MoonshotAI / MoonshotAI/kimi-code
Edit tool randomly starts failing
Nobody has claimed this yet.
- 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?
0.14.0
Which open platform/subscription were you using?
Kimi Code
Which model were you using?
kimi-k2.6
What platform is your computer?
Linux
What issue are you seeing?
Edit tool sometimes fail for no reason and after a few iterations the model decides to use cli or python scripts to do the replacements as the tool becomes useless. I suspect this is caused by invisible characters or spaces vs tabs and similar issue as visibly there is no difference. The tool should be able to auto fix these issue probably for at least known formats like python. This issue did not exist at original kimi-cli.
What steps can reproduce the bug?
Casual usage for coding, did not identified any concrete patterns
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
Start by running Kimi Code 0.14.0 with the kimi-k2.6 model on Linux and exercising the Edit tool during coding. No source file, test, or reliable reproduction pattern is named, so first identify a repeatable failure involving invisible characters or whitespace; done means the failure is reproduced and the expected handling is verified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- linux, python, typescript
- Domain
- cli, developer-experience, tooling
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100