"""
Gradio app for MentorFlow - Teacher-Student RL System
Deployed on Hugging Face Spaces with GPU support
"""

import sys
import os
import subprocess
from pathlib import Path
import gradio as gr  # Import directly, no patch needed

# Add project paths
sys.path.insert(0, str(Path(__file__).parent))
sys.path.insert(0, str(Path(__file__).parent / "teacher_agent_dev"))
sys.path.insert(0, str(Path(__file__).parent / "student_agent_dev"))

def run_comparison(iterations: int, seed: int, use_deterministic: bool, device: str):
    """
    Run strategy comparison with LM Student.
    """
    
    # Set device environment variable for subprocess
    if device == "cuda":
        try:
            import torch
            if torch.cuda.is_available():
                try:
                    gpu_name = torch.cuda.get_device_name(0)
                    gpu_count = torch.cuda.device_count()
                    print(f"✅ GPU available: {gpu_name} (Count: {gpu_count})")
                except Exception as e:
                    print(f"⚠️ GPU detection failed: {e}")
            else:
                print("⚠️ CUDA not available, falling back to CPU")
                device = "cpu"
        except ImportError:
            print("⚠️ PyTorch not available, falling back to CPU")
            device = "cpu"
        except Exception as e:
            print(f"⚠️ GPU check error: {e}, falling back to CPU")
            device = "cpu"
    
    # Set environment variable for subprocess
    os.environ["CUDA_DEVICE"] = device
    print(f"🔧 Using device: {device}")
    
    # Prepare command
    cmd = [
        sys.executable,
        "teacher_agent_dev/compare_strategies.py",
        "--iterations", str(iterations),
    ]
    
    if use_deterministic:
        cmd.append("--deterministic")
    else:
        cmd.extend(["--seed", str(int(seed))])
    
    try:
        env = os.environ.copy()
        env["CUDA_DEVICE"] = os.environ.get("CUDA_DEVICE", device)
        
        result = subprocess.run(
            cmd,
            cwd=str(Path(__file__).parent),
            env=env,
            capture_output=True,
            text=True,
            timeout=3600  # 1 hour timeout
        )
        
        stdout_text = result.stdout
        stderr_text = result.stderr
        
        full_output = f"=== STDOUT ===\n{stdout_text}\n\n=== STDERR ===\n{stderr_text}"
        
        if result.returncode != 0:
            return f"❌ Error occurred:\n{full_output}", None
        
        # Check multiple possible locations for the plot
        plot_paths = [
            Path(__file__).parent / "teacher_agent_dev" / "comparison_all_strategies.png",
            Path(__file__).parent / "comparison_all_strategies.png",
            Path.cwd() / "teacher_agent_dev" / "comparison_all_strategies.png",
        ]
        
        plot_path = None
        for path in plot_paths:
            if path.exists():
                plot_path = path
                break
        
        if plot_path:
            return f"✅ Comparison complete!\n\n{stdout_text}", str(plot_path)
        else:
            error_msg = f"⚠️ Plot not found at expected locations.\n"
            error_msg += f"Checked: {[str(p) for p in plot_paths]}\n\n"
            error_msg += f"Output:\n{full_output}"
            return error_msg, None
                
    except subprocess.TimeoutExpired:
        return "❌ Timeout: Comparison took longer than 1 hour", None
    except Exception as e:
        import traceback
        return f"❌ Error: {str(e)}\n\n{traceback.format_exc()}", None


def check_gpu():
    """Check if GPU is available on Hugging Face Spaces."""
    try:
        import torch
        if torch.cuda.is_available():
            try:
                gpu_name = torch.cuda.get_device_name(0)
                gpu_count = torch.cuda.device_count()
                cuda_version = torch.version.cuda
                return f"✅ GPU Available: {gpu_name} (Count: {gpu_count}, CUDA: {cuda_version})"
            except Exception as e:
                return f"✅ GPU Detected (accessing: {str(e)[:50]}...)"
        else:
            if os.getenv("SPACE_ID"):
                hf_hardware = os.getenv("SPACE_HARDWARE", "unknown")
                if "gpu" in hf_hardware.lower() or "t4" in hf_hardware.lower() or "l4" in hf_hardware.lower():
                    return f"⚠️ GPU Hardware ({hf_hardware}) allocated but not accessible yet. Try running anyway."
                return f"⚠️ No GPU on this Space (hardware: {hf_hardware}). Please configure GPU tier."
            return "⚠️ No GPU available, will use CPU"
    except ImportError:
        return "⚠️ PyTorch not installed"
    except Exception as e:
        return f"⚠️ GPU check error: {str(e)}"


# Create Gradio interface
with gr.Blocks(title="MentorFlow - Strategy Comparison") as demo:
    gr.Markdown("""
    # 🎓 MentorFlow - Teacher-Student RL System
    
    Compare three training strategies using LM Student (DistilBERT):
    1. **Random Strategy**: Random questions until student can pass difficult questions
    2. **Progressive Strategy**: Easy → Medium → Hard within each family
    3. **Teacher Strategy**: RL teacher agent learns optimal curriculum
    
    ## Usage
    1. Set parameters below
    2. Click "Run Comparison" to start training
    3. View results and generated plots
    """)
    
    # GPU Status
    with gr.Row():
        gpu_status = gr.Textbox(label="GPU Status", value=check_gpu(), interactive=False)
        refresh_btn = gr.Button("🔄 Refresh GPU Status")
    
    refresh_btn.click(fn=check_gpu, outputs=gpu_status, api_name="check_gpu")
    
    # Parameters
    with gr.Row():
        with gr.Column():
            iterations = gr.Slider(minimum=50, maximum=500, value=100, step=50, label="Iterations")
            seed = gr.Number(value=42, label="Random Seed")
            use_deterministic = gr.Checkbox(value=True, label="Deterministic Mode")
            device = gr.Radio(choices=["cuda", "cpu"], value="cuda", label="Device")
        
        with gr.Column():
            run_btn = gr.Button("🚀 Run Comparison", variant="primary", size="lg")
    
    # Output
    with gr.Row():
        with gr.Column(scale=1):
            output_text = gr.Textbox(label="Output", lines=15, max_lines=30, interactive=False)
        with gr.Column(scale=1):
            output_plot = gr.Image(label="Comparison Plot", type="filepath", height=500)
    
    # Run comparison
    run_btn.click(
        fn=run_comparison,
        inputs=[iterations, seed, use_deterministic, device],
        outputs=[output_text, output_plot],
        api_name="run_comparison"
    )

if __name__ == "__main__":
    # Standard HF Spaces configuration
    demo.launch(server_name="0.0.0.0", server_port=7860)