MoonshotAI / MoonshotAI/kimi-cli
Kimi-CLI does not seem to respect task timeout parameters, leading to persistent timeouts
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?
1.30
Which open platform/subscription were you using?
Kimi Code
Which model were you using?
kimi-for-coding
What platform is your computer?
Linux 6.8.0-101-generic x86_64 x86_64
What issue are you seeing?
Kimi-CLI no longer respects timeout limit set by the model in the tool call. The tasks seem to always be terminated at 60s, disregarding the timeout limit set by the model. This behavior is the same in VSCode Plugins as well as CLI. This leads to serious issues and breaks my workflows.
Please see the following screenshot for an example:
What steps can reproduce the bug?
Ask Kimi to run a long running task and there is high probability of triggering this issue. I tried to designed a prompt that can reliably trigger this issue but there is no success.
What is the expected behavior?
Kimi-CLI respects the timout parameter set by the model in tool calls, allowing long running tasks to finish.
Additional information
I suspect this issue is introduced by the background bash task feature in https://github.com/MoonshotAI/kimi-cli/pull/1477 . Dropping the version back to 1.22 fixes this problem.
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 reviewing pull request #1477, which introduced the background bash task feature, and compare timeout handling in the CLI and VSCode plugin. Reproduce a long-running task if possible and verify that model-provided timeout parameters are honored instead of a fixed 60-second limit; version 1.22 is a useful comparison point.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- bash, python
- Domain
- cli, devtools
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100