I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
0.6.18
Ollama Version (if applicable)
No response
Operating System
Debian 12
Browser (if applicable)
Firefox
Confirmation
I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.
Expected Behavior
Works as expected
Actual Behavior
The response stops and OpenWebUI continues the reply indefinitely, not ending it's turn.
Steps to Reproduce
Connect to a OpenAI API backend (tabbyapi in this case)
Click send on your message
Never-ending response back, even though the response itself freezes (but openwebui does not end the response)
Originally created by @frenzybiscuit on GitHub (Jul 26, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16046
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
0.6.18
### Ollama Version (if applicable)
_No response_
### Operating System
Debian 12
### Browser (if applicable)
Firefox
### Confirmation
- [x] I have read and followed all instructions in `README.md`.
- [x] I am using the latest version of **both** Open WebUI and Ollama.
- [x] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.**
- [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
- [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps:
- Start with the initial platform/version/OS and dependencies used,
- Specify exact install/launch/configure commands,
- List URLs visited, user input (incl. example values/emails/passwords if needed),
- Describe all options and toggles enabled or changed,
- Include any files or environmental changes,
- Identify the expected and actual result at each stage,
- Ensure any reasonably skilled user can follow and hit the same issue.
### Expected Behavior
Works as expected
### Actual Behavior
The response stops and OpenWebUI continues the reply indefinitely, not ending it's turn.
<img width="1077" height="912" alt="Image" src="https://github.com/user-attachments/assets/95b561fe-c22c-4e8e-917a-a9b82561ddd5" />
### Steps to Reproduce
Connect to a OpenAI API backend (tabbyapi in this case)
Click send on your message
Never-ending response back, even though the response itself freezes (but openwebui does not end the response)
### Logs & Screenshots
N/A
### Additional Information
Using ghcr.io/open-webui/open-webui:main
- AIOHTTP_CLIENT_TIMEOUT=30
- AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST=10
- AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST=10
- ENABLE_WEBSOCKET_SUPPORT=true
- WEBSOCKET_MANAGER=redis
- WEBSOCKET_REDIS_RUL=redis://redis:6379/0
- REDIS_URL=redis://redis:6379/0
GiteaMirror
added the bug label 2026-05-25 07:29:03 -05:00
@frenzybiscuit commented on GitHub (Jul 26, 2025):
I should note that this doesn't always happen, either. Seems random.
<!-- gh-comment-id:3123170829 -->
@frenzybiscuit commented on GitHub (Jul 26, 2025):
I should note that this doesn't always happen, either. Seems random.
<!-- gh-comment-id:3123328231 -->
@frenzybiscuit commented on GitHub (Jul 26, 2025):
I don't think it's the suggestion, but just in case it is I've included it here (100% original content).
[the-base.txt](https://github.com/user-attachments/files/21448612/the-base.txt)
that file doesn't help, any log when that happend?
As a possible "issue" context length(num_ctx), response length(max_tokens) or some timeout.
<!-- gh-comment-id:3123437885 -->
@rgaricano commented on GitHub (Jul 26, 2025):
that file doesn't help, any log when that happend?
As a possible "issue" context length(num_ctx), response length(max_tokens) or some timeout.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @frenzybiscuit on GitHub (Jul 26, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16046
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.6.18
Ollama Version (if applicable)
No response
Operating System
Debian 12
Browser (if applicable)
Firefox
Confirmation
README.md.Expected Behavior
Works as expected
Actual Behavior
The response stops and OpenWebUI continues the reply indefinitely, not ending it's turn.
Steps to Reproduce
Connect to a OpenAI API backend (tabbyapi in this case)
Click send on your message
Never-ending response back, even though the response itself freezes (but openwebui does not end the response)
Logs & Screenshots
N/A
Additional Information
Using ghcr.io/open-webui/open-webui:main
@frenzybiscuit commented on GitHub (Jul 26, 2025):
I should note that this doesn't always happen, either. Seems random.
@frenzybiscuit commented on GitHub (Jul 26, 2025):
I don't think it's the suggestion, but just in case it is I've included it here (100% original content).
the-base.txt
@rgaricano commented on GitHub (Jul 26, 2025):
that file doesn't help, any log when that happend?
As a possible "issue" context length(num_ctx), response length(max_tokens) or some timeout.