Claude Code 2.1.237 Ships a Concise Output Style and Fixes Gateway Caching
Claude Code 2.1.237 adds a built-in Concise output style that skips preamble and narration while doing the same work, and fixes prompt caching for sessions using an LLM gateway or custom base URL.
What it is
Claude Code 2.1.237 is the latest patch release of Anthropic's terminal coding agent.
What it does
It introduces a selectable Concise output style, toggled under Output style in /config, that has Claude lead with results instead of explaining itself first. It also fixes a bug where prompt caching silently broke for anyone routing requests through an LLM gateway or a custom base URL, unlike the default direct-to-Anthropic setup where caching worked fine.
Why it matters
Anyone running Claude Code behind a corporate proxy or gateway was quietly eating full-price tokens instead of cached ones, so this is a real cost fix, not just cosmetic. The Concise style is a small but welcome option for people who find the narration noisy in scripted or CI contexts.
How to use it
Update to 2.1.237, open /config, and switch Output style to Concise if you want less preamble; the gateway caching fix applies automatically with no configuration needed.
Claude Code 2.1.260 Adds a Live Diff Panel and Prompt-Cache Miss Reasons
Claude Code 2.1.260 adds a toggleable diff panel showing uncommitted changes beside the conversation and surfaces the likely cause of prompt-cache misses in /cost and the status line.
/skill-doctor: Claude Code Tells You Which Skills It Never Touched
Claude Code 2.1.261 adds a /skill-doctor command that reports which loaded skills went unused, plus configurable limits for how much Bash and task output Claude sees inline.
Claude Code 2.1.238: Readline Keybindings and a Token-Minting Hook for Plugins
Claude Code 2.1.238 adds a headersHelper setting that runs a command to mint short-lived auth headers for private plugin marketplace fetches, plus an optional readline-style Ctrl+W keybinding.