diff --git a/pyproject.toml b/pyproject.toml
index e48f692..2294f09 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -14,7 +14,7 @@ langchain-openai = "0.2.11"
 langgraph = "0.2.56"
 pandas = "^2.1.0"
 numpy = "^1.24.0"
-python-dotenv = "1.0.0"
+python-dotenv = "^1.0.0"
 matplotlib = "^3.9.2"
 
 [tool.poetry.group.dev.dependencies]
diff --git a/src/agents.py b/src/agents.py
index 66b912b..2968025 100644
--- a/src/agents.py
+++ b/src/agents.py
@@ -1,18 +1,33 @@
+import argparse
+import ast
+import json
 import math
+import operator
+import os
+from datetime import datetime
 from typing import Annotated, Any, Dict, Sequence, TypedDict
 
-import operator
+from dotenv import load_dotenv
 from langchain_core.messages import BaseMessage, HumanMessage
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_openai.chat_models import ChatOpenAI
 from langgraph.graph import END, StateGraph
 
-from src.tools import calculate_bollinger_bands, calculate_intrinsic_value, calculate_macd, calculate_obv, calculate_rsi, search_line_items, get_financial_metrics, get_insider_trades, get_market_cap, get_prices, prices_to_df
-
-import argparse
-from datetime import datetime
-import json
-import ast
+from src.tools import (
+    calculate_bollinger_bands,
+    calculate_intrinsic_value,
+    calculate_macd,
+    calculate_obv,
+    calculate_rsi,
+    get_financial_metrics,
+    get_insider_trades,
+    get_market_cap,
+    get_prices,
+    prices_to_df,
+    search_line_items,
+)
+
+load_dotenv()  # Load environment variables from .env file
 
 llm = ChatOpenAI(model="gpt-4o")
 
@@ -42,47 +57,56 @@ def market_data_agent(state: AgentState):
     else:
         start_date = data["start_date"]
 
-    # Get the historical price data
-    prices = get_prices(
-        ticker=data["ticker"], 
-        start_date=start_date, 
-        end_date=end_date,
-    )
-
-    # Get the financial metrics
-    financial_metrics = get_financial_metrics(
-        ticker=data["ticker"], 
-        report_period=end_date, 
-        period='ttm', 
-        limit=1,
-    )
-
-    # Get the insider trades
-    insider_trades = get_insider_trades(
-        ticker=data["ticker"], 
-        end_date=end_date,
-        limit=5,
-    )
-
-    # Get the market cap
-    market_cap = get_market_cap(
-        ticker=data["ticker"],
-    )
+    try:
+        # Get the historical price data
+        prices = get_prices(
+            ticker=data["ticker"],
+            start_date=start_date,
+            end_date=end_date,
+        )
+
+        # Get the financial metrics
+        financial_metrics = get_financial_metrics(
+            ticker=data["ticker"],
+            report_period=end_date,
+            period='ttm',
+            limit=1,
+        )
+
+        # Get the insider trades
+        insider_trades = get_insider_trades(
+            ticker=data["ticker"],
+            end_date=end_date,
+            limit=5,
+        )
+
+        # Get the market cap
+        market_cap = get_market_cap(
+            ticker=data["ticker"],
+        )
+
+        # Get the line_items
+        financial_line_items = search_line_items(
+            ticker=data["ticker"],
+            line_items=["free_cash_flow"],
+            period='ttm',
+            limit=1,
+        )
 
-    # Get the line_items
-    financial_line_items = search_line_items(
-        ticker=data["ticker"], 
-        line_items=["free_cash_flow"],
-        period='ttm',
-        limit=1,
-    )
+    except Exception as e:
+        error_message = f"Error fetching data: {str(e)}"
+        print(error_message)
+        return {
+            "messages": messages,
+            "data": {**data, "error": error_message}
+        }
 
