mirror of
https://github.com/open-webui/open-webui.git
synced 2026-05-06 19:08:59 -05:00
[GH-ISSUE #13322] issue: Think tags not playing well with Native Tools enabled. #16884
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#16884
Reference in New Issue
Block a user
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?
Originally created by @ivanwong1989 on GitHub (Apr 29, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13322
Originally assigned to: @tjbck on GitHub.
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.6.5
Ollama Version (if applicable)
0.6.6
Operating System
Windows 11
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Since the model's response has has a closing tag, it should be ending the think UI and proceed with the normal response.
this happens when there are native tools included(not even called)
Actual Behavior
It seems to get stuck, even though there is a tag there.
This happens when native tools are included(not even called, just included only). If there are no native tools attached, the thinking works just fine.
Steps to Reproduce
Logs & Screenshots
Additional Information
No response
@AlexRice13 commented on GitHub (Apr 29, 2025):
Same issue here, when calling Qwen3 MoE 30B-A3B trough RAGFlow API, the OpenWebUI just ignored and the thinking state last forever.
@freezlite commented on GitHub (Apr 29, 2025):
Same issue
@basirsedighi commented on GitHub (Apr 30, 2025):
Same here
@criscola commented on GitHub (May 1, 2025):
looks like a bug, Qwen3 MoE 30B-A3B stays stuck in thinking phase forever to me as well, although the final response is generated eventually
@bgeneto commented on GitHub (May 1, 2025):
I think this is more of a Qwen3 model family issue (or how it integrates with Ollama) rather than a problem with Open-WebUI. Maybe using a better chat_template in Ollama could resolve it (I’ve tried, but it didn’t work). The model isn’t thinking forever (at least not for me), but the real issue is that it always puts answers inside thinking tags when tools are used.
@basirsedighi commented on GitHub (May 2, 2025):
@bgeneto i dont think is its is a ollama issue, when functioncalling is to default it works perfectly , but when you switch it to native you see this behavor
UPDATE: 2025-05-02
Seems like i am wrong it is acctully a Ollama problem, thanks to @tjbck for clearification
@tjbck commented on GitHub (May 2, 2025):
Seems to be caused by responses not being properly streamed from the Ollama-end. Investigating.
@tjbck commented on GitHub (May 2, 2025):
Related: https://github.com/ollama/ollama/issues/9632
@basirsedighi It is indeed Ollama issue (tool streaming issue), with that being said, we also just addressed this edge case from our end in dev branch.
6d81eef425@ivanwong1989 commented on GitHub (May 2, 2025):
Does empty content think tags also cause it to loop forever?
@ivanwong1989 commented on GitHub (May 2, 2025):
Is possible it seems.
When i enable thinking for Qwen3, it tends to have BOTH thinking thoughts and response itself inside the thinking block, and forgets to enclose it ?
hmmm..
@ivanwong1989 commented on GitHub (May 2, 2025):
I pulled dev docker image 5 minutes ago.
with no_think
with think
YEAYY!!!!! THANK YOU!!! 100 Gracias!
@freezlite commented on GitHub (May 3, 2025):
Now
<think>cut and you can't see the process of thinking, if task requires multiple function calls you just seeing some response after every function call. Also function call has loading icon if you update the page even if response already done.It would be better to see thinking process because it spends a lot of time and you have no clue whats going on at that time.