MoonshotAI / MoonshotAI/kimi-code
misleading instruction in system prompt
Open
Beginner friendly
Nobody has claimed this yet.
bug
- Dominant language
- TypeScript
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 11h 53m
- Merged PRs (30d)
- 350
Description
What version of Kimi Code is running?
0.28.1
Which open platform/subscription were you using?
none
Which model were you using?
deepseek-v4-flash
What platform is your computer?
Linux 7.1.3-arch1-3 x86_64 unknown
What issue are you seeing?
The agent speaks Chinese due to this line in system.md:
Think and reply in the user's language, even after long stretches of English tool output; artifacts that go into the repository follow the project's conventions instead.
To fix this, remove the phrase even after long stretches of English tool output, as it leads the model to incorrectly assume the user's native language is not English.
What steps can reproduce the bug?
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
Open system.md and locate the quoted language instruction. Review how the wording could cause English users to receive Chinese responses, then make the requested wording-only change. Done means the phrase about long stretches of English tool output is absent while the rest of the instruction remains intact.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, cli
- Issue type
- Bug
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Quiet
- Clarity
- Clearly specified
- Newbie friendliness
- 68/100