github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-07 03:18:23 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #20150] issue: Tools not included for models in channel messages #57768

New Issue
Closed
opened 2026-05-05 21:34:55 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-05 21:34:55 -05:00
Owner
Copy Link

Originally created by @zhiweit on GitHub (Dec 24, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20150

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

Docker

Open WebUI Version

v0.6.43

Ollama Version (if applicable)

No response

Operating System

Ubuntu 22.04

Browser (if applicable)

Firefox 146.0.1

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

Custom workspace models configured with tools should work the same in channel messages; but the tools definitions are not included when sent to the chat completions API.

Include the tools for channel messages when sending to the chat completions API like how they were sent in normal chat messages.
E.g. The tools definition are sent in the chat completions API in a normal chat message

{
  "model": "gpt-4.1-mini",
  **"tools": [
    {
      "type": "function",
      "function": {
        "name": "aria_query_database",
        "parameters": {
          "type": "object",
          "required": [
            "query"
          ],
          "properties": {
            "query": {
              "type": "string",
              "examples": [
                "List all missions completed.",
                "Why did the mission tasks fail?"
              ],
              "description": "Decomposed single query from user's queries"
            },
            ... # truncated for brevity
  ]**,
  "stream": true,
  "messages": [
    {
      "role": "system",
      "content": "You are a detailed and helpful security AI assistant that helps draws on tools to create reports, conduct data analysis and troubleshooting. You have tools to retrieve more information about the robot mission, alerts event logs from the query_database tool."
    },
    {
      "role": "user",
      "content": "for my robot id 22, are there any missions that require intervention this week?"
    }
  ]
}

Actual Behavior

Context

I was trying out the channels feature to chat with my custom model that i have added an MCP tool server with it to chat with my own data. The model successfully calls the tool in normal chat because the tools were included in the chat completions API and open web ui handles the flow of getting the tool arguments, calling the tool, and generating the answer. This should be the same for messages sent in channel messages for custom models.

E.g. The logs from LiteLLM shows that the tools argument are not present in the chat completions API which probably caused the model to not call the tools.

{
  "model": "gpt-4.1-mini", 
  **# `tools` should be present here too when i am using my custom model**
  "stream": false,
  "messages": [
    {
      "role": "system",
      "content": "You are a detailed and helpful security AI assistant that helps draws on tools to create reports, conduct data analysis and troubleshooting. You have tools to retrieve more information about the robot mission, alerts event logs from the query_database tool. \nYou are aria-gpt-4.1-mini, participating in a threaded conversation. Be concise and conversational.Here's the thread history:\n\n\nadmin: aria-gpt-4.1-mini  how many unattended luggage alerts were there for colab 22 and colab 38 from 1 dec 2025 to 5 dec 2025?\n\n\nContinue the conversation naturally as aria-gpt-4.1-mini, addressing the most recent message while being aware of the full context."
    },
    {
      "role": "user",
      "content": "admin: aria-gpt-4.1-mini  how many unattended luggage alerts were there for colab 22 and colab 38 from 1 dec 2025 to 5 dec 2025?"
    }
  ]
}

Steps to Reproduce

  1. Install Docker
  2. Start open web ui using docker
  3. Add a MCP tool (Admin panel > Settings > External Tools )
  4. Create a new model (Workspace > New model)
  5. Check the MCP tool to add the tool to the model by default
  6. Chat with the new model in the Channels
  7. Observe the model does not call the tool (because the tools were not included in the chat completions API)

Logs & Screenshots

Image

Request log from LiteLLM of chat completions API after sending message in the channel

{
  "model": "gpt-4.1-mini",
  **# "tools": {...} should be provided here but was not sent**
  "stream": false,
  "messages": [
    {
      "role": "system",
      "content": "You are a detailed and helpful security AI assistant that helps draws on tools to create reports, conduct data analysis and troubleshooting. You have tools to retrieve more information about the robot mission, alerts event logs from the query_database tool. \nYou are aria-gpt-4.1-mini, participating in a threaded conversation. Be concise and conversational.Here's the thread history:\n\n\nadmin: aria-gpt-4.1-mini  how many unattended luggage alerts were there for colab 22 and colab 38 from 1 dec 2025 to 5 dec 2025?\n\n\nContinue the conversation naturally as aria-gpt-4.1-mini, addressing the most recent message while being aware of the full context."
    },
    {
      "role": "user",
      "content": "admin: aria-gpt-4.1-mini  how many unattended luggage alerts were there for colab 22 and colab 38 from 1 dec 2025 to 5 dec 2025?"
    }
  ]
}

