MoonshotAI / MoonshotAI/kimi-code
20k tokens to say "hi"
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?
0.28.0
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 previous version 0.27.0 consumed around 13,000 tokens, but after upgrading to 0.28.0, it now uses over 20,000 tokens just to reply with "hi". No AGENTS.md file or skills configured.
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
Start by reproducing the report with Kimi Code 0.28.0 and deepseek-v4-flash using a simple “hi” prompt, then compare its token usage with 0.27.0. Trace the CLI’s request or token-reporting path to identify what changed; done means the same prompt no longer consumes unexpectedly large token counts and the regression is covered by a reproducible test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai, cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100