Coding Tools
GitHub Copilot Chat Auto Mode Now Available
GitHub Changeloghigh confidence
Why it matters
- →Auto mode optimizes token usage and response quality by dynamically selecting models.
- →It provides flexibility for developers by allowing manual model selection when needed.
- →The feature respects user and admin settings, ensuring compliance with organizational policies.
GitHub has introduced an auto mode for Copilot Chat, now available to all users on github.com and the GitHub mobile app. This feature dynamically selects the most suitable AI model based on the complexity of user requests and model availability, optimizing for both cost and response quality. Users can still manually select models if desired, and the auto mode respects existing user and administrator settings. This update is designed to enhance the efficiency and adaptability of Copilot Chat 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
- 1GitHub Copilot Enhances Web Chat Experience
GitHub Changelog · May 18, 2026 · Same story
- 2GitHub Copilot App Now Supports Any Model Provider
Matt Wolfe · June 10, 2026 · Related
What happened next
- 3GitHub Copilot Chat Enhances User Controls
GitHub Changelog · August 10, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot Chat Enhances Agent Session Management
2 developments
- Jun 10 · GitHub Changelog
GitHub Copilot Chat Enhances Agent Session Management - Jun 17 · GitHub Changelog
GitHub Copilot Chat Auto Mode Now Available (This article)↳ GitHub Copilot Chat now features an auto mode that dynamically selects models like Claude Sonnet 4.6 or GPT-5.4 based on complexity to optim
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