[GH-ISSUE #17537] Issue: Sometimes hit the "'NoneType' object has no attribute 'find'" error when finishing the chat using GPT-OSS-120B A.I. Model #18324

New Issue

2026-04-20T00:32:30-05:00

GiteaMirror commented

2026-04-20 00:32:30 -05:00

Originally created by @joeMEGKH on GitHub (Sep 18, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17537

Check Existing Issues

I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.6.30

Ollama Version (if applicable)

v0.11.10

Operating System

MacOS Sequiua 15.6.1

Browser (if applicable)

Chrome 140.0.7339.128

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

Run normally without this error and completed the chat

Actual Behavior

Sometimes hit the "'NoneType' object has no attribute 'find'" error when finishing the chat using GPT-OSS-120B A.I. Model. However, sometimes it is normal.

Steps to Reproduce

1.Using mlx-openai-server with OpenAI GPT-OSS:120B-4bit mlx model on Mac OS
MLX-OPENAI-SERVER: https://github.com/cubist38/mlx-openai-server
2. Install Open WebUI v.0.6.30

Logs & Screenshots

Additional Information

No response

Originally created by @joeMEGKH on GitHub (Sep 18, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/17537 ### 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 am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.6.30 ### Ollama Version (if applicable) v0.11.10 ### Operating System MacOS Sequiua 15.6.1 ### Browser (if applicable) Chrome 140.0.7339.128 ### 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 Run normally without this error and completed the chat ### Actual Behavior <img width="976" height="245" alt="Image" src="https://github.com/user-attachments/assets/accef728-2d2c-4fd1-af5d-cd80bf78452d" /> Sometimes hit the "'NoneType' object has no attribute 'find'" error when finishing the chat using GPT-OSS-120B A.I. Model. However, sometimes it is normal. ### Steps to Reproduce 1.Using mlx-openai-server with OpenAI GPT-OSS:120B-4bit mlx model on Mac OS MLX-OPENAI-SERVER: https://github.com/cubist38/mlx-openai-server 2. Install Open WebUI v.0.6.30 ### Logs & Screenshots <img width="976" height="245" alt="Image" src="https://github.com/user-attachments/assets/bd82ed69-db84-47a3-b86c-95c27578cf28" /> ### Additional Information _No response_

GiteaMirror added the bug label 2026-04-20 00:32:31 -05:00

GiteaMirror closed this issue

2026-04-20 00:32:31 -05:00

GiteaMirror commented

2026-04-20 00:32:32 -05:00