[GH-ISSUE #20781] issue: GPT OSS Autocomplete broken #34815

Closed
opened 2026-04-25 08:59:55 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @iChristGit on GitHub (Jan 18, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20781

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

v0.7.2

Ollama Version (if applicable)

latest

Operating System

Win11

Browser (if applicable)

Edge/Zen

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

Autocomplete should start after users request:
Help me [complete here]

Actual Behavior

With GPT:OSS
The autocomplete also repeats user request:
Help me [help me [actual completion]]

Other models do not have issues with autocomplete.

Steps to Reproduce

1.Star a new chat with gpt:oss20b and try autocomplete

Logs & Screenshots

Image

Additional Information

No response

Originally created by @iChristGit on GitHub (Jan 18, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/20781 ### 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 v0.7.2 ### Ollama Version (if applicable) latest ### Operating System Win11 ### Browser (if applicable) Edge/Zen ### 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 Autocomplete should start after users request: Help me [complete here] ### Actual Behavior With GPT:OSS The autocomplete also repeats user request: Help me [help me [actual completion]] Other models do not have issues with autocomplete. ### Steps to Reproduce 1.Star a new chat with gpt:oss20b and try autocomplete ### Logs & Screenshots <img width="1197" height="166" alt="Image" src="https://github.com/user-attachments/assets/1b462d04-c672-49a9-bdf3-b1758be105d6" /> ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-25 08:59:55 -05:00
Author
Owner

@owui-terminator[bot] commented on GitHub (Jan 18, 2026):

🔍 Similar Issues Found

I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:

  1. #20775 issue: calls to tools in gpt-oss
    by chdid • Jan 18, 2026 • bug

  2. #20641 issue: Web Search and Builtin Tools permissions break search
    by HenkieTenkie62 • Jan 13, 2026 • bug


💡 Tips:

  • If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
  • If you found a solution in any of these issues, please share it here to help others

This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.

<!-- gh-comment-id:3765491461 --> @owui-terminator[bot] commented on GitHub (Jan 18, 2026): 🔍 **Similar Issues Found** I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions: 1. [#20775](https://github.com/open-webui/open-webui/issues/20775) **issue: calls to tools in gpt-oss** *by chdid • Jan 18, 2026 • `bug`* 2. [#20641](https://github.com/open-webui/open-webui/issues/20641) **issue: Web Search and Builtin Tools permissions break search** *by HenkieTenkie62 • Jan 13, 2026 • `bug`* --- 💡 **Tips:** - If this is a duplicate, please consider closing this issue and adding any additional details to the existing one - If you found a solution in any of these issues, please share it here to help others *This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
Author
Owner

@silentoplayz commented on GitHub (Jan 18, 2026):

Open WebUI's autocompletion feature:

  • Does not detect if a model is a "reasoning" or "thinking" model.
  • Does not alter autocomplete behavior based on model type.
  • Does not use different completion strategies for reasoning models.

The only model-related checks in the chat input are for capabilities like vision, web search, and image generation, but these affect UI buttons, not autocomplete.

Related reasoning features that exist independently:

  • reasoning_effort parameter control
  • reasoning_tags configuration (Default/Enabled/Disabled/Custom)
  • think parameter for Ollama models

But these are passed through to the model independently and do not influence how autocomplete works.

<!-- gh-comment-id:3765513102 --> @silentoplayz commented on GitHub (Jan 18, 2026): Open WebUI's autocompletion feature: - Does not detect if a model is a "reasoning" or "thinking" model. - Does not alter autocomplete behavior based on model type. - Does not use different completion strategies for reasoning models. The only model-related checks in the chat input are for capabilities like vision, web search, and image generation, but these affect UI buttons, not autocomplete. Related reasoning features that exist independently: - `reasoning_effort` parameter control - `reasoning_tags` configuration (Default/Enabled/Disabled/Custom) - `think` parameter for Ollama models But these are passed through to the model independently and do not influence how autocomplete works.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#34815