GitHub says Copilot cloud agent is no longer limited to pull-request workflows. The April 1 release adds branch-first execution, pre-code implementation plans, and deep repository research sessions.
GitHub said on April 7, 2026 that Copilot CLI can now use a developer’s own model provider or fully local models. The change adds Azure OpenAI, Anthropic, offline mode, and optional GitHub auth while keeping the same agentic terminal workflow.
GitHub said that starting April 24, 2026, interaction data from Copilot Free, Pro, and Pro+ users will be used to train and improve AI models unless users opt out. Business and Enterprise plans are excluded, but the change materially expands how individual-tier Copilot usage can feed back into model development.