app.py

    
    # Initialize form values based on selected template
    if selected_template and selected_template != "Custom Scenario":
        new_hires = decision_templates[selected_template]["new_hires"]
        new_marketing = decision_templates[selected_template]["new_marketing"]
        other_expenses = decision_templates[selected_template]["other_expenses"]
        growth_impact = decision_templates[selected_template]["growth_impact"]
        question = decision_templates[selected_template]["question"]
    else:
        new_hires = 0
        new_marketing = 0
        other_expenses = 0
        growth_impact = 0.0
        question = ""
    
    # Decision input form
    with st.form("decision_form"):
        st.subheader("Scenario Parameters")
        
        col1, col2 = st.columns(2)
        
        with col1:
            new_hires = st.number_input("New Engineering Hires", min_value=0, max_value=10, value=new_hires, 
                                       help=f"Each engineer costs ${ENGINEER_SALARY:,} per month")
            st.caption(f"Monthly Cost: ${new_hires * ENGINEER_SALARY:,}")
            
            new_marketing = st.number_input("Additional Monthly Marketing Budget", 
                                           min_value=0, max_value=50000, value=new_marketing, step=1000,
                                           help="Additional marketing spend per month")
        
        with col2:
            other_expenses = st.number_input("Other Additional Monthly Expenses", 
                                            min_value=0, max_value=50000, value=other_expenses, step=1000,
                                            help="Any other additional monthly expenses")
            
            growth_impact = st.slider("Estimated Impact on Monthly Growth Rate", 
                                     min_value=0.0, max_value=0.10, value=growth_impact, step=0.01, 
                                     format="%.2f",
                                     help="Estimated increase in monthly growth rate due to these investments")
            st.caption(f"New Growth Rate: {(startup_data['growth_rate'] + growth_impact) * 100:.1f}% (current: {startup_data['growth_rate'] * 100:.1f}%)")
        
        question = st.text_area("Describe your decision scenario", 
                               value=question,
                               height=100, 
                               placeholder="E.g., We're considering hiring two more engineers and increasing our marketing budget...")
        
        decision_summary = f"""
        - {new_hires} new engineers: ${new_hires * ENGINEER_SALARY:,}/month
        - Marketing increase: ${new_marketing:,}/month
        - Other expenses: ${other_expenses:,}/month
        - Total additional burn: ${new_hires * ENGINEER_SALARY + new_marketing + other_expenses:,}/month
        - Growth impact: +{growth_impact * 100:.1f}% monthly growth
        """
        
        st.markdown(f"**Decision Summary:**\n{decision_summary}")
        
        submitted = st.form_submit_button("Simulate Decision")
    
    if submitted:
        # Calculate current and new runway
        current_runway, new_runway, current_df, new_df = simulate_decision(
            startup_data['cash'],
            startup_data['burn_rate'],
            startup_data['revenue'],
            startup_data['growth_rate'],
            other_expenses,
            new_hires,
            new_marketing,
            growth_impact
        )
        
        # Display results
        st.markdown("<h3>Decision Impact Analysis</h3>", unsafe_allow_html=True)
        
        # Summary metrics
        col1, col2, col3 = st.columns(3)
        
        with col1:
            st.metric("Current Runway", f"{current_runway} months")
        with col2:
            runway_change = new_runway - current_runway
            st.metric("New Runway", f"{new_runway} months", 
                     delta=f"{runway_change} months", 
                     delta_color="off" if runway_change == 0 else ("normal" if runway_change > 0 else "inverse"))
        with col3:
            new_burn = startup_data['burn_rate'] + other_expenses + (new_hires * ENGINEER_SALARY) + new_marketing
            burn_change = new_burn - startup_data['burn_rate']
            burn_percentage = burn_change / startup_data['burn_rate'] * 100
            st.metric("New Monthly Burn", f"${new_burn:,}", 
                     delta=f"${burn_change:,} ({burn_percentage:.1f}%)", 
                     delta_color="inverse")
        
        # Cash projection comparison
        st.subheader("Cash Projection Comparison")
        
        # Combine dataframes for comparison
        current_df['Scenario'] = 'Current'
        new_df['Scenario'] = 'After Decision'
        
        combined_df = pd.concat([current_df, new_df])
        combined_df = combined_df.reset_index()
        combined_df = combined_df.rename(columns={'index': 'Date'})
        
        # Plot comparison
        fig = px.line(combined_df, x='Date', y='Cumulative_Cash', color='Scenario',
                     title="Cash Runway Comparison",
                     labels={'Cumulative_Cash': 'Remaining Cash'},
                     color_discrete_sequence=['#4c78a8', '#f58518'])
        
        fig.add_hline(y=0, line_dash="dash", line_color="red", annotation_text="Out of Cash")
        
        fig.update_layout(
            height=400,
            plot_bgcolor='rgba(240,247,255,0.8)',
            xaxis_title="Date",
            yaxis_title="Cash Balance ($)",
            font=dict(family="Arial, sans-serif", size=12),
            margin=dict(l=20, r=20, t=40, b=20),
        )
        
        st.plotly_chart(fig, use_container_width=True)
        
        # Get AI analysis
        if question:
            decision_params = {
                "new_hires": new_hires,
                "new_marketing": new_marketing,
                "other_expenses": other_expenses,
                "growth_impact": growth_impact
            }
            
            analysis_key = f"decision_analysis_{new_hires}_{new_marketing}_{other_expenses}_{growth_impact}"
            if analysis_key not in st.session_state.insights_cache:
                analysis = generate_ai_response(f"""
                You are a financial advisor for startups. A founder asks:
                "{question}"

                Here's their current financial situation:
                - Current cash: ${startup_data['cash']}
                - Monthly burn rate: ${startup_data['burn_rate']}
                - Monthly revenue: ${startup_data['revenue']}
                - Monthly growth rate: {startup_data['growth_rate'] * 100}%
                
                They're considering these changes:
                - Adding {decision_params['new_hires']} new engineers (${ENGINEER_SALARY}/month each)
                - Increasing marketing budget by ${decision_params['new_marketing']}/month
                - Adding ${decision_params['other_expenses']}/month in other expenses
                - Expecting {decision_params['growth_impact'] * 100}% additional monthly growth

                Analyze this decision thoroughly:
                1. Quantify the impact on runway (exact calculation)
                2. Assess the risk level (low, medium, high)
                3. Compare the ROI potential
                4. Provide 3 specific recommendations or alternatives
                5. Suggest timeline and milestones for implementation if approved

                Be direct and specific with numbers and timeframes.
                """)
                st.session_state.insights_cache[analysis_key] = analysis
            
            st.markdown("<div class='advisor-card'>", unsafe_allow_html=True)
            st.markdown("<span class='ai-badge'>AI Decision Analysis</span>", unsafe_allow_html=True)
            st.markdown(f"<p class='advice-text'>{st.session_state.insights_cache[analysis_key]}</p>", unsafe_allow_html=True)
            st.markdown("</div>", unsafe_allow_html=True)
            
            # Risk assessment
            risk_level = "High" if new_runway < 3 else ("Medium" if new_runway < 6 else "Low")
            risk_color = "danger-metric" if risk_level == "High" else ("warning-metric" if risk_level == "Medium" else "good-metric")
            
            st.markdown(f"""
            <div class='metric-card'>
                <p class='metric-label'>Risk Assessment</p>
                <p class='metric-value {risk_color}'>{risk_level} Risk Decision</p>
                <p>This decision would give you {new_runway} months of runway.</p>
            </div>
            """, unsafe_allow_html=True)

# Render Fund Monitoring page
def render_fund_monitoring():
    """Render the AI-powered fund monitoring page"""
    if not st.session_state.current_startup or st.session_state.current_startup not in st.session_state.startups:
        st.warning("No startup selected. Please upload data or select a sample startup.")
        render_upload_page()
        return
    
    # Get the selected startup data
    transactions_df = st.session_state.startups[st.session_state.current_startup]['transactions']
    
    st.markdown("<h1 class='main-header'>Investor Fund Monitoring</h1>", unsafe_allow_html=True)
    st.markdown("<p class='sub-header'>AI-powered fraud detection and spending analysis</p>", unsafe_allow_html=True)
    
    # How AI helps with fund monitoring
    with st.expander("ℹ️ How AI enhances fund monitoring"):
        st.markdown("""
        ### How AI Powers Your Fund Monitoring
        
        The fund monitoring system uses AI to help maintain investor trust and optimize spending:
        
        - **Anomaly Detection**: Our AI models identify unusual transactions that don't match typical startup spending patterns
        - **Risk Scoring**: Each transaction is assigned a risk score based on multiple factors like amount, category, vendor, and description
        - **Pattern Recognition**: The system identifies potentially concerning spending trends across categories over time
        - **Fraud Prevention**: AI algorithms flag transactions that match known patterns of misuse before they become issues
        - **Investor-Ready Reporting**: Generate reports that demonstrate responsible financial stewardship to investors
        
        This helps founders maintain investor trust, prevent misuse of funds, and create transparency in financial operations.
        """)
    
    st.write("Monitor your startup's spending to maintain investor trust and ensure proper fund usage. Our AI algorithms automatically flag suspicious transactions and identify spending patterns.")
    
