Terminal sandbox persistence across conversation turns

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #6412 fix(terminal): persistent sandbox envs survive between turns

  merged to main

  files: run_agent.py, tools/terminal_tool.py

  Show the diff

  • run_agent.py

    @@ -66,7 +66,7 @@
         handle_function_call,
         check_toolset_requirements,
     )
    -from tools.terminal_tool import cleanup_vm, get_active_env
    +from tools.terminal_tool import cleanup_vm, get_active_env, is_persistent_env
     from tools.tool_result_storage import maybe_persist_tool_result, enforce_turn_budget
     from tools.interrupt import set_interrupt as _set_interrupt
     from tools.browser_tool import cleanup_browser
    @@ -1687,9 +1687,25 @@ def _extract_reasoning(self, assistant_message) -> Optional[str]:
             return None
     
         def _cleanup_task_resources(self, task_id: str) -> None:
    -        """Clean up VM and browser resources for a given task."""
    +        """Clean up VM and browser resources for a given task.
    +
    +        Skips ``cleanup_vm`` when the active terminal environment is marked
    +        persistent (``persistent_filesystem=True``) so that long-lived sandbox
    +        containers survive between turns. The idle reaper in
    +        ``terminal_tool._cleanup_inactive_envs`` still tears them down once
    +        ``terminal.lifetime_seconds`` is exceeded. Non-persistent backends are
    +        torn down per-turn as before to prevent resource leakage (the original
    +        intent of this hook for the Morph backend, see commit fbd3a2fd).
    +        """
             try:
    -            cleanup_vm(task_id)
    +            if is_persistent_env(task_id):
    +                if self.verbose_logging:
    +                    logging.debug(
    +                        f"Skipping per-turn cleanup_vm for persistent env {task_id}; "
    +                        f"idle reaper will handle it."
    +                    )
    +            else:
    +                cleanup_vm(task_id)
             except Exception as e:
                 if self.verbose_logging:
                     logging.warning(f"Failed to cleanup VM for task {task_id}: {e}")

  • tools/terminal_tool.py

    @@ -814,6 +814,23 @@ def get_active_env(task_id: str):
             return _active_environments.get(task_id)
     
     
    +def is_persistent_env(task_id: str) -> bool:
    +    """Return True if the active environment for task_id is configured for
    +    cross-turn persistence (``persistent_filesystem=True``).
    +
    +    Used by the agent loop to skip per-turn teardown for backends whose whole
    +    point is to survive between turns (docker with ``container_persistent``,
    +    daytona, modal, etc.). Non-persistent backends (e.g. Morph) still get torn
    +    down at end-of-turn to prevent leakage. The idle reaper
    +    (``_cleanup_inactive_envs``) handles persistent envs once they exceed
    +    ``terminal.lifetime_seconds``.
    +    """
    +    env = get_active_env(task_id)
    +    if env is None:
    +        return False
    +    return bool(getattr(env, "_persistent", False))
    +
    +
     def get_active_environments_info() -> Dict[str, Any]:
         """Get information about currently active environments."""
         info = {