Coding Tools
GitHub Copilot Model Policy API GA
GitHub Changeloghigh confidence
Why it matters
- →Enables infrastructure-as-code management of AI model access across GitHub enterprises.
- →Allows programmatic enforcement of security and compliance policies at multiple hierarchy levels.
- →Reduces administrative overhead by replacing manual UI configuration with REST API automation.
GitHub has made its Copilot model policy REST API generally available, enabling programmatic management of AI model access for enterprises, teams, apps, and organizations. The update provides GET and PATCH endpoints at four distinct hierarchy levels, allowing administrators to retrieve and modify model availability settings via code. This release supports delegation strategies where enterprise policies can delegate control to specific organizations or teams depending on the configured mode. The move facilitates automated governance workflows for large-scale AI adoption.
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 Enforces Global Model Policy for Copilot
GitHub Changelog · August 26, 2026 · Same story
What happened next
- 2GitHub Copilot plugins GA with enterprise controls
GitHub Changelog · October 28, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot enterprise settings enforcement updates
3 developments
- Oct 13 · GitHub Changelog
GitHub Copilot enterprise settings enforcement updates - Oct 19 · GitHub Changelog
GitHub Copilot Model Policy API GA (This article)↳ GitHub Copilot Model Policy API GA enables programmatic enforcement of model restrictions via REST API for enterprise governance. - Oct 22 · GitHub Changelog
GitHub Copilot global default policy enforcement begins
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