AGENT SKILL

execute-code-fallback

Fallback from execute_code_sandbox to run_shell when e2b sandbox is unavailable

适用职业开发工程师
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
execute-code-fallback
description
Fallback from execute_code_sandbox to run_shell when e2b sandbox is unavailable

02 资源文件 1

03 SKILL.md 正文

Execute Code Fallback Pattern

When execute_code_sandbox fails due to e2b unavailability, immediately fall back to run_shell with embedded Python code. This ensures task continuity when the sandbox service is down.

When to Apply

Use this pattern when you observe:

  • execute_code_sandbox returns errors mentioning "e2b", "sandbox unavailable", or connection timeouts
  • Repeated sandbox execution failures (2+ attempts)
  • Error messages indicating the code execution environment is unreachable

Fallback Procedure

Step 1: Detect the Failure

Identify that execute_code_sandbox has failed. Common error indicators:

  • "e2b service unavailable"
  • "Sandbox connection failed"
  • "Execution environment not reachable"
  • Timeout errors during code execution

Step 2: Switch to run_shell with Embedded Python

Instead of:

execute_code_sandbox(code="...")

Use:

run_shell(command="python3 -c '...your Python code...'")

Step 3: Install Dependencies First (If Needed)

If your Python code requires external packages, install them first:

run_shell(command="pip install pandas requests matplotlib")

Then execute your main code:

run_shell(command="python3 << 'EOF'
import pandas as pd
import requests

# Your code here
print("Success")
EOF
")

Step 4: Use Heredoc for Multi-line Code

For complex Python scripts, use heredoc syntax for cleaner code:

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

# Complex logic here
data = {'key': 'value'}
with open('output.json', 'w') as f:
    json.dump(data, f)

print('File created successfully')
PYTHON_SCRIPT
")

Complete Example

Scenario: You need to process a CSV file and generate a report.

Original approach (sandbox):

execute_code_sandbox(code="""
import pandas as pd
df = pd.read_csv('data.csv')
summary = df.describe()
print(summary)
""")

Fallback approach (run_shell):

# First install dependencies if needed
run_shell(command="pip install pandas --quiet")

# Then execute the code
run_shell(command="python3 << 'EOF'
import pandas as pd
df = pd.read_csv('data.csv')
summary = df.describe()
print(summary)
EOF
")

Important Considerations

  1. State Persistence: Unlike execute_code_sandbox, run_shell executions may not share state between calls. Save intermediate results to files if needed.

  2. Working Directory: Ensure you're operating in the correct directory. Use pwd to verify or include cd /path/to/workdir in your commands.

  3. Python Version: Use python3 explicitly to avoid ambiguity. Verify with python3 --version if needed.

  4. Error Handling: Check the stdout/stderr from run_shell to confirm success. Failed Python scripts will return non-zero exit codes.

  5. Security: Be cautious when embedding user-provided data into shell commands. Escape appropriately or use file-based input.

  6. Performance: For large computations, run_shell may be slower than sandbox. Consider breaking into smaller steps if timeouts occur.

Quick Reference

Task Sandbox Approach Fallback Approach
Simple calculation execute_code_sandbox(code="print(2+2)") run_shell(command="python3 -c 'print(2+2)'")
Install + run execute_code_sandbox(code="import pkg; ...") run_shell(command="pip install pkg && python3 -c '...'")
Multi-line script execute_code_sandbox(code="...") run_shell(command="python3 << 'EOF'...EOF")
File I/O execute_code_sandbox(code="...") run_shell(command="python3 << 'EOF'...EOF")

Recovery Checklist

  • [ ] Confirm execute_code_sandbox failure (not a code bug)
  • [ ] Switch to run_shell immediately
  • [ ] Install required packages with pip install
  • [ ] Use heredoc for multi-line Python
  • [ ] Verify output and handle errors
  • [ ] Save intermediate results to files if multi-step

04 同仓库更多 Skills

HKUDS
HKUDS/AgentPilot

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.

★ 8.0k
HKUDS
HKUDS/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.

★ 8.0k
HKUDS
HKUDS/AgentPilot

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.

Skill与智能体开发
★ 8.0k
HKUDS
HKUDS/AgentPilot

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.

Skill与智能体开发
★ 8.0k
HKUDS
HKUDS/AgentPilot

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.

★ 8.0k
HKUDS
HKUDS/AgentPilot

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.

★ 8.0k