foxhunt/crates/ml-alpha/tests/multi_horizon_loader.rs

//! Phase A loader smoke tests.
//!
//! Real-data path is `--ignored`; runs only with FOXHUNT_TEST_DATA set.

use data::providers::databento::dbn_parser::InstrumentFilter;
use ml_alpha::data::loader::{
    discover_mbp10_files_sorted, MultiHorizonLoader, MultiHorizonLoaderConfig,
    DEFAULT_OUTCOME_LABEL_COST_ES,
};
use ml_alpha::heads::{HORIZONS, N_HORIZONS};
use std::path::PathBuf;

fn cfg_from_env() -> Option<MultiHorizonLoaderConfig> {
    let root = std::env::var("FOXHUNT_TEST_DATA").ok()?;
    let mbp10 = PathBuf::from(format!("{root}/mbp10"));
    let predec = PathBuf::from(format!("{root}/predecoded"));
    if !mbp10.exists() {
        return None;
    }
    let files = discover_mbp10_files_sorted(&mbp10).ok()?;
    Some(MultiHorizonLoaderConfig {
        files,
        predecoded_dir: predec,
        multi_resolution: ml_alpha::data::aggregation::MultiResolutionConfig::single_scale_32(),
        horizons: HORIZONS,
        n_max_sequences: 100,
        seed: 0xA1A2_A3A4,
        inference_only: false,
        outcome_label_cost: DEFAULT_OUTCOME_LABEL_COST_ES,
        instrument_filter: InstrumentFilter::All,
        frd_horizon_ticks: ml_alpha::rl::common::FRD_HORIZON_TICKS,
        frd_bucket_range_sigma: ml_alpha::rl::common::FRD_BUCKET_RANGE_SIGMA,
    })
}

#[test]
#[ignore]
fn loader_yields_seq_with_valid_labels() {
    let Some(cfg) = cfg_from_env() else {
        eprintln!("skipping: FOXHUNT_TEST_DATA not set or mbp10 dir missing");
        return;
    };
    let mut loader = MultiHorizonLoader::new(&cfg).expect("loader init");
    assert!(loader.n_files() > 0, "no DBN files found in mbp10 root");

    let mut count = 0;
    while let Some(seq) = loader.next_sequence().expect("next") {
        assert_eq!(seq.snapshots.len(), cfg.multi_resolution.total_positions());
        for h in 0..N_HORIZONS {
            assert_eq!(seq.labels[h].len(), cfg.multi_resolution.total_positions());
            for &v in &seq.labels[h] {
                assert!(v.is_nan() || v == 0.0 || v == 1.0, "label not binary: {v}");
            }
        }
        let any_valid = seq.labels.iter().any(|l| l.iter().any(|v| !v.is_nan()));
        assert!(any_valid, "expected at least one non-NaN label in a sequence");
        count += 1;
        if count >= 5 {
            break;
        }
    }
    assert!(count >= 5, "expected at least 5 sequences, got {count}");
}

#[test]
fn loader_errors_on_empty_files() {
    let cfg = MultiHorizonLoaderConfig {
        files: Vec::new(),
        predecoded_dir: PathBuf::from("/tmp/does_not_exist_foxhunt_test"),
        multi_resolution: ml_alpha::data::aggregation::MultiResolutionConfig::single_scale_32(),
        horizons: HORIZONS,
        n_max_sequences: 10,
        seed: 0,
        inference_only: false,
        outcome_label_cost: DEFAULT_OUTCOME_LABEL_COST_ES,
        instrument_filter: InstrumentFilter::All,
        frd_horizon_ticks: ml_alpha::rl::common::FRD_HORIZON_TICKS,
        frd_bucket_range_sigma: ml_alpha::rl::common::FRD_BUCKET_RANGE_SIGMA,
    };
    let res = MultiHorizonLoader::new(&cfg);
    assert!(res.is_err(), "expected error for empty file list");
}

#[test]
#[ignore]
fn loader_stride_4_yields_correct_spacing() {
    // A1: decision_stride removed; sequences are always consecutive snapshots.
    // Test repurposed: verifies consecutive-snapshot ts_ns monotonicity.
    let Some(mut cfg) = cfg_from_env() else {
        eprintln!("skipping: FOXHUNT_TEST_DATA not set or mbp10 dir missing");
        return;
    };
    // cfg.multi_resolution stays at default_three_scale() (total_positions=32).
    cfg.n_max_sequences = 5;
    let mut loader = MultiHorizonLoader::new(&cfg).expect("loader init");

    while let Some(seq) = loader.next_sequence().expect("next") {
        assert_eq!(seq.snapshots.len(), cfg.multi_resolution.total_positions());
        let dts_ns: Vec<i64> = (1..seq.snapshots.len())
            .map(|k| (seq.snapshots[k].ts_ns as i64) - (seq.snapshots[k - 1].ts_ns as i64))
            .filter(|d| *d >= 0) // ts_ns is monotonic in MBP-10
            .collect();
        assert!(!dts_ns.is_empty(), "no positive Δt in sequence");
        let mut sorted = dts_ns.clone();
        sorted.sort();
        let median = sorted[sorted.len() / 2];
        eprintln!("consecutive median Δt_ns between K-positions = {median}");
        assert!(median >= 0, "Δt_ns negative — ts_ns not monotonic?");
    }
}

#[test]
fn discover_errors_on_missing_root() {
    let res = discover_mbp10_files_sorted(&PathBuf::from(
        "/tmp/does_not_exist_foxhunt_test",
    ));
    assert!(res.is_err(), "expected error for missing root dir");
}