#!/usr/bin/env python3
"""Test that we can actually query a model and get a response."""

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

from backend.llm_client import query_model
from backend.config import COUNCIL_MODELS

async def test_query():
    """Test querying one of the council models."""
    if not COUNCIL_MODELS:
        print("✗ No council models configured")
        return False
    
    test_model = COUNCIL_MODELS[0]
    print(f"Testing query to model: {test_model}")
    print("-" * 60)
    
    try:
        response = await query_model(
            model=test_model,
            messages=[{"role": "user", "content": "Say 'Hello, GPU Ollama is working!' in one sentence."}],
            max_tokens_override=50,  # Short response for quick test
            timeout=30.0
        )
        
        if response and response.get('content'):
            content = response['content'].strip()
            print(f"✓ Query successful!")
            print(f"\nResponse:")
            print(f"  {content}")
            return True
        else:
            print(f"✗ Query returned no content")
            print(f"Response: {response}")
            return False
    except Exception as e:
        print(f"✗ Query failed: {type(e).__name__}: {e}")
        import traceback
        traceback.print_exc()
        return False

if __name__ == "__main__":
    success = asyncio.run(test_query())
    sys.exit(0 if success else 1)