Run Python through run_shell when code execution tools repeatedly fail. This workflow embeds a multiline script directly in a shell command, supporting tasks such as CSV conversion and PDF generation while checking execution output.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Use run_shell with embedded Python heredoc as reliable fallback when code execution tools fail
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Use this pattern when execute_code_sandbox or shell_agent tools consistently fail with "unknown error" for tasks such as:
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
Identify the failure: When execute_code_sandbox or shell_agent returns "unknown error" repeatedly (2+ attempts), switch to this fallback.
Write your Python script: Prepare the complete Python code you need to execute.
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
Handle multi-line scripts: For longer scripts, ensure proper indentation is preserved. The heredoc preserves whitespace exactly.
Check output: Parse the stdout from run_shell to verify success or capture errors.
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
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
<< 'EOF' not << EOF) to prevent shell variable expansion in your Python code| Issue | Solution |
|---|---|
| Script doesn't run | Ensure python3 is available in the shell environment |
| Indentation errors | Check that heredoc preserves spaces (use spaces, not tabs) |
| Module not found | Use python3 -m pip install <module> before running script |
| File not found | Use absolute paths or pwd to verify working directory |
The run_shell tool executes commands directly in the system shell, bypassing the sandbox restrictions or internal errors that affect execute_code_sandbox and shell_agent. The heredoc approach allows multi-line Python scripts while keeping everything in a single shell command.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
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.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.