Nemotron seems to ignore my request when using ollama

[karthikappy]

Description

I am trying to use a local LLM (nemotron-3-nano:30b) via ollama to run opencode. When I send a message in plan mode, I get a response stating that the model is in plan mode but has not received a request. I get a similar response in build mode (but sometimes i get tool calls that error out in the response.

OpenCode version

1.0.206

Steps to reproduce

1. Install ollama
2. Install opencode via npm
3. Create a new folder and create an opencode.json file

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "http://127.0.0.1:11434/v1",
      },
      "models": {
        "nemotron-3-nano:30b": {}
      }
    }
  }
}

4. Open a terminal in the current directory and start opencode, select the correct model and try to send a message

Screenshot and/or share link

https://opncd.ai/share/b5WLRobS

Operating System

Windows 11

Terminal

Windows Terminal