Summary
Claude Code v2.1.237 fixes prompt caching for sessions that use an LLM gateway or custom base URL. It also adds a selectable Concise style that leads with results and suppresses preamble and narration while preserving the work itself.
Why it matters
The caching fix targets a cost-sensitive path for teams routing Claude Code through gateways, while the output mode changes the interaction shape of agentic coding sessions.
Related coverage
- Cline Desktop adds local-to-cloud agent handoff
- Slack introduces shared code channels for team-visible coding agents
- OpenCode adds native Cloudflare AI Gateway passthroughs