Coding Tools
GitHub Copilot Expands Usage Metrics Reporting
GitHub Changeloghigh confidence
Why it matters
- →Provides detailed insights into individual user activity within the Copilot app.
- →Allows comparison of Copilot app usage with other coding surfaces.
- →Enhances understanding of AI-assisted coding's impact within organizations.
GitHub has expanded its Copilot usage metrics API to provide more detailed insights into individual user activity within the Copilot app. This update allows enterprise owners and billing managers to see which users are active, what code is being generated, and how it compares to other coding surfaces like IDEs. Previously, Copilot app usage was only visible at a high level, but now it includes detailed breakdowns by feature, model, and language. This enhancement helps organizations better understand and measure the impact of AI-assisted coding.
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 Releases Copilot App for Desktop
Matt Wolfe · June 5, 2026 · Same story
- 2GitHub Copilot Enhances Usage Metrics Accuracy
GitHub Changelog · July 2, 2026 · Same story
- 3GitHub Copilot app now in usage metrics API
GitHub Changelog · July 17, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot App Gains Independent Access Policy
3 developments
- Jul 27 · GitHub Changelog
GitHub Copilot App Gains Independent Access Policy - Jul 28 · GitHub Changelog
GitHub Copilot Expands Usage Metrics Reporting (This article)↳ GitHub Copilot now offers granular usage metrics by feature, model, and language for individual users via its API. - Jul 29 · GitHub Changelog
GitHub Automates Copilot Model Enablement↳ GitHub defaults new Copilot models on for Business and Enterprise users starting August 26 unless admins opt out.
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