Anthropic released Claude Code v2.1.319, introducing asynchronous execution for MCP tasks and enhanced configuration options for the Claude apps gateway. Key features include backgrounding MCP tool calls via `CLAUDE_CODE_DISABLE_MCP_TASK_BACKGROUND` and new `admin.pooled_conflict_rule` settings for managing multi-group budget allocation. The update also fixes numerous stability issues, including auto-mode denial explanations, diff pane errors with specific git states, and WebSocket proxy resolution failures. These changes primarily target developer experience improvements and enterprise gateway operability.
Read originalEarlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
Claude Code Releases · September 26, 2026 · Same story
Claude Code Releases · October 10, 2026 · Same story
This release quietly patches a gap in llama.cpp's OpenCL backend by adding support for the 'repeat' operation across f16, i32, i16, and bf16 types. For users relying on AMD or Intel GPUs via OpenCL rather than Vulkan or ROCm, this means fewer fallbacks to slower CPU execution for models that use these tensor operations. It’s a targeted fix that improves stability and performance on non-NVIDIA hardware without changing the core inference engine. The update also includes standard binaries for CUDA 13 and ROCm 10.0, keeping the stack current with latest driver ecosystems.
This release quietly closes the hardware gap for non-NVIDIA users by adding default support for ROCm 10.0 on both Linux and Windows, allowing AMD GPU owners to run local models without complex configuration. It also brings CUDA 13.5 builds to Ubuntu and Windows, future-proofing the toolchain for newer NVIDIA architectures while maintaining backward compatibility with CUDA 12. Apple Silicon KleidiAI is disabled in this build, a notable regression for Mac users who rely on that specific optimization. The update solidifies llama.cpp's position as the most versatile inference runtime available, covering everything from Snapdragon NPUs to Intel Arc via SYCL.
This release stabilizes the build pipeline by fixing a threading bug that caused test hangs on self-hosted runners, ensuring more reliable binaries for everyone. More importantly, it brings first-class support for ROCm 10.0 and CUDA 13 across Linux and Windows, closing the gap with NVIDIA's latest driver stacks. AMD users finally get parity with CUDA builds without manual configuration tweaks. The update also expands Apple Silicon coverage to include KleidiAI, though it remains disabled by default in this build. It’s a maintenance-heavy release that quietly modernizes the backend support matrix.