     return {
         "messages": messages,
         "data": {
-            **data, 
-            "prices": prices, 
-            "start_date": start_date, 
+            **data,
+            "prices": prices,
+            "start_date": start_date,
             "end_date": end_date,
             "financial_metrics": financial_metrics,
             "insider_trades": insider_trades,
@@ -99,23 +123,23 @@ def quant_agent(state: AgentState):
     data = state["data"]
     prices = data["prices"]
     prices_df = prices_to_df(prices)
-    
+
     # Calculate indicators
     # 1. MACD (Moving Average Convergence Divergence)
     macd_line, signal_line = calculate_macd(prices_df)
-    
+
     # 2. RSI (Relative Strength Index)
     rsi = calculate_rsi(prices_df)
-    
+
     # 3. Bollinger Bands (Bollinger Bands)
     upper_band, lower_band = calculate_bollinger_bands(prices_df)
-    
+
     # 4. OBV (On-Balance Volume)
     obv = calculate_obv(prices_df)
-    
+
     # Generate individual signals
     signals = []
-    
+
     # MACD signal
     if macd_line.iloc[-2] < signal_line.iloc[-2] and macd_line.iloc[-1] > signal_line.iloc[-1]:
         signals.append('bullish')
@@ -123,7 +147,7 @@ def quant_agent(state: AgentState):
         signals.append('bearish')
     else:
         signals.append('neutral')
-    
+
     # RSI signal
     if rsi.iloc[-1] < 30:
         signals.append('bullish')
@@ -131,7 +155,7 @@ def quant_agent(state: AgentState):
         signals.append('bearish')
     else:
         signals.append('neutral')
-    
+
     # Bollinger Bands signal
     current_price = prices_df['close'].iloc[-1]
     if current_price < lower_band.iloc[-1]:
@@ -140,7 +164,7 @@ def quant_agent(state: AgentState):
         signals.append('bearish')
     else:
         signals.append('neutral')
-    
+
     # OBV signal
     obv_slope = obv.diff().iloc[-5:].mean()
     if obv_slope > 0:
@@ -149,7 +173,7 @@ def quant_agent(state: AgentState):
         signals.append('bearish')
     else:
         signals.append('neutral')
-    
+
     # Add reasoning collection
     reasoning = {
         "MACD": {
@@ -169,22 +193,22 @@ def quant_agent(state: AgentState):
             "details": f"OBV slope is {obv_slope:.2f} ({signals[3]})"
         }
     }
-    
+
     # Determine overall signal
     bullish_signals = signals.count('bullish')
     bearish_signals = signals.count('bearish')
-    
+
     if bullish_signals > bearish_signals:
         overall_signal = 'bullish'
     elif bearish_signals > bullish_signals:
         overall_signal = 'bearish'
     else:
         overall_signal = 'neutral'
-    
+
     # Calculate confidence level based on the proportion of indicators agreeing
     total_signals = len(signals)
     confidence = max(bullish_signals, bearish_signals) / total_signals
-    
+
     # Generate the message content
     message_content = {
         "signal": overall_signal,
@@ -206,7 +230,7 @@ def quant_agent(state: AgentState):
     # Print the reasoning if the flag is set
     if show_reasoning:
         show_agent_reasoning(message_content, "Quant Agent")
-    
+
     return {
         "messages": [message],
         "data": data,
@@ -224,7 +248,7 @@ def fundamentals_agent(state: AgentState):
     # Initialize signals list for different fundamental aspects
     signals = []
     reasoning = {}
-    
+
     # 1. Profitability Analysis
     profitability_score = 0
     if metrics["return_on_equity"] > 0.15:  # Strong ROE above 15%
@@ -233,13 +257,13 @@ def fundamentals_agent(state: AgentState):
         profitability_score += 1
     if metrics["operating_margin"] > 0.15:  # Strong operating efficiency
         profitability_score += 1
-        
+
     signals.append('bullish' if profitability_score >= 2 else 'bearish' if profitability_score == 0 else 'neutral')
     reasoning["Profitability"] = {
         "signal": signals[0],
         "details": f"ROE: {metrics['return_on_equity']:.2%}, Net Margin: {metrics['net_margin']:.2%}, Op Margin: {metrics['operating_margin']:.2%}"
     }
-    
+
     # 2. Growth Analysis
     growth_score = 0
     if metrics["revenue_growth"] > 0.10:  # 10% revenue growth
@@ -248,13 +272,13 @@ def fundamentals_agent(state: AgentState):
         growth_score += 1
     if metrics["book_value_growth"] > 0.10:  # 10% book value growth
         growth_score += 1
-        
+
     signals.append('bullish' if growth_score >= 2 else 'bearish' if growth_score == 0 else 'neutral')
     reasoning["Growth"] = {
         "signal": signals[1],
         "details": f"Revenue Growth: {metrics['revenue_growth']:.2%}, Earnings Growth: {metrics['earnings_growth']:.2%}"
     }
-    
+
     # 3. Financial Health
     health_score = 0
     if metrics["current_ratio"] > 1.5:  # Strong liquidity
@@ -263,18 +287,18 @@ def fundamentals_agent(state: AgentState):
         health_score += 1
     if metrics["free_cash_flow_per_share"] > metrics["earnings_per_share"] * 0.8:  # Strong FCF conversion
         health_score += 1
-        
+
     signals.append('bullish' if health_score >= 2 else 'bearish' if health_score == 0 else 'neutral')
     reasoning["Financial_Health"] = {
         "signal": signals[2],
         "details": f"Current Ratio: {metrics['current_ratio']:.2f}, D/E: {metrics['debt_to_equity']:.2f}"
     }
-    
+
     # 4. Price to X ratios
     pe_ratio = metrics["price_to_earnings_ratio"]
     pb_ratio = metrics["price_to_book_ratio"]
     ps_ratio = metrics["price_to_sales_ratio"]
-    
+
     price_ratio_score = 0
     if pe_ratio < 25:  # Reasonable P/E ratio
         price_ratio_score += 1
@@ -282,7 +306,7 @@ def fundamentals_agent(state: AgentState):
         price_ratio_score += 1
     if ps_ratio < 5:  # Reasonable P/S ratio
         price_ratio_score += 1
-        
+
     signals.append('bullish' if price_ratio_score >= 2 else 'bearish' if price_ratio_score == 0 else 'neutral')
     reasoning["Price_Ratios"] = {
         "signal": signals[3],
@@ -307,38 +331,38 @@ def fundamentals_agent(state: AgentState):
         "signal": signals[4],
         "details": f"Intrinsic Value: ${intrinsic_value:,.2f}, Market Cap: ${market_cap:,.2f}"
     }
-    
+
     # Determine overall signal
     bullish_signals = signals.count('bullish')
     bearish_signals = signals.count('bearish')
-    
+
     if bullish_signals > bearish_signals:
         overall_signal = 'bullish'
     elif bearish_signals > bullish_signals:
         overall_signal = 'bearish'
     else:
         overall_signal = 'neutral'
-    
+
     # Calculate confidence level
     total_signals = len(signals)
     confidence = max(bullish_signals, bearish_signals) / total_signals
-    
+
     message_content = {
         "signal": overall_signal,
         "confidence": f"{round(confidence * 100)}%",
         "reasoning": reasoning
     }
-    
+
     # Create the fundamental analysis message
     message = HumanMessage(
         content=str(message_content),
         name="fundamentals_agent",
     )
-    
+
     # Print the reasoning if the flag is set
     if show_reasoning:
         show_agent_reasoning(message_content, "Fundamental Analysis Agent")
-    
+
     return {
         "messages": [message],
         "data": data,
@@ -354,7 +378,10 @@ def sentiment_agent(state: AgentState):
     # Loop through the insider trades, if transaction_shares is negative, then it is a sell, which is bearish, if positive, then it is a buy, which is bullish
     signals = []
     for trade in insider_trades:
-        if trade["transaction_shares"] < 0:
+        transaction_shares = trade.get("transaction_shares")
+        if transaction_shares is None:
+            continue
+        if transaction_shares < 0:
             signals.append("bearish")
         else:
             signals.append("bullish")
@@ -404,9 +431,17 @@ def risk_management_agent(state: AgentState):
     prices_df = prices_to_df(data["prices"])
 
