-
-
Notifications
You must be signed in to change notification settings - Fork 17.5k
Open
Labels
bugSomething isn't workingSomething isn't working
Description
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
v0.8.1
Ollama Version (if applicable)
No response
Operating System
MacOS 15.4.1
Browser (if applicable)
Firefox 147.0.3
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
- Tool call completes
- Assistant response continues after tool call
Actual Behavior
- Tool UI remains in "pending" mode (spinner)
- Assistant message ends
Steps to Reproduce
- Start Open WebUI 0.8.1 using docker
- Configure an external OpenAI API connection in responses mode
- In the model settings for gpt-5 (or chosen model), enable native tool calling, and ensure there is a tool available (built-in or custom)
- Start a chat with gpt-5, and instruct it to use an available tool
Logs & Screenshots
Screenshots included inline in previous messages
Docker logs show request succeeding/returning 200. Nothing relevant in browser logs
Additional Information
Clicking the "continue" button doesn't work - the response just stops in the same place
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't working