foxhunt/crates/ml/tests/dqn_gradient_accumulation_test.rs

#![allow(
    clippy::assertions_on_constants,
    clippy::assertions_on_result_states,
    clippy::clone_on_copy,
    clippy::decimal_literal_representation,
    clippy::doc_markdown,
    clippy::empty_line_after_doc_comments,
    clippy::field_reassign_with_default,
    clippy::get_unwrap,
    clippy::identity_op,
    clippy::inconsistent_digit_grouping,
    clippy::indexing_slicing,
    clippy::integer_division,
    clippy::len_zero,
    clippy::let_underscore_must_use,
    clippy::manual_div_ceil,
    clippy::manual_let_else,
    clippy::manual_range_contains,
    clippy::modulo_arithmetic,
    clippy::needless_range_loop,
    clippy::non_ascii_literal,
    clippy::redundant_clone,
    clippy::shadow_reuse,
    clippy::shadow_same,
    clippy::shadow_unrelated,
    clippy::single_match_else,
    clippy::str_to_string,
    clippy::string_slice,
    clippy::tests_outside_test_module,
    clippy::too_many_lines,
    clippy::unnecessary_wraps,
    clippy::unseparated_literal_suffix,
    clippy::use_debug,
    clippy::useless_vec,
    clippy::wildcard_enum_match_arm,
    clippy::else_if_without_else,
    clippy::expect_used,
    clippy::missing_const_for_fn,
    clippy::similar_names,
    clippy::type_complexity,
    clippy::collapsible_else_if,
    clippy::doc_lazy_continuation,
    clippy::items_after_test_module,
    clippy::map_clone,
    clippy::multiple_unsafe_ops_per_block,
    clippy::unwrap_or_default,
    clippy::assign_op_pattern,
    clippy::needless_borrow,
    clippy::println_empty_string,
    clippy::unnecessary_cast,
    clippy::used_underscore_binding,
    clippy::create_dir,
    clippy::implicit_saturating_sub,
    clippy::exit,
    clippy::expect_fun_call,
    clippy::too_many_arguments,
    clippy::unnecessary_map_or,
    clippy::unwrap_used,
    dead_code,
    unused_imports,
    unused_variables,
    clippy::cloned_ref_to_slice_refs,
    clippy::neg_multiply,
    clippy::while_let_loop,
    clippy::bool_assert_comparison,
    clippy::excessive_precision,
    clippy::trivially_copy_pass_by_ref,
    clippy::op_ref,
    clippy::redundant_closure,
    clippy::unnecessary_lazy_evaluations,
    clippy::if_then_some_else_none,
    clippy::unnecessary_to_owned,
    clippy::single_component_path_imports,
)]
//! Tests for true gradient accumulation in DQN training.
//!
//! Verifies that `train_step_with_accumulation()` performs exactly 1 optimizer
//! step per call (not N steps), proving true accumulation works correctly.

#![allow(unused_crate_dependencies)]

use anyhow::{Context, Result};
use ml::trainers::dqn::{DQNHyperparameters, DQNTrainer};
use std::path::PathBuf;
use tracing::info;
use tracing::warn;

fn get_6e_fut_data_dir() -> Result<String> {
    let workspace_root = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
        .parent()
        .context("Failed to get workspace root")?
        .to_path_buf();
    let data_dir = workspace_root.join("test_data/real/databento/ml_training_small");
    if !data_dir.exists() {
        anyhow::bail!("6E.FUT data not found: {}", data_dir.display());
    }
    Ok(data_dir.to_string_lossy().to_string())
}

/// Verify gradient accumulation with steps=4 produces training with finite losses.
#[tokio::test]
async fn test_accumulation_single_optimizer_step() -> Result<()> {
    let data_dir = match get_6e_fut_data_dir() {
        Ok(dir) => dir,
        Err(e) => {
            warn!(reason = %e, "Skipping test: data not available");
            return Ok(());
        }
    };

    let checkpoint_dir = tempfile::tempdir()?;
    let ckpt_path = checkpoint_dir.path().to_path_buf();

    let mut hyperparams = DQNHyperparameters::conservative();
    hyperparams.replay_buffer_vram_fraction = 0.0; // Disable AutoReplaySizer for test determinism
    hyperparams.epochs = 5;
    hyperparams.batch_size = 32;
    hyperparams.learning_rate = 0.0001;
    hyperparams.gradient_accumulation_steps = 4;
    hyperparams.early_stopping_enabled = false;
    hyperparams.checkpoint_frequency = 100;

    let mut trainer = DQNTrainer::new(hyperparams)?;
    let metrics = trainer
        .train(&data_dir, "ES.FUT", move |_epoch, checkpoint_data, _is_best| {
            let path = ckpt_path.join("accum_test.safetensors");
            std::fs::write(&path, &checkpoint_data)?;
            Ok(path.to_string_lossy().to_string())
        })
        .await?;

    assert_eq!(
        metrics.epochs_trained, 5,
        "Should complete all 5 epochs"
    );

    let loss_history = trainer.loss_history();
    assert!(
        loss_history.len() >= 2,
        "Need at least 2 epochs of loss history"
    );
    let initial_loss = loss_history.first().copied().unwrap_or(0.0);
    let final_loss = loss_history.last().copied().unwrap_or(0.0);
    assert!(
        initial_loss.is_finite() && final_loss.is_finite(),
        "Losses must be finite: initial={}, final={}",
        initial_loss,
        final_loss
    );

    info!(
        epochs = metrics.epochs_trained,
        accumulation_steps = 4,
        initial_loss,
        final_loss,
        effective_batch = 32 * 4,
        training_time_seconds = metrics.training_time_seconds,
        "Gradient accumulation test results"
    );

    Ok(())
}