抄作业 / 做成了什么 / Grok Bot

做了什么

Staff: desktop and iOS have no explicit Compact or same-bot new session. Auto-summary is not compact; the full transcript is sent, and there is no model picker.

场景

周报 / 简报

资料完整度

• ✓ 作者与原链接有
• ✓ 做了什么有
• ✓ 来源原文摘录有
• — 截图 / 媒体来源未提供
• — 步骤 / 章节来源未提供
• — 提示词 / 配置原文来源未提供
• — 结果 / 数字来源未提供
• ✓ 风险提示有
• ✓ 相关条目有

— 表示来源没有给出，本站不补写。

来源原文摘录

Describe the request We are rewriting the app around this. We need you to ship the primitives so a Bot is an object, not an unbounded thread. Problem Each Bot is one unbounded thread. Every turn reloads the full transcript (user messages, agent messages, tool dumps, screenshots, agent-to-agent pings). Obsolete traffic stays in the model context forever. There is no same-agent “new session,” no compact, and no way for the Bot to drop dead messages from what the model sees. The documented workaround is spawn another Bot. That explodes the roster, splits memory, and does not fix the product.

展开全文

Rewrite (what we are building against) • Split a Bot into Identity, Working set, Archive. Stop treating the chat log as the Bot. • Identity = name, description, memory, routines, skills, connectors. Survives forever. …

摘自论坛首帖，照录原文，未翻译。

提示词

来源没有给出可直接复制的提示词原文。

怎么复制

1. 读原文：forum.cursor.com ↗
2. 把原文里的步骤/提示词整理成一条消息交给 Bot
3. 先手动跑一次，再决定频率

风险与限制

• 定时运行会持续消耗额度：频率从低开始，跑稳再加
• 作者的结果不保证能复现，以原帖为准

用量预估

用金属计算器估一下