"""
Action model — compact menu for simultaneous-move tree search.

Bad: enumerate every price tick x every quantity x every TTL x every TIF.
Good: 8-24 meaningful actions per player, 3-12 per counterparty role.
"""
from __future__ import annotations

from dataclasses import dataclass, field
from typing import Any, Mapping, Optional, Tuple

from malkhut.state import ActionKind, AgentRole, OrderType, Side


@dataclass(frozen=True, slots=True)
class FulfilmentAction:
    """One atomic action candidate."""
    kind: ActionKind
    side: Optional[Side]
    order_type: Optional[OrderType]
    price_ticks_from_best: int
    qty_fraction: float
    ttl_ms: int
    cancel_order_id: Optional[str] = None
    reduce_only: bool = False
    post_only: bool = False
    metadata: Mapping[str, Any] = field(default_factory=dict)


@dataclass(frozen=True, slots=True)
class CounterpartyAction:
    """Adversarially useful aggregate actions that alter book/fill outcomes."""
    role: AgentRole
    kind: ActionKind
    side: Optional[Side]
    price_ticks_from_best: int
    qty_fraction_of_top: float
    toxicity: float = 0.0
    metadata: Mapping[str, Any] = field(default_factory=dict)


JointAction = Tuple[Any, ...]  # (our_action, cp_action_1, cp_action_2, ...)


@dataclass(frozen=True, slots=True)
class PlannedPolicy:
    """Output of the planner: distribution over actions + selected action."""
    actions: Tuple[FulfilmentAction, ...]
    probabilities: Tuple[float, ...]
    selected_action: FulfilmentAction
    diagnostics: Mapping[str, Any]


@dataclass(frozen=True, slots=True)
class RiskDecision:
    approved: bool
    action: Optional[FulfilmentAction]
    reason: str
    adjusted: bool = False