github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-06 10:58:17 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #22786] issue: Reasoning block leak while copying the chat response #35347

New Issue
Closed
opened 2026-04-25 09:34:17 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-25 09:34:17 -05:00
Owner
Copy Link

Originally created by @a4lg on GitHub (Mar 18, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22786

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

v0.8.8, v0.8.10 dev

Ollama Version (if applicable)

No response

Operating System

Windows 11 (browser)

Browser (if applicable)

Chrome 146.0.7680.80

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

All chat messages are pretty much the copy of the raw text (not including reasoning blocks and tool call-related blocks).

Actual Behavior

  1. Under certain circumstances, other blocks like reasoning are leaked into the copied text.
  2. On reasoning models, excess new lines are prefixed before the beginning.

Steps to Reproduce

Reproducing sub-issue 2 is pretty easy.

  1. Chat and receive a response from a reasoning model.
  2. Copy the response.
  3. It's almost certain that the message copied has one or more new lines at the beginning.

To reproduce sub-issue 1, an extra care must be taken to ensure that a few backticks "`" are created inside the reasoning block. I used:

Model: Qwen3.5-35B-A3B:UD-Q4_K_XL
Prompt: Write out a few number of backticks.

Logs & Screenshots

Sub-issue 2

Chat

Image

Copied Text

Image

Notice that there an excess new line at the start.

Sub-issue 1

Chat

Image

Copied Text

Image

In this invocation, three backticks are the final output.
Notice that the reasoning block is visible.

Additional Information

This is almost the same issue as #22197 but also applies to the response copy feature.

A follow-up PR after #22237 is to be submitted.

Originally created by @a4lg on GitHub (Mar 18, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/22786 ### 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 v0.8.8, v0.8.10 dev ### Ollama Version (if applicable) _No response_ ### Operating System Windows 11 (browser) ### Browser (if applicable) Chrome 146.0.7680.80 ### 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 All chat messages are pretty much the copy of the raw text (not including reasoning blocks and tool call-related blocks). ### Actual Behavior 1. Under certain circumstances, other blocks like reasoning are leaked into the copied text. 2. On reasoning models, excess new lines are prefixed before the beginning. ### Steps to Reproduce Reproducing sub-issue 2 is pretty easy. 1. Chat and receive a response from a reasoning model. 2. Copy the response. 3. It's almost certain that the message copied has one or more new lines at the beginning. To reproduce sub-issue 1, an extra care must be taken to ensure that a few backticks "`" are created inside the reasoning block. I used: Model: Qwen3.5-35B-A3B:UD-Q4_K_XL Prompt: Write out a few number of backticks. ### Logs & Screenshots # Sub-issue 2 ## Chat <img width="713" height="436" alt="Image" src="https://github.com/user-attachments/assets/772809f1-47a4-467d-b120-a18ac481e265" /> ## Copied Text <img width="306" height="46" alt="Image" src="https://github.com/user-attachments/assets/32affad0-cd52-4c69-aef5-153534539a83" /> Notice that there an excess new line at the start. # Sub-issue 1 ## Chat <img width="708" height="389" alt="Image" src="https://github.com/user-attachments/assets/103167d9-a431-4df8-84cf-ee489e9e0d5d" /> ## Copied Text <img width="2899" height="625" alt="Image" src="https://github.com/user-attachments/assets/b9f627d1-5a5c-4fc0-8f74-7c8df48e3f0a" /> In this invocation, three backticks are the final output. Notice that the reasoning block is visible. ### Additional Information This is almost the same issue as #22197 but also applies to the response copy feature. A follow-up PR after #22237 is to be submitted.
GiteaMirror added the bug label 2026-04-25 09:34:17 -05:00
GiteaMirror commented 2026-04-25 09:34:19 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Mar 21, 2026):

Should be addressed in dev, keep us posted!

<!-- gh-comment-id:4104638437 --> @tjbck commented on GitHub (Mar 21, 2026): Should be addressed in dev, keep us posted!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#35347
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?