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 now lets users assign Dependabot alerts to AI coding agents including Copilot, Claude, and Codex. The agents can analyze the advisory, open a draft pull request, and attempt to fix test failures, but GitHub says humans still need to review the output before merging.
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.
GitHub used X to point developers to a roadmap that hardens Actions across dependency locking, policy-based execution, and runner network controls. The plan includes workflow-level dependency locks, ruleset-based execution protections, and a native egress firewall for GitHub-hosted runners.
GitHub Changelog's March 19, 2026 X post announced that GPT-5.3-Codex is the first long-term support model for Copilot Business and Copilot Enterprise. GitHub says the model launched on February 5, 2026, stays available through February 4, 2027, and becomes the new base model by May 17, 2026.
GitHub Changelog said on April 3, 2026 that GPT-5.1 Codex, GPT-5.1-Codex-Max, and GPT-5.1-Codex-Mini were deprecated across all Copilot surfaces as of April 1. GitHub tells organizations to move workflows and model policies to supported models, with GPT-5.3-Codex named as the replacement.
GitHub Changelog's April 7, 2026 X post said Copilot CLI can now connect to Azure OpenAI, Anthropic, and other OpenAI-compatible endpoints, or run fully local models instead of GitHub-hosted routing. GitHub's changelog adds that offline mode disables telemetry, unauthenticated use is possible with provider credentials alone, and built-in sub-agents inherit the chosen provider.