    # AI insights for fund monitoring
    insights_key = f"fund_monitoring_{date.today().isoformat()}"
    if insights_key not in st.session_state.insights_cache:
        insights = generate_ai_response("""
        You are a financial fraud detection expert. Provide 2-3 critical spending patterns that investors typically look for when monitoring startup fund usage.
        Format as brief bullet points focused on maintaining investor trust.
        """)
        st.session_state.insights_cache[insights_key] = insights
    
    with st.expander("🔍 AI Monitoring Insights", expanded=True):
        st.markdown("<span class='ai-badge'>AI-Generated Insights</span>", unsafe_allow_html=True)
        st.markdown(st.session_state.insights_cache[insights_key])
    
    # Process transactions to detect suspicious ones with AI enhancement
    processed_df = detect_suspicious_transactions(transactions_df)
    
    # Summary metrics
    total_transactions = len(processed_df)
    suspicious_transactions = processed_df[processed_df['Suspicious']].copy()
    suspicious_count = len(suspicious_transactions)
    suspicious_amount = suspicious_transactions['Amount'].sum()
    total_amount = processed_df['Amount'].sum()
    
    col1, col2, col3, col4 = st.columns(4)
    
    with col1:
        st.markdown(f"""
        <div class='metric-card'>
            <p class='metric-label'>Total Transactions</p>
            <p class='metric-value'>{total_transactions}</p>
        </div>
        """, unsafe_allow_html=True)
    
    with col2:
        flagged_percent = suspicious_count/total_transactions*100 if total_transactions > 0 else 0
        status = "danger-metric" if flagged_percent > 10 else ("warning-metric" if flagged_percent > 5 else "good-metric")
        st.markdown(f"""
        <div class='metric-card'>
            <p class='metric-label'>Flagged Transactions</p>
            <p class='metric-value {status}'>{suspicious_count} ({flagged_percent:.1f}%)</p>
        </div>
        """, unsafe_allow_html=True)
    
    with col3:
        amount_percent = suspicious_amount/total_amount*100 if total_amount > 0 else 0
        status = "danger-metric" if amount_percent > 15 else ("warning-metric" if amount_percent > 7 else "good-metric")
        st.markdown(f"""
        <div class='metric-card'>
            <p class='metric-label'>Flagged Amount</p>
            <p class='metric-value {status}'>${suspicious_amount:,.0f} ({amount_percent:.1f}%)</p>
        </div>
        """, unsafe_allow_html=True)
    
    with col4:
        avg_risk = suspicious_transactions['Risk_Score'].mean() if not suspicious_transactions.empty else 0
        status = "danger-metric" if avg_risk > 50 else ("warning-metric" if avg_risk > 30 else "good-metric")
        st.markdown(f"""
        <div class='metric-card'>
            <p class='metric-label'>Average Risk Score</p>
            <p class='metric-value {status}'>{avg_risk:.1f}/100</p>
        </div>
        """, unsafe_allow_html=True)
    
    # Tabs for different views
    tab1, tab2 = st.tabs(["Flagged Transactions", "All Transactions"])
    
    with tab1:
        if suspicious_count > 0:
            # Add risk score visualization (color coded)
            suspicious_view = suspicious_transactions.copy()
            
            # Display dataframe
            st.dataframe(
                suspicious_view[['Date', 'Category', 'Vendor', 'Amount', 'Description', 'Risk_Score', 'Reason']], 
                use_container_width=True
            )
            
            # Get AI analysis of suspicious transactions
            fraud_key = f"fraud_{date.today().isoformat()}"
            if fraud_key not in st.session_state.insights_cache:
                suspicious_text = "\n".join([
                    f"- {row['Date']}: {row['Vendor']} (${row['Amount']:.2f}) - {row['Description']}"
                    for _, row in suspicious_transactions.head(5).iterrows()
                ])
                
                fraud_analysis = generate_ai_response(f"""
                You are a financial fraud detection expert. Review these flagged suspicious transactions:
                
                {suspicious_text}
                
                Provide a detailed analysis:
                1. Identify concerning patterns in these transactions
                2. Recommend specific actions to address these issues
                3. Suggest preventive measures to avoid similar issues in the future
                
                Format your response with clear sections and actionable recommendations.
                """)
                st.session_state.insights_cache[fraud_key] = fraud_analysis
            
            st.markdown("<div class='advisor-card'>", unsafe_allow_html=True)
            st.markdown("<span class='ai-badge'>AI Fraud Analysis</span>", unsafe_allow_html=True)
            st.markdown(f"<p class='advice-text'>{st.session_state.insights_cache[fraud_key]}</p>", unsafe_allow_html=True)
            st.markdown("</div>", unsafe_allow_html=True)
            
            # Action buttons
            st.subheader("Recommended Actions")
            
            col1, col2, col3 = st.columns(3)
            with col1:
                if st.button("🔍 Investigate All Flagged"):
                    st.session_state.investigation_started = True
            with col2:
                if st.button("📝 Generate Investor Report"):
                    st.session_state.report_generated = True  
            with col3:
                if st.button("✅ Mark Reviewed"):
                    st.session_state.marked_reviewed = True
            
            # Simulate action responses
            if 'investigation_started' in st.session_state and st.session_state.investigation_started:
                st.success("Investigation initiated for all flagged transactions. Your financial team will be notified.")
            
            if 'report_generated' in st.session_state and st.session_state.report_generated:
                st.success("Investor report generated and ready for review before sending.")
                
            if 'marked_reviewed' in st.session_state and st.session_state.marked_reviewed:
                st.success("All transactions marked as reviewed. Status will be updated in the system.")
        else:
            st.success("No suspicious transactions detected by our AI system. Your spending appears to be normal for a startup at your stage.")
    
    with tab2:
        st.dataframe(processed_df[['Date', 'Category', 'Vendor', 'Amount', 'Description', 'Suspicious', 'Risk_Score']], 
                    use_container_width=True)
    
    # Spending patterns
    st.subheader("Spending Pattern Analysis")
    
    # Category breakdown
    category_spending = processed_df.groupby('Category')['Amount'].sum().reset_index()
    
    col1, col2 = st.columns(2)
    
    with col1:
        fig = px.bar(category_spending, x='Category', y='Amount',
                    title="Spending by Category",
                    labels={'Amount': 'Total Spent ($)'},
                    color='Amount',
                    color_continuous_scale='Blues')
        fig.update_layout(
            height=400,
            plot_bgcolor='rgba(240,247,255,0.8)',
            xaxis_title="Category",
            yaxis_title="Amount Spent ($)",
            font=dict(family="Arial, sans-serif", size=12),
            margin=dict(l=20, r=20, t=40, b=20),
        )
        st.plotly_chart(fig, use_container_width=True)
    
    with col2:
        # AI spending pattern analysis
        spending_key = f"spending_pattern_{date.today().isoformat()}"
        if spending_key not in st.session_state.insights_cache:
            spending_pattern_analysis = generate_ai_response("""
            You are a startup spending analyst. Review the spending patterns and provide 3 key insights about:
            1. Categories that appear to have unusually high spending
            2. Potential areas where spending could be optimized
            3. Changes in spending patterns that investors might find concerning
            
            Format as concise, actionable bullet points.
            """)
            st.session_state.insights_cache[spending_key] = spending_pattern_analysis
        
        st.markdown("<div class='insight-card'>", unsafe_allow_html=True)
        st.markdown("<span class='ai-badge'>AI Spending Analysis</span>", unsafe_allow_html=True)
        st.markdown(st.session_state.insights_cache[spending_key])
        st.markdown("</div>", unsafe_allow_html=True)
    
    # AI-powered spending controls recommendation
    st.subheader("AI-Recommended Spending Controls")
    
    # Get AI recommendations for spending controls
    controls_key = f"spending_controls_{date.today().isoformat()}"
    if controls_key not in st.session_state.insights_cache:
        controls_recommendations = generate_ai_response("""
        You are a financial controls expert for startups. Based on the spending patterns and suspicious transactions, 
        recommend 3-4 specific spending controls that the startup should implement to prevent misuse of funds.
        
