principle-guard-the-context-window
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseGuard the Context Window
守护上下文窗口
The context window is finite and non-renewable within a session. Every token should be worth its cost.
Why: Context overflow degrades reasoning quality, creates compression artifacts, and halts progress.
Pattern:
- Isolate large payloads. Route verbose outputs, screenshots, and large documents to subagents. The main context gets summaries, not raw data.
- Keep frequently used content inline. Templates and references used on every invocation belong in the skill file, not in separate files that cost a read each time.
- Size phases and cap scope. Limit files per phase, set turn budgets, account for mechanism costs.
上下文窗口是有限的，并且在一个会话内无法续期。每个 token 都应物有所值。
原因： 上下文溢出会降低推理质量、产生压缩伪影并中断进度。
模式：
- 隔离大型载荷。 将冗长输出、截图和大型文档分流给子 Agent。主上下文只接收摘要，而非原始数据。
- 将常用内容保留在上下文中。 每次调用都会使用的模板和引用应放在 skill 文件中，而不是放在每次读取都需要额外开销的独立文件中。
- 划分阶段并限制范围。 限制每个阶段处理的文件数量，设置轮次预算，并考虑机制成本。