Additional Information

No response

Originally created by @zhiweit on GitHub (Dec 24, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/20150 ### 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 Docker ### Open WebUI Version v0.6.43 ### Ollama Version (if applicable) _No response_ ### Operating System Ubuntu 22.04 ### Browser (if applicable) Firefox 146.0.1 ### 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 Custom workspace models configured with tools should work the same in channel messages; but the `tools` definitions are not included when sent to the chat completions API. Include the tools for channel messages when sending to the chat completions API like how they were sent in normal chat messages. E.g. The tools definition are sent in the chat completions API in a normal chat message ```json { "model": "gpt-4.1-mini", **"tools": [ { "type": "function", "function": { "name": "aria_query_database", "parameters": { "type": "object", "required": [ "query" ], "properties": { "query": { "type": "string", "examples": [ "List all missions completed.", "Why did the mission tasks fail?" ], "description": "Decomposed single query from user's queries" }, ... # truncated for brevity ]**, "stream": true, "messages": [ { "role": "system", "content": "You are a detailed and helpful security AI assistant that helps draws on tools to create reports, conduct data analysis and troubleshooting. You have tools to retrieve more information about the robot mission, alerts event logs from the query_database tool." }, { "role": "user", "content": "for my robot id 22, are there any missions that require intervention this week?" } ] } ``` ### Actual Behavior ### Context I was trying out the channels feature to chat with my custom model that i have added an MCP tool server with it to chat with my own data. The model successfully calls the tool in normal chat because the tools were included in the chat completions API and open web ui handles the flow of getting the tool arguments, calling the tool, and generating the answer. This should be the same for messages sent in channel messages for custom models. E.g. The logs from LiteLLM shows that the `tools` argument are not present in the chat completions API which probably caused the model to not call the tools. ```json { "model": "gpt-4.1-mini", **# `tools` should be present here too when i am using my custom model** "stream": false, "messages": [ { "role": "system", "content": "You are a detailed and helpful security AI assistant that helps draws on tools to create reports, conduct data analysis and troubleshooting. You have tools to retrieve more information about the robot mission, alerts event logs from the query_database tool. \nYou are aria-gpt-4.1-mini, participating in a threaded conversation. Be concise and conversational.Here's the thread history:\n\n\nadmin: aria-gpt-4.1-mini how many unattended luggage alerts were there for colab 22 and colab 38 from 1 dec 2025 to 5 dec 2025?\n\n\nContinue the conversation naturally as aria-gpt-4.1-mini, addressing the most recent message while being aware of the full context." }, { "role": "user", "content": "admin: aria-gpt-4.1-mini how many unattended luggage alerts were there for colab 22 and colab 38 from 1 dec 2025 to 5 dec 2025?" } ] } ``` ### Steps to Reproduce 1. Install Docker 2. Start open web ui using docker 3. Add a MCP tool (Admin panel > Settings > External Tools ) 4. Create a new model (Workspace > New model) 5. Check the MCP tool to add the tool to the model by default 6. Chat with the new model in the Channels 7. Observe the model does not call the tool (because the tools were not included in the chat completions API) ### Logs & Screenshots <img width="1077" height="784" alt="Image" src="https://github.com/user-attachments/assets/67da28f2-4157-440f-9b5d-df8ac0a266f7" /> Request log from LiteLLM of chat completions API after sending message in the channel ```json { "model": "gpt-4.1-mini", **# "tools": {...} should be provided here but was not sent** "stream": false, "messages": [ { "role": "system", "content": "You are a detailed and helpful security AI assistant that helps draws on tools to create reports, conduct data analysis and troubleshooting. You have tools to retrieve more information about the robot mission, alerts event logs from the query_database tool. \nYou are aria-gpt-4.1-mini, participating in a threaded conversation. Be concise and conversational.Here's the thread history:\n\n\nadmin: aria-gpt-4.1-mini how many unattended luggage alerts were there for colab 22 and colab 38 from 1 dec 2025 to 5 dec 2025?\n\n\nContinue the conversation naturally as aria-gpt-4.1-mini, addressing the most recent message while being aware of the full context." }, { "role": "user", "content": "admin: aria-gpt-4.1-mini how many unattended luggage alerts were there for colab 22 and colab 38 from 1 dec 2025 to 5 dec 2025?" } ] } ``` ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-05 21:34:55 -05:00
GiteaMirror commented 2026-05-05 21:34:56 -05:00
Author
Owner
Copy Link