        For each control, provide:
        1. A clear policy statement
        2. Implementation steps
        3. Expected impact
        
        Format as concise, actionable recommendations.
        """)
        st.session_state.insights_cache[controls_key] = controls_recommendations
    
    st.markdown("<div class='advisor-card'>", unsafe_allow_html=True)
    st.markdown("<span class='ai-badge'>AI Control Recommendations</span>", unsafe_allow_html=True)
    st.markdown(f"<p class='advice-text'>{st.session_state.insights_cache[controls_key]}</p>", unsafe_allow_html=True)
    st.markdown("</div>", unsafe_allow_html=True)
    
    # Call-to-action
    st.info("📅 Need help implementing financial controls? Schedule a session with our AI financial advisor.")

# Render AI Financial Advisor page
def render_ai_financial_advisor():
    """Render the AI financial advisor page with voice chat capabilities"""
    if not st.session_state.current_startup or st.session_state.current_startup not in st.session_state.startups:
        st.warning("No startup selected. Please upload data or select a sample startup.")
        render_upload_page()
        return
    
    # Get the selected startup data
    startup_data = st.session_state.startups[st.session_state.current_startup]['profile']
    
    st.markdown("<h1 class='main-header'>AI Financial Advisor</h1>", unsafe_allow_html=True)
    st.markdown("<p class='sub-header'>Get expert financial guidance through our AI-powered advisor</p>", unsafe_allow_html=True)
    
    # How AI helps with financial advisory
    with st.expander("ℹ️ How AI powers your financial advisor"):
        st.markdown("""
        ### How AI Powers Your Financial Advisor
        
        Our AI financial advisor combines advanced language models with financial expertise:
        
        - **Natural Language Understanding**: The system interprets complex financial questions in plain English
        - **Domain-Specific Knowledge**: Our AI is trained on startup finance, venture capital, and financial modeling
        - **Context-Aware Responses**: The advisor takes into account your specific financial situation and history
        - **Voice Synthesis**: ElevenLabs voice technology creates natural, high-quality voice responses
        - **Customized Guidance**: AI tailors advice specifically to your stage, industry, and financial position
        
        This gives founders 24/7 access to high-quality financial guidance without the high cost of consultants.
        """)
    
    # Chat container
    st.markdown("<div style='background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;'>", unsafe_allow_html=True)
    
    # Display chat history
    st.subheader("Chat with your Financial Advisor")
    
    # Display chat messages
    for message in st.session_state.chat_history:
        if message["role"] == "user":
            st.markdown(f"<div style='background-color: #e6f7ff; padding: 10px; border-radius: 10px; margin-bottom: 10px;'><strong>You:</strong> {message['content']}</div>", unsafe_allow_html=True)
        else:
            st.markdown(f"<div style='background-color: #f0f7ff; padding: 10px; border-radius: 10px; margin-bottom: 10px;'><strong>Financial Advisor:</strong> {message['content']}</div>", unsafe_allow_html=True)
            
            # Show play button for voice if it exists
            if 'audio' in message and message['audio']:
                st.audio(message['audio'], format='audio/mp3')
    
    # Input for new message
    col1, col2 = st.columns([5, 1])
    
    with col1:
        user_input = st.text_input("Ask a financial question", key="user_question")
    
    with col2:
        use_voice = st.checkbox("Enable voice", value=True)
    
    # Common financial questions
    st.markdown("### Common Questions")
    question_cols = st.columns(3)
    
    common_questions = [
        "How much runway do we have at our current burn rate?",
        "Should we increase our marketing spend given our growth rate?",
        "When should we start preparing for our next fundraising round?",
        "How can we optimize our burn rate without impacting growth?",
        "What metrics should we focus on improving right now?",
        "How do our unit economics compare to similar startups?"
    ]
    
    selected_question = None
    
    for i, question in enumerate(common_questions):
        with question_cols[i % 3]:
            if st.button(question, key=f"q_{i}"):
                selected_question = question
    
    # Process user input (either from text input or selected question)
    if user_input or selected_question:
        question = user_input or selected_question
        
        # Add user message to chat history
        st.session_state.chat_history.append({"role": "user", "content": question})
        
        # Get AI response
        response = generate_ai_response(f"""
        You are a strategic financial advisor for startups. A founder asks:
        "{question}"

        Here's their current financial situation:
        - Stage: {startup_data['stage']}
        - Current cash: ${startup_data['cash']}
        - Monthly burn rate: ${startup_data['burn_rate']}
        - Monthly revenue: ${startup_data['revenue']}
        - Monthly growth rate: {startup_data['growth_rate'] * 100}%
        - Last funding: {startup_data['last_funding']}
        - Team size: {startup_data['employees']}

        Provide detailed, actionable advice addressing their question. Include:
        1. Clear assessment of their current situation
        2. 3-5 specific, actionable recommendations with expected outcomes
        3. Relevant metrics they should track
        4. Industry benchmarks for comparison
        5. Timeline for implementation and results

        Be specific with numbers, timeframes, and expected outcomes.
        """)
        
        # Generate voice response if enabled
        audio_data = None
        if use_voice:
            audio_data = generate_voice_response(response)
        
        # Add AI response to chat history
        st.session_state.chat_history.append({
            "role": "assistant", 
            "content": response,
            "audio": audio_data
        })
        
        # Rerun to display updated chat
        st.rerun()
    
    st.markdown("</div>", unsafe_allow_html=True)
    
    # Advanced tools
    st.subheader("Advanced Financial Tools")
    
    tool_cols = st.columns(3)
    
    with tool_cols[0]:
        st.markdown("""
        <div style='background-color: white; padding: 15px; border-radius: 10px; height: 200px; box-shadow: 0 4px 6px rgba(0,0,0,0.1);'>
            <h4>Financial Model Review</h4>
            <p>Upload your financial model for AI analysis and recommendations.</p>
            <div style='position: absolute; bottom: 15px;'>
                <button disabled style="background-color: #E6F3FF; color: #0066cc; border-radius: 5px; padding: 5px 10px; border: none;">Coming Soon</button>
            </div>
        </div>
        """, unsafe_allow_html=True)
    
    with tool_cols[1]:
        st.markdown("""
        <div style='background-color: white; padding: 15px; border-radius: 10px; height: 200px; box-shadow: 0 4px 6px rgba(0,0,0,0.1);'>
            <h4>Investor Pitch Review</h4>
            <p>Get AI feedback on your investor pitch deck and financial projections.</p>
            <div style='position: absolute; bottom: 15px;'>
                <button disabled style="background-color: #E6F3FF; color: #0066cc; border-radius: 5px; padding: 5px 10px; border: none;">Coming Soon</button>
            </div>
        </div>
        """, unsafe_allow_html=True)
    
    with tool_cols[2]:
        st.markdown("""
        <div style='background-color: white; padding: 15px; border-radius: 10px; height: 200px; box-shadow: 0 4px 6px rgba(0,0,0,0.1);'>
            <h4>Fundraising Strategy</h4>
            <p>Generate a customized fundraising strategy based on your metrics.</p>
            <div style='position: absolute; bottom: 15px;'>
                <button disabled style="background-color: #E6F3FF; color: #0066cc; border-radius: 5px; padding: 5px 10px; border: none;">Coming Soon</button>
            </div>
        </div>
        """, unsafe_allow_html=True)

# Main function
def main():
    # Initialize Gemini API
    initialize_gemini()
    
    # Create sidebar navigation
    create_sidebar()
    
    # Render the correct page based on session state
    if st.session_state.current_page == 'upload':
        render_upload_page()
    elif st.session_state.current_page == 'dashboard':
        render_financial_dashboard()
    elif st.session_state.current_page == 'simulator':
        render_decision_simulator()
    elif st.session_state.current_page == 'monitoring':
        render_fund_monitoring()
    elif st.session_state.current_page == 'advisor':
        render_ai_financial_advisor()

if __name__ == "__main__":
    main()
import streamlit as st
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go
from datetime import datetime, timedelta, date
import time
import io
import base64
import requests
import google.generativeai as genai

# Constants
DEFAULT_GROWTH_RATE = 0.08  # 8% monthly growth
DEFAULT_BURN_RATE = 85000   # $85,000 monthly burn
ENGINEER_SALARY = 10000     # $10,000 monthly cost per engineer ($120K/year)

# Initialize session state variables
if 'startups' not in st.session_state:
    st.session_state.startups = {}  # Dictionary to store multiple startup data
if 'current_startup' not in st.session_state:
    st.session_state.current_startup = None  # Currently selected startup
if 'current_page' not in st.session_state:
    st.session_state.current_page = 'upload'  # Default page
if 'insights_cache' not in st.session_state:
    st.session_state.insights_cache = {}
if 'chat_history' not in st.session_state:
    st.session_state.chat_history = [
        {"role": "assistant", "content": "Hi there! I'm your AI financial advisor. How can I help with your startup's finances today?"}
    ]

# Configure Google GenerativeAI (Gemini)
def initialize_gemini():
    """Initialize Google's GenerativeAI (Gemini) with API key"""
    try:
        # In production, get this from st.secrets or environment variables
        api_key = st.secrets.get("GEMINI_API_KEY", None)
        if api_key:
            genai.configure(api_key=api_key)
            return True
        else:
            st.warning("Gemini API key not found. Using simulated AI responses.")
            return False
    except Exception as e:
        st.error(f"Failed to initialize Gemini AI: {e}")
        return False

def generate_ai_response(prompt, simulate=True):
    """Generate text using Google's GenerativeAI (Gemini)"""
    if simulate:
        # Return a generic response for simulation
        return """
        Based on your financial situation, I recommend focusing on these key areas:

        1. **Extend Your Runway**: With your current burn rate, consider reducing non-essential expenses by 15-20%. Focus particularly on optimizing marketing efficiency while maintaining growth activities.

        2. **Accelerate Revenue Growth**: Your current monthly growth is good, but increasing it would significantly improve your cash position. Consider focusing sales efforts on higher-value customers with shorter sales cycles.

        3. **Prepare for Fundraising**: Begin conversations with existing investors about potential bridge funding. Prepare updated metrics showing clear progress on unit economics and customer acquisition.

        I recommend reviewing your expense categories weekly and tracking your burn rate closely.
        """
    else:
        try:
            # Initialize Gemini model
            model = genai.GenerativeModel('gemini-pro')
            response = model.generate_content(prompt)
            return response.text
        except Exception as e:
            st.error(f"Error generating AI response: {e}")
            return "Sorry, I couldn't generate a response at this time."

def generate_voice_response(text, simulate=True):
    """Generate voice response using ElevenLabs API"""
    if simulate:
        # Return empty audio data for simulation
        return None
    else:
        try:
            # Get API key from secrets
            api_key = st.secrets.get("ELEVENLABS_API_KEY", None)
            if not api_key:
                st.warning("ElevenLabs API key not found. Voice response not available.")
                return None
                
            # ElevenLabs API endpoint
            url = "https://api.elevenlabs.io/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM"  # Rachel voice ID
            
            # Headers and payload
            headers = {
                "Accept": "audio/mpeg",
                "Content-Type": "application/json",
                "xi-api-key": api_key
            }
            
            data = {
                "text": text,
                "model_id": "eleven_monolingual_v1",
                "voice_settings": {
                    "stability": 0.5,
                    "similarity_boost": 0.5
                }
            }
            
            # Make the API call
            response = requests.post(url, json=data, headers=headers)
            
            if response.status_code == 200:
                return response.content
            else:
                st.error(f"Error with ElevenLabs API: {response.status_code}")
                return None
                
        except Exception as e:
            st.error(f"Error generating voice response: {e}")
            return None

def switch_page(page_name):
    """Function to switch between pages"""
    st.session_state.current_page = page_name
    st.rerun()

# Calculate runway for business decisions
def calculate_runway(cash, burn_rate, revenue, growth_rate, months=24):
    """
    Calculate runway based on cash, burn, revenue and growth
    Returns runway in months and dataframe with projections
    """
    # Create date range
    current_date = datetime.now()
    date_range = [current_date + timedelta(days=30*i) for i in range(months)]
    
    # Initialize data structures
    cash_flow = []
    remaining_cash = cash
    monthly_revenue = revenue
    
    # Calculate cash flow for each month
    for i in range(months):
        # Calculate cash flow for this month
        net_burn = burn_rate - monthly_revenue
        cash_flow.append(net_burn)
        
        # Update remaining cash
        remaining_cash -= net_burn
        
        # Update revenue with growth
        monthly_revenue *= (1 + growth_rate)
    
    # Create dataframe
    df = pd.DataFrame({
        'Net_Burn': cash_flow,
        'Cumulative_Cash': [cash - sum(cash_flow[:i+1]) for i in range(len(cash_flow))]
    }, index=date_range)
    
    # Calculate runway (when cumulative cash goes negative)
    negative_cash = df[df['Cumulative_Cash'] < 0]
    if len(negative_cash) > 0:
        runway_months = (negative_cash.index[0] - current_date).days // 30
    else:
        runway_months = months
    
    return runway_months, df

# Simulate decisions
def simulate_decision(cash, burn_rate, revenue, growth_rate, 
                     additional_expenses, new_hires, marketing_increase, growth_impact):
    """
    Simulate the financial impact of a business decision
    """
    # Current projection
    current_runway, current_df = calculate_runway(
        cash, burn_rate, revenue, growth_rate
    )
    
    # New projection with decision impact
    new_burn_rate = burn_rate + additional_expenses + (new_hires * ENGINEER_SALARY) + marketing_increase
    new_growth_rate = growth_rate + growth_impact
    
    new_runway, new_df = calculate_runway(
        cash, new_burn_rate, revenue, new_growth_rate
    )
    
    return current_runway, new_runway, current_df, new_df

# Detect suspicious transactions
def detect_suspicious_transactions(transactions_df):
    """AI-enhanced suspicious transaction detection."""
    df = transactions_df.copy()
    
    # Define thresholds for each category
    category_thresholds = {
        "Travel": 3000,
        "Marketing": 10000,
        "Office": 7000,
        "Software": 6000,
        "Consulting": 5000,
        "Legal": 6000
    }
    
    # Define suspicious terms
    suspicious_terms = ['luxury', 'cruise', 'premium', 'personal', 'gift']
    
    # Add suspicious column
    df['Suspicious'] = False
    df['Reason'] = ""
    df['Risk_Score'] = 0
    
    # Check for suspicious patterns
    for idx, row in df.iterrows():
        reasons = []
        risk_score = 0
        
        # Check if amount exceeds category threshold
        if row['Category'] in category_thresholds:
            if row['Amount'] > category_thresholds[row['Category']]:
                reasons.append(f"Amount exceeds typical spending for {row['Category']}")
                risk_score += 30
                
                # Higher risk for significantly exceeding threshold
                excess_percentage = (row['Amount'] - category_thresholds[row['Category']]) / category_thresholds[row['Category']] * 100
                if excess_percentage > 100:  # More than double the threshold
                    risk_score += 20
        
        # Check for suspicious vendors or descriptions
        if any(term in str(row['Vendor']).lower() for term in suspicious_terms):
            reasons.append(f"Vendor name contains suspicious term")
            risk_score += 25
        
        if any(term in str(row['Description']).lower() for term in suspicious_terms):
            reasons.append(f"Description contains suspicious term")
            risk_score += 20
        
        # Check for rounded amounts (potential indicator of estimation/fabrication)
        if row['Amount'] % 1000 == 0 and row['Amount'] > 3000:
            reasons.append(f"Suspiciously round amount")
            risk_score += 15
        
        # Mark as suspicious if risk score is high enough
        if risk_score >= 30:
            df.at[idx, 'Suspicious'] = True
            df.at[idx, 'Reason'] = "; ".join(reasons)
            df.at[idx, 'Risk_Score'] = risk_score
    
    # Sort by risk score
    df = df.sort_values(by='Risk_Score', ascending=False)
    
    return df

# Parse CSV file to dataframe
def parse_csv_to_df(file):
    """Parse uploaded CSV file to Pandas DataFrame"""
    try:
        df = pd.read_csv(file)
        return df, None
    except Exception as e:
        return None, f"Error parsing CSV: {e}"

# Page config
st.set_page_config(
    page_title="StartupFinancePilot",
    page_icon="💰",
    layout="wide",
    initial_sidebar_state="expanded"
)

# Custom CSS
st.markdown("""
<style>
    #MainMenu {visibility: hidden;}
    footer {visibility: hidden;}
    .stDeployButton {display:none;}
    
    .main-header {
        font-size: 2.5rem;
        color: #0066cc;
        margin-bottom: 0.5rem;
    }
    .sub-header {
        font-size: 1.5rem;
        color: #5c5c5c;
        margin-bottom: 1.5rem;
    }
    .metric-card {
        background-color: #f8f9fa;
        border-radius: 10px;
        padding: 20px;
        box-shadow: 0 4px 6px rgba(0,0,0,0.1);
    }
    .metric-label {
        font-size: 1rem;
        color: #5c5c5c;
    }
    .metric-value {
        font-size: 1.8rem;
        color: #0066cc;
        font-weight: bold;
    }
    .good-metric {
        color: #28a745;
    }
    .warning-metric {
        color: #ffc107;
    }
    .danger-metric {
        color: #dc3545;
    }
    
    /* Style for sidebar buttons */
    div.stButton > button {
        width: 100%;
        padding: 10px 10px;
        border: none;
        background-color: #E6F3FF;
        color: #0066cc;
        border-radius: 10px;
        text-align: left;
        margin: 5px 0;
        font-weight: bold;
    }
    
    div.stButton > button:hover {
        background-color: #CCE5FF;
        color: #004080;
    }
    
    /* Style for title box */
    .title-box {
        background: linear-gradient(45deg, #0066cc, #66b3ff);
        padding: 20px;
        border-radius: 10px;
        margin-bottom: 20px;
        text-align: center;
        color: white;
        cursor: pointer;
    }
    
    .ai-badge {
        display: inline-block;
        background-color: #0066cc;
        color: white;
        border-radius: 4px;
        padding: 2px 6px;
        font-size: 0.7rem;
        font-weight: bold;
        margin-bottom: 8px;
    }
    
    .insight-card, .advisor-card {
        background-color: #f8f9fa;
        border-radius: 10px;
        padding: 15px;
        margin-bottom: 20px;
        box-shadow: 0 2px 4px rgba(0,0,0,0.05);
    }
    
    .advice-text {
        margin-top: 10px;
        line-height: 1.6;
    }
</style>
""", unsafe_allow_html=True)

# Create sidebar navigation
def create_sidebar():
    with st.sidebar:
        # Title box that works as home button
        st.markdown("""
            <div class="title-box">
                <h1>💰 StartupFinancePilot</h1>
                <p>AI-powered financial assistant for startups</p>
            </div>
        """, unsafe_allow_html=True)

        # Startup selector (if there are startups in the session state)
        if st.session_state.startups:
            st.subheader("Selected Startup")
            startup_names = list(st.session_state.startups.keys())
            selected_startup = st.selectbox(
                "Choose Startup", 
                startup_names,
                index=startup_names.index(st.session_state.current_startup) if st.session_state.current_startup in startup_names else 0
            )
            st.session_state.current_startup = selected_startup
            
            # Show basic startup info
            if selected_startup in st.session_state.startups:
                startup_data = st.session_state.startups[selected_startup]['profile']
                st.markdown(f"""
                **Stage:** {startup_data['stage']}  
                **Cash:** ${startup_data['cash']:,}  
                **Monthly Burn:** ${startup_data['burn_rate']:,}  
                **Monthly Revenue:** ${startup_data['revenue']:,}  
                """)

        st.markdown("<hr>", unsafe_allow_html=True)  # Divider
        
        # Upload data button at the top
        if st.button("📤 Upload Startup Data", use_container_width=True):
            switch_page('upload')

        # Navigation buttons
        if st.button("📊 Financial Dashboard", use_container_width=True):
            switch_page('dashboard')
            
        if st.button("🔮 Decision Simulator", use_container_width=True):
            switch_page('simulator')
            
        if st.button("🕵️ Fund Monitoring", use_container_width=True):
            switch_page('monitoring')
            
        if st.button("🤖 AI Financial Advisor", use_container_width=True):
            switch_page('advisor')

# Upload and process financial data files
def render_upload_page():
    """Render the upload page for startup data"""
    st.markdown("<h1 class='main-header'>Upload Your Startup Data</h1>", unsafe_allow_html=True)
    st.markdown("<p class='sub-header'>Upload CSV files or use sample data to get started</p>", unsafe_allow_html=True)
    
    with st.expander("Upload Instructions", expanded=False):
        st.markdown("""
        ### How to Upload Your Startup Data
        
        You can upload three types of files:
        
        1. **Company Profile** - A CSV with basic information about your startup including:
           - name, stage, founded, employees, last_funding, cash, burn_rate, revenue, growth_rate
        
        2. **Cash Flow Data** - A CSV with monthly cash flow data with columns:
           - Month, Revenue, Payroll, Marketing, Office, Software, Travel, Legal, Misc
        
        3. **Transaction Data** - A CSV with transaction details:
           - Date, Category, Vendor, Amount, Description, Flag
           
        If you don't have these files ready, you can use our sample data.
        """)
    
    col1, col2 = st.columns(2)
    
    with col1:
        startup_name = st.text_input("Startup Name", value="My Startup")
        
        profile_file = st.file_uploader("Upload Company Profile (CSV)", type=['csv'])
        cash_flow_file = st.file_uploader("Upload Cash Flow Data (CSV)", type=['csv'])
        transactions_file = st.file_uploader("Upload Transactions Data (CSV)", type=['csv'])
    
    with col2:
        st.markdown("""
        <div style="background-color: #f0f7ff; padding: 15px; border-radius: 10px; height: 90%;">
            <h4>Why Upload Your Data?</h4>
            <p>By uploading your actual financial data, you'll get:</p>
            <ul>
                <li>Personalized AI insights tailored to your startup</li>
                <li>Accurate runway projections based on your real spending patterns</li>
                <li>Custom recommendations to optimize your burn rate</li>
                <li>More realistic decision simulations</li>
            </ul>
            <p>All data is processed securely and never stored permanently.</p>
        </div>
        """, unsafe_allow_html=True)
    
    # Process the files if uploaded
    if st.button("Process Data"):
        # Initialize with default values
        startup_data = {
            "name": startup_name,
            "stage": "Seed",
            "founded": "12 months ago",
            "employees": 5,
            "last_funding": "Not specified",
            "cash": 100000,
            "burn_rate": 20000,
            "revenue": 5000,
            "growth_rate": 0.05
        }
        
        cash_flow_df = None
        transactions_df = None
        
        # Parse company profile
        if profile_file:
            try:
                profile_df, error = parse_csv_to_df(profile_file)
                if error:
                    st.error(error)
                else:
                    # Get the first row as a dictionary
                    if len(profile_df) > 0:
                        startup_data.update(profile_df.iloc[0].to_dict())
                        st.success(f"Successfully loaded company profile for {startup_data['name']}")
            except Exception as e:
                st.error(f"Error processing company profile: {e}")
        
        # Parse cash flow data
        if cash_flow_file:
            cash_flow_df, error = parse_csv_to_df(cash_flow_file)
            if error:
                st.error(error)
            else:
                # Add calculated fields if not present
                if "Total_Expenses" not in cash_flow_df.columns:
                    expense_columns = [col for col in cash_flow_df.columns if col not in ["Month", "Revenue", "Total_Expenses", "Net_Burn"]]
                    cash_flow_df["Total_Expenses"] = cash_flow_df[expense_columns].sum(axis=1)
                
                if "Net_Burn" not in cash_flow_df.columns:
                    cash_flow_df["Net_Burn"] = cash_flow_df["Total_Expenses"] - cash_flow_df["Revenue"]
                
                st.success("Successfully loaded cash flow data")
        
        # Parse transactions data
        if transactions_file:
            transactions_df, error = parse_csv_to_df(transactions_file)
            if error:
                st.error(error)
            else:
                # Ensure transactions data has required columns
                required_columns = ["Date", "Category", "Vendor", "Amount", "Description"]
                if all(col in transactions_df.columns for col in required_columns):
                    if "Flag" not in transactions_df.columns:
                        transactions_df["Flag"] = "Normal"  # Default flag
                    
                    st.success("Successfully loaded transactions data")
                else:
                    st.error("Transactions file is missing required columns")
        
