Coding Tools
GitHub Copilot Enhances Model Selection in VS Code
GitHub Changeloghigh confidence
Why it matters
- →Enhances developer productivity by automating model selection based on task needs.
- →Offers cost efficiency and transparency in AI model usage.
- →Simplifies the coding process by reducing manual intervention in model selection.
GitHub has introduced an auto model selection feature for Copilot in VS Code, which automatically routes tasks to the most appropriate AI model. This system evaluates tasks based on complexity, reasoning needs, and other factors to ensure optimal model selection. Users can see which model was used and switch models if desired. The feature promises improved token efficiency and cost savings, with no setup required, enhancing the coding experience for developers.
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
- 1Copilot Cloud Agent Adds Auto Model Selection
GitHub Changelog · May 14, 2026 · Same story
What happened next
- 2GitHub Copilot App Now Supports Any Model Provider
Matt Wolfe · June 10, 2026 · Same story
- 3GitHub Copilot Introduces Auto Model Selection Tiers
GitHub Changelog · September 14, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot Enhances Model Selection in VS Code
3 developments
- May 20 · GitHub Changelog
GitHub Copilot Enhances Model Selection in VS Code (This article) - May 20 · GitHub Changelog
GitHub Copilot Web Limits Model Selection↳ GitHub Copilot Web removes Gemini and GPT-5.2 Codex from model selection to improve consistency. - May 21 · GitHub Changelog
GitHub Copilot for Eclipse Goes Open Source↳ GitHub open-sourced its Copilot plugin for Eclipse under the MIT license.
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