MoonshotAI / MoonshotAI/kimi-code
TaskList: support search/filter/sort for sessions with many background tasks
Open
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 11h 53m
- Merged PRs (30d)
- 350
Description
问题描述
在长程会话里大量使用 run_in_background(后台命令 + 后台 subagent)之后,后台任务的查找体验会明显变差。主 agent 一个会话同时挂着 10-30 个后台任务(实验监控、日志 tail、多个子 agent)是常态,这时候:
- TaskList 只有
limit和active_only两个参数,想找一个任务只能把列表拉出来肉眼扫,description又是 3-5 个词的短标签,任务一多就大量雷同,很难区分。 - 结果里没有创建时间、完成时间字段,也没有排序参数,分不清哪条是最近的。
active_only是二值过滤,想只看failed或timed_out的任务做不到。- 超过
limit之后只能加大limit把整个列表重拉一遍,白白消耗 context。
主 agent 找到一个疑似 task_id 后还得逐个调 TaskOutput 确认,整个流程下来 context 消耗不小。
建议
以下任何一项都能显著改善:
- TaskList 支持按描述关键字过滤(
search参数) - 支持
status细分过滤,如running/completed/failed/stopped - 结果附带
created_at时间戳,并支持按时间排序 - 或者提供一个
/tasks交互命令,集中查看和跳转后台任务
希望官方考虑,感谢!
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 inspecting the existing TaskList and TaskOutput interfaces and how background tasks are represented. The issue proposes several possible directions rather than one scoped change, so first establish which filtering, sorting, or interactive-command behavior is wanted; done should include an agreed API and tests covering the selected behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- cli
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100