github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-06-08 18:17:14 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #23466] issue: Random response stops after tool call #123302

New Issue
Closed
opened 2026-05-21 02:35:40 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-21 02:35:40 -05:00
Owner
Copy Link

Originally created by @trinhkvo on GitHub (Apr 7, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/23466

Check Existing Issues

  • 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.

Image

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.

Image

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. ![Image](https://github.com/user-attachments/assets/0e1117fb-25e2-4785-8611-9c57f3d0217a) ### 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. ![Image](https://github.com/user-attachments/assets/e0c8c91d-fe64-4f81-ba44-ba8aa698ddb4) ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-21 02:35:40 -05:00
GiteaMirror commented 2026-05-21 02:35:45 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Apr 12, 2026):

Unable to reproduce.

<!-- gh-comment-id:4232792145 --> @tjbck commented on GitHub (Apr 12, 2026): Unable to reproduce.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#123302
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?