Coding Tools
GitHub Copilot Enhances Context Windows and Reasoning
GitHub Changeloghigh confidence
Why it matters
- →Larger context windows enable handling of more complex codebases and projects.
- →Configurable reasoning levels provide flexibility in managing speed and depth of AI assistance.
- →These enhancements improve the utility of GitHub Copilot for advanced coding tasks.
GitHub Copilot has expanded its capabilities with larger context windows and configurable reasoning levels. The new one-million-token context window allows users to work with larger codebases and complex projects without losing context. Additionally, configurable reasoning levels enable users to adjust the balance between speed and depth for challenging tasks. These features are currently available in VS Code, Copilot CLI, and the GitHub Copilot app, with plans to expand further. While these enhancements offer significant benefits, they also require more AI credits per use.
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 Copilot Enhances VS Code with New Features
GitHub Changelog · May 6, 2026 · Same story
- 2GitHub Copilot Enhances Code Review with New Features
GitHub Changelog · June 2, 2026 · Same story
What happened next
- 3GitHub Releases Copilot App for Desktop
Matt Wolfe · June 5, 2026 · Same story
Follow this story
Open the full story →GitHub Introduces Targeted Copilot Model Rules
3 developments
- May 26 · GitHub Changelog
GitHub Introduces Targeted Copilot Model Rules - Jun 2 · GitHub Changelog
GitHub Copilot Deprecates GPT-4.1 Model↳ GitHub deprecates GPT-4.1 across all Copilot experiences, requiring users to switch to supported models. - Jun 4 · GitHub Changelog
GitHub Copilot Enhances Context Windows and Reasoning (This article)↳ GitHub Copilot adds one-million-token context windows and configurable reasoning levels to handle complex projects.
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