FoundationAgents/OpenManus · error · RuntimeError

Failed to create sandbox: {e}

Error message

Failed to create sandbox: {e}

What it means

Raised by DockerSandbox.create (app/sandbox/core/sandbox.py:103) when any step of sandbox bring-up throws: container creation, volume binding preparation, or AsyncDockerizedTerminal init. On failure it awaits self.cleanup() to release the half-created container, then raises RuntimeError chained (`from e`) to the original exception. This is the inner exception that manager.create_sandbox wraps into error 23.

Source

Thrown at app/sandbox/core/sandbox.py:103

            self.container = self.client.containers.get(container["Id"])

            # Start container
            await asyncio.to_thread(self.container.start)

            # Initialize terminal
            self.terminal = AsyncDockerizedTerminal(
                container["Id"],
                self.config.work_dir,
                env_vars={"PYTHONUNBUFFERED": "1"}
                # Ensure Python output is not buffered
            )
            await self.terminal.init()

            return self

        except Exception as e:
            await self.cleanup()  # Ensure resources are cleaned up
            raise RuntimeError(f"Failed to create sandbox: {e}") from e

    def _prepare_volume_bindings(self) -> Dict[str, Dict[str, str]]:
        """Prepares volume binding configuration.

        Returns:
            Volume binding configuration dictionary.
        """
        bindings = {}

        # Create and add working directory mapping
        work_dir = self._ensure_host_dir(self.config.work_dir)
        bindings[work_dir] = {"bind": self.config.work_dir, "mode": "rw"}

        # Add custom volume bindings
        for host_path, container_path in self.volume_bindings.items():
            bindings[host_path] = {"bind": container_path, "mode": "rw"}

        return bindings

View on GitHub (pinned to 52a13f2a57)

Solutions

1. Look at __cause__ of this RuntimeError — it is the original docker/terminal error.
2. Test the same container manually: docker run -v <workdir>:<workdir> <image> sh.
3. Ensure the host work_dir exists and is writable; ensure the image has a shell.
4. Match docker library API version to the daemon (DowngradeAPI/upgrade issues).

try:
    sandbox = await DockerSandbox(config).create()
except RuntimeError as e:
    cause = e.__cause__  # original docker / terminal error
    log.error("create failed: %r", cause)
    raise

When it happens

Trigger: Container start fails due to invalid config (bad image, conflicting volume binds, unsupported options); container['Id'] fetch succeeds but exec session for the terminal fails; cleanup path itself errors; work_dir host dir cannot be created (permissions).

Common situations: Non-writable host path for the work_dir volume; image lacks /bin/sh so exec fails; Docker API version mismatch between client library and daemon; SELinux/AppArmor denying the bind mount.

Related errors

• Session not initialized
• Terminal not initialized
• Maximum number of sandboxes ({self.max_sandboxes}) reached
• Failed to create sandbox: {e}
• Sandbox not initialized

AI-assisted analysis of FoundationAgents/OpenManus@52a13f2a57 (2026-08-15). Data as JSON: /api/errors/3a96f30e6d4cd0ea. Report an issue: GitHub.