// rl_drawdown_stop.cu — per-step drawdown penalty + hard stop-loss.
//
// Runs AFTER rl_trade_context_update (which computes unrealized_r).
// Reads unrealized_r from trade_context_d and applies:
//
//   1. Per-step drawdown penalty: adds min(0, unrealized_r) × PENALTY_RATE
//      to rewards[b]. Creates continuous exit gradient on losing positions.
//      Penalty-only (never positive) = no exposure incentive.
//
//   2. Hard stop-loss: when unrealized_r < -STOP_THRESHOLD, force-close
//      by setting dones[b] = 1. The realized PnL at this point becomes
//      the final trade reward. Caps max loss per trade.
//
// Both thresholds are ISV-driven per feedback_isv_for_adaptive_bounds.
// Grid: ceil(B/32), Block: 32.

#define RL_DRAWDOWN_PENALTY_RATE_INDEX  586
#define RL_STOP_LOSS_THRESHOLD_INDEX    587
#define TRADE_CONTEXT_STRIDE            5
#define UNREALIZED_R_OFFSET             1

extern "C" __global__ void rl_drawdown_stop(
    const float* __restrict__ trade_context,  // [B, TRADE_CONTEXT_STRIDE]
    float*       __restrict__ rewards,         // [B] IN/OUT
    float*       __restrict__ dones,           // [B] IN/OUT
    float*       __restrict__ isv,
    int          b_size
) {
    const int b = blockIdx.x * blockDim.x + threadIdx.x;
    if (b >= b_size) return;

    const float unrealized_r = trade_context[b * TRADE_CONTEXT_STRIDE + UNREALIZED_R_OFFSET];
    const float penalty_rate = isv[RL_DRAWDOWN_PENALTY_RATE_INDEX];
    const float stop_thresh  = isv[RL_STOP_LOSS_THRESHOLD_INDEX];

    // Per-step drawdown penalty: only fires when losing (unrealized_r < 0).
    // min(0, x) * rate is always <= 0.
    if (unrealized_r < 0.0f) {
        rewards[b] += unrealized_r * penalty_rate;
    }

    // Hard stop-loss DISABLED: setting dones=1 here creates a state
    // mismatch — the lobsim position stays open while Q sees a false
    // close. The done signal must come from actual position changes
    // in the lobsim, not synthetic overrides. To implement hard
    // stop-loss properly, the action must be overridden to FlatL/FlatS
    // BEFORE the lobsim step, not after.
    (void) stop_thresh;
}