Coding Tools
GitHub Copilot deprecates legacy models in Oct 2026
GitHub Changeloghigh confidence
Why it matters
- →Developers must verify Copilot settings to avoid service disruption after the October 19 cutoff.
- →Enterprise admins need to audit model policies to ensure team access to supported architectures.
- →The deprecation marks a consolidation of GitHub's inference stack, phasing out legacy model paths.
GitHub has deprecated several older Copilot models effective October 19, 2026, affecting all major usage modes including chat, inline edits, and agent interactions. The company announced this change on September 18, urging users to update their workflows and integrations to utilize currently supported models. Enterprise administrators are advised to check their model policies in Copilot settings to ensure alternative models are enabled for their teams. No automatic removal occurs, but functionality may be impacted if unsupported models remain selected.
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 Deprecates Legacy Models in October 2026
GitHub Changelog · September 18, 2026 · Same story
- 2GitHub Copilot deprecates specific models
GitHub Changelog · October 2, 2026 · Same story
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.