        # If any files were processed, save the data to session state
        if profile_file or cash_flow_file or transactions_file:
            # Create a sample cash flow dataframe if none was uploaded
            if cash_flow_df is None:
                cash_flow_df = create_sample_cash_flow(startup_data)
            
            # Create a sample transactions dataframe if none was uploaded
            if transactions_df is None:
                transactions_df = create_sample_transactions(startup_data)
            
            # Store in session state
            st.session_state.startups[startup_data['name']] = {
                'profile': startup_data,
                'cash_flow': cash_flow_df,
                'transactions': transactions_df
            }
            
            # Set as current startup
            st.session_state.current_startup = startup_data['name']
            
            st.success(f"Successfully added {startup_data['name']} to your startups")
            st.info("You can now analyze this startup's data in the dashboard")
            
            # Redirect to dashboard
            switch_page('dashboard')
    
    # Sample data options
    st.subheader("Or Use Sample Data")
    
    sample_col1, sample_col2 = st.columns(2)
    
    with sample_col1:
        if st.button("Use TechHealth AI Sample"):
            # Load sample data (function would generate or load from file)
            load_sample_data("TechHealth AI")            
            st.success("Successfully loaded TechHealth AI sample data")
            # Redirect to dashboard
            switch_page('dashboard')
    
    with sample_col2:
        if st.button("Use GreenTech Innovations Sample"):
            # Load another sample (function would generate or load from file)
            load_sample_data("GreenTech Innovations")            
            st.success("Successfully loaded GreenTech Innovations sample data")
            # Redirect to dashboard
            switch_page('dashboard')

def create_sample_cash_flow(startup_data):
    """Create a sample cash flow dataframe for a startup"""
    cash_flow_data = {
        "Month": [f"Month {i}" for i in range(1, 7)],
        "Revenue": [startup_data['revenue'] * (1 + startup_data['growth_rate'])**i for i in range(6)],
        "Payroll": [startup_data['burn_rate'] * 0.7] * 6,
        "Marketing": [startup_data['burn_rate'] * 0.15] * 6,
        "Office": [startup_data['burn_rate'] * 0.05] * 6,
        "Software": [startup_data['burn_rate'] * 0.03] * 6,
        "Travel": [startup_data['burn_rate'] * 0.02] * 6,
        "Legal": [startup_data['burn_rate'] * 0.01] * 6,
        "Misc": [startup_data['burn_rate'] * 0.04] * 6
    }
    cash_flow_df = pd.DataFrame(cash_flow_data)
    cash_flow_df["Total_Expenses"] = cash_flow_df[["Payroll", "Marketing", "Office", "Software", "Travel", "Legal", "Misc"]].sum(axis=1)
    cash_flow_df["Net_Burn"] = cash_flow_df["Total_Expenses"] - cash_flow_df["Revenue"]
    return cash_flow_df

def create_sample_transactions(startup_data):
    """Create sample transaction data for a startup"""
    transactions_data = {
        "Date": [(datetime.now() - timedelta(days=i*5)).strftime("%Y-%m-%d") for i in range(10)],
        "Category": ["Payroll", "Marketing", "Office", "Software", "Travel", "Legal", "Misc", "Payroll", "Marketing", "Office"],
        "Vendor": ["Payroll Provider", "Facebook Ads", "Office Rent", "AWS", "Travel Agency", "Legal Firm", "Miscellaneous", "Payroll Provider", "Google Ads", "Office Supplies"],
        "Amount": [startup_data['burn_rate'] * 0.7, startup_data['burn_rate'] * 0.15, startup_data['burn_rate'] * 0.05, startup_data['burn_rate'] * 0.03, startup_data['burn_rate'] * 0.02, startup_data['burn_rate'] * 0.01, startup_data['burn_rate'] * 0.04, startup_data['burn_rate'] * 0.7, startup_data['burn_rate'] * 0.15, startup_data['burn_rate'] * 0.05],
        "Description": ["Monthly Payroll", "Ad Campaign", "Monthly Rent", "Cloud Services", "Business Travel", "Legal Services", "Miscellaneous Expenses", "Monthly Payroll", "Ad Campaign", "Office Supplies"],
        "Flag": ["Normal", "Normal", "Normal", "Normal", "Normal", "Normal", "Normal", "Normal", "Normal", "Normal"]
    }
    return pd.DataFrame(transactions_data)

def load_sample_data(sample_name):
    """Load sample data for demonstration"""
    if sample_name == "TechHealth AI":
        # Create TechHealth AI sample
        startup_data = {
            "name": "TechHealth AI",
            "stage": "Seed",
            "founded": "18 months ago",
            "employees": 12,
            "last_funding": "$1.2M seed round 10 months ago",
            "cash": 320000,
            "burn_rate": 85000,
            "revenue": 15000,
            "growth_rate": 0.08
        }
    else:
        # Create GreenTech Innovations sample
        startup_data = {
            "name": "GreenTech Innovations",
            "stage": "Series A",
            "founded": "3 years ago",
            "employees": 25,
            "last_funding": "$4.5M Series A 8 months ago",
            "cash": 2800000,
            "burn_rate": 220000,
            "revenue": 75000,
            "growth_rate": 0.12
        }
    
    # Generate cash flow and transaction data
    cash_flow_df = create_sample_cash_flow(startup_data)
    transactions_df = create_sample_transactions(startup_data)
    
    # Add some suspicious transactions for the sample
    if sample_name == "TechHealth AI":
        suspicious_transactions = pd.DataFrame([
            {"Date": "2023-11-05", "Category": "Travel", "Vendor": "Caribbean Cruises", "Amount": 8500, "Description": "Team Retreat Planning", "Flag": "Suspicious"},
            {"Date": "2023-11-12", "Category": "Marketing", "Vendor": "LuxuryGifts Inc", "Amount": 4200, "Description": "Client Appreciation", "Flag": "Suspicious"},
            {"Date": "2023-11-22", "Category": "Office", "Vendor": "Premium Furniture", "Amount": 12000, "Description": "Office Upgrades", "Flag": "Suspicious"}
        ])
        transactions_df = pd.concat([suspicious_transactions, transactions_df], ignore_index=True)
    
    # Store in session state
    st.session_state.startups[startup_data['name']] = {
        'profile': startup_data,
        'cash_flow': cash_flow_df,
        'transactions': transactions_df
    }
    
    # Set as current startup
    st.session_state.current_startup = startup_data['name']

# Render Financial Dashboard
def render_financial_dashboard():
    """Render the AI-powered financial dashboard page"""
    if not st.session_state.current_startup or st.session_state.current_startup not in st.session_state.startups:
        st.warning("No startup selected. Please upload data or select a sample startup.")
        render_upload_page()
        return
    
    # Get the selected startup data
    startup_data = st.session_state.startups[st.session_state.current_startup]['profile']
    cash_flow_df = st.session_state.startups[st.session_state.current_startup]['cash_flow']
    
    st.markdown("<h1 class='main-header'>Financial Dashboard</h1>", unsafe_allow_html=True)
    st.markdown("<p class='sub-header'>AI-powered financial insights at a glance</p>", unsafe_allow_html=True)
    
    # How AI helps with financial dashboards
    with st.expander("ℹ️ How AI enhances your financial dashboard"):
        st.markdown("""
        ### How AI Powers Your Financial Dashboard
        
        The financial dashboard uses AI to transform raw financial data into actionable intelligence:
        
        - **Automated Analysis**: Instead of manually calculating runway and burn rates, our AI model analyzes your data and highlights critical trends
        - **Predictive Forecasting**: AI forecasts your runway using pattern recognition and predictive analytics to account for varying growth rates
        - **Anomaly Detection**: The system identifies unusual spending patterns or concerning financial trends that human analysis might miss
        - **Strategic Recommendations**: Based on your specific financial situation, the AI provides tailored recommendations to optimize your runway
        - **Benchmark Comparison**: Your metrics are automatically compared against industry standards for startups at your funding stage
        
        This helps founders save time, catch financial issues early, and make data-driven decisions without needing financial expertise.
        """)
    
