anthropics / anthropics/claude-code
[BUG] Claude execution interrupted
- 主要言語
- Python
- スター
- 145k
- フォーク
- 23.1k
- PR マージ指標
- PR 指標を取得中
説明
### Preflight Checklist
- [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
### What's Wrong?
When I use claude to perform a task, it always stops automatically halfway, with the icon not flashing and turning gray. What's the reason for this? I need a prompt to continue working. The information is as follows:
Read 9 files (ctrl+o to expand)
✻ Churned for 1m 45s
※ recap: Learning the codebase by reading every source file. I've covered config, router, layout, and types. Next
up: the API layer, store modules, and utility files.
(disable recaps in /config)
### What Should Happen?
Claude, do not stop executing in the middle until the task is completed
### Error Messages/Logs
```shell
```
### Steps to Reproduce
I use the command /learn-codebase provided by the claude-mem plugin to learn project content. However, during the learning process, it suddenly stops, the icon stops flashing and turns gray, requiring someone to remind claude to continue working
### Claude Model
Other
### Is this a regression?
No, this never worked
### Last Working Version
_No response_
### Claude Code Version
V2.1.243
### Platform
Other
### Operating System
Windows
### Terminal/Shell
Windows Terminal
### Additional Information
_No response_
コントリビューションガイド
このリポジトリのコントリビューションガイドは索引されていません
調査の方向性
Start by reproducing /learn-codebase through the claude-mem plugin on Windows Terminal with Claude Code v2.1.243, and capture the execution logs when the icon turns gray after the “Churned” recap. Compare runs to determine whether the interruption is in Claude Code or the plugin; done means the learning task continues until completion or reports a clear error.
索引モデルが issue の本文から書いたものです。
評価
- 技術スタック
- python
- 領域
- cli, devtools, operating-systems
- issue の種類
- バグ
- 難易度
- 4/5
- 見積もり時間
- 3〜5日
- 活発さ
- 活発
- 明瞭さ
- 説明が足りない
- 初心者へのやさしさ
- 35/100