Coding Tools
GitHub Enhances Copilot Cloud Agent Configuration
GitHub Changeloghigh confidence
Why it matters
- →Enables organization-level management of secrets and variables for Copilot cloud agent.
- →Reduces redundancy by allowing shared configurations across repositories.
- →Simplifies large-scale configuration management for developers.
GitHub has improved the configuration of its Copilot cloud agent by adding dedicated 'Agents' secrets and variables. This change allows developers to manage these settings at the organization level, facilitating easier sharing across repositories. Previously, configurations had to be set up for each repository individually, which was inefficient for larger organizations. This update simplifies the process, making it easier to manage access to private resources and configure MCP servers across multiple repositories.
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.
What happened next
- 1GitHub Introduces Copilot Cloud Agent Audit API
GitHub Changelog · May 18, 2026 · Same story
- 2GitHub's Copilot Cloud Agent Now Available for Linear
GitHub Changelog · July 23, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot CLI Plugins Enter Public Preview
3 developments
- May 6 · GitHub Changelog
GitHub Copilot CLI Plugins Enter Public Preview - May 8 · GitHub Changelog
GitHub Enhances Copilot Cloud Agent Configuration (This article)↳ GitHub adds organization-level secrets and variables to streamline Copilot cloud agent configuration across multiple repositories. - May 12 · GitHub Changelog
GitHub Enhances Copilot Code Review Comments↳ Copilot code review now uses severity labels and groups similar comments to reduce redundancy.
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