Coding Tools
GitHub Copilot adds feature-level engagement metrics
GitHub Changeloghigh confidence
Why it matters
- →Enables precise measurement of which Copilot features drive actual developer productivity.
- →Distinguishes between passive automation and active agent usage for better ROI analysis.
- →Provides rolling population data for more stable adoption trend tracking.
GitHub has updated its Copilot impact dashboard and associated APIs to display detailed feature engagement metrics for enterprise administrators. The update distinguishes between passive features, such as automatic code reviews, and active tools like agent edits and the CLI, providing a clearer picture of developer adoption. Additionally, AI adoption phase reporting now includes the full rolling 28-day population for each phase, offering a more stable metric than previous daily-active-only counts. These changes are available to enterprise owners and billing managers with the appropriate permissions.
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 Enhances AI Adoption Metrics for Enterprises
GitHub Changelog · June 26, 2026 · Same story
- 2Copilot API Adds Review Metrics for AI Adoption
GitHub Changelog · July 8, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot CLI adds agentic usage metrics
3 developments
- Sep 17 · GitHub Changelog
GitHub Copilot CLI adds agentic usage metrics - Sep 17 · GitHub Changelog
GitHub Copilot adds feature-level engagement metrics (This article)↳ GitHub Copilot introduces feature-level engagement metrics to distinguish passive code reviews from active agent edits and CLI usage for ent - Sep 18 · GitHub Changelog
GitHub Copilot adds model tiers and Sentry integration↳ GitHub Copilot introduces efficiency, balance, and intelligence tiers for cost-performance control alongside Sentry integration to turn cras
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