mirror of
https://github.com/open-webui/computer.git
synced 2026-11-05 01:17:24 +00:00
[GH-ISSUE #112] bug: Response output repeats infinitely due to missing stream termination #54
Labels
No labels
enhancement
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
open-webui/computer#54
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
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 @JKGeovision on GitHub (Jul 8, 2026).
Original GitHub issue: https://github.com/open-webui/computer/issues/112
Hello,
I discovered a bug where the ai response output repeats the same text block dozens of times in a single turn. This happens when the model finishes generating a response but the streaming connection is not properly terminated.
Steps to reproduce:
I suspect the issue is that the harness does not correctly detect or signal stream termination.
Thank you again for your work and I wish you all a great day,
Joshua Krimmer
@owui-terminator[bot] commented on GitHub (Jul 8, 2026):
🔍 Related Issues Found
I found some existing issues that might be related. Please check if any of these are duplicates or contain helpful solutions:
This issue is about streaming lifecycle handling in the same chat_task path. Although it reports early termination on
usageevents rather than infinite repetition, both involve incorrect stream end detection and response finalization in streaming responses.by sandrogauci
💡 If your issue is a duplicate, please close it and add any additional details to the existing issue instead.
This comment was generated automatically. React with 👍 if helpful, 👎 if not.
@tjbck commented on GitHub (Jul 9, 2026):
Should be addressed!
@JKGeovision commented on GitHub (Jul 10, 2026):
Hello,
I have tested the changes but noticed that the model still executes the same tool multiple times even though it confirms it is done.
Thanks again for your work and have a great day,
Joshua Krimmer
@tjbck commented on GitHub (Jul 12, 2026):
@JKGeovision which model/ai agent are you using here? any other details you think are relevant that you can provide us with?
@JKGeovision commented on GitHub (Jul 12, 2026):
Hello,
thanks for the fast response. I am using a local llama.cpp connection and use Qwen3.6 35B with Q6 as the model. I am also using the same model on other harnesses or chat apps like Open WebUI and never observed the model repeating itself like this before. Is there a log or something like that which could contain useful information?
Thanks again for your work and have a great day,
Joshua Krimmer
@tjbck commented on GitHub (Jul 21, 2026):
@JKGeovision are you still facing this issue?
@cclecle commented on GitHub (Jul 23, 2026):
Same problem here, confirmed with 6 different models. These models are running on llamacpp, working perfectly through OWUI. Seeing many repeatition loops using 'computer'.
@tjbck commented on GitHub (Jul 23, 2026):
@cclecle could you confirm with the latest release?
@cclecle commented on GitHub (Jul 23, 2026):
I just tried, and it was still happening, but it was a continuation of a previously broken chat. I am trying with new chat(s) now.. !
I also configured the connexion as 'llamacpp' now, it was left to default.
@cclecle commented on GitHub (Jul 23, 2026):
Still happening :-/
It has something to do with tool calls I think.
Analysing the issue with an agent atm...
Edit: ChatGPT Diagnosis, I let the maintainers use it or not.
Repeated Assistant Responses After Tool Calls.pdf
Edit 2: I was running in non-thinking mode, now with thinking enabled (no code change), I am not seeing repetition anymore.. will try more and update here.
@tjbck commented on GitHub (Jul 23, 2026):
@cclecle could you confirm with the latest?
@cclecle commented on GitHub (Jul 23, 2026):
Not able to reproduce anymore, both in thinking and non-thinking mode :)
Will test more during the weekend, but it looks very promising.
thank you !
@cclecle commented on GitHub (Jul 24, 2026):
hum, not 100% sure its Computer or my llamacpp or model, but I am seeing a new different behaviour .
Sometime the model think, but does not send the final answer.
I will try to talk with the model using normal owui or llamacpp web to check if it has the same behaviour.