foxhunt/crates/ml-backtesting/tests/decision_floor_coldstart.rs

//! Regression test for the cold-start sentinel-skip bug surfaced during
//! the trunk-grows smoke (2026-05-19). Before the kernel floor was
//! added, `step_decision*` would observe sentinel `isv_kelly_d` (all
//! zeros from `alloc_zeros`) and skip every horizon → `market_target =
//! (noop, 0)` forever, which prevented any trade from ever firing.
//!
//! Per `pearl_blend_formulas_must_have_permanent_floor.md` and
//! `pearl_kelly_cap_signal_driven_floors.md`: the decision policy uses
//! `max(floor, computed)` on Kelly fraction AND on the recent-Sharpe
//! aggregation weight so cold-start produces a non-zero target.
//!
//! Asserts: with sentinel isv_kelly_d, strong directional alpha
//! (p_h=0.8 ⇒ long) + floors > 0 ⇒ market_target side=0 (buy),
//! size >= 1 lot.

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

fn cfg_uniform(n: usize, kelly: f32, sharpe: f32) -> 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:        kelly,
        sharpe_weight_floor:     sharpe,
        threshold:               0.0,
        cost_per_lot_per_side:   0.0,
        use_cold_start_stopgap:  false,
    })
}

#[test]
#[ignore = "requires CUDA"]
fn cold_start_sentinel_state_still_fires_a_trade() -> Result<()> {
    let dev = match MlDevice::cuda(0) {
        Ok(d) => d,
        Err(e) => {
            eprintln!("skipping: cuda device unavailable ({e})");
            return Ok(());
        }
    };
    let mut sim = LobSimCuda::new(1, &dev)?;
    // Do NOT seed isv_kelly — leave at zeros (alloc_zeros' sentinel).
    // Strong directional alpha across all horizons → conviction-driven
    // sig_mag = 0.6 for every horizon, dir = +1.
    sim.broadcast_alpha(&[0.8, 0.8, 0.8, 0.8, 0.8])?;
    sim.step_decision_with_latency(0, &cfg_uniform(1, 0.20, 0.10))?;
    let (side, size) = sim.read_market_target(0)?;
    assert_eq!(side, 0, "cold-start with p_h=0.8 must produce a long; got side={side}");
    assert!(size >= 1, "cold-start size {size} < 1 — the kernel floor isn't firing");
    Ok(())
}

/// After the first trade closes as a loss, the original kernel set
/// `realised_return_var = ret²` which collapses `cap_units` to ~0 and
/// permanently locks the policy out of further trading despite strong
/// alpha signal. The fix gates the variance-derived cap behind a
/// sample-size threshold (`n_trades_seen >= MIN_TRADES_FOR_VAR_CAP`)
/// so cap_lots falls back to `max_lots` while statistics are unreliable.
///
/// Test: write an IsvKellyState with n_trades_seen=1 and a large
/// realised_return_var (mimicking the post-loss state from the smoke),
/// then prove that the decision kernel still produces a non-zero trade.
#[test]
#[ignore = "requires CUDA"]
fn post_first_loss_state_does_not_lock_out_further_trades() -> Result<()> {
    let dev = match MlDevice::cuda(0) {
        Ok(d) => d,
        Err(e) => {
            eprintln!("skipping: cuda device unavailable ({e})");
            return Ok(());
        }
    };
    let mut sim = LobSimCuda::new(1, &dev)?;
    // Seed isv_kelly_d with the exact state pattern the smoke produced:
    // one closed-loss trade, large realised_return_var. Pre-fix, the
    // variance-derived cap collapses to ~0.
    let post_loss: [IsvKellyStateHost; 5] = std::array::from_fn(|_| IsvKellyStateHost {
        pnl_ema_win: 0.0,
        pnl_ema_loss: 10.18,   // magnitude of the lone loss return
        win_rate_ema: 0.0,
        n_trades_seen: 1,      // exactly 1 closed trade — under MIN_TRADES_FOR_VAR_CAP
        realised_return_var: 103.6,  // ret² from the smoke (10.18²)
        recent_sharpe: -1.0,   // very negative — would have starved the weight side too
    });
    sim.write_isv_kelly(0, &post_loss)?;
    sim.broadcast_alpha(&[0.8, 0.8, 0.8, 0.8, 0.8])?;
    sim.step_decision_with_latency(0, &cfg_uniform(1, 0.20, 0.10))?;
    let (side, size) = sim.read_market_target(0)?;
    assert_eq!(side, 0, "post-loss state must still fire a long with strong alpha (got side={side})");
    assert!(size >= 1, "post-loss size {size} < 1 — n_trades_seen gate isn't bypassing the variance cap");
    Ok(())
}

#[test]
#[ignore = "requires CUDA"]
fn cold_start_with_zero_floor_reproduces_old_bug() -> Result<()> {
    // Mirror of the test above but with floors = 0 — the kernel must
    // then behave like the old sentinel-skip pre-fix code: no trade ever
    // fires. Lets us prove the fix actually changes behaviour (and not
    // some other unrelated code path).
    let dev = match MlDevice::cuda(0) {
        Ok(d) => d,
        Err(e) => {
            eprintln!("skipping: cuda device unavailable ({e})");
            return Ok(());
        }
    };
    let mut sim = LobSimCuda::new(1, &dev)?;
    sim.broadcast_alpha(&[0.8, 0.8, 0.8, 0.8, 0.8])?;
    sim.step_decision_with_latency(0, &cfg_uniform(1, 0.0, 0.0))?;
    let (side, size) = sim.read_market_target(0)?;
    assert_eq!(side, 2, "with zero floors, sentinel state must still skip (side=noop)");
    assert_eq!(size, 0);
    Ok(())
}