Coding Tools
GitHub Introduces Copilot Cloud Agent Audit API
GitHub Changeloghigh confidence
Why it matters
- →Provides developers with a scalable way to audit repository configurations.
- →Enhances security and compliance management for GitHub repositories.
- →Empowers developers to maintain a robust security posture efficiently.
GitHub has introduced a new REST API that enables developers to audit their Copilot cloud agent configurations programmatically. The API, now in public preview, provides detailed information about a repository's setup, including MCP server configuration, enabled tools, and firewall settings. This tool aims to help developers understand and manage the security posture of their repositories at scale. By offering this capability, GitHub is enhancing the ability of developers to ensure their repositories are secure and compliant.
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 Introduces Copilot Agent Tasks REST API
GitHub Changelog · May 13, 2026 · Same story
What happened next
- 2GitHub Launches Agent Tasks REST API for Copilot
GitHub Changelog · June 4, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot Spaces API Now Available
3 developments
- May 18 · GitHub Changelog
GitHub Copilot Spaces API Now Available - May 18 · GitHub Changelog
GitHub Introduces Copilot Cloud Agent Audit API (This article)↳ GitHub launches Copilot Cloud Agent Audit API in public preview to programmatically check MCP server config, tools, workflows, and firewall - May 18 · GitHub Changelog
GitHub Expands Copilot Cloud Agent Model Options↳ GitHub adds Claude Haiku 4.5 and GPT-5.4-mini with a 0.33x multiplier to Copilot Cloud Agent for faster, cheaper task execution
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