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

v0.7.2

Ollama Version (if applicable)

v0.14.3

Operating System

Linux Mint 19.1

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

When I ask the model to do something in opencode it calls a tool and after that it gives the answer I asked, this works when I use the model directly from the Ollama API as shown below:

user@host dir % opencode run "Create the file 'README' with the contents 'hello world', let me know if it succeeded" --model ollama/glm-4.7-flash:bf16-80k

I'll create the README file with the specified content.

| Write Users/user/dir/README

README created successfully with content "hello world".

Actual Behavior

But when I use the same model from Ollama but route it trough the WebUI API, it always stops the execution after a tool call shown below, it correctly creates the file but after that it stops. This happens all the time in opencode with this configuration every time it calls a tool it stops execution and I have to manually type continue after each tool call

user@host dir % opencode run "Create the file 'README' with the contents 'hello world', let me know if it succeeded" --model webui/glm-4.7-flash:bf16-80k
| Write Users/user/dir/README

Steps to Reproduce

1. Setup ollama (v0.14.3) and install the model glm-4.7-flash:bf16 with a context_size of 80_000 (it can be smaller).
2. add that Ollama service to WebUI as a connection, so the model is accessible there
3. Enable API access for users
4. Install opencode (1.1.20)
5. configure opencode to be able to use the model trough open WebUI

example opencode config:
{
"$schema": "https://opencode.ai/config.json",
"permission": {
"edit": "allow",
"bash": "ask",
"webfetch": "ask",
"doom_loop": "ask",
"external_directory": "ask"
},
"provider": {
"webui": {
"npm": "@ai-sdk/openai-compatible",
"name": "WebUI",
"options": {
"baseURL": "http://{{ip_webui}}:{{port_webui}}/api/v1",
"apiKey": "{{key}}"
},
"models": {
"glm-4.7-flash:bf16-80k": {
"name": "GLM 4.7 Flash"
}
}
},
}

Logs & Screenshots

No weird logs:

2026-01-23 15:20:21.170 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56959 - "GET /api/v1/groups/ HTTP/1.1" 200
2026-01-23 15:20:21.172 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56956 - "GET /api/v1/auths/admin/config/ldap HTTP/1.1" 200
2026-01-23 15:20:21.182 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56955 - "GET /api/version/updates HTTP/1.1" 200
2026-01-23 15:20:21.194 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56958 - "GET /api/version/updates HTTP/1.1" 200
2026-01-23 15:20:21.284 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56957 - "GET /api/v1/auths/admin/config/ldap HTTP/1.1" 200
2026-01-23 15:20:31.788 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56961 - "GET /_app/version.json HTTP/1.1" 304
2026-01-23 15:21:31.788 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56967 - "GET /_app/version.json HTTP/1.1" 304
2026-01-23 15:22:31.782 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56969 - "GET /_app/version.json HTTP/1.1" 304
2026-01-23 15:23:31.779 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56970 - "GET /_app/version.json HTTP/1.1" 304
2026-01-23 15:24:31.781 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56973 - "GET /_app/version.json HTTP/1.1" 304
2026-01-23 15:25:31.786 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56974 - "GET /_app/version.json HTTP/1.1" 304
2026-01-23 15:26:31.790 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56976 - "GET /_app/version.json HTTP/1.1" 304
2026-01-23 15:27:18.064 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:60853 - "POST /api/v1/chat/completions HTTP/1.1" 200
2026-01-23 15:27:31.786 | INFO     | uvicorn.protocols.http.httptools_impl:send:483 - 10.55.163.237:56977 - "GET /_app/version.json HTTP/1.1" 304

Additional Information

config for the model in webUI is all default: glm-4.7-flash_bf16-80k-1769159953751.json