run-shell-fallback

Run Shell Fallback Pattern

This skill provides a reliable workaround when execute_code_sandbox or read_file fail with 'unknown error' by switching to run_shell with inline Python code.

When to Use

Apply this pattern when you encounter:

• execute_code_sandbox fails with "unknown error" or timeout
• read_file fails to read accessible files with "unknown error"
• Sandbox environment is unreliable for your specific task

How to Implement

1. File Reading Fallback

When read_file fails, use run_shell with Python or cat:

For text files:

run_shell(command="cat /path/to/file.txt")

For structured parsing (Python one-liner):

run_shell(command="python3 -c \"import json; print(json.load(open('/path/to/file.json')))\"")

For multi-line Python processing:

run_shell(command="python3 << 'EOF'
with open('/path/to/file.txt', 'r') as f:
    content = f.read()
    # Process content here
    print(content.upper())
EOF")

2. Code Execution Fallback

When execute_code_sandbox fails, use run_shell with inline Python:

Simple one-liners:

run_shell(command="python3 -c \"print('Hello'); import os; print(os.getcwd())\"")

Multi-line scripts (heredoc):

run_shell(command="python3 << 'EOF'
import os
import json

def process_data(data):
    return {k: v.upper() if isinstance(v, str) else v for k, v in data.items()}

with open('input.json') as f:
    data = json.load(f)
    
result = process_data(data)
print(json.dumps(result, indent=2))
EOF")

With inline file write:

run_shell(command="python3 << 'EOF'
result = {'status': 'success', 'count': 42}
with open('output.json', 'w') as f:
    json.dump(result, f, indent=2)
print('File written successfully')
EOF")

3. Decision Flow

1. Attempt execute_code_sandbox or read_file
2. If failure with 'unknown error':
   a. Determine task type (code execution vs file reading)
   b. Choose inline Python approach (-c for simple, heredoc for complex)
   c. Execute via run_shell
   d. Parse output as needed
3. Continue with task using results from run_shell