Anthropic released Claude Code v2.1.277, focusing on stability and configuration flexibility. Key changes include support for AGENTS.md as a fallback when CLAUDE.md is missing, and enhanced proxy handling via the CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY flag. The update resolves numerous crashes related to malformed JSON configurations, session resumption errors, and plugin management issues. Additional fixes address file editing edge cases, sandbox command exemptions, and headless session cost tracking.
Read originalAnthropic 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.
This release stabilizes Claude Code by fixing crashes that occurred when resuming sessions with malformed transcripts or memory files. It also improves the developer experience by syncing skills and plugins from your claude.ai account to terminal sessions, ensuring consistency across environments. Security is tightened by preventing install scripts from running on npm-sourced plugins, while usability sees gains in artifact publishing and image handling. The update addresses critical edge cases that previously broke workflows, making the tool more reliable for daily use.
Anthropic quietly patched a critical regression in Claude Code that broke all API requests for users routing traffic through proxies or gateways. The issue stemmed from an invalid input tag 'advisor_20260301' introduced in the previous version, effectively locking out enterprise and custom infrastructure setups. This fix restores basic functionality for developers who cannot connect directly to Anthropic's endpoints, highlighting the fragility of recent CLI updates.
This release quietly closes the hardware gap for local inference by adding default builds for CUDA 13 and ROCm 10.0. NVIDIA users on newer driver stacks can finally run without workarounds, while AMD GPU owners get parity with the latest ROCm version. Apple Silicon support is explicitly disabled in this build, a notable regression for Mac users who need to wait for the next patch. The inclusion of OpenVINO and SYCL builds further cements llama.cpp as the universal runtime for diverse hardware, ensuring no major accelerator is left behind.
This release prioritizes stability over new features, addressing critical correctness issues in vector handling for GET_ROWS operations. By fixing vec4 alignment checks and updating CUDA libraries to versions 12.8 and 13.3, it ensures reliable performance across NVIDIA hardware on both Linux and Windows. The inclusion of ROCm 10.0 builds further solidifies AMD GPU support without requiring complex configuration. While no new model architectures are added, these fixes prevent silent corruption in local inference tasks that could otherwise go unnoticed.
This release finally closes a gap in how llama.cpp handles sliding window attention patterns during model conversion. Previously, loaders silently ignored array-based SWA configurations from models like OLMo2 and Gemma3n, relying on hardcoded defaults that masked potential precision loss. The new Model-Saver now explicitly writes per-layer SWA flags and MLA geometry, ensuring bit-exact roundtrips for a dozen architectures including Plamo3 and Cohere2. This matters because it guarantees that converted GGUF files preserve the exact inference behavior of their original checkpoints, eliminating silent degradation for complex attention mechanisms.