MoonshotAI / MoonshotAI/kimi-code
优化模型提供商限流场景的使用体验，希望能参考 https://github.com/earendil-works/pi 这个 agent 的处理方式，它能明显减少用户在频繁碰到限流问题时需手动敲 “继续” 提示词的次数
Open
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 11h 53m
- Merged PRs (30d)
- 350
Description
优化模型提供商限流场景的使用体验，希望能参考 https://github.com/earendil-works/pi 这个 agent 的处理方式，它能明显减少用户在频繁碰到限流问题时需手动敲 “继续” 提示词的次数。（pi 的缺省是重试 3 次）
kimi code当中虽然配置了如下参数，但是体验依旧不如 pi 好，希望后续版本能够优化优化这个场景的体验。
[loop_control]
max_retries_per_step = 3
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 reading how the CLI handles the [loop_control] setting, especially max_retries_per_step, and compare the desired behavior with the referenced pi agent. Done should reduce the need to manually enter “继续” during repeated provider rate-limit responses while preserving the configured retry behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- cli
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100