debug_hf_space.py

"""
Debug Hugging Face Space - Check logs and diagnose issues
"""
import os
import sys
from huggingface_hub import HfApi
import time

# Configuration
YOUR_USERNAME = "nocapdev"
SPACE_NAME = "my-gradio-momask"
TOKEN = os.getenv("HUGGINGFACE_TOKEN")

def main():
    print("=" * 80)
    print(" " * 25 + "HF Space Debugger")
    print("=" * 80)

    if not TOKEN:
        print("\n❌ ERROR: HUGGINGFACE_TOKEN not set")
        print("Set it with: $env:HUGGINGFACE_TOKEN = 'hf_your_token'")
        print("\nAlternatively, check logs manually at:")
        print(f"https://huggingface.co/spaces/{YOUR_USERNAME}/{SPACE_NAME}/logs")
        return

    api = HfApi(token=TOKEN)
    repo_id = f"{YOUR_USERNAME}/{SPACE_NAME}"

    print(f"\n📍 Space: {repo_id}")
    print(f"🔗 URL: https://huggingface.co/spaces/{repo_id}")
    print(f"📊 Logs: https://huggingface.co/spaces/{repo_id}/logs")

    try:
        # Get space runtime info
        print("\n" + "─" * 80)
        print("🔧 RUNTIME INFORMATION")
        print("─" * 80)

        runtime = api.get_space_runtime(repo_id=repo_id)

        print(f"Status: {runtime.stage}")
        print(f"Hardware: {runtime.hardware or 'CPU basic (free)'}")

        # Try to get SDK info if available
        try:
            print(f"SDK: {runtime.sdk}")
        except AttributeError:
            print(f"SDK: gradio (inferred)")

        try:
            print(f"SDK Version: {runtime.sdk_version or 'N/A'}")
        except AttributeError:
            print(f"SDK Version: N/A")

        # Analyze status
        if runtime.stage == "RUNNING":
            print("\n✅ Space is RUNNING")
        elif runtime.stage == "BUILDING":
            print("\n⏳ Space is BUILDING... (wait a few minutes)")
        elif runtime.stage == "STOPPED":
            print("\n⚠️  Space is STOPPED (may have crashed)")
        elif runtime.stage == "SLEEPING":
            print("\n😴 Space is SLEEPING (will wake on visit)")
        else:
            print(f"\n⚠️  Unexpected stage: {runtime.stage}")

        # Hardware analysis
        print("\n" + "─" * 80)
        print("💻 HARDWARE ANALYSIS")
        print("─" * 80)

        hardware = str(runtime.hardware or 'cpu-basic').lower()

        if 'cpu' in hardware or runtime.hardware is None:
            print("⚠️  Using CPU (FREE tier)")
            print("   • Generation time: 10-30 minutes per prompt")
            print("   • This is NORMAL for free tier")
            print("   • Recommendation: Upgrade to GPU or be patient")
        elif 't4' in hardware:
            print("✅ Using T4 GPU")
            print("   • Generation time: 20-60 seconds per prompt")
            print("   • Good performance")
        elif 'a10' in hardware or 'a100' in hardware:
            print("✅ Using High-end GPU")
            print("   • Generation time: 10-30 seconds per prompt")
            print("   • Excellent performance")

        # Get space info
        print("\n" + "─" * 80)
        print("📦 SPACE FILES")
        print("─" * 80)

        try:
            files = api.list_repo_files(repo_id=repo_id, repo_type="space")

            # Check critical files
            critical_files = ['app.py', 'requirements.txt', 'README.md']
            for file in critical_files:
                if file in files:
                    print(f"✅ {file}")
                else:
                    print(f"❌ {file} - MISSING!")

            # Check for checkpoints
            checkpoint_files = [f for f in files if 'checkpoint' in f.lower() or f.endswith('.tar') or f.endswith('.pth')]

            if checkpoint_files:
                print(f"\n✅ Found {len(checkpoint_files)} checkpoint files")
                print("   Sample files:")
                for f in checkpoint_files[:5]:
                    print(f"   • {f}")
                if len(checkpoint_files) > 5:
                    print(f"   ... and {len(checkpoint_files) - 5} more")
            else:
                print("\n⚠️  NO checkpoint files found!")
                print("   • Models may not be uploaded")
                print("   • App will fail to initialize")
                print("   • Action: Upload checkpoints/ directory")

        except Exception as e:
            print(f"⚠️  Could not list files: {e}")

        # Provide debugging steps
        print("\n" + "=" * 80)
        print("🔍 DEBUGGING STEPS")
        print("=" * 80)

        print("\n1. CHECK LOGS MANUALLY:")
        print(f"   Visit: https://huggingface.co/spaces/{repo_id}/logs")
        print("   Look for:")
        print("   • 'Using device: cpu' or 'Using device: cuda'")
        print("   • Any ERROR messages")
        print("   • 'Model checkpoints not found'")
        print("   • Traceback or exception messages")

        print("\n2. COMMON ERROR PATTERNS:")
        print("   • 'FileNotFoundError' → Models not uploaded")
        print("   • 'CUDA out of memory' → Need more GPU RAM")
        print("   • 'Killed' or 'SIGKILL' → Out of RAM")
        print("   • Hangs at '[1/4] Generating...' → CPU is slow (wait 20 mins)")

        print("\n3. QUICK TESTS:")
        print("   • Visit the Space URL")
        print("   • Try prompt: 'a person walks forward'")
        print("   • Monitor Logs tab while it runs")

        if 'cpu' in hardware or runtime.hardware is None:
            print("\n⚠️  CPU PERFORMANCE WARNING:")
            print("   Your Space is using CPU. Expected behavior:")
            print("   • First load: 2-5 minutes (loading models)")
            print("   • Each generation: 10-30 minutes")
            print("   • This is NORMAL for CPU!")
            print("   • Solutions:")
            print("     - Wait patiently (free)")
            print("     - Upgrade to T4 GPU (~$0.60/hour)")

        print("\n4. IMMEDIATE ACTION:")
        print("   Copy the ERROR message from Logs tab and share it")

        print("\n" + "=" * 80)

    except Exception as e:
        print("\n" + "=" * 80)
        print("❌ ERROR CHECKING SPACE")
        print("=" * 80)
        print(f"Error: {e}")
        print("\nManual debugging required:")
        print(f"1. Visit: https://huggingface.co/spaces/{repo_id}")
        print(f"2. Click 'Logs' tab")
        print(f"3. Copy the last 50 lines")
        print(f"4. Share the error messages")
        print("\n" + "=" * 80)

if __name__ == "__main__":
    try:
        main()
    except KeyboardInterrupt:
        print("\n\nCancelled by user")
    except Exception as e:
        print(f"\n\nUnexpected error: {e}")
        import traceback
        traceback.print_exc()