MoonshotAI / MoonshotAI/kimi-cli
kimiCode用量计算有问题 || There is a problem with kimiCode usage calculation
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.4k
- Forks
- 1.3k
- Avg merge
- 9h 47m
- Merged PRs (30d)
- 2
Description
2个任务就消耗完了2小时的额度,用量计算使用token,K2.6的思维链过长,token完全不够用。订阅了会员2小时只能问2次,有点搞笑
官方说明是这样的:
核心优势
广泛兼容: 完美适配 Kimi Code CLI、Claude Code、Roo Code,轻松融入各类开发工作流。
极速响应: 最高输出速度可达 100 Tokens/s,大幅提升编码效率。
高频并发: 每 5 小时的 Tokens 总量可支持约 300-1200 次 API 请求,最高并发上限达30,确保复杂项目不间断。
不是按照api请求次数来算的吗
Two tasks have consumed the 2-hour quota. Usage calculation uses tokens. The thinking chain of K2.6 is too long and tokens are not enough. If you subscribe to the membership, you can only ask twice in 2 hours, which is a bit funny.
The official description is this:
Core advantages
Widely compatible: Perfectly adapted to Kimi Code CLI, Claude Code, Roo Code, and easily integrated into various development workflows.
Extremely fast response: The maximum output speed can reach 100 Tokens/s, greatly improving coding efficiency.
High-frequency concurrency: The total amount of Tokens every 5 hours can support approximately 300-1200 API requests, with a maximum concurrency limit of 30, ensuring uninterrupted access to complex projects.
Isn't it calculated based on the number of api requests?
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
No files, tests, or entry points are identified in the issue. Start by reproducing the reported two-task quota usage and trace where Kimi Code usage is reported or displayed; compare the observed accounting with the documented token and request limits. Done means the accounting behavior is explained and, if incorrect, covered by a verified fix or regression test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend, cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100