Claude 支持回溯编辑历史消息并从该处重新对话
Claude 现在能回退到对话中任意一条消息改提示词重新跑，之后的内容自动丢弃，调试长对话方便多了。
Claude 更新后允许用户在对话中回退到任意一条消息，编辑提示词后从该处继续对话。系统会自动丢弃被编辑消息之后的内容和工具调用，避免模型被冲突的上下文干扰。团队称这是用户长期请求的功能，现已上线。
You can now go back through a conversation, edit prompts and resume the conversation from there.
It works by discarding the messages/ tool calls post the edited prompt to make sure the model doesn’t get confused.
This has been a long requested feature, happy team shipped it!
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude, 提示词工程, 编程助手.
Source attribution: curated from Vaibhav Srivastav (@reach_vb).
