Merged PR 255: Fix issue where red agent acted too early

## Fixed:
- data manipulation red agent now considers episode reset when calculating next action time
- Moved attack logic out of data manipulation bot `run` method into dedicated `attack` method, because `run` is triggered by episode reset logic. This means the attack no longer always happens at step 1 of every episode.

## Test process
*How have you tested this (if applicable)?*

## Checklist
- [x] PR is linked to a **work item**
- [x] **acceptance criteria** of linked ticket are met
- [x] performed **self-review** of the code
- [ ] written **tests** for any new functionality added with this PR
- [na] updated the **documentation** if this PR changes or adds functionality
- [na] written/updated **design docs** if this PR implements new functionality
- [x] updated the **change log**
- [x] ran **pre-commit** checks for code style
- [x] attended to any **TO-DOs** left in the code

Related work items: #2173

CHANGELOG.md

@@ -8,7 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 - Made packet capture and system logging optional (off by default). To turn on, change the io_settings.save_pcap_logs and io_settings.save_sys_logs settings in the config.
 - Made observation space flattening optional (on by default). To turn off for an agent, change the agent_settings.flatten_obs setting in the config.
-
+- Fixed an issue where the data manipulation attack was triggered at episode start.
 
 ### Added
 - Network Hardware - Added base hardware module with NIC, SwitchPort, Node, and Link. Nodes have

src/primaite/game/agent/data_manipulation_bot.py

@@ -15,7 +15,6 @@ class DataManipulationAgent(AbstractScriptedAgent):
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
-
         self._set_next_execution_timestep(self.agent_settings.start_settings.start_step)
 
     def _set_next_execution_timestep(self, timestep: int) -> None:
@@ -46,3 +45,8 @@ class DataManipulationAgent(AbstractScriptedAgent):
         self._set_next_execution_timestep(current_timestep + self.agent_settings.start_settings.frequency)
 
         return "NODE_APPLICATION_EXECUTE", {"node_id": 0, "application_id": 0}
+
+    def reset_agent_for_episode(self) -> None:
+        """Set the next execution timestep when the episode resets."""
+        super().reset_agent_for_episode()
+        self._set_next_execution_timestep(self.agent_settings.start_settings.start_step)

src/primaite/game/agent/interface.py

@@ -135,6 +135,10 @@ class AbstractAgent(ABC):
         request = self.action_manager.form_request(action_identifier=action, action_options=options)
         return request
 
+    def reset_agent_for_episode(self) -> None:
+        """Agent reset logic should go here."""
+        pass
+
 
 class AbstractScriptedAgent(AbstractAgent):
     """Base class for actors which generate their own behaviour."""

src/primaite/game/agent/rewards.py

@@ -181,7 +181,6 @@ class WebServer404Penalty(AbstractReward):
         """
         web_service_state = access_from_nested_dict(state, self.location_in_state)
         if web_service_state is NOT_PRESENT_IN_STATE:
-            print("error getting web service state")
             return 0.0
         most_recent_return_code = web_service_state["last_response_status_code"]
         # TODO: reward needs to use the current web state. Observation should return web state at the time of last scan.

src/primaite/game/game.py

@@ -162,6 +162,7 @@ class PrimaiteGame:
         self.simulation.reset_component_for_episode(episode=self.episode_counter)
         for agent in self.agents:
             agent.reward_function.total_reward = 0.0
+            agent.reset_agent_for_episode()
 
     def close(self) -> None:
         """Close the game, this will close the simulation."""

src/primaite/simulator/system/services/red_services/data_manipulation_bot.py

@@ -73,7 +73,7 @@ class DataManipulationBot(DatabaseClient):
     def _init_request_manager(self) -> RequestManager:
         rm = super()._init_request_manager()
 
-        rm.add_request(name="execute", request_type=RequestType(func=lambda request, context: self.run()))
+        rm.add_request(name="execute", request_type=RequestType(func=lambda request, context: self.attack()))
 
         return rm
 
@@ -169,6 +169,12 @@ class DataManipulationBot(DatabaseClient):
         Calls the parent classes execute method before starting the application loop.
         """
         super().run()
+
+    def attack(self):
+        """Perform the attack steps after opening the application."""
+        if not self._can_perform_action():
+            _LOGGER.debug("Data manipulation application attempted to execute but it cannot perform actions right now.")
+            self.run()
         self._application_loop()
 
     def _application_loop(self):
@@ -199,4 +205,4 @@ class DataManipulationBot(DatabaseClient):
 
         :param timestep: The timestep value to update the bot's state.
         """
-        self._application_loop()
+        pass

src/primaite/simulator/system/software.py

@@ -278,7 +278,7 @@ class IOSoftware(Software):
 
         Returns true if the software can perform actions.
         """
-        if self.software_manager and self.software_manager.node.operating_state is NodeOperatingState.OFF:
+        if self.software_manager and self.software_manager.node.operating_state is not NodeOperatingState.ON:
             _LOGGER.debug(f"{self.name} Error: {self.software_manager.node.hostname} is not online.")
             return False
         return True