MoonshotAI / MoonshotAI/kimi-cli
使用自定义 agent 启动时未加载AGENTS.md到上下文 || AGENTS.md is not loaded into the context when starting with a custom agent
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?
1.39
Which open platform/subscription were you using?
/login
Which model were you using?
kimi-k2.6
What platform is your computer?
Microsoft Windows NT 10.0.26200.0 x64
What issue are you seeing?
当我默认启动和使用自定义agent启动时，分别询问是否加载 AGENTS.md 到上下文输出如下：
默认启动：
What steps can reproduce the bug?
自定义agent测试
What is the expected behavior?
自定义agent可以自动加载 AGENTS.md
Additional information
No response
What version of Kimi Code CLI is running?
1.39
Which open platform/subscription were you using?
/login
Which model were you using?
kimi-k2.6
What platform is your computer?
Microsoft Windows NT 10.0.26200.0 x64
What issue are you seeing?
When I start by default and when I start with a custom agent, I am asked whether to load AGENTS.md into the context and the output is as follows:
Start by default:
What steps can reproduce the bug?
Custom agent testing
What is the expected behavior?
Custom agents can automatically load AGENTS.md
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
Start by reproducing the issue with Kimi Code CLI 1.39 on Windows using the reported custom-agent startup, then compare its context-loading behavior with a default startup. The fix is complete when a custom agent automatically loads AGENTS.md into the context as expected.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cli
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100