Coding Tools
GitHub Copilot Expands Code Review Capabilities
GitHub Changeloghigh confidence
Why it matters
- →Copilot can now handle larger and more complex pull requests, increasing its utility for developers.
- →Organizations can use Copilot code review without needing individual licenses, simplifying billing.
- →Feedback on comment resolution helps improve the tool's accuracy and effectiveness.
GitHub has enhanced its Copilot code review tool, enabling it to review pull requests from bots and handle very large pull requests without previous size limitations. This update allows organizations to use Copilot code review without individual licenses, billing directly to the organization. Users can now specify reasons for resolving comments, offering feedback to improve the tool. These changes make Copilot code review more adaptable and efficient for large projects and automated processes.
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.
How we got here
- 1GitHub Enhances Copilot Code Review with New Features
GitHub Changelog · May 19, 2026 · Same story
- 2GitHub Copilot Enhances Code Review with New Features
GitHub Changelog · June 2, 2026 · Same story
Follow this story
Open the full story →Slack introduces collaborative vibe-coding channels
5 developments
- Aug 20 · The Verge AI
Slack introduces collaborative vibe-coding channels - Aug 21 · The Rundown AI
Slack introduces collaborative coding feature - Aug 21 · GitHub Changelog
GitHub Copilot Integrates with Slack in Public Preview↳ GitHub Copilot integrates with Slack in public preview, allowing users to mention @GitHub for AI coding assistance and task management. - Aug 25 · GitHub Changelog
GitHub Copilot App Adds Customize Tab↳ GitHub Copilot adds a Customize tab integrating MCP servers, plugins, skills, and canvases into one interface. - Aug 27 · GitHub Changelog
GitHub Copilot Expands Code Review Capabilities (This article)↳ Copilot Code Review now handles bot-authored PRs and large files, allows org-level billing without individual licenses, and lets users speci
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