Anthropic released Claude Code v2.1.274, focusing on stability fixes for MCP integrations and session management. Key updates include resolving a bug where Streamable HTTP MCP tool calls timed out after five minutes regardless of server settings, and fixing corrupted transcripts that previously caused endless retry loops. The update also improves background agent handling during session resumption and adjusts memory pressure thresholds to prevent premature termination of long-running tasks. These changes aim to reduce interruptions for developers using complex multi-step AI workflows.
Read originalThis release stabilizes the core agent loop by fixing critical bugs in prompt caching and subagent resume logic that previously broke context reuse. Plugin management gets a significant upgrade with dynamic folder scanning, allowing developers to hot-load tools without restarting the session. The update also hardens security around symlink traversal and refines telemetry routing for enterprise gateways. While not feature-heavy, these fixes make Claude Code more reliable for complex, multi-step coding workflows.
Anthropic quietly patched a regression in Claude Code that broke LLM-gateway and proxy setups. The previous version incorrectly forced Cloud-gateway sign-in when the CLAUDE_CODE_USE_GATEWAY variable was set, even with API keys or custom auth headers configured. This update restores the expected behavior where the variable is ignored unless specific Anthropic credentials are present. Developers relying on custom authentication flows can now resume their workflows without configuration changes.
This release targets the most painful friction points in long-running coding sessions: broken prompt caching and lost context during resumption. By fixing how MCP tools and system prompts are recorded and replayed, Anthropic ensures that switching models or reconnecting doesn't wipe your conversation history or force redundant tool definitions. The addition of a maxEffortLevel setting gives developers precise control over compute costs across all cloud providers, while specific fixes for VS Code and remote sessions stabilize the daily driver experience. It’s a maintenance-heavy update that quietly restores reliability to complex workflows.
This release patches a critical remote code execution vulnerability in the llama.cpp server that allowed unauthenticated attackers to hijack memory via dangling pointers. The flaw stemmed from caching compute graphs that referenced freed buffers, enabling heap corruption and arbitrary code execution through subsequent tensor commands. By discarding cached graphs when buffers are freed, the fix forces a safe fallback to full recomputation without changing the API. This is a vital security update for anyone running the llama.cpp server remotely, closing a direct path to system compromise.
A copy-paste error in llama.cpp was corrupting matrix transpositions on Spacemit hardware, causing significant data corruption for int16 operations. This release patches the specific RVV instruction call to ensure correct computation on these RISC-V based chips. While niche, it prevents silent inference failures for users relying on this specific accelerator architecture. The update also ships binaries for CUDA 13 and ROCm 10.0, keeping the runtime current with latest driver ecosystems.
This release quietly closes the hardware gap for local inference by adding native builds for CUDA 13 and ROCm 10.0 alongside existing CUDA 12 binaries. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get hardware acceleration, while Apple Silicon support remains available but explicitly disabled in this specific binary set. The simultaneous availability of these distinct backend versions means the runtime is now truly agnostic to the underlying GPU architecture. It is a pragmatic update that removes friction for anyone trying to run models on modern, non-CUDA-12 hardware.