@owui-terminator[bot] commented on GitHub (Dec 24, 2025):

🔍 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. #19864 issue:
    by Haervwe • Dec 10, 2025 • bug

  2. #20092 issue:
    by VideoRyan • Dec 22, 2025 • bug

  3. #19899 issue: openrouter Models not showing up in the model selection list.
    by AZComputerSolutions • Dec 12, 2025 • bug

  4. #19777 issue:
    by Yaute7 • Dec 05, 2025 • bug

  5. #20019 issue:
    by j63440490 • Dec 17, 2025 • bug

Show 5 more related issues

  1. #19877 issue:
    by dotmobo • Dec 11, 2025 • bug

  2. #19103 issue: no response from the model when ask in "channels"
    by silenceroom • Nov 11, 2025 • bug

  3. #19563 issue:
    by naruto7g • Nov 28, 2025 • bug

  4. #14835 issue: Tools info not shown in UI
    by m-ibm • Jun 10, 2025 • bug

  5. #19211 issue:
    by Byrnes9 • Nov 16, 2025 • 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:3688348994 --> @owui-terminator[bot] commented on GitHub (Dec 24, 2025): 🔍 **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. [#19864](https://github.com/open-webui/open-webui/issues/19864) **issue:** *by Haervwe • Dec 10, 2025 • `bug`* 2. [#20092](https://github.com/open-webui/open-webui/issues/20092) **issue:** *by VideoRyan • Dec 22, 2025 • `bug`* 3. [#19899](https://github.com/open-webui/open-webui/issues/19899) **issue: openrouter Models not showing up in the model selection list.** *by AZComputerSolutions • Dec 12, 2025 • `bug`* 4. [#19777](https://github.com/open-webui/open-webui/issues/19777) **issue:** *by Yaute7 • Dec 05, 2025 • `bug`* 5. [#20019](https://github.com/open-webui/open-webui/issues/20019) **issue:** *by j63440490 • Dec 17, 2025 • `bug`* <details> <summary>Show 5 more related issues</summary> 6. [#19877](https://github.com/open-webui/open-webui/issues/19877) **issue:** *by dotmobo • Dec 11, 2025 • `bug`* 7. [#19103](https://github.com/open-webui/open-webui/issues/19103) **issue: no response from the model when ask in "channels"** *by silenceroom • Nov 11, 2025 • `bug`* 8. [#19563](https://github.com/open-webui/open-webui/issues/19563) **issue:** *by naruto7g • Nov 28, 2025 • `bug`* 9. [#14835](https://github.com/open-webui/open-webui/issues/14835) **issue: Tools info not shown in UI** *by m-ibm • Jun 10, 2025 • `bug`* 10. [#19211](https://github.com/open-webui/open-webui/issues/19211) **issue:** *by Byrnes9 • Nov 16, 2025 • `bug`* </details> --- 💡 **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.
GiteaMirror commented 2026-05-05 21:34:57 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Dec 24, 2025):

https://github.com/open-webui/open-webui/issues/8050

<!-- gh-comment-id:3688947347 --> @tjbck commented on GitHub (Dec 24, 2025): https://github.com/open-webui/open-webui/issues/8050
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#57768
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?