MoonshotAI / MoonshotAI/kimi-cli
Please display the full thinking traces in Kimi CLI
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?
kimi, version 1.33.0
Which open platform/subscription were you using?
Kimi Code
Which model were you using?
kimi-for-coding
What platform is your computer?
Linux 6.8.0-101-generic x86_64 x86_64
What issue are you seeing?
Since updating to Kimi CLI 1.33, the model's thinking process is no longer displayed in either the terminal or the VS Code plugin. This is a significant step backward for power users.
I understand that many users may not care about the thinking trace, but visibility into the model's reasoning is essential for debugging and understanding model behavior. Hiding that information through either the UI or the API actively works against developers. I chose Kimi specifically because it felt like an open, transparent alternative to tools like Codex and Claude Code. That transparency was a core part of its value proposition.
If Kimi CLI is moving toward becoming just another black-box, closed coding assistant, it loses what made it worth choosing in the first place. I hope this gets addressed in a future update, potentially as a (persistent) option flag to toggle thinking process display. I will cancel my Kimi subscription if this is not addressed.
What steps can reproduce the bug?
Simply open the Kimi-CLI in terminal or VS Code plugin and trigger the thinking trace. Note the thinking traces are no longer displayed after 1.33.
What is the expected behavior?
The thinking trace should be displayed, at least via either config or an option flag.
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
Reproduce the regression with Kimi CLI 1.33.0 by triggering a thinking trace in the terminal and the VS Code plugin. Trace how thinking output is handled in each interface and review any configuration or option-flag paths; done means the trace is displayed in at least one supported interface without breaking normal output.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100