MoonshotAI / MoonshotAI/kimi-code
No thinking indictor makes it feel like it has hung
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?
0.21.0
Which open platform/subscription were you using?
oauth
Which model were you using?
kimi-k2.7
What platform is your computer?
Linux 6.5.0-45-generic x86_64 x86_64
What issue are you seeing?
Kimi looks like it is doing nothing when it is thinking
What steps can reproduce the bug?
Just type a prompt which requires a lot of thinking, you'll see what I mean
What is the expected behavior?
Earlier we used to see thinking in UI. Not anymore. Not even indicator that it's doing something.
Additional information
Well I downgraded to 'solve' the issue.
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 in Kimi Code 0.21.0 on Linux with oauth and kimi-k2.7, using a prompt that requires substantial thinking. Trace the CLI's thinking or progress display and restore a visible indicator; done means users can distinguish ongoing work from a hung process.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- cli
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100