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 #4535] [BUG]: Chat widget Thinking #2884

New Issue
Closed
opened 2026-02-22 18:31:40 -05:00 by yindo · 7 comments
yindo commented 2026-02-22 18:31:40 -05:00
Owner
Copy Link
Copy Source

Originally created by @alainlizotte on GitHub (Oct 13, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4535

Originally assigned to: @angelplusultra on GitHub.

How are you running AnythingLLM?

Docker (local)

What happened?

When using a thinking model (Qwen3), the chat widget doesn't show the thinking bubble anymore since the last update.
It goes from the three dots (...) to a blank page and gives the answer after thinking proces is done.

Please, bring back the thinking bubble :)

Are there known steps to reproduce?

Select a thinking model.

Add the chat widget to a web page.

Ask a question.

Originally created by @alainlizotte on GitHub (Oct 13, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4535 Originally assigned to: @angelplusultra on GitHub. ### How are you running AnythingLLM? Docker (local) ### What happened? When using a thinking model (Qwen3), the chat widget doesn't show the thinking bubble anymore since the last update. It goes from the three dots (...) to a blank page and gives the answer after thinking proces is done. Please, bring back the thinking bubble :) ### Are there known steps to reproduce? Select a thinking model. Add the chat widget to a web page. Ask a question.
yindo added the possible buginvestigatingembed-widget labels 2026-02-22 18:31:40 -05:00
yindo closed this issue 2026-02-22 18:31:40 -05:00
yindo commented 2026-02-22 18:31:40 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Oct 13, 2025):

Can you elaborate on what specific provider you are using to run Qwen3?

@timothycarambat commented on GitHub (Oct 13, 2025): Can you elaborate on what specific provider you are using to run Qwen3?
yindo commented 2026-02-22 18:31:40 -05:00
Author
Owner
Copy Link
Copy Source

@alainlizotte commented on GitHub (Oct 13, 2025):

Ollama

https://ollama.com/library/qwen3

@alainlizotte commented on GitHub (Oct 13, 2025): Ollama https://ollama.com/library/qwen3
yindo commented 2026-02-22 18:31:40 -05:00
Author
Owner
Copy Link
Copy Source

@alainlizotte commented on GitHub (Oct 13, 2025):

I just noticed that it won't show in AnythingLLM UI neither...

@alainlizotte commented on GitHub (Oct 13, 2025): I just noticed that it won't show in AnythingLLM UI neither...
yindo commented 2026-02-22 18:31:40 -05:00
Author
Owner
Copy Link
Copy Source

@alainlizotte commented on GitHub (Oct 13, 2025):

Ollama also got an update recently.

@alainlizotte commented on GitHub (Oct 13, 2025): Ollama also got an update recently.
yindo commented 2026-02-22 18:31:41 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Oct 13, 2025):

Do you know which version of ollama you are one and also which specific variety of qwen3 (0.6, 1.7, ...32b) etc? I actually ran into a massive issue with Ollama's downright broken models of qwen3 32B, where the model was just busted, and it had nothing to do with our tool and was a bug with Ollama/model. Possibly semi-related

@timothycarambat commented on GitHub (Oct 13, 2025): Do you know which version of ollama you are one and also which specific variety of qwen3 (0.6, 1.7, ...32b) etc? I actually ran into a massive issue with Ollama's downright broken models of qwen3 32B, where the model was just busted, and it had nothing to do with our tool and was a bug with Ollama/model. [Possibly semi-related](https://github.com/ollama/ollama/issues/12511)
yindo commented 2026-02-22 18:31:41 -05:00
Author
Owner
Copy Link
Copy Source

@alainlizotte commented on GitHub (Oct 13, 2025):

I'm using qwen3:8b-q4_K_M
Ollama 0.12.5

I just tried in PowerShell and it's working fine. I can see the thinking process.

@alainlizotte commented on GitHub (Oct 13, 2025): I'm using qwen3:8b-q4_K_M Ollama 0.12.5 I just tried in PowerShell and it's working fine. I can see the thinking process.
yindo commented 2026-02-22 18:31:41 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Oct 27, 2025):

Moving to #4576

@timothycarambat commented on GitHub (Oct 27, 2025): Moving to #4576
yindo changed title from [BUG]: Chat widget Thinking to [GH-ISSUE #4535] [BUG]: Chat widget Thinking 2026-06-05 14:49:05 -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 embed-widget investigating 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#2884
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?