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

Git Clone

Open WebUI Version

0.6.43

Ollama Version (if applicable)

No response

Operating System

Windows 10 / Ubuntu 24.04.1 LTS

Browser (if applicable)

Chrome / 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

When I select a fragment of a text in the model responses, a popup shows and I can ASK or EXPLAIN the answer. If I click on ASK or EXPLAIN, the model provides extra information about the text selected.

Actual Behavior

The popup shows up, but trying to use ASK or EXPLAIN results in an error message An error occurred while fetching the explanation and nothing happens.

Steps to Reproduce

1. Select some text from the model answer
2. Wait for the ASK / EXPLAIN popup to show up
3. Select an option

Logs & Screenshots

The browser network activity shows a call to: /api/chat/completions returning a 400 server error with the json {"detail":"'NoneType' object has no attribute 'get'"}

OWUI console shows only this line: 2025-12-23 15:23:39.240 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:53721 - "POST /api/chat/completions HTTP/1.1" 400

Additional Information

I'm using external models using the OpenAI completions API.
Tested locally via GIT clone and in a server using Docker.
Tested with different models but ALL of them external models (no ollama models)
Might be related to this bug report: #15579