Coding Tools
GitHub Copilot Enhances Code Review with New Features
GitHub Changeloghigh confidence
Why it matters
- →Enhances code review efficiency by integrating team-specific tools and standards.
- →Allows for scalable review depth, aligning with code complexity and business value.
- →Reduces bottlenecks in code review processes, freeing up senior engineers for other tasks.
GitHub has announced enhancements to its Copilot code review tool, now in public preview. The update introduces agent skills and MCP support, allowing Copilot to integrate with team-specific tools and standards. A new medium analysis tier is also available, routing complex pull requests to a higher-reasoning model for deeper analysis. These features aim to streamline code reviews by reducing reliance on senior engineers and aligning review intensity with code complexity. The update is available for Copilot Pro, Pro+, Business, and Enterprise users.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
What happened next
- 1GitHub Copilot Enhances Code Review with Agent Skills
GitHub Changelog · July 29, 2026 · Same story
- 2GitHub Copilot Expands Code Review Capabilities
GitHub Changelog · August 27, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot Introduces Usage-Based Billing
5 developments
- Jun 1 · GitHub Changelog
GitHub Copilot Introduces Usage-Based Billing - Jun 2 · AI News
GitHub Copilot shifts to token-based billing - Jun 2 · GitHub Changelog
GitHub Copilot Enhances Code Review with New Features (This article)↳ GitHub Copilot adds a medium analysis tier and MCP support to adapt review depth and pull context from third-party platforms. - Jun 2 · GitHub Changelog
GitHub Copilot Code Review Debuts for Azure Repos - Jun 7 · TechCrunch AI
Microsoft's GitHub Copilot Pricing Sparks 'Tokenpocalypse' Concerns↳ Critics dub Copilot's token-based billing the 'Tokenpocalypse' amid fears of broader AI price hikes as firms seek profitability.
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases