Run Python through a saved script when execute_code_sandbox or shell_agent repeatedly fails. The workflow writes code to a file, executes it through run_shell, and checks errors and expected outputs such as spreadsheets or documents.
Reliable Python execution workflow when execute_code_sandbox or shell_agent fail
Review the instructions the agent will receive before you install.
Use this pattern when:
execute_code_sandbox returns unknown errors or fails repeatedlyshell_agent cannot successfully execute Python codeInstead of delegating Python execution to agents, use this two-step inline approach:
.py file using write_filerun_shell with python <script.py>Use write_file to create a Python script with all necessary code inline:
write_file
path: /path/to/script.py
content: |
import pandas as pd
# Your complete Python code here
df = pd.DataFrame({...})
df.to_excel('output.xlsx', index=False)
Run the script directly:
run_shell
command: python /path/to/script.py
This approach is more reliable because:
# Step 1: Write the script
write_file:
path: create_report.py
content: |
import pandas as pd
from openpyxl import Workbook
# Create data
data = {'Column1': [1, 2, 3], 'Column2': ['A', 'B', 'C']}
df = pd.DataFrame(data)
# Save to Excel
df.to_excel('report.xlsx', index=False)
print('Excel file created successfully')
# Step 2: Execute
run_shell:
command: python create_report.py
| Issue | Solution |
|---|---|
| Module not found | Add pip install commands before python command |
| Permission errors | Check file paths are writable |
| Script not found | Use absolute path or cd to directory first |
| Output not created | Check for Python errors in run_shell output |
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.