Update agents/reasoner.py

agents/reasoner.py

@@ -2,6 +2,8 @@ import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
 import io
+from PIL import Image   # ⭐ REQUIRED FOR IMAGE FIX
+
 
 # ============================================================
 #  SLOTING OPTIMIZATION — PHASE 1
@@ -61,6 +63,7 @@ def run_picking_optimization(message, picking_df):
     df = df.sort_values("Distance").reset_index(drop=True)
     reasoning_steps.append("Calculated Manhattan distance & sorted sequence.")
 
+    # --- Generate plot ---
     plt.figure(figsize=(6, 6))
     plt.plot(df["x"], df["y"], marker="o", linestyle="-")
     plt.title("Optimized Picking Route")
@@ -69,8 +72,11 @@ def run_picking_optimization(message, picking_df):
 
     buffer = io.BytesIO()
     plt.savefig(buffer, format="png")
-    buffer.seek(0)
     plt.close()
+    buffer.seek(0)
+
+    # ⭐ Convert BytesIO → PIL (Gradio requirement)
+    image = Image.open(buffer)
 
     reasoning_steps.append("Generated walking route visualization.")
 
@@ -80,7 +86,7 @@ def run_picking_optimization(message, picking_df):
         "#### 🔍 Reasoning\n" + "\n".join([f"- {r}" for r in reasoning_steps])
     )
 
-    return explanation, buffer
+    return explanation, image
 
 
 # ============================================================
@@ -114,7 +120,7 @@ def run_demand_forecast(message, slotting_df):
 
     reasoning_steps.append("Generated 7-day demand projection.")
 
-    # Plot forecast
+    # --- Plot forecast ---
     plt.figure(figsize=(6, 4))
     plt.plot(forecast_df["Day"], forecast_df["Forecasted_Demand"], marker="o")
     plt.title("7-Day Demand Forecast")
@@ -123,8 +129,11 @@ def run_demand_forecast(message, slotting_df):
 
     buffer = io.BytesIO()
     plt.savefig(buffer, format="png")
-    buffer.seek(0)
     plt.close()
+    buffer.seek(0)
+
+    # ⭐ Convert BytesIO → PIL
+    image = Image.open(buffer)
 
     explanation = (
         "### 📈 Demand Forecasting\n"
@@ -132,11 +141,11 @@ def run_demand_forecast(message, slotting_df):
         "#### 🔍 Reasoning\n" + "\n".join([f"- {r}" for r in reasoning_steps])
     )
 
-    return explanation, buffer, forecast_df
+    return explanation, image, forecast_df
 
 
 # ============================================================
-#  REPLENISHMENT OPTIMIZATION — MODULE 2
+#  REPLENISHMENT ANALYSIS — MODULE 2
 # ============================================================
 
 def run_replenishment_analysis(message, slotting_df):
@@ -244,16 +253,13 @@ def run_rebalancing_analysis(message, slotting_df):
 # ============================================================
 
 def run_workforce_optimization(message, slotting_df):
-    """
-    Estimate workforce needed based on SKU demand load.
-    """
     reasoning = []
     df = slotting_df.copy()
 
     if "Frequency" not in df.columns:
         return "Cannot calculate workforce — missing Frequency column.", None
 
-    df["Workload"] = df["Frequency"] * 1.2  # weight multiplier
+    df["Workload"] = df["Frequency"] * 1.2
     total_workload = df["Workload"].sum()
     workers_needed = max(1, int(total_workload // 150))
 
@@ -279,10 +285,6 @@ def run_workforce_optimization(message, slotting_df):
 # ============================================================
 
 def run_dock_scheduling(message, slotting_df):
-    """
-    Simple dock scheduling:
-    - Assigns SKUs to docks based on demand priority
-    """
     reasoning = []
     df = slotting_df.copy()