MoonshotAI / MoonshotAI/kimi-cli
开启Plan模式后下次交互会产生乱码 || After turning on Plan mode, the next interaction will produce garbled characters
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.4k
- Forks
- 1.3k
- Avg merge
- 9h 47m
- Merged PRs (30d)
- 2
Description
What version of Kimi Code CLI is running?
kimi code for vscode最新版
Which open platform/subscription were you using?
直接登录的账户
Which model were you using?
2.6
What platform is your computer?
windows
What issue are you seeing?
kimi code for vscode开启Plan模式后下次交互会产生乱码
What steps can reproduce the bug?
kimi code只要进入过Plan模式就会导致下一次用户主动发起的对话会产生下面这种乱码,不论是kimi自己请求进入还是我手动点击plan模式按钮。kimi自己请求进入的情况下kimi自己这一次的任务是没有问题的,但是我开启的下一次对话就会变成这样。这种情况我已经遇到了很多次了,浪费了我很多token。
What is the expected behavior?
No response
Additional information
kimi code for vscode latest version
Which open platform/subscription were you using?
Direct login account
Which model were you using?
2.6
What platform is your computer?
windows
What issue are you seeing?
kimi code for vscode will produce garbled characters after the next interaction after turning on Plan mode
What steps can reproduce the bug?
As long as kimi code has entered Plan mode, the next conversation initiated by the user will produce the following garbled code, whether Kimi requests entry or I manually click the plan mode button. If kimi requests entry, there is no problem with kimi's mission this time, but the next conversation I open will become like this. I have encountered this situation many times and wasted a lot of my tokens.
What is the expected behavior?
No response
Additional information
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No source file or test is named. Reproduce on Windows in Kimi Code for VSCode with model 2.6 by entering Plan mode, then starting the next user-initiated conversation; trace the Plan-mode state and subsequent interaction handling. Done means the next conversation no longer displays garbled characters, whether Plan mode was entered manually or requested by Kimi.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, vscode
- Domain
- cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100