`qwen extension install` cannot find the `qwen-extension.json` configuration file

[bisslot]

What happened?

Operating System: Windows 11
QWEN CLI: 0.6.0

Hello, I tried installing the Conductor extension from the Gemini marketplace but was unsuccessful. QWEN returned the following error message:

PS C:\Users\MyCat> qwen extensions install https://github.com/gemini-cli-extensions/conductor --auto-update
Configuration file not found at C:\Users\MyCat\AppData\Local\Temp\qwen-extension2vcnYp\qwen-extension.json

Conductor extension URL: https://geminicli.com/extensions/?name=gemini-cli-extensionsconductor

I don't know how to solve this problem, and why does the report say it can't find the configuration file?

What did you expect to happen?

I hope to get a good answer.

Client information

Client Information

Run qwen to enter the interactive CLI, then run the /about command.

╭──────────────────────────────────────────────────────────────────────────────────────────────────────╮
│                                                                                                      │
│ 关于 Qwen Code                                                                                       │
│                                                                                                      │
│ CLI 版本                           0.6.0                                                             │
│ Git 提交                           17eb20c1                                                          │
│ 模型                               coder-model                                                       │
│ 沙箱                               no sandbox                                                        │
│ 操作系统平台                       win32                                                             │
│ 操作系统架构                       x64                                                               │
│ 操作系统版本                       10.0.22631                                                        │
│ Node.js 版本                       v24.12.0                                                          │
│ NPM 版本                           11.6.0                                                            │
│ 会话 ID                            e6b3d775-fe41-4f2e-bb85-59e80949deca                              │
│ 认证方式                           qwen-oauth                                                        │
│ 内存使用                           241.8 MB                                                          │
│                                                                                                      │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────╯

Login information

No response

Anything else we need to know?

No response

[github-actions]

⚠️ Missing Required Information

Thank you for reporting this issue! To help us investigate and resolve this problem more effectively, we need some additional information:

• Qwen Code version
• full output of the /about command (recommended)

How to provide this information:

Please run the following command and paste the complete output:

qwen
# Then in the interactive CLI, run:
/about

The output should look like:

CLI Version             0.0.14
Git Commit              9a0cb64a
Model                   coder-model
Sandbox                 no sandbox
OS                      darwin
Auth Method             qwen-oauth

Once you provide this information, we'll be able to assist you better. Thank you! 🙏

[Justin-Noel]

I am going to try this out later, but I suspect the global gemini -> qwen rename will require you to at least rename gemini-extension.json to qwen-extenstion.json. There may be other subtle differences that might require a fork and patch.

[Justin-Noel]

Checking out conductor locally and changing gemini-extension.json to qwen-extenstion.json allowed qwen to install the extension and I ran the setup routine on an existing project using a local gpt-oss-120b and seemed to do ok. I noticed in the gemini-extensions conductor repo there is a PR that already contains this change plus, Claude Code, Codex and VSCode support. There are a lot of changes and it is not obvious which are beneficial to qwen.

gemini-cli-extensions/conductor#49

[bisslot]

Checking out conductor locally and changing gemini-extension.json to qwen-extenstion.json allowed qwen to install the extension and I ran the setup routine on an existing project using a local gpt-oss-120b and seemed to do ok. I noticed in the gemini-extensions conductor repo there is a PR that already contains this change plus, Claude Code, Codex and VSCode support. There are a lot of changes and it is not obvious which are beneficial to qwen.

gemini-cli-extensions/conductor#49

Thank you for your reproduction and the detailed information — this is very helpful. @Justin-Noel