Coding Tools
Codex and Agent Enhancements in JetBrains IDEs
GitHub Changeloghigh confidence
Why it matters
- →Codex as an agent provider increases flexibility in task management within JetBrains IDEs.
- →Enhanced customization options with Hooks and MCP server management improve workflow efficiency.
- →Custom model support for enterprise users expands the adaptability of GitHub Copilot.
JetBrains IDEs have rolled out a significant update featuring Codex as a new agent provider in public preview. This addition allows developers to select the most suitable agent for their tasks directly within the IDE. The update also includes support for Hooks and improved MCP server management, enhancing customization capabilities. GitHub Copilot Business and Enterprise users can now configure custom models, expanding the tool's flexibility. These changes, coupled with performance and reliability improvements, aim to streamline the development process for users.
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.
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.