Run Python through run_shell when execute_code_sandbox fails unexpectedly. The skill explains how to pass multiline code using a heredoc, a shell syntax for inline text, then check standard output and error messages.
Fallback method for executing Python when execute_code_sandbox fails with unknown errors
Review the instructions the agent will receive before you install.
Use this skill when execute_code_sandbox returns 'unknown error' or fails unexpectedly, even on simple Python code like print statements.
Switch to using run_shell with Python heredoc syntax instead of execute_code_sandbox.
python3 << 'EOF'
# Your Python code here
print("Hello World")
result = 2 + 2
print(f"Result: {result}")
EOF
Instead of:
execute_code_sandbox(code="print('Hello')")
Use:
run_shell(command="python3 << 'EOF'\nprint('Hello')\nEOF")
For multi-line code, build the command string:
code = """
import json
data = {"status": "ok", "count": 42}
print(json.dumps(data))
"""
run_shell(command=f"python3 << 'EOF'\n{code}\nEOF")
run_shell executes commands directly in the shell environment, bypassing sandbox issues<< 'EOF') allows clean multi-line Python code without complex escaping'EOF') to prevent variable expansion.py file first, then executing:
run_shell(command="python3 /path/to/script.py")
# Step 1: Try execute_code_sandbox
try:
result = execute_code_sandbox(code="print(2+2)")
except Exception as e:
# Step 2: Fallback to run_shell with heredoc
result = run_shell(command="python3 << 'EOF'\nprint(2+2)\nEOF")
# Parse stdout to get the output
output = result.stdout.strip()
| Issue | Solution |
|---|---|
| Python not found | Use which python3 to verify installation |
| Heredoc not working | Ensure single quotes around EOF delimiter |
| Complex imports fail | Install required packages or write to .py file |
| Output not captured | Check run_shell stdout, not return value |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Prepare audio stems, the separate parts of a track, for mixing by matching their durations with silence, loops, or crossfades. Verify each generated and processed file before moving to the next production step.
Produce audio in separate stems, meaning individual instrument tracks, and verify each output as you go. Align track lengths with silence, loops, or crossfades, then apply effects, mix a master, and package the files.
Build serverless endpoints that relay external API requests for a dashboard while keeping API keys on the server. Includes Vercel examples for input checks, caching, cross-origin access, and consistent JSON responses.
Produce a master track and separate audio parts through a structured Python workflow. Apply filters and reverb, export WAV files with consistent settings, package them in a ZIP archive, and check that the deliverables meet the requested specifications.
Keep document creation moving when web searches and page retrieval repeatedly fail. The skill preserves the original task, uses the model’s existing knowledge, and clearly identifies information that could not be checked against external sources.
When Python execution repeatedly fails in execute_code_sandbox, use a file-based alternative: save the script, run it through the shell, and capture results or errors. The guidance covers paths, imports, timeouts, structured output, and optional cleanup.