//! Body Map Viewer workshop-gate benches (T-1178 / T-1154, brief appendix
//! ②/③; tyre-implications.md §3.2). Two anti-extrapolation measurements the
//! T-1143 planetary-rung post-mortem specifically named as the gap that must
//! close before round 1 of the body-map-viewer workshop can start:
//!
//! - **T-1178 (②):** does the row-chunked `par_iter` throughput measured at
//!   4,096 cells (`zoom_ladder_bench.rs`, 1.785 µs/cell District cutoff)
//!   HOLD at real step-canvas sizes (330K, 2.07M, 8.3M cells)? MEASURE, never
//!   extrapolate.
//! - **T-1154 (③):** per-cell derive cost at block (128 m) and tile-adjacent
//!   (1–4 m) spacing — the ladder's un-costed bottom rungs
//!   (`atlas-zoom-ladder-t1143.md` §2: "not estimated").
//!
//! ## Why this is a NEW file, not an extension of `zoom_ladder_bench.rs`
//!
//! `zoom_ladder_bench.rs` measures per-cell rate at the FIXED 4,096-cell
//! shape (`grid_side = 64`, matching the D-226 window wire cap) — that shape
//! is deliberate there (it's the served-window ceiling). This file measures
//! the opposite question: does the SAME per-cell code path hold its rate when
//! swept out to real canvas dimensions the served-window ceiling forbids.
//! Different shape, different question, kept in its own file per the batch
//! instruction (do not touch `server/src/atlas/mod.rs`; extend the bench or
//! add a new file — this adds a new file to avoid entangling two
//! differently-shaped measurement passes in one).
//!
//! ## The `n`-cap problem (why this cannot go through `AtlasLayerRequest`)
//!
//! `build_district_window_layer`'s caller-facing entry (`handle_atlas_request`
//! / `clamp_window_n_v2`) hard-clamps `n` so `side² ≤ WIRE_CAP_CELLS = 4,096`
//! — a REAL client can never request a 330K-cell window over the wire, by
//! design (D-226 T-1124 §2). So "run it through the production path at
//! 330K/8.3M cells" cannot mean "send an `AtlasLayerRequest` for that size" —
//! no such request is legal. It means: call the actual
//! `build_district_window_layer` function — same signature, same row-chunked
//! `into_par_iter()` loop, same `derive_window_cell`/`scatter_row` internals,
//! same `derive_at_metres` calls — with an `n` no wire request could carry,
//! because `build_district_window_layer` itself has NO internal clamp (the
//! clamp lives one layer up, in the request handler). Confirmed by direct
//! read of `layer_proxy.rs:1515-1628` this session. This is exactly what the
//! ticket anticipates: "If the production path caps window n such that you
//! cannot request 330K cells through it directly, bench the underlying
//! chunked loop at those counts and say exactly what you ran."
//!
//! ## Square vs. rectangular canvases
//!
//! `build_district_window_layer` only derives SQUARE `side×side` grids ('n'
//! is a single extent). The real step-canvas shapes the ticket names are
//! 16:9 rectangles (768×432, 1920×1080, 3840×2160) — not square. Two
//! measurements are taken for each cell-count target:
//!
//! 1. **Square, through `build_district_window_layer` itself** (District
//!    granularity, `n = side`, real function call, unmodified) — the closest
//!    possible approach to "the actual production entry point," at the
//!    nearest square cell count to the target (e.g. side=576 → 331,776
//!    cells, matching 768×432's 331,776 exactly).
//! 2. **Real 16:9 rectangle, via a row-chunked loop that mirrors
//!    `build_district_window_layer`'s internals cell-for-cell** (same
//!    `into_par_iter()` row chunking, same `derive_at_metres` call, same
//!    per-cell output quantization copied from `derive_window_cell`) but
//!    sized to the actual non-square canvas. This is necessarily a
//!    hand-written replica for the rectangular case (documented inline,
//!    diffed explicitly against the real function in the module doc above),
//!    since no production entry point derives a rectangle. Labelled
//!    "MEASURED (replica loop)" in the results table to distinguish it from
//!    "MEASURED (production fn)".
//!
//! Both converge on the same number at the same cell count (verified by the
//! square case landing within noise of the rectangle case at 331,776 ≈ 576²)
//! — see the results doc for the cross-check.
//!
//! Run: `cargo test --release --test bmv_gridunit_bench -- --ignored --nocapture`

