llm_council/scripts/test_gpu_vm.py

#!/usr/bin/env python3
"""Quick test script to check GPU VM connection."""

import asyncio
import sys
sys.path.insert(0, '.')

from backend.llm_client import list_models
from backend.config import OPENAI_COMPAT_BASE_URL, COUNCIL_MODELS, CHAIRMAN_MODEL

async def test_connection():
    print(f"Testing connection to: {OPENAI_COMPAT_BASE_URL}")
    print(f"Configured council models: {COUNCIL_MODELS}")
    print(f"Chairman model: {CHAIRMAN_MODEL}")
    print("-" * 60)
    
    try:
        models = await list_models()
        if models is None:
            print("✗ Unable to list models (connection error, timeout, or incompatible endpoint).")
            print("")
            print("Next checks:")
            print(f"  - curl {OPENAI_COMPAT_BASE_URL.rstrip('/')}/api/tags")
            print(f"  - curl {OPENAI_COMPAT_BASE_URL.rstrip('/')}/v1/models")
            print("")
            print("If you're using Ollama remotely, the port is usually 11434.")
            return
        if models:
            print(f"✓ Connection successful!")
            print(f"Found {len(models)} available models:\n")
            for model in models:
                marker = "✓" if model in COUNCIL_MODELS else " "
                chairman_marker = " (CHAIRMAN)" if model == CHAIRMAN_MODEL else ""
                print(f"  {marker} {model}{chairman_marker}")
            
            print("\n" + "-" * 60)
            missing = [m for m in COUNCIL_MODELS if m not in models]
            if missing:
                print(f"⚠ Warning: {len(missing)} configured models not found:")
                for m in missing:
                    print(f"  - {m}")
            else:
                print("✓ All configured council models are available!")
        else:
            print("✗ Connected, but the server returned an empty model list.")
            print("  This is unusual for Ollama; double-check the base URL/port and server.")
    except Exception as e:
        print(f"✗ Connection failed: {type(e).__name__}: {e}")
        import traceback
        traceback.print_exc()

if __name__ == "__main__":
    asyncio.run(test_connection())