Anthropic has released Claude Code v2.1.287, introducing 'Claude Mods' that enable plugins to modify deeper behavioral aspects of the agent. A new built-in mod, 'You should know,' acts as a side agent to flag potential errors or oversights during coding sessions. The update also resolves numerous stability bugs affecting remote control connections, session persistence, and cloud sync reliability. Accessibility improvements include fixes for screen reader mode, ensuring better navigation and feedback for visually impaired users.
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 · July 4, 2026 · Same story
Claude Code Releases · July 15, 2026 · Same story
Duncan Rogoff · August 10, 2026 · Same story
Anthropic quietly fixed a critical credential leakage bug where MCP error messages were exposing raw API keys in plaintext logs. Beyond the security patch, this release stabilizes the notoriously fragile background agent system by fixing subagent hand-offs and connection stalls that previously caused silent failures. The update also tightens session management for cloud environments, ensuring large transcripts actually load instead of hanging indefinitely. It’s a maintenance-heavy release, but essential for anyone running complex, multi-step automated workflows.
Anthropic quietly upgrades its local coding agent with Sonnet 5.5 as the new default, bringing a massive 1M context window to developers' terminals. This isn't just a model swap; it fundamentally changes how much codebase history you can keep in memory without manual chunking. The release also patches critical stability issues like malformed image crashes and broken MCP reconnections, making the tool significantly more reliable for complex workflows. For builders, this means deeper context awareness and fewer interruptions during long coding sessions.
This release prioritizes security hygiene and session reliability over new features. The addition of CLAUDE_CODE_DISABLE_WEB_FETCH is a critical control for enterprise environments needing to restrict external data access. Bug fixes address subtle race conditions in cloud sessions and artifact publishing that could lead to data loss or incorrect state. SSH and plugin installation issues are resolved, ensuring smoother remote workflows. It’s a maintenance update that tightens the tool's operational boundaries.
The v0.31.0rc3 release of vLLM brings a critical infrastructure tweak to the new Model Runner V2: support for randomized dummy inputs. This isn't a feature for end-users but a developer-facing fix that stabilizes how the runner handles initial tensor shapes during compilation and warm-up phases. By allowing randomized inputs, it reduces the likelihood of shape-mismatch errors when tracing models with dynamic dimensions. For builders running large-scale inference workloads, this means fewer silent failures and more robust model loading sequences in production environments.
This release quietly expands llama.cpp's hardware reach with two major additions: ROCm 10.0 for AMD GPUs and native support for Linux arm64 Snapdragon devices. The inclusion of ROCm 10 is significant, as it brings AMD users closer to parity with CUDA in terms of supported versions, reducing the friction for local inference on non-NVIDIA hardware. Meanwhile, Snapdragon support opens up a new class of mobile AI acceleration, allowing developers to leverage Adreno GPUs and Hexagon NPUs directly. While Apple Silicon builds have KleidiAI disabled by default, the core value here is the broadening of accessible compute backends without requiring complex custom compilation.
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who previously lagged behind NVIDIA. The standout addition is native support for Linux arm64 Snapdragon devices, enabling local AI on mobile-class silicon with CPU, Adreno GPU, and Hexagon NPU acceleration. While KleidiAI on Apple Silicon is currently disabled in this build, the broader expansion to diverse accelerators means developers no longer need to compile from source to target non-NVIDIA hardware. The world now has a single binary ecosystem that runs everywhere from x86 servers to ARM mobile chips.