Anthropic has released Claude Code v2.1.280, updating the default Opus model to version 5.5 with a 1M context window and a pricing structure of $4/$20 per million tokens. The update addresses several stability issues in background subagents, specifically fixing prompt cache misses caused by tool list rebuilding and preventing lost reports during conversation compaction. UI improvements include mouse wheel support for fullscreen lists and fixes for Windows terminal character rendering and keyboard shortcuts. Additional patches resolve API errors related to proxy gateways and fix crashes associated with malformed session histories.
Read originalThis release stabilizes Claude Code by patching a cascade of crashes and session hangs that plagued recent versions. The most notable functional shift is the fallback to AGENTS.md when CLAUDE.md is absent, aligning with broader industry standards for agent configuration. Gateway improvements allow better proxy handling for egress-bound environments, while numerous fixes address edge cases in file editing, plugin management, and resume functionality. It’s a maintenance-heavy update that restores reliability rather than introducing new capabilities.
Anthropic quietly fixed a cost leak in Claude Code’s auto mode. By defaulting to the server-side classifier for API and enterprise users, the update eliminates charges for classifier overhead that previously bled into session costs. This shift means developers no longer pay double for the same logic, while still retaining the ability to opt out via environment variables if needed. The change is a subtle but necessary correction to pricing transparency in automated coding workflows.
The llama-server now binds to multiple addresses, a practical upgrade for anyone running local inference behind reverse proxies or complex network setups. This change removes the previous single-address limitation, allowing flexible routing without external workarounds. While the release includes standard binaries for CUDA 13 and ROCm 10.0, the networking feature is the real differentiator here. It makes self-hosted deployments slightly more robust for power users who need granular control over traffic flow.
This release quietly cements llama.cpp as the universal inference runtime by finally bringing full ROCm 10.0 support to both Linux and Windows, closing a long-standing gap for AMD GPU users who previously had to rely on workarounds or older versions. The inclusion of CUDA 13 builds alongside CUDA 12 ensures compatibility with the latest NVIDIA driver stacks without forcing users into beta territory. Perhaps most notably, the addition of native Snapdragon support on Linux marks a significant step toward efficient AI inference on ARM-based mobile and edge devices, expanding the hardware ecosystem beyond traditional x86 and NVIDIA dominance.
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to both Linux and Windows builds. The real surprise is the inclusion of a setup guide for Linux arm64 on Snapdragon devices, bridging the gap between mobile silicon and local LLMs. CUDA 13 support is now standard across platforms, ensuring compatibility with the latest NVIDIA stacks. While KleidiAI on macOS is disabled in this specific build, the broader platform coverage means developers no longer need to compile from source for most hardware configurations.