Anthropic has released Claude Code v2.1.267, focusing on stability improvements for long-running development sessions and multi-provider configurations. Key updates include a new maxEffortLevel setting to cap compute effort across Bedrock, Vertex, and Foundry, alongside critical fixes for prompt-cache misses when resuming sessions or switching models. The update also resolves issues with MCP tool definitions being dropped during reconnections and improves error handling for artifact publishing and credential expiration. Additional patches address VS Code extension hangs, remote session stability, and UI rendering glitches in mobile and web clients.
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 quietly fixes critical permission bypasses that could have allowed dangerous shell commands to slip through the safety net. By tightening how Bash permissions are analyzed and correcting memory directory handling, Anthropic is hardening the tool against accidental data leaks or destructive operations. The update also resolves persistent authentication failures on enterprise cloud platforms like Bedrock and Vertex, ensuring smoother workflows for teams relying on managed settings. These fixes stabilize the agent environment without adding new features.
This release candidate addresses a critical configuration gap for hybrid models in vLLM by enabling the dense prefix cache by default. Previously, these mixed-precision or multi-head architectures likely suffered from inefficient memory usage or required manual flags to achieve optimal performance. By automating this optimization, the update ensures that users running complex model topologies get better throughput out of the box without tweaking internal parameters. It is a quiet but necessary step toward making vLLM robust for heterogeneous hardware setups.
This release quietly extends llama.cpp's hardware support to the latest driver stacks, adding official binaries for ROCm 10.0 and CUDA 13 across Linux and Windows. For AMD users, this means native compatibility with newer GPU architectures without manual compilation tweaks, while NVIDIA users gain access to the latest CUDA runtime optimizations. The inclusion of WebGPU in CI signals ongoing work toward browser-based inference, though it remains a background effort for now. There are no new model formats or quantization methods here, just broader infrastructure coverage that keeps llama.cpp relevant as hardware evolves.
A critical precision bug in llama.cpp’s Apple Silicon backend has been patched, resolving total inference failures on models with high-activation ranges like Mistral Small 4. The issue stemmed from f16 saturation during matrix multiplication, which turned entire output tensors into NaN values for inputs exceeding ~32 tokens. By implementing an exact, power-of-two rescaling mechanism in the Metal kernel, the fix restores correctness without significant performance penalties. This ensures local inference on M-series chips remains viable for complex MoE architectures that previously crashed.