shell-python-fallback

Shell Python Fallback

When to Use

Use this pattern when execute_code_sandbox or shell_agent tools consistently fail with "unknown error" for tasks such as:

• Data processing and transformation
• PDF generation (reportlab, etc.)
• File parsing and manipulation
• Any Python script execution that requires reliability

The Pattern

Instead of using code execution tools, embed your Python script directly in a run_shell command using a heredoc:

python3 << 'EOF'
# Your Python code here
import sys
print("Hello from embedded Python")
EOF

Step-by-Step Instructions

1. Identify the failure: When execute_code_sandbox or shell_agent returns "unknown error" repeatedly (2+ attempts), switch to this fallback.

2. Write your Python script: Prepare the complete Python code you need to execute.

3. Embed in run_shell: Use run_shell with a heredoc syntax:

Command: python3 << 'EOF'
import json
# Your complete script here
data = {"key": "value"}
print(json.dumps(data))
EOF

1. Handle multi-line scripts: For longer scripts, ensure proper indentation is preserved. The heredoc preserves whitespace exactly.

2. Check output: Parse the stdout from run_shell to verify success or capture errors.

Example: PDF Generation

python3 << 'EOF'
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("output.pdf", pagesize=letter)
c.drawString(100, 750, "Hello World")
c.save()
print("PDF created successfully")
EOF

Example: Data Processing

python3 << 'EOF'
import csv
import json

data = []
with open('input.csv', 'r') as f:
    reader = csv.DictReader(f)
    for row in reader:
        data.append(row)

with open('output.json', 'w') as f:
    json.dump(data, f, indent=2)

print(f"Processed {len(data)} records")
EOF

Best Practices

• Quote the EOF delimiter (<< 'EOF' not << EOF) to prevent shell variable expansion in your Python code
• Include error handling in your Python script with try/except blocks
• Print status messages to stdout so you can verify execution succeeded
• Use absolute paths or ensure working directory is correct
• Test incrementally: Start with a minimal script, then expand