sentiment-engine/MALKHUT/malkhut/planner/action_menu.py

"""
Action menu builder — reduces impossible action space to compact meaningful set.

Menu size target:
    our actions: 8-24
    each counterparty role: 3-12
    depth: 2-4
"""
from __future__ import annotations

from typing import List, Optional, Tuple

from malkhut.state import (
    ActionKind,
    FulfilmentPolicyParams,
    IntentKind,
    MarketWorldState,
    OpenOrderState,
    OrderType,
    Side,
    TradePathState,
)
from malkhut.actions import FulfilmentAction


CHASE_MIN_OFFSET = 0  # minimum offset ticks for chase
CHASE_MAX_OFFSET = 5  # maximum offset ticks for chase


def _side_for_intent(intent_kind: IntentKind) -> Side:
    if intent_kind in (IntentKind.ENTER_LONG, IntentKind.ADD_LONG, IntentKind.REDUCE_SHORT, IntentKind.EXIT_SHORT):
        return Side.BUY
    return Side.SELL


def _exit_side_for_position(state: MarketWorldState) -> Optional[Side]:
    path = state.trade_path
    if path is None:
        return None
    return Side.SELL if path.side == Side.BUY else Side.BUY


def _path_risk_says_exit(state: MarketWorldState, params: FulfilmentPolicyParams) -> bool:
    path = state.trade_path
    if path is None:
        return False

    if abs(path.mae_bps) >= params.mae_tail_cut_bps:
        if path.recovery_velocity_bps_per_s < params.recovery_velocity_min_bps_per_s:
            return True

    if path.time_in_loss_s > params.max_time_in_loss_s:
        return True

    if path.failed_recovery_count >= params.failed_recovery_cut_count:
        return True

    if path.mfe_bps > 0:
        giveback = path.distance_from_mfe_bps / max(path.mfe_bps, 1e-12)
        if giveback >= params.mfe_giveback_cut_fraction:
            return True

    return False


def build_our_actions(
    state: MarketWorldState,
    params: FulfilmentPolicyParams,
) -> Tuple[FulfilmentAction, ...]:
    intent = state.intent
    if intent is None:
        return (FulfilmentAction(ActionKind.NOOP, None, None, 0, 0.0, 0),)

    side = _side_for_intent(intent)
    actions: List[FulfilmentAction] = []

    # Always allow no-op
    actions.append(FulfilmentAction(
        kind=ActionKind.NOOP, side=None, order_type=None,
        price_ticks_from_best=0, qty_fraction=0.0, ttl_ms=100,
    ))

    # Existing order management
    for oo in state.open_orders:
        if oo.symbol != intent.symbol:
            continue

        actions.append(FulfilmentAction(
            kind=ActionKind.CANCEL, side=oo.side, order_type=None,
            price_ticks_from_best=0, qty_fraction=0.0, ttl_ms=0,
            cancel_order_id=oo.client_order_id,
        ))

        for offset in params.quote_offsets_ticks:
            actions.append(FulfilmentAction(
                kind=ActionKind.CANCEL_REPLACE, side=side,
                order_type=OrderType.LIMIT,
                price_ticks_from_best=offset, qty_fraction=0.25,
                ttl_ms=params.passive_ttl_ms, cancel_order_id=oo.client_order_id,
                post_only=intent.prefer_maker, reduce_only=intent.reduce_only,
                metadata={"requote": True, "requote_offset": offset},
            ))

    # Passive quote placements
    for offset in params.quote_offsets_ticks:
        for frac in params.quote_size_fractions:
            actions.append(FulfilmentAction(
                kind=ActionKind.PLACE, side=side,
                order_type=OrderType.LIMIT,
                price_ticks_from_best=offset, qty_fraction=frac,
                ttl_ms=params.passive_ttl_ms,
                post_only=intent.prefer_maker, reduce_only=intent.reduce_only,
            ))

    # Aggressive crossing — urgency-driven maker/taker decision
    # Below threshold: passive only (maker). Above: aggressive (taker).
    # The system learns the cheapest/fastest path as a function of urgency.
    if intent.urgency > params.urgency_taker_threshold:
        # High urgency: aggressive taker fills
        for frac in (0.05, 0.10, 0.25):
            actions.append(FulfilmentAction(
                kind=ActionKind.CROSS_SPREAD, side=side,
                order_type=OrderType.LIMIT, price_ticks_from_best=0,
                qty_fraction=frac, ttl_ms=params.aggressive_ttl_ms,
                time_in_force="IOC",
                reduce_only=intent.reduce_only,
                metadata={"urgency": intent.urgency, "mode": "taker"},
            ))
    elif intent.urgency > params.urgency_taker_threshold * 0.5:
        # Medium urgency: aggressive but with IOC (partial fill OK)
        for frac in (0.03, 0.06):
            actions.append(FulfilmentAction(
                kind=ActionKind.CROSS_SPREAD, side=side,
                order_type=OrderType.LIMIT, price_ticks_from_best=0,
                qty_fraction=frac, ttl_ms=params.aggressive_ttl_ms,
                time_in_force="IOC",
                reduce_only=intent.reduce_only,
                metadata={"urgency": intent.urgency, "mode": "taker_partial"},
            ))
    # Low urgency: passive only (maker) — no taker actions added

    # Path-risk exits
    if _path_risk_says_exit(state, params):
        actions.append(FulfilmentAction(
            kind=ActionKind.FULL_EXIT, side=_exit_side_for_position(state),
            order_type=OrderType.MARKET, price_ticks_from_best=0,
            qty_fraction=1.0, ttl_ms=0, reduce_only=True,
            metadata={"reason": "path_risk_exit"},
        ))

    # Chase actions (cancel → wait → retry with configurable wait_to_retry_ms)
    if params.chase_enabled and params.wait_to_retry_ms > 0:
        chase_ttl = params.wait_to_retry_ms
        for offset in range(CHASE_MIN_OFFSET, min(CHASE_MAX_OFFSET + 1, params.chase_offset_ticks + 1)):
            for frac in params.quote_size_fractions:
                actions.append(FulfilmentAction(
                    kind=ActionKind.PLACE, side=side,
                    order_type=OrderType.LIMIT,
                    price_ticks_from_best=offset, qty_fraction=frac,
                    ttl_ms=chase_ttl,
                    post_only=True,
                    metadata={"chase": True, "chase_offset": offset,
                              "chase_max_retries": params.chase_max_retries},
                ))

    return tuple(actions)