-
Notifications
You must be signed in to change notification settings - Fork 60k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug] 当主动中断生成之后重新编辑输入,之前的输入会被加入到履历里面 #6052
Comments
Title: [Bug] When the automatic interrupt is generated and the input is re-edited, the previous input will be added to the history. 📦 Deployment methodVercel 📌 Software version2.15.8 💻 System environmentmacOS 📌 System version15.1 🌐 BrowserChrome 📌 Browser versionVersion 130.0.6723.117 (Official Build) (arm64) 🐛 Problem descriptionWhen the input is re-edited after the automatic interruption is generated, the previous input will be added to the history. 📷 Steps to reproduceFirst copy a large paragraph, and then click Stop when the AI is generated to interrupt the generation. 🚦 Expected resultsAt this time, the only message for User in the message list is "What did I just say?". AI should not see messages before editing. If it summarizes the previous message, it means that the text before editing is also regarded as a message. 📝 Supplementary informationNo response |
嗯这就合理了 |
Well, that makes sense |
📦 部署方式
Vercel
📌 软件版本
2.15.8
💻 系统环境
macOS
📌 系统版本
15.1
🌐 浏览器
Chrome
📌 浏览器版本
Version 130.0.6723.117 (Official Build) (arm64)
🐛 问题描述
当主动中断生成之后重新编辑输入,之前的输入会被加入到履历里面
📷 复现步骤
先复制一大段话,然后在AI 生成的时候点击终止打断生成。
然后编辑输入的那一段话,改成「我刚才说了什么?」,再重新生成。
此时,输出会是之前复制的那一大段话的总结。
🚦 期望结果
这个时候消息列表里面 User 的消息就只有「我刚才说了什么?」。AI 不应该看到编辑之前的消息。如果它总结了之前的消息的话,说明把编辑前的文本也当做了一条消息。
📝 补充信息
No response
The text was updated successfully, but these errors were encountered: