When execute_code_sandbox fails for Python code that depends on external libraries, use run_shell with a heredoc Python script as a reliable fallback. The shell environment typically has better access to installed packages and system configuration than the sandbox.

When to Use This Pattern

Apply this skill when:

execute_code_sandbox returns errors related to missing libraries (e.g., ModuleNotFoundError)
The code requires packages that may not be installed in the sandbox environment
You need PDF generation, data visualization, or other library-heavy operations
Previous sandbox execution attempts have failed with import errors

How to Implement

Step 1: Identify the Failure

Check if the sandbox error indicates a library/dependency issue:

ModuleNotFoundError: No module named 'xxx'
ImportError: cannot import name 'xxx'

When to Use This Pattern

Apply this skill when:

execute_code_sandbox returns errors related to missing libraries (e.g., ModuleNotFoundError)
The code requires packages that may not be installed in the sandbox environment
You need PDF generation, data visualization, or other library-heavy operations
Previous sandbox execution attempts have failed with import errors

How to Implement

Step 1: Identify the Failure

Check if the sandbox error indicates a library/dependency issue:

ModuleNotFoundError: No module named 'xxx'
ImportError: cannot import name 'xxx'

Python Shell Fallback

When to Use This Pattern

How to Implement

Step 1: Identify the Failure

Python Shell Fallback

When to Use This Pattern

How to Implement

Step 1: Identify the Failure

Step 2: Convert to Shell Execution

Step 3: Execute via run_shell

Prose

Coding Agent (bash-first)

Create Prompt

Strategic Compact

Strategic Compact

Strategic Compact