Intermittent "Node {Code node name} run failed: error: operation not permitted" when code block is placed right after input block in workflows

[sigvardt]

Self Checks

• [X] This is only for bug report, if you would like to ask a question, please head to Discussions.
• [X] I have searched for existing issues search for existing issues, including closed ones.
• [X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [X] Please do not modify this template :) and fill in all the required fields.

Dify version

Version 0.6.8

Cloud or Self Hosted

Cloud

Steps to reproduce

For workflows, make the following setup:

1. Make a workflow which has a code execution block right after the input block

Example code which provokes the issue: `def main(text: str) -> dict: """ Escapes unescaped newline characters in the given string.

Args:
text (str): The input string containing potential unescaped newline characters.

Returns:
dict: A dictionary containing the key 'result' with the value being the new string with all unescaped newline characters escaped.
"""
escaped_text = []
i = 0
while i < len(text):
    if text[i] == '\\' and i + 1 < len(text) and text[i + 1] == 'n':
        # This is already an escaped newline
        escaped_text.append('\\n')
        i += 2
    elif text[i] == '\n':
        # This is an unescaped newline
        escaped_text.append('\\n')
        i += 1
    else:
        escaped_text.append(text[i])
        i += 1

return {
    'result': ''.join(escaped_text)
}

`

Seems to be a timing issue. If you move the block down in the line of the workflow, then the issue never happens.

✔️ Expected Behavior

• Code execution node intermittently fails, but completes always upon retry

❌ Actual Behavior

• Consistent success or failure

[dosubot[bot]]

The error "Node {Code node name} run failed: error: operation not permitted" in Dify version 0.6.8 (Cloud) is likely due to the sandboxed execution environment that restricts certain functionalities for security reasons. Here are some steps to diagnose and resolve the issue:

1. Review Code for Restricted Operations: Ensure your code does not attempt to perform any restricted operations like direct file system access, network calls, or operating system-level commands.

2. Check Input and Output Variable Handling: Verify that input and output variables are correctly defined and referenced in your code node configuration.

3. Consider Timing and Dependency Issues: Since the issue occurs when the code block is placed immediately after the input block, there might be a dependency or initialization issue. Ensure the input block has completed its execution and the data is available before the code block starts.

4. Use Debugging and Logging Tools: Utilize Dify's debugging and logging tools to gather more information about the error. Fetch workflow logs, run details, and node tracing lists to diagnose the issue.

5. Implement Workflow Event Callbacks: Implement the WorkflowEventTriggerCallback class to handle various workflow events such as workflow run started, succeeded, or failed, and node execution started, succeeded, or failed. This can help in publishing detailed events to a queue manager for further analysis.

6. View Logs and Traces in the UI: Use the Dify UI to view detailed logs and traces. By clicking "View Log—Details," you can see a comprehensive overview of the run, including input/output, metadata, and more. By clicking "View Log—Trace," you can review the input/output, token consumption, runtime duration, etc., of each node throughout the complete execution process of the workflow.

By following these steps, you should be able to diagnose and resolve the "operation not permitted" error in your Dify workflow. If the issue persists, consider providing more detailed logs or specific scenarios where the error occurs for further analysis.

Details

Sources

• en/features/workflow/nodes/code.md
• en/features/workflow/node/code.md
• api/core/workflow/nodes/code/code_node.py
• api/core/tools/provider/builtin/code/tools/simple_code.yaml
• api/core/tools/provider/builtin/judge0ce/tools/executeCode.py
• web/service/log.ts
• api/core/app/apps/workflow/workflow_event_trigger_callback.py
• zh_CN/guides/workflow/debug_and_preview/log.md
• en/features/workflow/preview-and-run/log.md

About Dosu This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[115341chenzehao]

The error "Node {Code node name} run failed: error: operation not permitted" in Dify version 0.6.8 (Cloud) is likely due to the sandboxed execution environment that restricts certain functionalities for security reasons. Here are some steps to diagnose and resolve the issue:

1. Review Code for Restricted Operations: Ensure your code does not attempt to perform any restricted operations like direct file system access, network calls, or operating system-level commands.
2. Check Input and Output Variable Handling: Verify that input and output variables are correctly defined and referenced in your code node configuration.
3. Consider Timing and Dependency Issues: Since the issue occurs when the code block is placed immediately after the input block, there might be a dependency or initialization issue. Ensure the input block has completed its execution and the data is available before the code block starts.
4. Use Debugging and Logging Tools: Utilize Dify's debugging and logging tools to gather more information about the error. Fetch workflow logs, run details, and node tracing lists to diagnose the issue.
5. Implement Workflow Event Callbacks: Implement the WorkflowEventTriggerCallback class to handle various workflow events such as workflow run started, succeeded, or failed, and node execution started, succeeded, or failed. This can help in publishing detailed events to a queue manager for further analysis.
6. View Logs and Traces in the UI: Use the Dify UI to view detailed logs and traces. By clicking "View Log—Details," you can see a comprehensive overview of the run, including input/output, metadata, and more. By clicking "View Log—Trace," you can review the input/output, token consumption, runtime duration, etc., of each node throughout the complete execution process of the workflow.

By following these steps, you should be able to diagnose and resolve the "operation not permitted" error in your Dify workflow. If the issue persists, consider providing more detailed logs or specific scenarios where the error occurs for further analysis.

Details

To continue the conversation, mention @dosu.

If I hope to execute a script to access the database of another server, does Dify's design allow this operation?

[junonya]

@sigvardt It looks like you don't have enough permissions on the Dify server. Try changing the Dify server permissions using the chomod command.

[sigvardt]

@sigvardt It looks like you don't have enough permissions on the Dify server. Try changing the Dify server permissions using the chomod command.

@junonya I am on the managed cloud version of dify.ai and do as such not have access to server settings.

[crazywoola]

See this https://github.com/langgenius/dify/issues/4993 for updates