I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
0.8.12
Ollama Version (if applicable)
N/A
Operating System
Windows 11
Browser (if applicable)
Edge
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
The model should finish running tool calls and providing responses completely.
Actual Behavior
Sometimes the response just stops after a tool call, which is pretty random. It might finish a few tool calls and keep going, then suddenly stop after a random one.
I finally found an example where it stops. For some reason, the AI model (Qwen 3.5 122B-A10B) could analyze other images, but with this one (attached), it finishes read_file and then just stops.
Steps to Reproduce
Use the attached image and ask the model to analyze the image.
My configurations:
Open WebUI v0.8.12 (docker) + Open-Terminal v0.11.32 (docker with root user access, multi-user enabled)
llama-swap with llama.cpp (b86xx)
Qwen3.5-122B-A10B UD IQ4_NL - using Native tool call, context size 150,000
No filter enabled.
Logs & Screenshots
Open WebUI docker log doesn't show anything abnormal.
Additional Information
No response
Originally created by @trinhkvo on GitHub (Apr 7, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/23466
### Check Existing Issues
- [x] I have searched for any existing and/or related issues.
- [x] I have searched for any existing and/or related discussions.
- [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
0.8.12
### Ollama Version (if applicable)
N/A
### Operating System
Windows 11
### Browser (if applicable)
Edge
### 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
The model should finish running tool calls and providing responses completely.
### Actual Behavior
Sometimes the response just stops after a tool call, which is pretty random. It might finish a few tool calls and keep going, then suddenly stop after a random one.
I finally found an example where it stops. For some reason, the AI model (Qwen 3.5 122B-A10B) could analyze other images, but with this one (attached), it finishes `read_file` and then just stops.
### Steps to Reproduce
Use the attached image and ask the model to analyze the image.
My configurations:
- Open WebUI v0.8.12 (docker) + Open-Terminal v0.11.32 (docker with root user access, multi-user enabled)
- llama-swap with llama.cpp (b86xx)
- Qwen3.5-122B-A10B UD IQ4_NL - using Native tool call, context size 150,000
- No filter enabled.
### Logs & Screenshots
Open WebUI docker log doesn't show anything abnormal.
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-15 16:00:19 -05:00
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 @trinhkvo on GitHub (Apr 7, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/23466
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.8.12
Ollama Version (if applicable)
N/A
Operating System
Windows 11
Browser (if applicable)
Edge
Confirmation
README.md.Expected Behavior
The model should finish running tool calls and providing responses completely.
Actual Behavior
Sometimes the response just stops after a tool call, which is pretty random. It might finish a few tool calls and keep going, then suddenly stop after a random one.
I finally found an example where it stops. For some reason, the AI model (Qwen 3.5 122B-A10B) could analyze other images, but with this one (attached), it finishes
read_fileand then just stops.Steps to Reproduce
Use the attached image and ask the model to analyze the image.
My configurations:
Logs & Screenshots
Open WebUI docker log doesn't show anything abnormal.
Additional Information
No response
@tjbck commented on GitHub (Apr 12, 2026):
Unable to reproduce.