Jev 101
开始指南
搜索
中文 EN

使用案例 agent-context-compaction

Agents ✦ 86outlineAuthor-reported — measure on your traces

原文保留的上下文压缩

对 tool 历史 keep/delete；保留段原文拼接。

Who: Coding-agent / long-session product teams. Steps: (1) Candidate tool-call/result blocks as state. (2) Noul/Choice keep vs delete/truncate. (3) Code splices kept text verbatim (no rewrite summary). Expected effect: shrink context without lossy paraphrase of kept spans (author claim). Caveat: keeping text verbatim ≠ proving omitted history was unnecessary.

来源：tamaratran/fast-jev-compaction ↗ 文档 / 来源 ↗
1

复制提示词（保留英文原文效果最好）。

2

在代码里实现——调用 System One / Jev，由你的程序组合答案。

3

回答它的设置问题——大多数提示词会先采访你，然后进入固定节奏。

提示词

提示词 
Audience: coding-agent / long-session products.
Steps:
1) Snapshot tool-call/result blocks.
2) Noul/Choice: keep | delete | truncate.
3) Code splices kept text verbatim — no summary rewrite of kept spans.
Expected effect: smaller context with verbatim retention (author claim).
Caveat: omit ≠ proven unnecessary.

需要授权：typesafe-sdkcoding-agent

它是怎么搭起来的

以下说明为英文原文（来自社区作者），提示词本身建议保留英文。

Sources: fast-jev-compaction · cobanov “Context and compaction” in awesome-jev · aliaihub agent-supervision showcase.

Keep verbatim spans the agent must not invent. Sibling pattern: tool-result sieve. Compaction quality claims from community repos are author-reported.

Sources (wave-2 deepen)

为什么它好用

Decision model chooses what stays; code owns transcript bytes.

本案例收集自公开的 Jev 社区，版权归原作者所有。提示词属于参考资料：运行前请先审阅内容， 并且不要让 bot 超出你实际授予的权限行事。