[GH-ISSUE #22882] issue: Empty finalized assistant response remains in loading skeleton state

Originally created by @ultramancode on GitHub (Mar 20, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/22882 ### 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 Git Clone ### Open WebUI Version v0.8.10 ### Ollama Version (if applicable) _No response_ ### Operating System Docker(Linux container) ### Browser (if applicable) _No response_ ### 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 When an assistant response finishes with empty content, the message should finalize clearly instead of looking like it is still loading. - Show loading skeleton only while generation is in progress. - If generation is done and content is empty, show a localized empty-state text (e.g., "No content"). ### Actual Behavior If the assistant completion ends with empty content, the message bubble can keep showing the loading skeleton even after the request is finished. This looks like an infinite loading state, although generation has already completed. ### Steps to Reproduce 1. Send the prompt: "Respond with an empty string. Output nothing at all" 2. Observe the assistant message area: - The message is finished, but the loading skeleton is still visible. ### Logs & Screenshots <img width="842" height="298" alt="Image" src="https://github.com/user-attachments/assets/c56e410a-73d4-4a5f-9370-ac55336ae54f" /> [Browser console screenshot] Backend logs show no server error; /api/chat/completions returned 200 and the assistant message was persisted as done=true with empty content. ### Additional Information I have a fix ready and will open a PR shortly.

GiteaMirror commented

2026-04-25 09:35:04 -05:00

Owner

Originally created by @ultramancode on GitHub (Mar 20, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22882

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

v0.8.10

Ollama Version (if applicable)

No response

Operating System

Docker(Linux container)

Browser (if applicable)

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 an assistant response finishes with empty content, the message should finalize clearly instead of looking like it is still loading.

Show loading skeleton only while generation is in progress.
If generation is done and content is empty, show a localized empty-state text (e.g., "No content").

Actual Behavior

If the assistant completion ends with empty content, the message bubble can keep showing the loading skeleton even after the request is finished.

This looks like an infinite loading state, although generation has already completed.

Steps to Reproduce

Send the prompt: "Respond with an empty string. Output nothing at all"
Observe the assistant message area:
- The message is finished, but the loading skeleton is still visible.

Logs & Screenshots

[Browser console screenshot]

Backend logs show no server error;
/api/chat/completions returned 200 and the assistant message was persisted as done=true with empty content.

Additional Information

I have a fix ready and will open a PR shortly.

GiteaMirror added the bug label 2026-04-25 09:35:04 -05:00

GiteaMirror closed this issue

2026-04-25 09:35:05 -05:00

Author

@ultramancode commented on GitHub (Mar 20, 2026):

I opened a follow-up PR for this issue: #22883

@ultramancode commented on GitHub (Mar 20, 2026): I opened a follow-up PR for this issue: #22883

[GH-ISSUE #22882] issue: Empty finalized assistant response remains in loading skeleton state #35363