//! Stop-controller spec §9.1 unit tests.
//! See docs/superpowers/specs/2026-05-19-isv-driven-stop-controller-design.md.

use anyhow::Result;
use ml_backtesting::sim::{BatchedSimConfig, LobSimCuda, UniformSimParams};
use ml_core::device::MlDevice;

fn level_book(mid: f32, tick: f32) -> ([f32; 10], [f32; 10], [f32; 10], [f32; 10]) {
    let mut bid_px = [0.0; 10];
    let mut bid_sz = [0.0; 10];
    let mut ask_px = [0.0; 10];
    let mut ask_sz = [0.0; 10];
    for k in 0..10 {
        bid_px[k] = mid - tick * (k as f32 + 1.0);
        ask_px[k] = mid + tick * (k as f32 + 1.0);
        bid_sz[k] = 20.0;
        ask_sz[k] = 20.0;
    }
    (bid_px, bid_sz, ask_px, ask_sz)
}

#[test]
#[ignore = "requires CUDA"]
fn atr_ema_bootstrap_first_observation() -> Result<()> {
    let dev = match MlDevice::cuda(0) {
        Ok(d) => d,
        Err(e) => { eprintln!("skipping: cuda unavailable ({e})"); return Ok(()); }
    };
    let mut sim = LobSimCuda::new(1, &dev)?;

    // Event 0: snapshot at mid=5500. After: prev_mid=5500, atr_mid_ema=0.
    let (bp, bs, ap, az) = level_book(5500.0, 0.25);
    sim.apply_snapshot(&bp, &bs, &ap, &az)?;
    assert_eq!(sim.read_atr_mid_ema(0)?, 0.0, "ATR is 0 after first snapshot");
    let prev0 = sim.read_prev_mid(0)?;
    assert!((prev0 - 5500.0).abs() < 1e-4, "prev_mid bootstrapped to 5500, got {prev0}");

    // Event 1: snapshot at mid=5500.5. Δ=0.5. After: atr_mid_ema=0.5 (replace, not blend).
    let (bp, bs, ap, az) = level_book(5500.5, 0.25);
    sim.apply_snapshot(&bp, &bs, &ap, &az)?;
    let atr1 = sim.read_atr_mid_ema(0)?;
    assert!((atr1 - 0.5).abs() < 1e-4, "ATR after 2nd snapshot equals |Δmid|=0.5, got {atr1}");

    // Events 2..200: jitter book. ATR stays positive and finite, bounded by max Δ.
    let mut mid = 5500.5_f32;
    let mut max_delta: f32 = 0.5;
    for i in 0..198 {
        let drift = if i % 3 == 0 { 0.25 } else if i % 3 == 1 { -0.25 } else { 0.0 };
        mid += drift;
        max_delta = max_delta.max(drift.abs());
        let (bp, bs, ap, az) = level_book(mid, 0.25);
        sim.apply_snapshot(&bp, &bs, &ap, &az)?;
    }
    let atr_final = sim.read_atr_mid_ema(0)?;
    assert!(atr_final > 0.0 && atr_final.is_finite(),
            "ATR positive + finite after 200 snapshots, got {atr_final}");
    assert!(atr_final <= max_delta + 1e-3,
            "ATR bounded by max observed Δ={max_delta}, got {atr_final}");
    Ok(())
}

fn cfg_default(n: usize) -> BatchedSimConfig {
    BatchedSimConfig::from_uniform(n, &UniformSimParams {
        target_annual_vol_units: 50.0,
        annualisation_factor:    825.0,
        max_lots:                5,
        latency_ns:              0,
        kelly_frac_floor:        0.20,
        sharpe_weight_floor:     0.10,
        threshold:               0.0,
        cost_per_lot_per_side:   0.0,
        use_cold_start_stopgap:  false,
    })
}

#[test]
#[ignore = "requires CUDA"]
fn stop_check_skipped_when_flat() -> Result<()> {
    let dev = match MlDevice::cuda(0) {
        Ok(d) => d,
        Err(e) => { eprintln!("skipping: cuda unavailable ({e})"); return Ok(()); }
    };
    let mut sim = LobSimCuda::new(1, &dev)?;
    let (bp, bs, ap, az) = level_book(5500.0, 0.25);
    sim.apply_snapshot(&bp, &bs, &ap, &az)?;