     # Fetch messages from other agents
-    quant_message = next(msg for msg in state["messages"] if msg.name == "quant_agent")
-    fundamentals_message = next(msg for msg in state["messages"] if msg.name == "fundamentals_agent")
-    sentiment_message = next(msg for msg in state["messages"] if msg.name == "sentiment_agent")
+    try:
+        quant_message = next(msg for msg in state["messages"] if msg.name == "quant_agent")
+        fundamentals_message = next(msg for msg in state["messages"] if msg.name == "fundamentals_agent")
+        sentiment_message = next(msg for msg in state["messages"] if msg.name == "sentiment_agent")
+    except StopIteration as e:
+        error_message = f"Error fetching messages from other agents: {str(e)}"
+        print(error_message)
+        return {
+            "messages": state["messages"],
+            "data": {**data, "error": error_message}
+        }
 
     try:
         fundamental_signals = json.loads(fundamentals_message.content)
@@ -463,7 +498,7 @@ def risk_management_agent(state: AgentState):
     total_portfolio_value = portfolio['cash'] + current_stock_value
 
     base_position_size = total_portfolio_value * 0.25  # Start with 25% max position of total portfolio
-    
+
     if market_risk_score >= 4:
         # Reduce position for high risk
         max_position_size = base_position_size * 0.5
@@ -556,10 +591,18 @@ def portfolio_management_agent(state: AgentState):
     portfolio = state["data"]["portfolio"]
 