    # AI Insights Summary
    insights_key = f"dashboard_{date.today().isoformat()}"
    if insights_key not in st.session_state.insights_cache:
        insights = generate_ai_response(f"""
        You are a financial advisor for startups. Based on this startup's data:
        - Current cash: ${startup_data['cash']}
        - Monthly burn rate: ${startup_data['burn_rate']}
        - Monthly revenue: ${startup_data['revenue']}
        - Monthly growth rate: {startup_data['growth_rate'] * 100}%
        
        Provide the top 3 most important financial insights that the founder should know today.
        Format each insight as a brief, action-oriented bullet point.
        """)
        st.session_state.insights_cache[insights_key] = insights
    
    with st.expander("📊 AI Financial Insights", expanded=True):
        st.markdown("<span class='ai-badge'>AI-Generated Insights</span>", unsafe_allow_html=True)
        st.markdown(st.session_state.insights_cache[insights_key])
    
    # Key metrics
    col1, col2, col3, col4 = st.columns(4)
    
    # Calculate runway
    runway_months, runway_df = calculate_runway(
        startup_data['cash'], 
        startup_data['burn_rate'], 
        startup_data['revenue'], 
        startup_data['growth_rate']
    )
    
    # Determine status colors based on financial health indicators
    runway_status = "danger-metric" if runway_months < 6 else ("warning-metric" if runway_months < 9 else "good-metric")
    burn_status = "danger-metric" if startup_data['burn_rate'] > 100000 else ("warning-metric" if startup_data['burn_rate'] > 80000 else "good-metric")
    revenue_status = "good-metric" if startup_data['revenue'] > 20000 else ("warning-metric" if startup_data['revenue'] > 10000 else "danger-metric")
    
    with col1:
        st.markdown(f"""
        <div class='metric-card'>
            <p class='metric-label'>Current Cash</p>
            <p class='metric-value'>${startup_data['cash']:,}</p>
        </div>
        """, unsafe_allow_html=True)
    
    with col2:
        st.markdown(f"""
        <div class='metric-card'>
            <p class='metric-label'>Monthly Burn</p>
            <p class='metric-value {burn_status}'>${startup_data['burn_rate']:,}</p>
        </div>
        """, unsafe_allow_html=True)
    
    with col3:
        st.markdown(f"""
        <div class='metric-card'>
            <p class='metric-label'>Monthly Revenue</p>
            <p class='metric-value {revenue_status}'>${startup_data['revenue']:,}</p>
        </div>
        """, unsafe_allow_html=True)
    
    with col4:
        st.markdown(f"""
        <div class='metric-card'>
            <p class='metric-label'>Runway</p>
            <p class='metric-value {runway_status}'>{runway_months} months</p>
        </div>
        """, unsafe_allow_html=True)
    
    # Financial charts
    st.subheader("Financial Overview")
    
    tab1, tab2, tab3 = st.tabs(["Runway Projection", "Revenue vs. Expenses", "Burn Rate Trend"])
    
    with tab1:
        # Runway projection chart
        fig = px.line(runway_df.reset_index(), x='index', y='Cumulative_Cash', 
                     title="Cash Runway Projection",
                     labels={'index': 'Date', 'Cumulative_Cash': 'Remaining Cash ($)'},
                     color_discrete_sequence=['#0066cc'])
        fig.add_hline(y=0, line_dash="dash", line_color="red", annotation_text="Out of Cash")
        fig.update_layout(
            height=400,
            plot_bgcolor='rgba(240,247,255,0.8)',
            xaxis_title="Date",
            yaxis_title="Cash Balance ($)",
            font=dict(family="Arial, sans-serif", size=12),
            margin=dict(l=20, r=20, t=40, b=20),
        )
        st.plotly_chart(fig, use_container_width=True)
        
        # Get analysis from AI
        with st.expander("🔍 AI Financial Analysis", expanded=True):
            # Use cache to avoid repeated API calls
            analysis_key = f"runway_{date.today().isoformat()}"
            if analysis_key not in st.session_state.insights_cache:
                analysis = generate_ai_response(f"""
                You are a financial advisor for startups. Analyze this startup's financial data:
                - Current cash: ${startup_data['cash']}
                - Monthly burn rate: ${startup_data['burn_rate']}
                - Monthly revenue: ${startup_data['revenue']}
                - Monthly growth rate: {startup_data['growth_rate'] * 100}%

                Provide a detailed analysis of their runway and financial health. Include:
                1. Exact runway calculation in months
                2. Assessment of financial health (critical, concerning, stable, or healthy)
                3. Benchmarks compared to similar seed-stage startups
                4. Three specific, actionable recommendations to improve runway
                5. Key metrics they should focus on

                Format your response in a structured, easy-to-read format with clear sections and bullet points.
                """)
                st.session_state.insights_cache[analysis_key] = analysis
                
            st.markdown("<span class='ai-badge'>AI Financial Analysis</span>", unsafe_allow_html=True)
            st.markdown(st.session_state.insights_cache[analysis_key])
    
    with tab2:
        # Revenue vs Expenses chart
        rev_exp_df = cash_flow_df.copy()
        fig = px.bar(rev_exp_df, x='Month', y=['Revenue', 'Total_Expenses'],
                    title="Revenue vs. Expenses",
                    barmode='group',
                    labels={'value': 'Amount ($)', 'variable': 'Category'},
                    color_discrete_sequence=['#28a745', '#dc3545'])
        fig.update_layout(
            height=400,
            plot_bgcolor='rgba(240,247,255,0.8)',
            xaxis_title="Month",
            yaxis_title="Amount ($)",
            font=dict(family="Arial, sans-serif", size=12),
            legend_title="",
            margin=dict(l=20, r=20, t=40, b=20),
        )
        st.plotly_chart(fig, use_container_width=True)
        
        # Calculate revenue growth
        revenue_growth = [(cash_flow_df['Revenue'].iloc[i] / cash_flow_df['Revenue'].iloc[i-1] - 1) * 100 if i > 0 else 0 
                          for i in range(len(cash_flow_df))]
        avg_growth = sum(revenue_growth[1:]) / len(revenue_growth[1:])
        
        col1, col2 = st.columns(2)
        with col1:
            st.metric("Average Monthly Revenue Growth", f"{avg_growth:.1f}%")
        with col2:
            expense_growth = (cash_flow_df['Total_Expenses'].iloc[-1] / cash_flow_df['Total_Expenses'].iloc[0] - 1) * 100
            st.metric("Total Expense Growth", f"{expense_growth:.1f}%", delta=f"{expense_growth - avg_growth:.1f}%", delta_color="inverse")
    
    with tab3:
        # Burn rate trend
        fig = px.line(cash_flow_df, x='Month', y='Net_Burn',
                     title="Monthly Net Burn Trend",
                     labels={'Net_Burn': 'Net Burn ($)'},
                     color_discrete_sequence=['#dc3545'])
        fig.update_layout(
            height=400,
            plot_bgcolor='rgba(240,247,255,0.8)',
            xaxis_title="Month",
            yaxis_title="Net Burn ($)",
            font=dict(family="Arial, sans-serif", size=12),
            margin=dict(l=20, r=20, t=40, b=20),
        )
        
        # Add efficiency ratio as a second y-axis
        efficiency_ratio = [cash_flow_df['Revenue'].iloc[i] / cash_flow_df['Total_Expenses'].iloc[i] * 100 
                            for i in range(len(cash_flow_df))]
        
        fig.add_trace(go.Scatter(
            x=cash_flow_df['Month'], 
            y=efficiency_ratio,
            name='Efficiency Ratio (%)',
            yaxis='y2',
            line=dict(color='#0066cc', width=2, dash='dot')
        ))
        
        fig.update_layout(
            yaxis2=dict(
                title='Efficiency Ratio (%)',
                overlaying='y',
                side='right',
                range=[0, max(efficiency_ratio) * 1.2]
            )
        )
        
        st.plotly_chart(fig, use_container_width=True)
        
        with st.expander("🔎 Understanding Efficiency Ratio"):
            st.info("The efficiency ratio measures how efficiently your startup is generating revenue relative to expenses. A higher percentage means you're getting more revenue per dollar spent. Venture-backed startups typically aim for at least 40% before Series B funding.")
    
