大上下文，生成太快导致前端卡死

[Passerby1011]

📦 部署环境

Docker

📦 部署模式

服务端模式(lobe-chat-database 镜像)

📌 软件版本

1.77.17

💻 系统环境

Ubuntu

🌐 浏览器

Chrome

🐛 问题描述

一个较长的上文（一条消息），大概在70k，使用gemini-flash-2.0模型，生成速度太快，导致前端界面卡死

📷 复现步骤

No response

🚦 期望结果

当上下文很长时，前端界面可以流畅一点，将更多的运算放到客户端来

📝 补充信息

No response

[lobehubbot]

👀 @Passerby1011

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

📦 Deployment environment

Docker

📦 Deployment mode

Server-side mode (lobe-chat-database mirror)

📌 Software version

1.77.17

💻 System environment

Ubuntu

🌐 Browser

Chrome

🐛 Question description

A longer text (a message), about 70k, uses the gemini-flash-2.0 model, the generation speed is too fast, causing the front-end interface to be stuck

📷 Reproduction steps

No response

🚦 Expected results

When the context is long, the front-end interface can be smoother and put more operations on the client.

📝 Supplementary information

No response