     # Get the quant agent, fundamentals agent, and risk management agent messages
-    quant_message = next(msg for msg in state["messages"] if msg.name == "quant_agent")
-    fundamentals_message = next(msg for msg in state["messages"] if msg.name == "fundamentals_agent")
-    sentiment_message = next(msg for msg in state["messages"] if msg.name == "sentiment_agent")
-    risk_message = next(msg for msg in state["messages"] if msg.name == "risk_management_agent")
+    try:
+        quant_message = next(msg for msg in state["messages"] if msg.name == "quant_agent")
+        fundamentals_message = next(msg for msg in state["messages"] if msg.name == "fundamentals_agent")
+        sentiment_message = next(msg for msg in state["messages"] if msg.name == "sentiment_agent")
+        risk_message = next(msg for msg in state["messages"] if msg.name == "risk_management_agent")
+    except StopIteration as e:
+        error_message = f"Error fetching messages from other agents: {str(e)}"
+        print(error_message)
+        return {
+            "messages": state["messages"],
+            "data": {**state["data"], "error": error_message}
+        }
 
     # Create the prompt template
     template = ChatPromptTemplate.from_messages(
@@ -579,21 +622,21 @@ def portfolio_management_agent(state: AgentState):
                 1. Fundamental Analysis (50% weight)
                    - Primary driver of trading decisions
                    - Should determine overall direction
-                
+
                 2. Technical/Quant Analysis (35% weight)
                    - Secondary confirmation
                    - Helps with entry/exit timing
-                
+
                 3. Sentiment Analysis (15% weight)
                    - Final consideration
                    - Can influence sizing within risk limits
-                
+
                 The decision process should be:
                 1. First check risk management constraints
                 2. Then evaluate fundamental outlook
                 3. Use technical analysis for timing
                 4. Consider sentiment for final adjustment
-                
+
                 Provide the following in your output:
                 - "action": "buy" | "sell" | "hold",
                 - "quantity": <positive integer>
@@ -635,7 +678,7 @@ def portfolio_management_agent(state: AgentState):
     # Generate the prompt
     prompt = template.invoke(
         {
-            "quant_message": quant_message.content, 
+            "quant_message": quant_message.content,
             "fundamentals_message": fundamentals_message.content,
             "sentiment_message": sentiment_message.content,
             "risk_message": risk_message.content,
@@ -675,25 +718,30 @@ def show_agent_reasoning(output, agent_name):
 
 ##### Run the Hedge Fund #####
 def run_hedge_fund(ticker: str, start_date: str, end_date: str, portfolio: dict, show_reasoning: bool = False):
-    final_state = app.invoke(
-        {
-            "messages": [
-                HumanMessage(
-                    content="Make a trading decision based on the provided data.",
-                )
-            ],
-            "data": {
-                "ticker": ticker,
-                "portfolio": portfolio,
-                "start_date": start_date,
-                "end_date": end_date,
+    try:
+        final_state = app.invoke(
+            {
+                "messages": [
+                    HumanMessage(
+                        content="Make a trading decision based on the provided data.",
+                    )
+                ],
+                "data": {
+                    "ticker": ticker,
+                    "portfolio": portfolio,
+                    "start_date": start_date,
+                    "end_date": end_date,
+                },
+                "metadata": {
+                    "show_reasoning": show_reasoning,
+                }
             },
-            "metadata": {
-                "show_reasoning": show_reasoning,
-            }
-        },
-    )
-    return final_state["messages"][-1].content
+        )
+        return final_state["messages"][-1].content
+    except Exception as e:
+        error_message = f"Error running hedge fund: {str(e)}"
+        print(error_message)
+        return error_message
 
 # Define the new workflow
 workflow = StateGraph(AgentState)
@@ -726,28 +774,28 @@ def run_hedge_fund(ticker: str, start_date: str, end_date: str, portfolio: dict,
     parser.add_argument('--start-date', type=str, help='Start date (YYYY-MM-DD). Defaults to 3 months before end date')
     parser.add_argument('--end-date', type=str, help='End date (YYYY-MM-DD). Defaults to today')
     parser.add_argument('--show-reasoning', action='store_true', help='Show reasoning from each agent')
-    
+
     args = parser.parse_args()
-    
+
     # Validate dates if provided
     if args.start_date:
         try:
             datetime.strptime(args.start_date, '%Y-%m-%d')
         except ValueError:
             raise ValueError("Start date must be in YYYY-MM-DD format")
-    
+
     if args.end_date:
         try:
             datetime.strptime(args.end_date, '%Y-%m-%d')
         except ValueError:
             raise ValueError("End date must be in YYYY-MM-DD format")
-    
+
     # Sample portfolio - you might want to make this configurable too
     portfolio = {
         "cash": 100000.0,  # $100,000 initial cash
         "stock": 0         # No initial stock position
     }
-    
+
     result = run_hedge_fund(
         ticker=args.ticker,
         start_date=args.start_date,