Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #4108] [BUG]: as i invoke the @agent (default one), the answer is "Could not respond to message. Cannot read properties of null (reading 'choices')" #2616

New Issue
Closed
opened 2026-02-22 18:30:28 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:30:28 -05:00
Owner
Copy Link
Copy Source

Originally created by @jiemji on GitHub (Jul 8, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4108

Originally assigned to: @shatfield4 on GitHub.

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

i wanted to try the default @agent

Image

I use a qwen3:30B-A3b model with GenericOpenIA provider. I've also try with a gpt-40 on azure.
The models works well by the way when i chat with them.

Any idea on how fix this ? is there any data to provide to investigate ?

Are there known steps to reproduce?

Create a workspace
Create a thread
Ask some action to the @agent :)

Originally created by @jiemji on GitHub (Jul 8, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4108 Originally assigned to: @shatfield4 on GitHub. ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? i wanted to try the default @agent <img width="818" height="358" alt="Image" src="https://github.com/user-attachments/assets/0fdfc349-07e9-4606-a435-9317291f6e8c" /> I use a qwen3:30B-A3b model with GenericOpenIA provider. I've also try with a gpt-40 on azure. The models works well by the way when i chat with them. Any idea on how fix this ? is there any data to provide to investigate ? ### Are there known steps to reproduce? Create a workspace Create a thread Ask some action to the @agent :)
yindo added the possible bugneeds info / can't replicate labels 2026-02-22 18:30:28 -05:00
yindo closed this issue 2026-02-22 18:30:28 -05:00
yindo commented 2026-02-22 18:30:28 -05:00
Author
Owner
Copy Link
Copy Source

@shatfield4 commented on GitHub (Jul 9, 2025):

Are you connecting to a locally run qwen3:30B-A3b or what provider are you using to connect to this model? This is most likely an issue with the provider or model you are connecting to but if you can provide any more info on how you are connecting to these models we can definitely dig deeper and get it patched.

We do have info here on how to run AnythingLLM in debug mode and if you are able to do this and get the error again, paste the error logs here and we can take a look.

@shatfield4 commented on GitHub (Jul 9, 2025): Are you connecting to a locally run qwen3:30B-A3b or what provider are you using to connect to this model? This is most likely an issue with the provider or model you are connecting to but if you can provide any more info on how you are connecting to these models we can definitely dig deeper and get it patched. We do have info [here](https://docs.anythingllm.com/installation-desktop/debug#anythingllm-debug-mode-on-macos) on how to run AnythingLLM in debug mode and if you are able to do this and get the error again, paste the error logs here and we can take a look.
yindo commented 2026-02-22 18:30:28 -05:00
Author
Owner
Copy Link
Copy Source

@jiemji commented on GitHub (Jul 10, 2025):

Hello, i was connecting to an instance hosting multiple LLMs in the company i work for.
In fact, the problem seems coming from the API i've used (on généric open AI connexion). Tests using an another API point on the instance are good.
Thanks for the support.

@jiemji commented on GitHub (Jul 10, 2025): Hello, i was connecting to an instance hosting multiple LLMs in the company i work for. In fact, the problem seems coming from the API i've used (on généric open AI connexion). Tests using an another API point on the instance are good. Thanks for the support.
yindo commented 2026-02-22 18:30:28 -05:00
Author
Owner
Copy Link
Copy Source

@DroneMeOut commented on GitHub (Sep 11, 2025):

It gives me the same problem and I am only using Gemini via API calls.

@DroneMeOut commented on GitHub (Sep 11, 2025): It gives me the same problem and I am only using Gemini via API calls.
yindo changed title from [BUG]: as i invoke the @agent (default one), the answer is "Could not respond to message. Cannot read properties of null (reading 'choices')" to [GH-ISSUE #4108] [BUG]: as i invoke the @agent (default one), the answer is "Could not respond to message. Cannot read properties of null (reading 'choices')" 2026-06-05 14:47:34 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label needs info / can't replicate possible bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2616
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?