verify-success-after-unknown-error
Verify task completion by checking filesystem state when execute_code_sandbox or run_shell return misleading unknown errors
- 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
- verify-success-after-unknown-error
- description
- Verify task completion by checking filesystem state when execute_code_sandbox or run_shell return misleading unknown errors
02 资源文件 1
- 其他.skill_id48 B
03 SKILL.md 正文
Verify Success After Unknown Error
Purpose
When execute_code_sandbox or run_shell return "unknown error" messages, the underlying task may have actually succeeded. This skill provides a systematic approach to verify actual completion before assuming failure and retrying unnecessarily.
When to Apply
Use this pattern when:
execute_code_sandboxreturns "unknown error" but your code may have completedrun_shellfails with unclear error messages- File creation, modification, or transformation tasks report errors
- The error message is generic/unspecified rather than a clear failure reason
Verification Steps
Step 1: Check Expected Output Files
After receiving an unknown error, immediately verify if expected files were created:
# Example: Verify file creation after execute_code_sandbox
from tools import list_dir, read_file
# List directory to check if files exist
files = list_dir(path="/workspace/output")
print(files)
# Check specific file existence
expected_files = ["report.pdf", "data.xlsx"]
for f in expected_files:
try:
content = read_file(filetype="pdf", file_path=f"/workspace/output/{f}")
print(f"✓ {f} exists and is readable")
except:
print(f"✗ {f} not found or unreadable")
Step 2: Validate File Content/State
Don't just check existence — verify the files have expected content:
# For spreadsheets
file_content = read_file(filetype="xlsx", file_path="/workspace/output/schedule.xlsx")
# Verify expected sheets, columns, or data exist
# For text/json files
file_content = read_file(filetype="txt", file_path="/workspace/output/result.json")
# Parse and validate structure
# For directories
dir_contents = list_dir(path="/workspace/output")
# Verify expected number of files or specific files exist
Step 3: Decision Logic
IF expected files exist AND content is valid:
→ Task succeeded despite error message
→ Proceed to next step without retry
ELIF files exist but content is incomplete:
→ Partial success, may need targeted fix
ELSE (files missing or corrupted):
→ True failure, retry or debug required
Code Example: Complete Pattern
def execute_with_verification(code, expected_files):
"""Execute code and verify success even if error returned."""
# Attempt execution
result = execute_code_sandbox(code=code)
# Check for unknown/generic errors
if "unknown error" in result.get("output", "").lower() or result.get("error"):
print("Received error, verifying actual outcome...")
# Verify filesystem state
all_present = True
for f in expected_files:
try:
list_dir(path=f"/workspace/{f}") # or appropriate path
print(f"✓ {f} verified")
except:
print(f"✗ {f} missing")
all_present = False
if all_present:
print("Task completed successfully despite error message")
return {"status": "success_verified", "files": expected_files}
else:
print("True failure - files not created")
return {"status": "failed", "error": result.get("error")}
return {"status": "success", "output": result.get("output")}
Shell Command Example
# After run_shell returns error, verify with:
ls -la /workspace/output/
test -f /workspace/output/result.pdf && echo "File exists" || echo "File missing"
file /workspace/output/result.pdf # Verify file type is correct
Benefits
- Saves iterations: Avoids unnecessary retries when task already succeeded
- Handles tool bugs: Works around sandbox/shell tool reporting issues
- Faster completion: Move forward immediately when verification passes
- Clearer debugging: Distinguishes true failures from false positives
Anti-Patterns to Avoid
- ✗ Immediately retrying on any error without verification
- ✗ Assuming "unknown error" means complete failure
- ✗ Only checking file existence without validating content
- ✗ Skipping verification for "minor" tasks (any file output should be verified)
Related Tools
list_dir— Check directory contentsread_file— Validate file content and accessibilityexecute_code_sandbox— Primary execution tool this pattern supportsrun_shell— Shell execution tool this pattern supports
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.