Spaces:
Sleeping
Sleeping
File size: 4,476 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 | """
Pydantic v2 models for SupportOps Arena environment state.
All models use Pydantic v2 syntax exclusively.
"""
from pydantic import BaseModel, Field, field_validator, model_validator
from enum import Enum
from datetime import datetime
import uuid
from typing import Any
# ─── Enums ───────────────────────────────────────────────────
class NetworkStatus(str, Enum):
"""Network connectivity status."""
HEALTHY = "HEALTHY"
DEGRADED = "DEGRADED"
DOWN = "DOWN"
UNKNOWN = "UNKNOWN"
class VPNStatus(str, Enum):
"""VPN connection status."""
CONNECTED = "CONNECTED"
FAILED = "FAILED"
TIMEOUT = "TIMEOUT"
NA = "N/A"
class AuthStatus(str, Enum):
"""Authentication system status."""
OK = "OK"
LOCKED = "LOCKED"
EXPIRED = "EXPIRED"
MFA_FAIL = "MFA_FAIL"
class ServiceHealth(str, Enum):
"""Service health status."""
HEALTHY = "HEALTHY"
DEGRADED = "DEGRADED"
DOWN = "DOWN"
UNKNOWN = "UNKNOWN"
class TaskLevel(str, Enum):
"""Task difficulty level."""
EASY = "easy"
MEDIUM = "medium"
HARD = "hard"
# ─── Sub-models ──────────────────────────────────────────────
class UserContext(BaseModel):
"""User context information."""
department: str
role: str
device_type: str
os_version: str
location: str # "onsite" | "remote"
model_config = {"frozen": False}
class LogEntry(BaseModel):
"""System log entry."""
timestamp: str
level: str # "INFO" | "WARN" | "ERROR" | "DEBUG"
service: str
message: str
is_misleading: bool = False # Hidden from agent, used by grader
model_config = {"frozen": False}
class ActionRecord(BaseModel):
"""Record of a past action in action_history."""
step: int
action_name: str
rationale: str | None = None
reward_received: float
timestamp: str
model_config = {"frozen": False}
# ─── Core Models ─────────────────────────────────────────────
class EnvObservation(BaseModel):
"""
What the AGENT sees. No hidden info.
This is the observation returned to the agent at each step.
"""
ticket_id: str
ticket_summary: str
user_context: UserContext
network_status: NetworkStatus
vpn_status: VPNStatus
auth_status: AuthStatus
service_health: dict[str, ServiceHealth]
system_logs: list[LogEntry]
action_history: list[ActionRecord]
step_count: int
escalation_allowed: bool
confidence_score: float | None = None # Optional agent field
task_level: TaskLevel
steps_remaining: int
model_config = {"frozen": False}
class HiddenState(BaseModel):
"""
Internal ground truth. NEVER sent to agent.
Only accessible via state() method for graders.
"""
root_cause: str
root_cause_category: str # "network" | "auth" | "dns" | "vpn" | "sso" | "hardware"
correct_remediation: str # Which ActionType resolves this
correct_remediation_alts: list[str] = Field(default_factory=list) # Acceptable alternates
misleading_log_index: int | None = None # Which log entry is the red herring
severity: str # "low" | "medium" | "high" | "critical"
affected_users_count: int # Side-effect blast radius
ticket_variant_id: str # For adversary tracking
model_config = {"frozen": False}
class EnvState(BaseModel):
"""
Full internal state. Graders only.
Contains both observable and hidden state.
"""
episode_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
task_level: TaskLevel
observation: EnvObservation
hidden: HiddenState
cumulative_reward: float = 0.0
done: bool = False
created_at: str = Field(default_factory=lambda: datetime.utcnow().isoformat())
action_log: list[ActionRecord] = Field(default_factory=list)
diagnostic_steps_taken: int = 0 # Tracks unlock threshold
model_config = {"frozen": False}
class StepResult(BaseModel):
"""
Result returned from environment step() method.
Standard RL tuple: (observation, reward, done, info).
"""
observation: EnvObservation
reward: float
done: bool
info: dict[str, Any]
model_config = {"frozen": False}
|