sandbox-exec-fallback
Fallback pattern for executing Python code when execute_code_sandbox fails by writing to file and running via shell
- License 许可
- MIT
- 所属仓库
- HKUDS/AgentPilot
- 最近更新
- 2026-11-12
- Stars
- ★ 8.0k
- Forks
- 944
01 前言 Front Matter
- name
- sandbox-exec-fallback
- description
- Fallback pattern for executing Python code when execute_code_sandbox fails by writing to file and running via shell
02 资源文件 1
- 其他.skill_id35 B
03 SKILL.md 正文
Sandbox Execution Fallback
When to Use
Use this skill when execute_code_sandbox fails during Python code execution, particularly for tasks involving:
- Spreadsheet generation (xlsx, csv)
- Data processing and transformations
- File output operations
- Complex computations requiring libraries
Recovery Pattern
When execute_code_sandbox returns an error or fails to produce expected output:
Step 1: Write Python Code to File
Use write_file to save your Python script to a file:
# Use write_file tool with:
path: "script.py"
content: <your complete Python code as a string>
Step 2: Execute via Shell
Use run_shell to execute the script:
# Use run_shell tool with:
command: "python3 script.py"
timeout: <appropriate timeout, e.g., 300 for long-running tasks>
Step 3: Verify Output
Check the shell output for:
- Success messages or printed results
- Error messages (if any, diagnose and fix the script)
- File creation confirmations
Step 4: Access Generated Files
If the script creates output files (e.g., spreadsheets), they will be in the current working directory. Use list_dir to confirm, then read_file to access if needed.
Why This Works
- Same Python Environment:
python3in the shell uses the same environment as the sandbox - More Robust: Shell execution handles long-running or memory-intensive tasks better
- Debuggable: Errors are captured in stdout/stderr for easier diagnosis
- Identical Results: Produces the same output as sandbox execution when successful
Example: Spreadsheet Generation
Original code that failed in execute_code_sandbox:
import pandas as pd
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
df.to_excel('output.xlsx', index=False)
print("File created successfully")
Recovery Execution:
write_filewith path="generate_spreadsheet.py" and the code above as contentrun_shellwith command="python3 generate_spreadsheet.py"- Verify output.xlsx was created with
list_dir
Tips
- Increase
timeoutfor complex operations (default 30s may be insufficient) - Add explicit print statements for debugging
- Handle exceptions in your script and print error messages
- Clean up temporary script files after successful execution if needed
04 同仓库更多 Skills
agentpilot
Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.
remember
Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.
skill-discovery
Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.
delegate-task
Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.
write-special-chars-ts-check
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.
write-special-chars-readback
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of /tmp helper scripts.