issue: @Model not working in prompt templates #6400

New Issue

2025-11-11T16:54:05-06:00

GiteaMirror commented

2025-11-11 16:54:05 -06:00

Originally created by @cybergexl on GitHub (Sep 14, 2025).

Check Existing Issues

I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.6.28

Ollama Version (if applicable)

No response

Operating System

Debian

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

In the workspace > prompts > when adding a prompt that begins with <@the name of the desired model> as one might do in a conversation, the model is not changed dynamically, even though one might expect it to be, since it is specified in the first line of the prompt.

Actual Behavior

<@the name of the desired model> is added to the prompt as text but is not interpreted when sending the conversation.

Steps to Reproduce

Go to Workspace > Prompts > Add New Prompt
Enter a title and a command (anything will do...)
In the prompt content, enter “@Sonoma Sky Alpha” (for example, to choose a specific model) and add content to the line, such as “Which LLM model am I using?”
Save
Create a new conversation and call up the prompt with “/”
Send

Logs & Screenshots

Additional Information

No response

Originally created by @cybergexl on GitHub (Sep 14, 2025). ### 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 am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.6.28 ### Ollama Version (if applicable) _No response_ ### Operating System Debian ### 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). - [ ] 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 In the workspace > prompts > when adding a prompt that begins with <@the name of the desired model> as one might do in a conversation, the model is not changed dynamically, even though one might expect it to be, since it is specified in the first line of the prompt. ### Actual Behavior <@the name of the desired model> is added to the prompt as text but is not interpreted when sending the conversation. ### Steps to Reproduce 1. Go to Workspace > Prompts > Add New Prompt 2. Enter a title and a command (anything will do...) 3. In the prompt content, enter “@Sonoma Sky Alpha” (for example, to choose a specific model) and add content to the line, such as “Which LLM model am I using?” 4. Save 5. Create a new conversation and call up the prompt with “/” 6. Send ### Logs & Screenshots <img width="1007" height="442" alt="Image" src="https://github.com/user-attachments/assets/a7d4d008-3d27-4c26-bcc1-9093a7997071" /> ### Additional Information _No response_

GiteaMirror added the bug label 2025-11-11 16:54:05 -06:00

GiteaMirror closed this issue

2025-11-11 16:54:06 -06:00

GiteaMirror commented

2025-11-11 16:54:06 -06:00