Claude Code 2.1.304 adds guided /auto-mode-setup and warns Pro/Max users before resuming an inactive conversation would eat into the 5-hour usage limit

Claude Code v2.1.304 was published to npm on Oct 19, 2026 (19:47 UTC). The headline addition is /auto-mode-setup, a guided setup that reads your project and recent sessions to teach auto mode about your environment; it now also works on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled sessions, where enterprises often run Claude Code. A new /claude-api managed-agents-secure command compares a Managed Agents agent's settings with Anthropic's published security guide and reports without changing anything. Pro and Max users now get a warning when resuming an inactive conversation would use a noticeable share of the 5-hour usage limit, with the option to start fresh and let Claude look up the old conversation instead. Mods gain decider: "person" (only a human permission dialog or host callback may approve; otherwise refused) and e.isReadOnly in tool.check. The release fixes roughly 40 issues, notably claude --worktree removing the worktree and its branch without asking when HEAD was detached or on another branch, which could lose commits, and CLAUDE_CODE_AUTO_COMPACT_WINDOW=200k silently setting a 100K window. No benchmarks were published. Practical steps: run /auto-mode-setup in your repo, audit Managed Agents with the new check, and upgrade promptly if you rely on --worktree.