Ah apologies, effort levels not breaking the prompt cache is live on API but not yet on Claude Code. Should be live within a day or so, will QT when it’s ready. Was OOO and did not realize this didn’t go out with the…

Anthropic 的 Claude 模型已支持“降低推理 effort 时不破坏 prompt cache”的新机制,但该功能目前只在 API 上线,尚未同步到 Claude Code 客户端。官方预计一两天内补发,这直接影响开发者调用成本和缓存命中效率。








