FoundationAgents/OpenManus · warning · SandboxTimeoutError

Command execution timed out after {timeout or self.config.ti

Error message

Command execution timed out after {timeout or self.config.timeout} seconds

What it means

Raised as SandboxTimeoutError (app/sandbox/core/exceptions.py:12) by DockerSandbox.run_command (app/sandbox/core/sandbox.py:162) when AsyncDockerizedTerminal.run_command raises TimeoutError: the command did not finish within `timeout or self.config.timeout` seconds. The configured/per-call timeout is echoed in the message. The exec may still be running in the container — the timeout only abandons waiting.

Source

Thrown at app/sandbox/core/sandbox.py:162

            cmd: Command to execute.
            timeout: Timeout in seconds.

        Returns:
            Command output as string.

        Raises:
            RuntimeError: If sandbox not initialized or command execution fails.
            TimeoutError: If command execution times out.
        """
        if not self.terminal:
            raise RuntimeError("Sandbox not initialized")

        try:
            return await self.terminal.run_command(
                cmd, timeout=timeout or self.config.timeout
            )
        except TimeoutError:
            raise SandboxTimeoutError(
                f"Command execution timed out after {timeout or self.config.timeout} seconds"
            )

    async def read_file(self, path: str) -> str:
        """Reads a file from the container.

        Args:
            path: File path.

        Returns:
            File contents as string.

        Raises:
            FileNotFoundError: If file does not exist.
            RuntimeError: If read operation fails.
        """
        if not self.container:
            raise RuntimeError("Sandbox not initialized")

View on GitHub (pinned to 52a13f2a57)

Solutions

Pass a larger per-call timeout: await sandbox.run_command(cmd, timeout=600).
Raise the default in SandboxSettings (config.timeout) for known-slow operations.
For interactive or very long jobs, run in background (nohup ... &) and poll for the output file instead of blocking run_command.
Make sure the command is non-interactive: close stdin, pass -y/--yes flags, redirect stdin from /dev/null.

Example fix

# before
out = await sandbox.run_command("pip install -r requirements.txt")

# after
out = await sandbox.run_command("pip install -r requirements.txt", timeout=600)

Defensive patterns

Strategy: try-catch

Try / catch

from app.sandbox.core.exceptions import SandboxTimeoutError
try:
    out = await sandbox.run_command(cmd, timeout=120)
except SandboxTimeoutError:
    out = await sandbox.run_command(cmd + " < /dev/null", timeout=600)  # non-interactive, longer budget

Prevention

Pass explicit timeouts sized to the command (installs/builds need minutes)
Close stdin or redirect from /dev/null for non-interactive commands
Run very long jobs detached and poll for completion
Raise config.timeout default if most commands exceed it

When it happens

Trigger: Long-running commands (pip install, builds, test suites) exceeding the default config.timeout; commands that block on stdin because they were never given input; hung network calls inside the container; per-call timeout argument smaller than the command needs.

Common situations: Default sandbox timeout (often 30–60s) too low for package installs; `python` invoked without -c/-i flags waiting on stdin; container has no network so apt/pip hang until timeout; CI cold cache making first runs slow.

Understand the failure class

Timeouts: ETIMEDOUT, deadlines, and hung requests — what actually expires when a request times out.

Related errors

AI-assisted analysis of FoundationAgents/OpenManus@52a13f2a57 (2026-08-15). Data as JSON: /api/errors/dcdce5cc32727fda. Report an issue: GitHub.