MoonshotAI / MoonshotAI/kimi-code
goal模式使用单独子代理验收结果
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 11h 53m
- Merged PRs (30d)
- 350
Description
What feature would you like to see?
goal模式使用单独的子代理验收结果,以改善长程任务中的效果。
Additional information
目前kimi-code的goal模式设计由主agent同时负责开发与目标验收(这个结论来源于使用kimi-code分析kimi-code源码),而claude code中goal模式使用单独的模型负责目标验收。之前使用kimi-code+kimi-k2.7-code,使用goal模式的时候会出现主agent误判任务达成的情况。尝试在提示词中指定需要独立的子agent负责验收,效果有所改善,但好像会出现这些子agent调试网页使用的资源没有释放的问题。昨晚测试了kimi-code+kimi-k3感觉效果挺好,可能是因为模型上下文窗口变长了加上模型能力大幅增强。
使用单独的子agent负责任务验收上下文会干净一点,但成本也许会更高。前面和k2.7-code讨论的时候它认为目前主agent自己开发自己验收的设计是为了在简单任务中节省成本。
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 locating the goal-mode implementation and reviewing how the main agent currently develops and evaluates tasks. Check the existing subagent behavior and whether browser-debugging resources are released. Done should mean goal evaluation can use a separate subagent while preserving the current cost-conscious behavior for simple tasks.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100