MoonshotAI / MoonshotAI/kimi-cli
Status of agent unknown. It is not possible to dive in agentic session to overview.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.4k
- Forks
- 1.3k
- Avg merge
- 9h 47m
- Merged PRs (30d)
- 2
Description
What version of Kimi Code CLI is running?
1.47.0
Which open platform/subscription were you using?
kimi code
Which model were you using?
kimi-for-coding
What platform is your computer?
Linux 6.19.11-100.fc42.x86_64 x86_64 unknown
What issue are you seeing?
I start dialogue and begun 4 independent agents. 3 of them made them job and finish with results. Other on work more that 1h and I can't understand what it is doing. I see steps observed at high level, but what's inside?
It will be good to dive into agentic session and review it like main one.
I also not shure that it can handle to me me account limits. I pretty shure that api will not allow agent to continue work when quate reached, but in case it is not main dialogue how I will understand that it stop by quota limit?
Yes, I check it by myself online, but that is not what expected to be
What steps can reproduce the bug?
Ask question that can be divided into several parallel steps and propose do it in agentic research. After that you can have multi agents started for sub tasks. You can click on oach to overview high level of process (promt, steps and final result in case agent word complete).
Exceted behavior - dive into agentic session like in main one and have full overview of q/a and thoughts. Possible there will quota warnings also that should be catche by code itself and escalated to main dialogue.
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
No files, tests, or entry points are named. First reproduce the parallel-agent workflow in Kimi Code CLI and inspect the existing agent overview behavior. Done should provide a way to enter an agent session, review its full question-and-answer activity, and surface quota-related stops or warnings in the main dialogue.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cli
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100