from fastapi import FastAPI , UploadFile , File , Form 
from fastapi.responses import JSONResponse
from pydantic import BaseModel
from brainstroming_agent.agent import brainstroming_graph
import pandas as pd
from typing import Optional , List
from context_analysis_agent.agent import IntroductionChatbot
from business_interaction_agent.agent import BusinessInteractionChatbot
from context_analysis_agent.utils.utils import save_to_db
import ast
from brainstroming_agent.utils.utils import encode_image_to_base64 , generate_final_story, generate_image


import json

# Store brainstorming results per thread_id

app = FastAPI()
context_analysis_graph = IntroductionChatbot()
business_interaction_graph = BusinessInteractionChatbot()
brainstrom_graph = brainstroming_graph()

stored_data={}
stored_data['business_details']={"business_type": "restaurant", "platform": "instagram", "target_audience": "youths", "business_goals": "to go global", "offerings": "nepali foods", "Challenges_faced": "finding new customers, attracting large customers"}

class UserMessage(BaseModel):
    message: str
@app.post("/context-analysis")
def context_analysis(msg: UserMessage):
    response = context_analysis_graph.chat(msg.message)
    if context_analysis_graph.is_complete(response):
        details = context_analysis_graph.extract_details()
        if type(details) != dict:
            details = details.model_dump()
        print('Business_details:',details)
        if isinstance(details, str):
            details= ast.literal_eval(details)
        print('Details Type:',type(details))
        save_to_db(details)
        stored_data['business_details'] = details
        return {"response": response, "business_details": details, "complete": True}
    return {"response": response, "complete": False}



@app.post("/business-interaction")
def business_interaction(interaction: str):
    response,business_details = business_interaction_graph.chat(interaction , stored_data['business_details'])
    stored_data['business_details']=business_details
    return {'response': response}


@app.post("/brainstrom")
def brainstroming_endpoint(
    query: List[str],  # sent as JSON body
    preferred_topics: Optional[list] = [],
    images: Optional[List[UploadFile]] = [],  # ✅ Optional UploadFile list
    thread_id: Optional[str] = "default-session",
):
    # Convert uploaded images to base64
    image_base64_list = [encode_image_to_base64(img) for img in images]

    # Invoke LangGraph
    result = brainstrom_graph.invoke({
        'topic': query,
        'images': image_base64_list,
        'latest_preferred_topics':preferred_topics,
        'business_details': (lambda d: d['business_details'] if 'business_details' in d else {})(stored_data)

    },
    config={"configurable": {"thread_id": thread_id}})
    stored_data['brainstroming_response']=result
    # brainstorm_store[thread_id] = result

    return {
        'response': result,
    }

@app.post("/generate-final-story")
def generate_final_story_endpoint():
    final_story =   generate_final_story(stored_data["brainstroming_response"])
    stored_data['final_story']=final_story
    return {
        'response': final_story
    }

@app.post("/generate-image")  
def generate_image_endpoint():
    image = generate_image(str(stored_data['final_story']))
    stored_data['generated_image']=image
    return {
        'response':image
    }