Spaces:
Sleeping
Sleeping
File size: 8,995 Bytes
9c1645f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 | """
Baseline heuristic agent for SupportOps Arena.
Rule-based agent using decision tree logic (no ML required).
"""
import logging
from typing import Any
from env.state import EnvObservation, NetworkStatus, VPNStatus, AuthStatus, ServiceHealth
from env.actions import ActionType
from env.environment import SupportOpsArena
logger = logging.getLogger(__name__)
class BaselineAgent:
"""
Scripted heuristic baseline agent.
Uses a simple decision tree strategy:
1. Gather initial evidence (logs + auth)
2. Apply rule-based diagnostics based on observations
3. Choose lowest-risk remediation
4. Escalate if uncertain after gathering evidence
Expected performance:
- Easy: 0.65-0.75
- Medium: 0.40-0.55
- Hard: 0.20-0.35
"""
def __init__(self, seed: int | None = None):
"""
Initialize baseline agent.
Args:
seed: Random seed for reproducibility (currently unused as agent is deterministic)
"""
self.seed = seed
self._action_history: list[str] = []
async def select_action(self, observation: EnvObservation) -> ActionType:
"""
Select next action based on current observation.
Args:
observation: Current environment observation
Returns:
ActionType to take
"""
step = observation.step_count
max_steps = observation.steps_remaining + step
# Phase 1: Initial diagnostic (steps 1-2)
if step == 0:
return ActionType.INSPECT_LOGS
if step == 1:
return ActionType.CHECK_AUTHENTICATION
# Phase 2: Targeted diagnostics (steps 2-4)
if step < 4:
# Check auth status
if observation.auth_status in [
AuthStatus.LOCKED,
AuthStatus.EXPIRED,
AuthStatus.MFA_FAIL
]:
if "check_permissions" not in self._action_history:
self._action_history.append("check_permissions")
return ActionType.CHECK_PERMISSIONS
# Check network status
if observation.network_status in [NetworkStatus.DEGRADED, NetworkStatus.DOWN]:
if "inspect_network" not in self._action_history:
self._action_history.append("inspect_network")
return ActionType.INSPECT_NETWORK
# Check VPN status
if observation.vpn_status in [VPNStatus.FAILED, VPNStatus.TIMEOUT]:
if "query_device_status" not in self._action_history:
self._action_history.append("query_device_status")
return ActionType.QUERY_DEVICE_STATUS
# Check for service issues
has_service_issues = any(
status in [ServiceHealth.DEGRADED, ServiceHealth.DOWN]
for status in observation.service_health.values()
)
if has_service_issues:
if "run_diagnostic_script" not in self._action_history:
self._action_history.append("run_diagnostic_script")
return ActionType.RUN_DIAGNOSTIC
# Default: query device
if "query_device_status" not in self._action_history:
self._action_history.append("query_device_status")
return ActionType.QUERY_DEVICE_STATUS
# Phase 3: Apply remediation (steps 4+)
# Determine remediation based on observations
remediation = self._determine_remediation(observation)
if remediation:
if remediation.value not in self._action_history:
self._action_history.append(remediation.value)
return remediation
# Phase 4: Resolve or escalate
# Check if we have enough evidence
diagnostic_count = len(self._action_history)
evidence_threshold = max_steps * 0.6
# If we've gathered enough evidence and applied a fix, resolve
if diagnostic_count >= 4 and len(self._action_history) >= 5:
# Check if escalation is available and we're uncertain
if observation.escalation_allowed and diagnostic_count < evidence_threshold * 0.8:
self._action_history.append("escalate_ticket")
return ActionType.ESCALATE_TICKET
# Otherwise resolve
self._action_history.append("resolve_ticket")
return ActionType.RESOLVE_TICKET
# Need more diagnostics or stuck - escalate if possible
if observation.escalation_allowed and diagnostic_count >= evidence_threshold:
self._action_history.append("escalate_ticket")
return ActionType.ESCALATE_TICKET
# Gather more evidence
if "search_internal_kb" not in self._action_history:
self._action_history.append("search_internal_kb")
return ActionType.SEARCH_INTERNAL_KB
# Last resort: resolve
self._action_history.append("resolve_ticket")
return ActionType.RESOLVE_TICKET
def _determine_remediation(self, observation: EnvObservation) -> ActionType | None:
"""
Determine appropriate remediation based on observations.
Returns:
Remediation action or None if more diagnostics needed
"""
# Auth issues → reset credentials
if observation.auth_status in [
AuthStatus.LOCKED,
AuthStatus.EXPIRED,
AuthStatus.MFA_FAIL
]:
if observation.diagnostic_steps_taken >= 2:
return ActionType.RESET_CREDENTIALS
# Network/DNS issues → flush DNS or reconfigure
if observation.network_status in [NetworkStatus.DEGRADED, NetworkStatus.DOWN]:
if observation.diagnostic_steps_taken >= 2:
# Check if it's likely DNS
dns_indicators = sum(
1 for log in observation.system_logs
if "dns" in log.message.lower()
)
if dns_indicators > 0:
return ActionType.FLUSH_DNS
else:
return ActionType.RECONFIGURE_CLIENT
# VPN issues → reconfigure client
if observation.vpn_status in [VPNStatus.FAILED, VPNStatus.TIMEOUT]:
if observation.diagnostic_steps_taken >= 2:
return ActionType.RECONFIGURE_CLIENT
# Service issues → restart service (high risk, so be cautious)
has_critical_service_down = any(
status == ServiceHealth.DOWN
for status in observation.service_health.values()
)
if has_critical_service_down:
if observation.diagnostic_steps_taken >= 3:
return ActionType.RESTART_SERVICE
# No clear remediation yet
return None
async def run_episode(
self,
env: SupportOpsArena,
task_level: str = "easy"
) -> dict[str, Any]:
"""
Run one complete episode.
Args:
env: Environment instance
task_level: Difficulty level
Returns:
Dictionary with episode results
"""
# Reset tracking
self._action_history = []
# Reset environment
observation = await env.reset(task_level=task_level, seed=self.seed)
total_reward = 0.0
done = False
steps = 0
logger.info(f"Starting baseline agent episode on {task_level}")
# Run episode
while not done and steps < 50: # Safety limit
# Select action
action = await self.select_action(observation)
# Take step
result = await env.step(action)
observation = result.observation
total_reward += result.reward
done = result.done
steps += 1
logger.debug(
f"Step {steps}: {action.value} -> reward={result.reward:.2f}, "
f"done={done}"
)
# Get final state
final_state = await env.state()
logger.info(
f"Episode completed: steps={steps}, "
f"reward={total_reward:.2f}, "
f"score={final_state.cumulative_reward:.2f}"
)
return {
"steps": steps,
"total_reward": total_reward,
"cumulative_reward": final_state.cumulative_reward,
"done": done,
"task_level": task_level,
}
def reset(self) -> None:
"""Reset agent state for new episode."""
self._action_history = []
|