    # Expense breakdown
    st.subheader("Expense Breakdown")
    
    # Last month expenses
    last_month = cash_flow_df.iloc[-1]
    expense_categories = ['Payroll', 'Marketing', 'Office', 'Software', 'Travel', 'Legal', 'Misc']
    expense_values = [last_month[cat] for cat in expense_categories]
    
    col1, col2 = st.columns([2, 1])
    
    with col1:
        fig = px.pie(values=expense_values, names=expense_categories, 
                    title="Current Month Expense Breakdown",
                    color_discrete_sequence=px.colors.sequential.Blues_r)
        fig.update_layout(
            height=400,
            font=dict(family="Arial, sans-serif", size=12),
            margin=dict(l=20, r=20, t=40, b=20),
        )
        fig.update_traces(textposition='inside', textinfo='percent+label')
        st.plotly_chart(fig, use_container_width=True)
    
    with col2:
        # Expense analysis
        st.markdown("<h4>Expense Analysis</h4>", unsafe_allow_html=True)
        
        # Calculate industry benchmarks (simulated)
        benchmarks = {
            "Payroll": "70-80%",
            "Marketing": "10-15%",
            "Office": "5-8%",
            "Software": "3-5%"
        }
        
        # Create a table with expense categories, amounts, and % of total
        expense_df = pd.DataFrame({
            "Category": expense_categories,
            "Amount": expense_values,
            "% of Total": [v / sum(expense_values) * 100 for v in expense_values]
        })
        
        # Add benchmark column
        expense_df["Industry Benchmark"] = expense_df["Category"].map(
            lambda x: benchmarks.get(x, "N/A")
        )
        
        # Format the dataframe for display
        formatted_df = expense_df.copy()
        formatted_df["Amount"] = formatted_df["Amount"].apply(lambda x: f"${x:,.0f}")
        formatted_df["% of Total"] = formatted_df["% of Total"].apply(lambda x: f"{x:.1f}%")
        
        st.table(formatted_df)
        
        # AI-powered spending optimization
        with st.expander("💡 AI Spending Optimization"):
            st.markdown("<span class='ai-badge'>AI Recommendation</span>", unsafe_allow_html=True)
            
            # Use cache to avoid repeated API calls
            spending_key = f"spending_{date.today().isoformat()}"
            if spending_key not in st.session_state.insights_cache:
                spending_recommendation = generate_ai_response("""
                Based on your expense breakdown, recommend 2-3 specific ways to optimize spending to extend runway.
                Focus on industry best practices for seed-stage startups.
                """)
                st.session_state.insights_cache[spending_key] = spending_recommendation
                
            st.markdown(st.session_state.insights_cache[spending_key])
            
    # Fundraising Readiness Assessment
    st.subheader("Fundraising Readiness")
    
    # Get AI analysis of fundraising readiness
    fundraising_key = f"fundraising_{date.today().isoformat()}"
    if fundraising_key not in st.session_state.insights_cache:
        # Calculate metrics for assessment
        runway_calc = startup_data['cash'] / (startup_data['burn_rate'] - startup_data['revenue'])
        
        # Calculate some example metrics
        try:
            mrr_growth = (cash_flow_df['Revenue'].iloc[-1] / cash_flow_df['Revenue'].iloc[-2] - 1) * 100
            gross_margin = (cash_flow_df['Revenue'].iloc[-1] - cash_flow_df['Total_Expenses'].iloc[-1] / 2) / cash_flow_df['Revenue'].iloc[-1] * 100
        except:
            mrr_growth = 5.0
            gross_margin = 60.0
            
        metrics = {
            "MRR Growth": f"{mrr_growth:.1f}%",
            "Gross Margin": f"{gross_margin:.1f}%",
            "CAC": "$950",  # Example value
            "LTV": "$4,500",  # Example value
            "Churn": "3.2%",  # Example value
        }
        
        metrics_text = "\n".join([f"- {k}: {v}" for k, v in metrics.items()])
        
        fundraising_analysis = generate_ai_response(f"""
        You are a startup fundraising advisor. Analyze this startup's readiness for their next funding round:
        
        Company Profile:
        - Stage: {startup_data['stage']}
        - Last Funding: {startup_data['last_funding']}
        - Current Cash: ${startup_data['cash']}
        - Monthly Burn: ${startup_data['burn_rate']}
        - Runway: {runway_calc:.1f} months
        
        Key Metrics:
        {metrics_text}
        
        Provide a comprehensive fundraising readiness assessment:
        1. Overall fundraising readiness score (0-10)
        2. Assessment of current metrics compared to investor expectations for next round
        3. Identify the 3 most critical metrics to improve before fundraising
        4. Recommend specific targets for each key metric
        5. Suggest timeline and specific milestones for fundraising preparation
        6. Estimate reasonable valuation range based on metrics and market conditions
        
        Be specific with numbers, timelines, and actionable targets.
        """)
        st.session_state.insights_cache[fundraising_key] = fundraising_analysis
    
    st.markdown("<div class='advisor-card'>", unsafe_allow_html=True)
    st.markdown("<span class='ai-badge'>AI Fundraising Assessment</span>", unsafe_allow_html=True)
    st.markdown(f"<p class='advice-text'>{st.session_state.insights_cache[fundraising_key]}</p>", unsafe_allow_html=True)
    st.markdown("</div>", unsafe_allow_html=True)
    
    # Call-to-action for advisor
    st.info("📅 Need personalized guidance on fundraising? Schedule a session with our AI financial advisor to get detailed recommendations.")

# Render Decision Simulator page
def render_decision_simulator():
    """Render the AI-powered decision simulator page"""
    if not st.session_state.current_startup or st.session_state.current_startup not in st.session_state.startups:
        st.warning("No startup selected. Please upload data or select a sample startup.")
        render_upload_page()
        return
    
    # Get the selected startup data
    startup_data = st.session_state.startups[st.session_state.current_startup]['profile']
    
    st.markdown("<h1 class='main-header'>Decision Simulator</h1>", unsafe_allow_html=True)
    st.markdown("<p class='sub-header'>AI-powered analysis of business decisions</p>", unsafe_allow_html=True)
    
    # How AI helps with decision-making
    with st.expander("ℹ️ How AI enhances your decision-making"):
        st.markdown("""
        ### How AI Powers Your Decision Simulator
        
        The decision simulator uses AI to help you make better strategic decisions:
        
        - **Scenario Analysis**: Our AI model simulates multiple financial scenarios based on your input variables
        - **Risk Assessment**: The system automatically evaluates risk levels based on your cash runway and growth metrics
        - **Return Prediction**: AI algorithms predict potential returns on investments like hiring or marketing
        - **Opportunity Cost Analysis**: The model compares different allocations of capital to maximize growth
        - **Personalized Recommendations**: Based on your specific situation, the AI provides tailored alternatives
        
        This helps founders make data-driven decisions with less guesswork, avoid costly mistakes, and optimize resource allocation.
        """)
    
    st.write("Test the financial impact of key business decisions before implementing them. Our AI advisor will analyze the risks and benefits.")
    
    # Quick decision templates
    st.subheader("Common Scenarios")
    
    decision_templates = {
        "Hiring Engineering Team": {
            "description": "Evaluate the impact of growing your engineering team",
            "new_hires": 3,
            "new_marketing": 0,
            "other_expenses": 2000,
            "growth_impact": 0.02,
            "question": "We're considering hiring 3 more engineers to accelerate product development. How will this affect our runway and what growth impact should we expect to justify this investment?"
        },
        "Marketing Expansion": {
            "description": "Test increasing your marketing budget",
            "new_hires": 0,
            "new_marketing": 15000,
            "other_expenses": 0,
            "growth_impact": 0.04,
            "question": "We want to increase our marketing spend by $15K/month to drive growth. What growth rate would we need to achieve to make this financially viable?"
        },
        "Office Expansion": {
            "description": "Analyze the cost of moving to a larger office",
            "new_hires": 0,
            "new_marketing": 0,
            "other_expenses": 8000,
            "growth_impact": 0.01,
            "question": "We're considering moving to a larger office space that would add $8K/month to our expenses. Is this justified at our current stage?"
        },
        "Custom Scenario": {
            "description": "Create your own custom scenario",
            "new_hires": 0,
            "new_marketing": 0,
            "other_expenses": 0,
            "growth_impact": 0.0,
            "question": ""
        }
    }
    
    # Template selection
    template_cols = st.columns(4)
    selected_template = None
    
    for i, (template_name, template) in enumerate(decision_templates.items()):
        with template_cols[i]:
            if st.button(f"{template_name}\n{template['description']}", key=f"template_{i}"):
                selected_template = template_name"