Excel File Creation Fallback

When execute_code_sandbox fails for openpyxl or Excel operations, delegate to shell_agent which can autonomously handle dependency and environment issues.

When to Use

• execute_code_sandbox fails with import errors for openpyxl or related libraries
• The sandbox environment lacks required dependencies
• You need to create or modify Excel files with complex requirements
• Repeated sandbox execution failures for file I/O operations

Steps

Step 1: Attempt with execute_code_sandbox first

Try creating the Excel file using Python's openpyxl library in the code sandbox:

from openpyxl import Workbook

wb = Workbook()
ws = wb.active
ws.append(['Column1', 'Column2', 'Column3'])
wb.save('output.xlsx')

Step 2: If it fails, switch to shell_agent

Delegate the task to shell_agent with a clear, comprehensive task description:

Create an Excel file named 'output.xlsx' with the following structure:
- Sheet 1: Data with columns [Date, Metric, Value]
- Include sample data rows with realistic values
- Apply basic formatting (bold headers, cell borders)
- Add a summary section with totals or averages
- Save the file in the current directory

Step 3: Let shell_agent handle the environment

The shell_agent will:

• Decide whether to use Python or Bash
• Install dependencies if needed (e.g., pip install openpyxl)
• Write and execute the code
• Automatically retry and fix errors (up to several rounds)
• Confirm the file was created successfully

Example Task Descriptions

Basic Excel file:

Create an Excel file named 'sales_report.xlsx' with headers: Date, Product, Quantity, Price, Total. Add 10 sample rows of data and a formula column for Total (Quantity * Price).