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
0.8.5
Ollama Version (if applicable)
No response
Operating System
Ubuntu2404
Browser (if applicable)
No response
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
Two model requests
Actual Behavior
One question per request
Steps to Reproduce
I have disabled all title generation, tag creation, and similar features, but every time I request a model, it still triggers an automatic request. What exactly happens during the first model request?
Logs & Screenshots
Additional Information
No response
Originally created by @17Reset on GitHub (Feb 28, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/21950
### 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
0.8.5
### Ollama Version (if applicable)
_No response_
### Operating System
Ubuntu2404
### 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
Two model requests
### Actual Behavior
One question per request
### Steps to Reproduce
I have disabled all title generation, tag creation, and similar features, but every time I request a model, it still triggers an automatic request. What exactly happens during the first model request?
### Logs & Screenshots
<!-- Failed to upload "image.png" -->
<img width="472" height="89" alt="Image" src="https://github.com/user-attachments/assets/6636ebe5-3147-4781-8e53-57f256ca6d50" />
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-18 05:03:33 -05:00
Given that this single indentation bug disrupts fundamental core functionalities (causing double inference/compute waste for normal chats and completely breaking non-native tools), and the fix has already been implemented in dev for days, I hope we can get a release as soon as possible.
This specific bug manifests in drastically different symptoms: double generations, massive TTFT delays, un-disableable Task models, or broken tools… It is difficult for normal users to realize they are facing the same root cause. This is exactly why duplicate issues keep popping up every day.
<!-- gh-comment-id:3976487428 -->
@fathom0324 commented on GitHub (Feb 28, 2026):
This has been fixed in 3c8d658160809f6d651837cf93d89dddc1d17caf in dev branch.
Given that this single indentation bug disrupts fundamental core functionalities (causing double inference/compute waste for normal chats and completely breaking non-native tools), and the fix has already been implemented in dev for days, I hope we can get a release as soon as possible.
This specific bug manifests in drastically different symptoms: double generations, massive TTFT delays, un-disableable Task models, or broken tools… It is difficult for normal users to realize they are facing the same root cause. This is exactly why duplicate issues keep popping up every day.
@fathom0324 users can also install the dev branch if they need this fix urgently. We have ample tutorials for it and post reminders regularly on various platforms that people using the dev branch are very valuable in finding bugs early.
And users can also use the search but most of the duplicate issues here never use the search before opening a new issue.
<!-- gh-comment-id:3976734944 -->
@Classic298 commented on GitHub (Feb 28, 2026):
@fathom0324 users can also install the dev branch if they need this fix urgently. We have ample tutorials for it and post reminders regularly on various platforms that people using the dev branch are very valuable in finding bugs early.
And users can also use the search but most of the duplicate issues here never use the search before opening a new issue.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @17Reset on GitHub (Feb 28, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/21950
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
0.8.5
Ollama Version (if applicable)
No response
Operating System
Ubuntu2404
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Two model requests
Actual Behavior
One question per request
Steps to Reproduce
I have disabled all title generation, tag creation, and similar features, but every time I request a model, it still triggers an automatic request. What exactly happens during the first model request?
Logs & Screenshots
Additional Information
No response
@fathom0324 commented on GitHub (Feb 28, 2026):
This has been fixed in
3c8d658160in dev branch.Given that this single indentation bug disrupts fundamental core functionalities (causing double inference/compute waste for normal chats and completely breaking non-native tools), and the fix has already been implemented in dev for days, I hope we can get a release as soon as possible.
This specific bug manifests in drastically different symptoms: double generations, massive TTFT delays, un-disableable Task models, or broken tools… It is difficult for normal users to realize they are facing the same root cause. This is exactly why duplicate issues keep popping up every day.
@Classic298 commented on GitHub (Feb 28, 2026):
Duplicate fixed in dev
@Classic298 commented on GitHub (Feb 28, 2026):
@fathom0324 users can also install the dev branch if they need this fix urgently. We have ample tutorials for it and post reminders regularly on various platforms that people using the dev branch are very valuable in finding bugs early.
And users can also use the search but most of the duplicate issues here never use the search before opening a new issue.