#!/usr/bin/env python3
"""
Debug: Voir ce que le VLM retourne réellement
"""

import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent.parent))

from core.detection.ollama_client import OllamaClient


def test_vlm_response():
    """Tester différents prompts avec le VLM"""
    
    client = OllamaClient(model="qwen3-vl:8b")
    screenshot_path = "rpa_vision_v3/examples/test_ui_screenshot.png"
    
    print("=" * 80)
    print("TEST 1: Prompt simple")
    print("=" * 80)
    
    prompt1 = "Describe what you see in this image."
    result1 = client.generate(prompt1, image_path=screenshot_path, temperature=0.1)
    
    if result1["success"]:
        print(f"✓ Réponse reçue ({len(result1['response'])} caractères)")
        print(f"\nRéponse:\n{result1['response']}\n")
    else:
        print(f"❌ Erreur: {result1['error']}")
    
    print("\n" + "=" * 80)
    print("TEST 2: Demander de lister les boutons")
    print("=" * 80)
    
    prompt2 = "List all the buttons you can see in this image. For each button, tell me its label."
    result2 = client.generate(prompt2, image_path=screenshot_path, temperature=0.1)
    
    if result2["success"]:
        print(f"✓ Réponse reçue ({len(result2['response'])} caractères)")
        print(f"\nRéponse:\n{result2['response']}\n")
    else:
        print(f"❌ Erreur: {result2['error']}")
    
    print("\n" + "=" * 80)
    print("TEST 3: Demander JSON simple")
    print("=" * 80)
    
    prompt3 = """List the buttons in this image as JSON.
Format: [{"label": "button text"}]
Return only the JSON array."""
    
    result3 = client.generate(prompt3, image_path=screenshot_path, temperature=0.0)
    
    if result3["success"]:
        print(f"✓ Réponse reçue ({len(result3['response'])} caractères)")
        print(f"\nRéponse:\n{result3['response']}\n")
    else:
        print(f"❌ Erreur: {result3['error']}")


if __name__ == "__main__":
    test_vlm_response()