MoonshotAI / MoonshotAI/kimi-cli

VS Code 插件:紧凑模式下 thinking 块无法展开查看完整内 || VS Code plug-in: The thinking block cannot be expanded to view the complete content in compact mode

Open
#1,877 2 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
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?

1.33.0

Which open platform/subscription were you using?

kimi code(vs code)

Which model were you using?

kimi-k2.6-code-preview

What platform is your computer?

MacOS

What issue are you seeing?

在 VS Code 插件的最新版本中,当 show_thinking_stream = false(默认)时,thinking 块被渲染为紧凑的单行指示器(Thinking... → Thought for Xs · N tokens)。但此时无法点击展开查看模型的完整思考过程,导致事后无法回看 reasoning 内容。

而在之前的版本中,即使不实时流式展示 thinking,thinking 块也是一个可折叠/展开的卡片组件。

What steps can reproduce the bug?

给紧凑模式的 Thought for Xs · N tokens 单行指示器增加点击展开功能,显示完整 Markdown 格式的 thinking 内容。
或者在 thinking 块结束时,将完整 thinking 以可折叠卡片的形式写入历史记录,而不是仅保留 summary。

What is the expected behavior?

No response

Additional information

No response


What version of Kimi Code CLI is running?

1.33.0

Which open platform/subscription were you using?

kimi code(vs code)

Which model were you using?

kimi-k2.6-code-preview

What platform is your computer?

MacOS

What issue are you seeing?

In the latest version of the VS Code plugin, when show_thinking_stream = false (default), thinking blocks are rendered as compact single-line indicators (Thinking... → Thought for Xs · N tokens). However, you cannot click to expand to view the complete thinking process of the model at this time, making it impossible to review the reasoning content afterwards.

In previous versions, even if thinking was not displayed in real-time streaming, the thinking block was a collapsible/expandable card component.

What steps can reproduce the bug?

Add a click-to-expand function to the compact mode Thought for Xs · N tokens single-line indicator to display the complete thinking content in Markdown format.
Or at the end of the thinking block, write the full thinking to the history as a collapsible card instead of just keeping the summary.

What is the expected behavior?

No response

Additional information

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the issue in the VS Code plugin with show_thinking_stream=false on Kimi Code CLI 1.33.0, then trace the compact “Thought for Xs · N tokens” indicator and its history rendering. Done means the compact indicator can be expanded to show the complete Markdown thinking content, or the completed thinking is retained as a collapsible history card.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, vscode
Domain
cli, devtools
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.