import gradio as gr
import os
import json
import mimetypes
from dotenv import load_dotenv

# Your exact requested imports
from google import genai
from google.genai import types

# --- Configuration and Client Initialization ---
load_dotenv()

try:
    # Initializing the client exactly as in your code
    client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])
except KeyError:
    raise gr.Error("FATAL: GEMINI_API_KEY not found. Please set it in your Hugging Face Space secrets.")

# --- Core Gradio Function ---

def analyze_device_condition(video_file_path):
    if not video_file_path:
        return "Please upload video", "", ""

    try:
        # 1. Prepare video file
        mime_type, _ = mimetypes.guess_type(video_file_path)
        if not mime_type or not mime_type.startswith("video"):
            raise ValueError("Unsupported file type.")
        
        with open(video_file_path, "rb") as video:
            video_part = types.Part(
                inline_data=types.Blob(mime_type=mime_type, data=video.read())
            )
        
        # 2. Prepare the prompt
        prompt = """
        Analyze the provided video. Respond ONLY with a valid JSON object with three keys:
        1. "device_type": A short string identifying the device.
        2. "condition": A single word: "Mint", "Excellent", "Good", "Fair", or "Poor".
        3. "reason": A brief string explaining the condition.
        """
        prompt_part = types.Part.from_text(prompt)

        # 3. --- THIS IS THE KEY CORRECTION ---
        #    Wrapping the parts inside types.Content, exactly like your reference code.
        contents = [
            types.Content(parts=[prompt_part, video_part])
        ]
        # --- END OF CORRECTION ---
        
        # 4. Use gemini-2.5-flash and the specified config
        model_name = "gemini-2.5-flash"
        generate_content_config = types.GenerateContentConfig(
            temperature=0.2,
            response_mime_type="application/json"
        )
        
        # 5. Call the API using the streaming method from your code
        print(f"Log: Sending request to model: {model_name}...")
        stream = client.models.generate_content_stream(
            model=f"models/{model_name}",
            contents=contents,
            generation_config=generate_content_config,
        )

        # 6. Handle the streamed response to build the complete JSON string
        response_text = "".join(chunk.text for chunk in stream)

        # 7. Parse the final JSON response
        parsed_json = json.loads(response_text)
        device_type = parsed_json.get("device_type", "N/A")
        condition = parsed_json.get("condition", "N/A")
        reason = parsed_json.get("reason", "N/A")

        return device_type, condition, reason

    except Exception as e:
        error_message = f"An error occurred: {e}"
        print(f"ERROR: {error_message}")
        return error_message, "", ""

# --- Gradio Interface ---
with gr.Blocks(theme=gr.themes.Soft()) as demo:
    gr.Markdown("# 📱 Device Condition Analyzer")
    video_input = gr.Video(label="Upload or Record Video", sources=["upload", "webcam"], format="mp4")
    submit_button = gr.Button("Analyze Device", variant="primary")
    with gr.Row():
        device_type_output = gr.Textbox(label="Device Type")
        condition_output = gr.Textbox(label="Condition")
        reason_output = gr.Textbox(label="Reason / Details")

    submit_button.click(
        fn=analyze_device_condition,
        inputs=video_input,
        outputs=[device_type_output, condition_output, reason_output],
        show_progress='full'
    )

demo.launch(debug=True)