Remote Ollama stopped working

I had runnig opencode with ollama on a second computer in the local network. It was working fine.

One of the recent updates broke my installation and I'm unable to get it running again. (Since I use opencode only sometimes I cannot pinpoint the exact version that broke for me).

My config to reproduce this:

{
  "$schema": "https://opencode.ai/config.json",
  "disabled_providers": [ "opencode" ],
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama",
      "options": {
        "baseURL": "http://192.168.1.26:11434/v1"
      },
      "models": {
        "qwen3:8b": {
          "name": "Qwen3"
        }
      }
    }
  }
}

Then opencode replies to any prompt with "Error: Was there a typo in the url or port?"

Running opencode with log level Debug writes

ERROR 2025-09-18T07:25:08 +2ms service=session.prompt session=ses_6a4498a9dffesactQKgvG248ok error=Was there a typo in the url or port? model=qwen3:8b failed to generate title
ERROR 2025-09-18T07:25:08 +0ms service=session.prompt session=ses_6a4498a9dffesactQKgvG248ok error={"error":{"code":"FailedToOpenSocket","path":"http://192.168.1.26:11434/v1/chat/completions","errno":0}} stream error
INFO  2025-09-18T07:25:08 +1ms service=session.prompt session=ses_6a4498a9dffesactQKgvG248ok type=error part
ERROR 2025-09-18T07:25:08 +0ms service=session.prompt session=ses_6a4498a9dffesactQKgvG248ok error=Was there a typo in the url or port? process

to the log file.

Observations:

I can curl the URL
Other programs on my local computer communicate well with the remote ollama server
Using the hostname of the server results in the same error (I use the IP to report the bug to avoid any influence may caused by DNS issues)
Replacing the IP with localhost or 127.0.0.1 and running ollama locally DOES work!
I disabled the opencode providers to avoid any clutter in the ui or selecting the right model. Removing the line form the config does not solve or change the problem.

opencode v0.9.11

This issue might be a duplicate of existing issues. Please check:

bug? Ollama does not work as a provider unless configured with an API key #227: Ollama does not work as a provider unless configured with an API key - This issue describes similar connectivity problems with remote Ollama servers and mentions configuration requirements
Provider ollama, AI_APICallError: json: cannot unmarshal array into Go struct field #116: Provider ollama AI_APICallError - Shows similar JSON unmarshaling errors when connecting to Ollama providers

The FailedToOpenSocket error you're experiencing when connecting to remote Ollama (but not localhost) appears to be related to how opencode handles remote Ollama connections, which has been reported before.

Feel free to ignore if none of these address your specific case.

EDIT: I clear also ~/.cache/opencode

EDIT: I added an API key, same result.

It's working on my machine though

i'm using qwen2.5:0.5b for testing purpose and it works.
Please check if you ollama server is listening on all interface,

Try running:
❯ curl http://192.168.1.26:11434/api/generate -d '{ "model": "qwen3:8b", "prompt": "What is water made of?" }'

if it doesn't work, then set this environment variable

OLLAMA_HOST=0.0.0.0:11434

This seems like something specific to your setup rather than an opencode issue

Thank a lot for trying to reproduce it!

However as stated initially I indeed can curl the remote Ollama and other AI applications work well:

curl http://192.168.1.26:11434/api/generate -d '{ "model": "qwen3:8b", "prompt": "What is water made of?" }'
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.271567Z","response":"\u003cthink\u003e","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.285369Z","response":"\n","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.298985Z","response":"Okay","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.312553Z","response":",","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.326395Z","response":" the","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.340083Z","response":" user","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.353762Z","response":" is","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.367425Z","response":" asking","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.381219Z","response":" \"","done":false}
{"model":"qwen3:8b","created_at":"2025-09-18T15:53:07.394836Z","response":"What","done":false}
...

So its here only my opencode setup that is broken, but the debug log does any good hints. How can I debug this further?