    // Position is flat (just allocated, zeros). Stop check must not fire;
    // alpha decides the action.
    sim.broadcast_alpha(&[0.8, 0.8, 0.8, 0.8, 0.8])?;
    sim.step_decision_with_latency(0, &cfg_default(1))?;

    let (side, size) = sim.read_market_target(0)?;
    // Strong bullish alpha + flat position → entry side=0 size>=1.
    // Not (3, 0) (force-flat) and not unchanged from the initial alloc-zero state.
    assert_eq!(side, 0, "with flat position, stop must not write side=3; got side={side}");
    assert!(size >= 1, "entry should fire under p=0.8 + flat (size={size})");
    Ok(())
}

use ml_backtesting::policy::IsvKellyStateHost;

#[test]
#[ignore = "requires CUDA"]
fn sl_fires_when_unrealized_breaks_distance() -> Result<()> {
    let dev = match MlDevice::cuda(0) {
        Ok(d) => d,
        Err(e) => { eprintln!("skipping: cuda unavailable ({e})"); return Ok(()); }
    };
    let mut sim = LobSimCuda::new(1, &dev)?;

    // Seed isv: 5 horizons with pnl_ema_loss=2.0 → sl_distance=2.0.
    // pnl_ema_win=0.0 forces cold-start branch in decision kernel (kelly_frac →
    // floor=0.20, cap_lots → max_lots=5). With alpha=0.95 this gives
    // lots=round(0.9*0.20*5)=round(0.9)=1 — position opens.
    let seeded: [IsvKellyStateHost; 5] = std::array::from_fn(|_| IsvKellyStateHost {
        pnl_ema_win:  0.0,
        pnl_ema_loss: 2.0,
        win_rate_ema: 0.5,
        n_trades_seen: 0,
        realised_return_var: 0.0,
        recent_sharpe: 0.5,
    });
    sim.write_isv_kelly(0, &seeded)?;

    // Two snapshots so atr_mid_ema becomes nonzero (small).
    let (bp, bs, ap, az) = level_book(5500.0, 0.25);
    sim.apply_snapshot(&bp, &bs, &ap, &az)?;
    let (bp2, bs2, ap2, az2) = level_book(5500.1, 0.25);
    sim.apply_snapshot(&bp2, &bs2, &ap2, &az2)?;

    // Open a long position via strong-alpha + step_decision + manual fill.
    sim.broadcast_alpha(&[0.95, 0.95, 0.95, 0.95, 0.95])?;
    sim.step_decision_with_latency(0, &cfg_default(1))?;
    let mut ts: u64 = 1_000_000;
    for _ in 0..3 {
        sim.step_resting_orders(ts, 0.0)?;
        ts += 1_000_000;
    }
    let pos_open = sim.read_pos(0)?;
    assert!(pos_open.position_lots > 0,
            "test setup: long position should open, got {}", pos_open.position_lots);

    // Drive mid down by 3.0 (>= sl_distance=2.0). Stop must fire force-flat.
    let (bp3, bs3, ap3, az3) = level_book(5497.0, 0.25);
    sim.apply_snapshot(&bp3, &bs3, &ap3, &az3)?;
    sim.broadcast_alpha(&[0.95, 0.95, 0.95, 0.95, 0.95])?;
    sim.step_decision_with_latency(ts, &cfg_default(1))?;

    let (side, size) = sim.read_market_target(0)?;
    assert_eq!(side, 3, "SL must fire with force-flat (3, 0); got side={side}");
    assert_eq!(size, 0, "force-flat encoding has abs_sz=0; got size={size}");
    Ok(())
}

#[test]
#[ignore = "requires CUDA"]
fn trail_arms_then_fires() -> Result<()> {
    let dev = match MlDevice::cuda(0) {
        Ok(d) => d,
        Err(e) => { eprintln!("skipping: cuda unavailable ({e})"); return Ok(()); }
    };
    let mut sim = LobSimCuda::new(1, &dev)?;

    // Cold-start ISV (forces kelly_frac_floor + max_lots cap) so position opens.
    // pnl_ema_loss large enough that SL won't fire during the +5pt walk.
    let cold_start: [IsvKellyStateHost; 5] = std::array::from_fn(|_| IsvKellyStateHost {
        pnl_ema_win:  0.0,
        pnl_ema_loss: 10.0,    // big SL so trail fires first
        win_rate_ema: 0.0,
        n_trades_seen: 0,
        realised_return_var: 0.0,
        recent_sharpe: 0.0,
    });
    sim.write_isv_kelly(0, &cold_start)?;

    let (bp, bs, ap, az) = level_book(5500.0, 0.25);
    sim.apply_snapshot(&bp, &bs, &ap, &az)?;
    let (bp2, bs2, ap2, az2) = level_book(5500.1, 0.25);
    sim.apply_snapshot(&bp2, &bs2, &ap2, &az2)?;

    // Open long.
    sim.broadcast_alpha(&[0.95, 0.95, 0.95, 0.95, 0.95])?;
    sim.step_decision_with_latency(0, &cfg_default(1))?;
    let mut ts: u64 = 1_000_000;
    for _ in 0..3 { sim.step_resting_orders(ts, 0.0)?; ts += 1_000_000; }
    assert!(sim.read_pos(0)?.position_lots > 0, "setup: long opened");

    // After opening, switch ISV to one with pnl_ema_win=1.5 (trail_distance target).
    // The trail check reads this fresh state on subsequent decision steps.
    let trail_state: [IsvKellyStateHost; 5] = std::array::from_fn(|_| IsvKellyStateHost {
        pnl_ema_win:  1.5,
        pnl_ema_loss: 10.0,
        win_rate_ema: 0.5,
        n_trades_seen: 20,
        realised_return_var: 0.5,
        recent_sharpe: 0.5,
    });
    sim.write_isv_kelly(0, &trail_state)?;

    // Walk mid up to ratchet trail HWM past trail_distance=1.5.
    for &m in &[5501.0_f32, 5502.0, 5503.0, 5504.0, 5505.0] {
        let (b, bs, a, asz) = level_book(m, 0.25);
        sim.apply_snapshot(&b, &bs, &a, &asz)?;
        sim.broadcast_alpha(&[0.95, 0.95, 0.95, 0.95, 0.95])?;
        sim.step_decision_with_latency(ts, &cfg_default(1))?;
        ts += 1_000_000;
    }
    let hwm_armed = sim.read_trail_hwm(0)?;
    assert!(hwm_armed > 1.5, "HWM should ratchet past trail_distance=1.5, got {hwm_armed}");

    // Drop mid by trail_distance+ε from peak to fire trail.
    let (b, bs, a, asz) = level_book(5502.0, 0.25);  // drop from peak 5505 to 5502 = 3.0
    sim.apply_snapshot(&b, &bs, &a, &asz)?;
    sim.broadcast_alpha(&[0.95, 0.95, 0.95, 0.95, 0.95])?;
    sim.step_decision_with_latency(ts, &cfg_default(1))?;

    let (side, size) = sim.read_market_target(0)?;
    assert_eq!(side, 3, "trail must fire force-flat; got side={side}");
    assert_eq!(size, 0);
    Ok(())
}

#[test]
#[ignore = "requires CUDA"]
fn multi_horizon_mask_averages_emas() -> Result<()> {
    let dev = match MlDevice::cuda(0) {
        Ok(d) => d,
        Err(e) => { eprintln!("skipping: cuda unavailable ({e})"); return Ok(()); }
    };
    let mut sim = LobSimCuda::new(1, &dev)?;

    // Cold-start to open. After opening, overwrite ISV so averaging arithmetic
    // yields mean_sl = 3.0 across all open horizons in the mask:
    //   h0.pnl_ema_loss=2.0, h1=4.0, h2=h3=h4=3.0  →  mean = (2+4+3*3)/5 = 3.0
    // attribution_mask = 0x1F (all 5 bits) because sharpe_weight_floor=0.10
    // makes every horizon weight > 1e-9 in decision_policy_default.
    // Snapshots placed relative to vwap_entry to avoid ask-spread sensitivity.
    // Bit-pick-first (h0=2.0) would fire at Δ_entry=2.5 → test catches it.
    // Bit-pick-max (h1=4.0) would not fire at Δ_entry=4.5 → test catches it.
    // Correct mean (3.0) → no fire at Δ_entry=2.5, fire at Δ_entry=4.5.
    let cold_start: [IsvKellyStateHost; 5] = std::array::from_fn(|_| IsvKellyStateHost {
        pnl_ema_win:  0.0,
        pnl_ema_loss: 10.0,
        win_rate_ema: 0.0,
        n_trades_seen: 0,
        realised_return_var: 0.0,
        recent_sharpe: 0.0,
    });
    sim.write_isv_kelly(0, &cold_start)?;

