Ollama setup trouble.

[qwerty108109]

Question

This time around when setting up OpenCoder with Ollama to use offline, I am having a lot of trouble.
This is what my configuration file looks like.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama (PC1)",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "ministral-3:3b": {
          "name": "ministral-3:3b"
        }
      }  
    }  
  }  
}  

Whenever I use the /models it does not give me an option for my Ollama models.

I am currently using Linux Debbie 13 and I am using opencode Version 1.0.134.
Ollama Version 0.13.1

[github-actions]

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

• need help setting up ollama #4862: Ollama provider initialization fails with similar configuration setup (ProviderInitError with TypeError)
• Why is opencode not working with local llms via Ollama? #4428: Similar issues with Ollama models not working despite correct configuration
• bug? Ollama does not work as a provider unless configured with an API key #227: Ollama requires API key configuration even for localhost setup

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

[qwerty108109]

No, I can't get my Ollama models to come up at all.

[qwerty108109]

My Ollama models do not even appear as an option.