MoonshotAI / MoonshotAI/kimi-cli
1.44.0版本 在长对话中，注意力集中在意图实现上，把"读取规范"当成了背景噪音忽略agent.md中的规定 || Version 1.44.0 In a long conversation, attention is focused on intent implementation, treating "reading specifications" as background noise and ignoring the regulations in agent.md
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?
1.44.0
Which open platform/subscription were you using?
/login
Which model were you using?
kimi-for-coding
What platform is your computer?
No response
What issue are you seeing?
使用zed打开最新版的kimicodecli，在发送意图后，没有自动读取agentmd文件中的规定信息，直接进行了问题处理
What steps can reproduce the bug?
使用zed打开最新版的kimicodecli，在发送意图后，没有自动读取agentmd文件中的规定信息，直接进行了问题处理
What is the expected behavior?
No response
Additional information
No response
What version of Kimi Code CLI is running?
1.44.0
Which open platform/subscription were you using?
/login
Which model were you using?
kimi-for-coding
What platform is your computer?
No response
What issue are you seeing?
Use zed to open the latest version of kimicodecli. After sending the intention, the specified information in the agentmd file is not automatically read, and the problem is solved directly.
What steps can reproduce the bug?
Use zed to open the latest version of kimicodecli. After sending the intention, the specified information in the agentmd file is not automatically read, and the problem is solved directly.
What is the expected behavior?
No response
Additional information
No response
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
Reproduce the issue by running Kimi Code CLI 1.44.0 through Zed with an agent.md file and a long conversation. First verify whether the file is read after the initial intent, then compare behavior in a shorter conversation. Done means the agent.md instructions are consistently applied instead of being skipped during long conversations.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 32/100