Coding Tools
GitHub Copilot Adds Repository-Level Usage Metrics
GitHub Changeloghigh confidence
Why it matters
- →Provides granular insights into AI-driven coding activity at the repository level.
- →Enables targeted AI deployment and optimization within codebases.
- →Enhances understanding of Copilot's impact on development workflows.
GitHub has introduced repository-level usage metrics for its Copilot tool, providing detailed insights into AI-driven pull request activity. The new REST API endpoints allow users to access daily reports on how Copilot's coding agent and code review features are utilized within specific repositories. This enhancement offers a more granular view compared to previous organization-level metrics, enabling developers and organizations to better assess and optimize AI integration in their workflows. The update is available to enterprise and organization users 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 Copilot Enhances Usage Metrics Accuracy
GitHub Changelog · July 2, 2026 · Same story
What happened next
- 2GitHub Copilot Expands Usage Metrics Reporting
GitHub Changelog · July 28, 2026 · Same story
Follow this story
Open the full 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.