// SDD-120 §3 items 1-2 — realtime capture bench harness.
//
// - `bench_capture_alloc_count`: dhat-backed heap-allocation count
//   across 1000 post-warmup `CaptureState::ingest` calls. Realizes
//   the SRS-219 clause-a zero-allocation invariant. Local-developer
//   surface additionally asserts that the post-warmup count is 0
//   so a regression hard-fails locally; the CI advisory comparator
//   in `compare_baseline.rs` carries the same `tolerance = 0` rule
//   independently.
// - `bench_capture_callback_wall_clock`: criterion default-warmup
//   wall-clock bench of `ingest` on the same synthetic buffer.
//
// dhat is invasive — it replaces the global allocator for the
// whole bench binary, but only this bench binary; production
// builds and other benches are unaffected per Cargo's per-bench
// compilation model.

#[cfg(any(target_os = "ios", target_os = "macos", target_os = "android"))]
fn main() {}

#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
#[global_allocator]
static ALLOC: dhat::Alloc = dhat::Alloc;

#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
use chanora_audio::bench_seam::CaptureBenchHandle;
#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
use criterion::{black_box, criterion_group, criterion_main, Criterion};

#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
mod common;
#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
use common::{synthetic_capture_buffer, FRAME_SAMPLES};

#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
fn bench_capture_alloc_count(c: &mut Criterion) {
    // Build the dhat profiler in test mode so it is process-local
    // and does not write a JSON heap-dump file. Held for the
    // duration of this bench function.
    let _profiler = dhat::Profiler::builder().testing().build();

    let mut handle = CaptureBenchHandle::new(48_000, 1);
    let buf = synthetic_capture_buffer(FRAME_SAMPLES, 1);

    // 100-call warm-up to prime first-call allocations (ring
    // growth, opus encoder lazy state, mono_scratch / pcm_accum
    // capacity). SDD-120 §3 item 1.
    for _ in 0..100 {
        handle.ingest_f32(&buf);
    }

    let stats_warm = dhat::HeapStats::get();
    let blocks_warm = stats_warm.total_blocks;

    // 1000 post-warmup calls — measurement window.
    for _ in 0..1000 {
        handle.ingest_f32(&buf);
    }

    let stats_final = dhat::HeapStats::get();
    let blocks_final = stats_final.total_blocks;
    let delta = blocks_final - blocks_warm;

    // Local-developer surface: hard-fail on any regression.
    // The CI advisory comparator carries the same rule with a
    // markdown 🔴 marker on regression instead of a panic.
    assert_eq!(
        delta, 0,
        "post-warmup heap allocation regression: {} blocks (SRS-219 clause a)",
        delta
    );

    // Register the metric value with criterion so it appears in
    // `target/criterion/.../estimates.json` for the §5 emitter to
    // pick up. We bench a no-op closure here because the actual
    // measurement is the delta computed above; criterion's
    // function-time-mean is uninteresting for an alloc-count
    // metric. The §5 emitter reads the `capture_alloc_count`
    // metric value out of band via a sidecar file written below.
    c.bench_function("capture_alloc_count", |b| {
        b.iter(|| {
            black_box(delta);
        });
    });

    // Sidecar file for §5 emit_baseline: criterion's own
    // estimates.json carries the no-op closure timing, NOT the
    // alloc count, so we write the canonical alloc-count value
    // here and the emitter reads it directly.
    if let Ok(dir) = std::env::var("CARGO_TARGET_DIR")
        .map(std::path::PathBuf::from)
        .or_else(|_| std::env::current_dir().map(|d| d.join("target")))
    {
        let path = dir.join("criterion").join("capture_alloc_count.sidecar");
        if let Some(parent) = path.parent() {
            let _ = std::fs::create_dir_all(parent);
        }
        let _ = std::fs::write(&path, format!("{}", delta));
    }
}

#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
fn bench_capture_callback_wall_clock(c: &mut Criterion) {
    let mut handle = CaptureBenchHandle::new(48_000, 1);
    let buf = synthetic_capture_buffer(FRAME_SAMPLES, 1);

    // Pre-warm so first-call allocations do not skew the
    // measurement window (criterion's default warmup is 3 s which
    // is more than enough; this loop is belt-and-braces).
    for _ in 0..100 {
        handle.ingest_f32(&buf);
    }

    c.bench_function("capture_callback_wall_clock", |b| {
        b.iter(|| {
            handle.ingest_f32(black_box(&buf));
        });
    });
}

#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
criterion_group!(
    realtime_capture,
    bench_capture_alloc_count,
    bench_capture_callback_wall_clock
);
#[cfg(not(any(target_os = "ios", target_os = "macos", target_os = "android")))]
criterion_main!(realtime_capture);