Improve Budget Sheet handling

app.py

@@ -25,13 +25,30 @@ df2_all = pd.read_excel(
 df1 = {}
 for sheet, raw_df in df1_all.items():
     if sheet == "Budget":
-        # Load rows 3–33 with headers at row 3
-        df1[sheet] = pd.read_excel(
+        # Load raw first
+        budget_raw = pd.read_excel(
+            os.path.join("data_source", "OC Onboarding Information.xlsx"),
+            sheet_name="Budget",
+            header=None
+        )
+
+        # Part 1: detailed breakdown (rows 3–20 with headers at row 3)
+        budget_details = pd.read_excel(
             os.path.join("data_source", "OC Onboarding Information.xlsx"),
             sheet_name="Budget",
             header=2,
-            nrows=31  # rows 3–33 inclusive
+            nrows=17  # rows 3–19 (inclusive)
         )
+
+        # Part 2: summary section (rows 21–33)
+        # Take row 3 (index 3 in header=None) as column headers
+        summary_headers = budget_raw.iloc[3].tolist()
+        budget_summary = budget_raw.iloc[21:33].reset_index(drop=True)
+        budget_summary.columns = summary_headers
+
+        # Add into df1 dict
+        df1["Budget_Details"] = budget_details
+        df1["Budget_Summary"] = budget_summary
     elif sheet == "Rooms per category":
         # use row 4 as header
         df1[sheet] = pd.read_excel(
@@ -64,17 +81,29 @@ for sheet, raw_df in df2_all.items():
 # Build schema info for prompts
 def get_schema_info():
     lines = ["Report 1 - OC Onboarding Information:"]
+
     for sheet, df in df1.items():
-        if sheet == "Budget":
-            lines.append(f'Sheet: {sheet} (rows 3–33). This sheet contains the full hotel budget, including both detailed line items (by channel/segment) and summary metrics (total revenue, occupancy %, RevPAR, capacity).')
+        if sheet == "Budget_Details":
+            lines.append("Sheet: Budget_Details (rows 3–20). Contains detailed breakdown by channel/segment.")
+        elif sheet == "Budget_Summary":
+            lines.append("Sheet: Budget_Summary (rows 21–33). Contains summary metrics (totals, occupancy %, RevPAR, room capacity, date ranges).")
+            # Add all rows as examples
+            try:
+                all_rows = df.to_dict(orient="records")
+                lines.append("Example rows:")
+                for row in all_rows:
+                    lines.append(str(row))
+            except Exception:
+                lines.append("Example rows: [no data available]")
         else:
             lines.append(f"Sheet: {sheet}, Columns: {list(df.columns)}")
-        # Add one example row for context
-        try:
-            sample = df.head(1).to_dict(orient="records")[0]
-            lines.append(f"Example row: {sample}")
-        except Exception:
-            lines.append("Example row: [no data available]")
+            # Add one example row for context
+            try:
+                sample = df.head(1).to_dict(orient="records")[0]
+                lines.append(f"Example row: {sample}")
+            except Exception:
+                lines.append("Example row: [no data available]")
+
     lines.append("\nReport 2 - The Alex Ideas Report:")
     for sheet, df in df2.items():
         lines.append(f"Sheet: {sheet}, Columns: {list(df.columns)}")
@@ -83,6 +112,7 @@ def get_schema_info():
             lines.append(f"Example row: {sample}")
         except Exception:
             lines.append("Example row: [no data available]")
+
     return "\n".join(lines)
 
 schema_info = get_schema_info()
@@ -126,9 +156,11 @@ If absolutely no relation to provided sheets, respond with:
 
 The reports are OC Onboarding Information and The Alex Ideas Report.
 OC Onboarding Information (df1) is the initial hotel data including a budget set by the hotel for the year.
+- "Budget_Details": line-item breakdown (channels, rates, revenue, etc.)
+- "Budget_Summary": summary rows (total occupancy, RevPar for each month, etc.)
 The Alex Ideas Report (df2) is the real reports about revenue of the hotel for the year. 
 
-They have the following schema (sheet names, columns, and example rows, but Budget sheet is fully loaded):
+They have the following schema (sheet names, columns, and example rows, but Budget_Summary sheet is fully loaded):
 {schema_info}
 
 The user asked:

data_source/~$OC Onboarding Information.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba618d8286013600f65acebe72668364adb0684e160cc6ef2f3bf68995fddd5d
+size 165

data_source/~$The Alex Ideas Report.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba618d8286013600f65acebe72668364adb0684e160cc6ef2f3bf68995fddd5d
+size 165