    let (bp, bs, ap, az) = level_book(5500.0, 0.25);
    sim.apply_snapshot(&bp, &bs, &ap, &az)?;
    let (bp2, bs2, ap2, az2) = level_book(5500.1, 0.25);
    sim.apply_snapshot(&bp2, &bs2, &ap2, &az2)?;

    sim.broadcast_alpha(&[0.95, 0.95, 0.95, 0.95, 0.95])?;
    sim.step_decision_with_latency(0, &cfg_default(1))?;
    let mut ts: u64 = 1_000_000;
    for _ in 0..3 { sim.step_resting_orders(ts, 0.0)?; ts += 1_000_000; }
    let pos_open = sim.read_pos(0)?;
    assert!(pos_open.position_lots > 0, "setup: long opens, got {}", pos_open.position_lots);

    // Read the actual VWAP entry price so snapshot mids are placed relative to it,
    // making the test robust to ask-spread and tick size.
    let entry_px = pos_open.vwap_entry;
    assert!(entry_px > 0.0, "vwap_entry must be set after fill, got {entry_px}");

    // Seed multi-horizon ISV state. pnl_ema_win=100.0 keeps trail_distance huge
    // so the trail never fires during the test.
    // See setup comment above: mean=3.0, regression discriminators at Δ=2.5/4.5.
    let mut seeded: [IsvKellyStateHost; 5] = std::array::from_fn(|_| IsvKellyStateHost {
        pnl_ema_win:  100.0,
        pnl_ema_loss: 3.0,
        win_rate_ema: 0.5,
        n_trades_seen: 20,
        realised_return_var: 0.5,
        recent_sharpe: 0.5,
    });
    seeded[0].pnl_ema_loss = 2.0;
    seeded[1].pnl_ema_loss = 4.0;
    // h2, h3, h4 remain 3.0. Mean = (2+4+3+3+3)/5 = 3.0.
    sim.write_isv_kelly(0, &seeded)?;

    // Snapshots placed so bid[0] = entry_px - delta_from_entry (for a long):
    //   unrealized_pl_per_lot = bid[0] - entry_px = -delta_from_entry
    // sl_distance = fmaxf(mean_ema_loss=3.0, atr). ATR after these moderate
    // price moves stays < 3.0 (the move is ~2.5 from the open level), so
    // sl_distance == 3.0.  (If ATR somehow > 3.0, sl_distance > 3.0 and the
    // no-fire leg is still safe; only the fire leg could be affected but
    // we use Δ=4.5 which gives 1.5× headroom above the 3.0 floor.)
    //
    // No-fire: Δ_from_entry = 2.5 — bid[0] = entry_px - 2.5 → mid = entry_px - 2.25
    let mid_no_fire = entry_px - 2.25;
    let (bp3, bs3, ap3, az3) = level_book(mid_no_fire, 0.25);
    sim.apply_snapshot(&bp3, &bs3, &ap3, &az3)?;
    sim.broadcast_alpha(&[0.95, 0.95, 0.95, 0.95, 0.95])?;
    sim.step_decision_with_latency(ts, &cfg_default(1))?;
    let (side_at_25, _) = sim.read_market_target(0)?;
    assert_ne!(side_at_25, 3,
               "Δ=2.5 < mean_sl=3.0 must not fire under correct averaging; got side={side_at_25}");
    ts += 1_000_000;

    let atr_at_check = sim.read_atr_mid_ema(0)?;
    assert!(
        atr_at_check < 3.0,
        "test precondition: ATR must stay below mean_sl=3.0 to make sl_distance = max(ema_loss=3.0, atr) = 3.0; got atr={atr_at_check}"
    );

    // Fire: Δ_from_entry = 4.5 (> mean_sl=3.0 and > any reasonable ATR floor)
    //   bid[0] = entry_px - 4.5 → mid = entry_px - 4.25
    let mid_fire = entry_px - 4.25;
    let (bp4, bs4, ap4, az4) = level_book(mid_fire, 0.25);
    sim.apply_snapshot(&bp4, &bs4, &ap4, &az4)?;
    sim.broadcast_alpha(&[0.95, 0.95, 0.95, 0.95, 0.95])?;
    sim.step_decision_with_latency(ts, &cfg_default(1))?;
    let (side_at_45, size_at_45) = sim.read_market_target(0)?;
    assert_eq!(side_at_45, 3, "Δ=4.5 > mean_sl=3.0 must fire force-flat; got side={side_at_45}");
    assert_eq!(size_at_45, 0);
    Ok(())
}