Suddenly encountering API Error: 400 while using Claude Code, making conversations unusable? Even the built-in /resume command fails to restore functionality. This article dives deep into the root cause: Claude’s extended thinking mode generates unmodifiable thinking blocks, and when subsequent requests attempt to modify these blocks, a 400 error is triggered. The article provides two solutions: first, creating a custom /resume-new command that bypasses the issue by reading only conversation summaries instead of complete history; second, restoring conversations after disabling thinking mode. The /resume-new command is more elegant, as it doesn’t inherit problematic history and can proactively provide context introduction. The article details the creation method, execution flow, and differences from the built-in /resume, offering a practical guide for developers facing the same issue.
Original link:Linux.do
最新评论
I don't think the title of your article matches the content lol. Just kidding, mainly because I had some doubts after reading the article.
这个AI状态研究很深入,数据量也很大,很有参考价值。
我偶尔阅读 这个旅游网站。激励人心查看路线。
文章内容很有深度,AI模型的发展趋势值得关注。
内容丰富,对未来趋势分析得挺到位的。
Thank you for your sharing. I am worried that I lack creative ideas. It is your article that makes me full of hope. Thank you. But, I have a question, can you help me?
光纤技术真厉害,文章解析得挺透彻的。
文章内容很实用,想了解更多相关技巧。