[GH-ISSUE #22470] issue: temp chats: openai api native tool calling doesn't follow json schema

Originally created by @pfn on GitHub (Mar 9, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/22470 ### 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 0.8.9 ### Ollama Version (if applicable) _No response_ ### Operating System linux ### Browser (if applicable) chrome ### 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 Temp chats should send proper schema to openai backend as normal chats do. This is a continuation of https://github.com/open-webui/open-webui/discussions/22379 as it was originally stated to be for everything, however it only occurs in temp chats. ### Actual Behavior Temp chats collapse tool-role content into assistant-role content. This causes models to stop calling tools because they are entrained to thinking that they can just output the tool result directly. ### Steps to Reproduce * Log payload in backend/open_webui/routers/openai.py * Set native tool calling * Start a temp chat * Generate an image * confirm the generation * observe the json payload sent ### Logs & Screenshots see https://github.com/open-webui/open-webui/discussions/22379 for full logs ### Additional Information Why is this important? There are very often times when I'm generating image content that I do not want logged into my chat history. After a while, the image generator stops running because the model refuses to make the tool_call and instead thinks it can perform the tool function by simply emitting hallucinated result json.

GiteaMirror commented

2026-04-25 09:28:52 -05:00

Owner

Originally created by @pfn on GitHub (Mar 9, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22470

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

0.8.9

Ollama Version (if applicable)

No response

Operating System

linux

Browser (if applicable)

chrome

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

Temp chats should send proper schema to openai backend as normal chats do.

This is a continuation of https://github.com/open-webui/open-webui/discussions/22379 as it was originally stated to be for everything, however it only occurs in temp chats.

Actual Behavior

Temp chats collapse tool-role content into assistant-role content. This causes models to stop calling tools because they are entrained to thinking that they can just output the tool result directly.

Steps to Reproduce

Log payload in backend/open_webui/routers/openai.py
Set native tool calling
Start a temp chat
Generate an image
confirm the generation
observe the json payload sent

Logs & Screenshots

see https://github.com/open-webui/open-webui/discussions/22379 for full logs

Additional Information

Why is this important? There are very often times when I'm generating image content that I do not want logged into my chat history. After a while, the image generator stops running because the model refuses to make the tool_call and instead thinks it can perform the tool function by simply emitting hallucinated result json.

GiteaMirror added the bug label 2026-04-25 09:28:52 -05:00

GiteaMirror closed this issue

2026-04-25 09:28:53 -05:00

[GH-ISSUE #22470] issue: temp chats: openai api native tool calling doesn't follow json schema #35247