src/streamlit_app.py

import streamlit as st
from PIL import Image
from core.inference import load_deepfake_model
from ui.styles import apply_custom_styles
from ui.components import render_header, render_result, render_footer

# --- Page Config ---
st.set_page_config(
    page_title="Deepfake Image Detector",
    page_icon="🕵️",
    layout="centered",
    initial_sidebar_state="collapsed",
)

# --- Apply UI ---
apply_custom_styles()
render_header()

# ✅ FIX 1: Use cache instead of session_state + spinner
@st.cache_resource
def get_model():
    return load_deepfake_model()

classifier = get_model()

# --- Upload ---
st.markdown("### 📤 Image Upload")

uploaded_file = st.file_uploader(
    "Select or Drag & Drop an Image (JPG, JPEG, PNG)",
    type=["jpg", "jpeg", "png"],
    label_visibility="collapsed"
)

if uploaded_file is not None:
    try:
        image = Image.open(uploaded_file).convert("RGB")
    except Exception as e:
        st.error(f"Image loading error: {e}")
        st.stop()

    col1, col2, col3 = st.columns([1, 2, 1])
    with col2:
        st.image(image, caption="Uploaded Image", use_container_width=True)

    # --- Analyze Button ---
    if st.button("Analyze Image"):
        try:
            # ✅ FIX 2: Safe spinner (only during inference)
            with st.spinner("Running Deepfake Detection..."):
                results = classifier(image)

            top_result = results[0]
            label = top_result['label'].lower()
            score = top_result['score']

            is_fake = "fake" in label
            confidence_percentage = round(score * 100, 2)

            # --- Show Result ---
            render_result(is_fake, confidence_percentage)

        except Exception as e:
            st.error(f"Error: {e}")

# --- Footer ---
render_footer()