infiniflow/ragflow · error · RuntimeError

Unexpected error during execution: {str(e)}

Error message

Unexpected error during execution: {str(e)}

What it means

Catch-all for any non-ServerError exception during Aliyun code execution — covers SDK client-side failures (serialization of arguments, enum mismatch), local parsing of the structured result, and network errors that do not surface as ServerError. The original exception text is embedded.

Source

Thrown at agent/sandbox/providers/aliyun_codeinterpreter.py:311

                exit_code=exit_code,
                execution_time=execution_time,
                metadata={
                    "instance_id": instance_id,
                    "language": normalized_lang,
                    "context_id": result.get("contextId") if isinstance(result, dict) else None,
                    "timeout": timeout,
                    "result_present": structured_result.get("present", False),
                    "result_value": structured_result.get("value"),
                    "result_type": structured_result.get("type"),
                },
            )

        except ServerError as e:
            if "timeout" in str(e).lower():
                raise TimeoutError(f"Execution timed out after {timeout} seconds")
            raise RuntimeError(f"Failed to execute code: {str(e)}")
        except Exception as e:
            raise RuntimeError(f"Unexpected error during execution: {str(e)}")

    def destroy_instance(self, instance_id: str) -> bool:
        """
        Destroy an Aliyun Code Interpreter instance.

        Args:
            instance_id: ID of the instance to destroy

        Returns:
            True if destruction successful, False otherwise
        """
        if not self._initialized or not self._config:
            raise RuntimeError("Provider not initialized. Call initialize() first.")

        try:
            # Delete sandbox by ID directly
            Sandbox.delete_by_id(sandbox_id=instance_id)

View on GitHub (pinned to 554fb1133a)

Solutions

1. Read str(e) to classify: connection errors mean the instance is gone — recreate it; parse errors mean SDK/result-shape drift.
2. Ensure `arguments` contains only JSON-serializable values.
3. Pin the agentrun-sdk version tested with this provider.
4. Verify the instance still exists (or just recreate) before retrying execution.

try:
    result = provider.execute_code(instance_id, code, "python", timeout=10)
except RuntimeError as e:
    msg = str(e).lower()
    if "not exist" in msg or "connect" in msg:
        instance = provider.create_instance("python")  # dead sandbox: recreate and retry
        result = provider.execute_code(instance.instance_id, code, "python", timeout=10)
    else:
        raise

When it happens

Trigger: execute_code when: the arguments dict cannot be serialized into the runner format, the agentrun-sdk version changed result shapes and the structured-result parsing breaks, Sandbox.connect to a dead instance raises, or the response JSON is not a dict as expected.

Common situations: instance_id points to an already-destroyed sandbox; SDK version drift (the file notes CodeLanguage enum changes around 0.0.26); non-JSON-serializable values inside arguments; transient connectivity loss mid-request.

Related errors

• Unexpected error creating instance: {str(e)}
• Provider not initialized. Call initialize() first.
• Failed to create sandbox instance: {str(e)}
• Failed to initialize sandbox provider: {provider_type}. Conf
• Execution timed out after {timeout} seconds

AI-assisted analysis of infiniflow/ragflow@554fb1133a (2026-08-15). Data as JSON: /api/errors/730a8e3350a9e427. Report an issue: GitHub.