GitHub Copilot May 2026 Update Adds Planning and Code Review Tools to Visual Studio
GitHub has released its May 2026 update for Copilot in Visual Studio 2026, introducing new tooling for planning, code review, and work management. The update is available to all GitHub Copilot users.
GitHub Copilot May 2026 Update Adds Planning and Code Review Tools to Visual Studio
GitHub has released its May 2026 update for Copilot in Visual Studio 2026, introducing new capabilities for planning, code review, and work management.
What's New
According to GitHub, the update focuses on three core areas:
- Planning tools: New features to help developers plan their work within Visual Studio
- Code review capabilities: Enhanced tooling for reviewing code changes
- Work management: Improved features for managing development tasks
The update is available to all GitHub Copilot users running Visual Studio 2026. GitHub has not disclosed specific details about the individual features or how they integrate with existing Copilot functionality.
Deployment
The May 2026 update follows GitHub's regular monthly release cadence for Copilot improvements across its supported IDEs. Visual Studio 2026 users with active Copilot subscriptions should receive the update automatically.
GitHub Copilot is available in two subscription tiers: Copilot Individual at $10/month and Copilot Business at $19/user/month. Enterprise customers have access to Copilot Enterprise with additional features.
What This Means
GitHub continues its pattern of incremental monthly updates to Copilot across different IDEs. The focus on planning and review tools suggests GitHub is expanding beyond code completion into broader software development workflow assistance. However, without specific feature details or performance metrics, it's difficult to assess the practical impact of these additions compared to existing Visual Studio features or competing AI coding assistants from Tabnine, Codeium, and others.
Related Articles
NVIDIA releases 96 GiB NVFP4 build of Qwen3.8-Flash-Next for single-GPU Blackwell and DGX Spark
NVIDIA has published Qwen3.8-Flash-Next-FP4-Local, a 96 GiB NVFP4 quantization of Alibaba's 125B-parameter MoE model, on Hugging Face. NVIDIA reports 91.5% on GPQA Diamond versus 92.2% for BF16. It requires NVIDIA's custom vLLM containers because upstream support has not landed.
Hugging Face Transformers v5.20.1 adds Reflection AI's Beam model and fixes loading on older torch
Hugging Face's Transformers v5.20.1 adds Beam, a model from Reflection AI that the release notes describe as token-efficient, frontier-scale, and aimed at coding and agentic work. The patch also fixes a regression that broke model loading on older torch versions. Beam's specifications and pricing were not disclosed in the release notes.
Cline v4.1.25 adds cloud sandbox sessions and makes Gemini 4 Argon the default model for its own provider
Cline v4.1.25 introduces Cline Cloud sessions, which run tasks in a hosted sandbox on a chosen GitHub repo and branch, and is rolling out gradually. The release also changes default models for more than 25 providers and fixes a five-minute timeout affecting local models in LM Studio and Ollama.
Google rolls out Gemini 4 Argon to Antigravity for AI Pro and Ultra subscribers with separate weekly quota
Google is rolling out Gemini 4 Argon, its latest flagship model, to the Antigravity agentic development platform for AI Pro and AI Ultra subscribers. Argon has a separate weekly-only quota on top of the existing Gemini 3.8 Flash quota. Google also published internal case studies, which are company-reported and not independently verified.
Comments
Loading...