context usage in-chat notifications
维护者通常 2 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 新手友好度
- 42/100
- Issue 类型
- 功能
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- clojure
调研方向
The issue names no files or tests; start by locating how ECA handles configuration and evaluates context usage after each turn. Compare that flow with the proposed behavior: threshold messages should be appended once per threshold, reset after compaction, and remain disabled unless configured.
由索引模型根据 Issue 内容生成。
描述
What
It could be useful, if ECA could announce into the chat session itself, that the context is "getting closed to filled", allowing the current agentic flow to potentially react on that. For example, agentic task can be prompted in that way, that `if you see that we're getting close to context compaction, pause your current work and store all the precious task details into your task.md file, so it doesn't get lost on compaction".
How - configuration (very approximate, just for the general idea)
{
"contextNotifications": {
"thresholds": [70, 85],
"template": "[eca] Context at {percent}% ({used}/{limit} tokens, compaction at {compactAt}%)."
}
}
How - approximate behavior:
- ECA evaluates the context usage after each turn.
- When the usage crosses a threshold for the first time, ECA appends one message to the conversation.
- ECA appends the message. It does not rewrite earlier content. Prompt caching stays valid.
- ECA fires each threshold one time only per chat session. After a compaction, the thresholds reset.
- Without a template, ECA appends a neutral status line only.
- Without contextNotifications, the behavior does not change. The feature is off by default.
Backstory and discussion (slack) :
https://clojurians.slack.com/archives/C093426FPUG/p1789028953654579
Notes from Akiz:
Yeah, the template should be probably handled like others. I guess we can go just with one message here. But if we want to repeat when it changes from 90% to 95% for example then I would go with the repeated message that is not part of the history (which shouldn't invalidate the cache). Both is possible. Maybe the simpler approach is enough.
Maybe wait with any code analysis until memory shipsas it sounds like something it might profit from some new abstractions. I am also wondering if models will try to call eca_compact when they will see this threshold
- 主要语言
- Clojure
- 星标
- 1k
- 派生
- 82
- 平均合并
- 3 天 39 分钟
- 30 天内合并 PR
- 15
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南，环境需要你自己搭建：先看它的 README，通用步骤见我们的新手贡献指南。
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
editor-code-assistant/eca 的其他 Issue
-
bug
难度 1/5 1 小时以内 新手友好度 92/100
editor-code-assistant/eca#655 ·
维护者通常 2 天内回复
-
bug
难度 4/5 3-5 天 新手友好度 25/100
editor-code-assistant/eca#652 ·
维护者通常 2 天内回复
-
难度 5/5 一周以上 新手友好度 12/100
editor-code-assistant/eca#648 · 1 条评论 ·
维护者通常 2 天内回复
-
难度 3/5 1-2 天 新手友好度 35/100
editor-code-assistant/eca#644 · 1 条评论 ·
维护者通常 2 天内回复
-
Add the ability to see what changed in the system prompt可能已有人在做 @zikajk 于 9 天前认领。 未关闭enhancement
editor-code-assistant/eca#642 · 已指派 1 人 ·
维护者通常 2 天内回复
查看 editor-code-assistant/eca 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 75/100
NoahTheDuke/splint#57 · 1 条评论 ·
-
难度 2/5 1-3 小时 新手友好度 70/100
维护者通常 1 天内回复
-
IOP MCP
难度 2/5 1-3 小时 新手友好度 84/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 70/100
calcit-lang/calcit#2133 ·
维护者通常 1 天内回复
-
worker/start rejects middleware supplied as a Var可能已有人在做 @rajp152k 于 3 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 75/100