llm_council/scripts/test_gpu_vm_detailed.py

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

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

import httpx
from backend.config import OPENAI_COMPAT_BASE_URL

async def test_endpoints():
    base_url = "http://10.0.30.63"
    ports = [8000, 11434]
    endpoints = [
        "/v1/models",
        "/api/tags",
        "/api/version",
        "/",
    ]
    
    print("Testing GPU VM connection...")
    print("=" * 60)
    
    for port in ports:
        print(f"\nTesting port {port}:")
        print("-" * 60)
        for endpoint in endpoints:
            url = f"{base_url}:{port}{endpoint}"
            try:
                async with httpx.AsyncClient(timeout=5.0) as client:
                    resp = await client.get(url)
                    print(f"  {endpoint:20} -> Status: {resp.status_code}")
                    if resp.status_code == 200:
                        try:
                            data = resp.json()
                            if isinstance(data, dict):
                                if 'data' in data:
                                    models = data['data']
                                    print(f"    Found {len(models)} models via /v1/models")
                                    if models:
                                        print(f"    First model: {models[0].get('id', models[0])}")
                                elif 'models' in data:
                                    models = data['models']
                                    print(f"    Found {len(models)} models via /api/tags")
                                    if models:
                                        print(f"    First model: {models[0].get('name', models[0])}")
                                else:
                                    print(f"    Response keys: {list(data.keys())[:5]}")
                            elif isinstance(data, list):
                                print(f"    Found {len(data)} items")
                        except:
                            print(f"    Response (first 200 chars): {resp.text[:200]}")
            except httpx.TimeoutException:
                print(f"  {endpoint:20} -> Timeout")
            except httpx.ConnectError:
                print(f"  {endpoint:20} -> Connection refused")
            except Exception as e:
                print(f"  {endpoint:20} -> Error: {type(e).__name__}")

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