@HendrikSP

@HendrikSP can you curl the completions endpoint tho? /v1/chat/completions

Yes, i can:

curl http://192.168.1.26:11434/v1/chat/completions -d '{ "model": "qwen3:8b", "messages": [ { "role": "user", "content": "What is water made of?" } ] }'

{"id":"chatcmpl-681","object":"chat.completion","created":1758214346,"model":"qwen3:8b","system_fingerprint":"fp_ollama","choices":[{"index":0,"message":{"role":"assistant","content":"\u003cthink\u003e\nOkay, the user is asking, \"What is water m...

Hi, thank you for your help here. I went down the rabbit hole and tried a an simple example using ai-sdk directly. Not working. Tried to use just fetch. Not working. Found out that bun and node are affected. Tried a different Terminal App - works. It seems that Apple is blocking my other Terminal, but the only affected programs seems to be node and bun as far as I can tell. The Terminal App have permissions to access the local net. I will look into that myself now. Thanks again! :)

Damn.

PS: Working now everywhere. Seems an Update of the Terminal app and a long running tmux session was the problem. Why only the JS engines had been effected is not clear nor logical to me. :)

PS: Working now everywhere. Seems an Update of the Terminal app and a long running tmux session was the problem. Why only the JS engines had been effected is not clear nor logical to me. :)

I have the same problem, tmux getting blocked after a while and opencode gives an error when trying to connect to the llm server. Tmux kill-server solves the blocking, but this is not ideal...

just wanted to comment that I've been trying to debug the same behaviour; I normally use long running tmux sessions for everything and couldn't understand why I got the Error: Was there a typo in the url or port? error.

Starting a terminal without tmux (raw bash or zsh for example), lets you run opencode connecting to remote ollama just fine.

very weird behaviour 🤷

I ran into this. I did not have tmux running on either host or client machine. The only way I could get it to work was by SSH tunnel then changing the baseURL to 127.0.0.1

I ran into this. I did not have tmux running on either host or client machine. The only way I could get it to work was by SSH tunnel then changing the baseURL to 127.0.0.1

I could not get to work. trying from macos (opencode) to windows (llama.cpp lllama-server /v1 openai). using the LAN IP address always is saying Error: Was there a typo in the url or port?

my workstation is macos, and the GTX card is installed in a windows machine, so I am not willing to run opencode on windows.

Be careful if you use iTerm2, I switched to another terminal, in this case Ghostty and the local IP worked. Beforehand I had to SSH port forwarding. So yes check your local environment first, no idea why some terminals just block access to local IP's for now reason at all.

Be careful if you use iTerm2, I switched to another terminal, in this case Ghostty and the local IP worked. Beforehand I had to SSH port forwarding. So yes check your local environment first, no idea why some terminals just block access to local IP's for now reason at all.

thanks for the tip. by the way, I tried enabling debug logging verbosity and I couldn't find any difference in the log file. the most frustrating thing on this is lack of visibility into the error/conditions.

I installed Ghostty on my macos, ran opencode uninstall and then brew install opencode, saving my old config.json into config directory and starting opencode in a ghostty session.

There were macOS network access dialog and Little Snitch (firewall) warnings I had to allow. Got Error: Was there a typo in the url or port the first time I tried /init.

but then after approving the access to LAN for firewalls, opencode started working with my llama.cpp llama-server qwen3-coder-next model running on another host in my LAN.

it's possible that my iTerm2.app didn't have the right firewall allowances which led to the earlier errors.

Navigation Menu

Repository navigation

Remote Ollama stopped working #2667

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Remote Ollama stopped working #2667

Description

Activity

github-actions commented on Sep 18, 2025

HendrikSP commented on Sep 18, 2025

HendrikSP commented on Sep 18, 2025

Dark-Kernel commented on Sep 18, 2025

rekram1-node commented on Sep 18, 2025

HendrikSP commented on Sep 18, 2025

rekram1-node commented on Sep 18, 2025

HendrikSP commented on Sep 18, 2025

HendrikSP commented on Sep 18, 2025

Dark-Kernel commented on Sep 18, 2025

HendrikSP commented on Sep 18, 2025

pieterst67 commented on Oct 1, 2025

preflightsiren commented on Feb 4, 2026

rfrowe commented on Feb 28, 2026

idcrook commented on Mar 2, 2026

YukiGibson commented on Mar 3, 2026

idcrook commented on Mar 3, 2026

idcrook commented on Mar 3, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions