Claude Code v2.1.304 introduces the /auto-mode-setup command. It reads your project structure and session history to configure auto mode automatically, and adds Quick, Standard, and Deep review levels configurable per organization and per repository.
Claude Code Review reached general availability on October 15 for Team and Enterprise plans, enabling automatic PR reviews with Quick, Standard, or Deep levels. Google embedded Gemini into Android Messages to detect scam texts in real time using Private AI Compute. Anthropic launched Claude Haiku 5.5 β its fastest and most affordable small model yet, with a 1M-token context window.
Claude Code 2.1.292 adds an effort parameter to the Agent tool, letting you run subagents at five levels β low through max β to balance cost and quality per task. The release also adds a --marketplace flag to plugin install, letting you register the marketplace and install a plugin in a single command.
Claude Code 2.1.290 introduces the "You Should Know" built-in mod β a side agent that catches what both you and Claude might miss. A new managed agents onboarding command lets you bootstrap multi-agent architectures with a single line. VS Code users get a visual Agent Map showing every sub-agent at a glance.
Claude Code 2.1.288 significantly improves smart resume and recovery flows. Sessions interrupted mid-task restore context more accurately, plugin and MCP error messages are clearer, and stability is improved across cloud, SDK, screen reader, and terminal environments.