use std::time::Instant;

use settled_reach_server::atlas::district_profile::{
    derive_at_metres, BodyParams, ClimateConstants,
};
use settled_reach_server::atlas::drainage;
use settled_reach_server::atlas::features::TerrainAnalysis;
use settled_reach_server::atlas::heightmap::{load_heightmap_png, BodyHeightmap};
use settled_reach_server::atlas::layer_proxy::{build_district_window_layer, WindowGranularity};
use settled_reach_server::atlas::scale;
use settled_reach_server::seed::{SeedChain, SeedDomain};

// ---------------------------------------------------------------------------
// Shared fixtures — same shape as zoom_ladder_bench.rs's own fixtures, reused
// rather than re-invented so the two files' numbers are directly comparable.
// ---------------------------------------------------------------------------

fn bench_hm() -> BodyHeightmap {
    let (w, h) = (128u32, 64u32);
    let n = (w * h) as usize;
    let data = (0..n)
        .map(|i| {
            let r = (i / w as usize) as f32 / h as f32;
            let c = (i % w as usize) as f32 / w as f32;
            (r * 0.6 + c * 0.4).min(1.0)
        })
        .collect();
    BodyHeightmap {
        body_id: "bench".into(),
        width: w,
        height: h,
        data,
        sea_level: 0.3,
    }
}

fn bench_ta(hm: &BodyHeightmap) -> TerrainAnalysis {
    let dr = drainage::analyze(&hm.data, hm.width, hm.height, hm.sea_level);
    TerrainAnalysis::analyze(hm, &dr)
}

fn bench_river_network(
    hm: &BodyHeightmap,
) -> settled_reach_server::atlas::body_world_state::RiverNetwork {
    drainage::analyze(&hm.data, hm.width, hm.height, hm.sea_level).river_network
}

fn bench_params() -> BodyParams {
    BodyParams {
        hydrosphere: Some("ocean".into()),
        atmosphere: Some("breathable".into()),
        planet_class: Some("temperate".into()),
        body_radius_km: Some(6371.0),
        ..Default::default()
    }
}

/// The real committed GJ1c heightmap, downsampled to the production working
/// grid (512×256) — used for the "real body" cross-check bench so the
/// headline numbers are not solely a synthetic-gradient artifact.
fn gj1c_fixture() -> (BodyHeightmap, TerrainAnalysis) {
    let src = std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR"))
        .join("../wiki/star-systems/GJ-1/bodies/GJ1c/heightmap.png");
    let heightmap = load_heightmap_png(&src, "GJ1c", 0.3).expect("decode committed GJ1c heightmap");
    let small = heightmap.downsample(512, 256);
    let dr = drainage::analyze(&small.data, small.width, small.height, small.sea_level);
    let ta = TerrainAnalysis::analyze(&small, &dr);
    (small, ta)
}

/// Report the actual Rayon global-pool thread count in use, not an assumed
/// constant — so the results doc records what really ran, on whatever
/// machine state existed at run time.
fn rayon_threads_report() -> String {
    format!(
        "available_parallelism={}, rayon::current_num_threads={}",
        std::thread::available_parallelism()
            .map(|n| n.get())
            .unwrap_or(0),
        rayon::current_num_threads()
    )
}

// ---------------------------------------------------------------------------
// T-1178 (Measurement ②) — square canvases through the REAL production fn.
// ---------------------------------------------------------------------------

/// Square windows through the actual, unmodified `build_district_window_layer`
/// — same function a real `DeriveWindow` work item calls — at `n` values no
/// wire request could legally carry (the `WIRE_CAP_CELLS` clamp lives in the
/// caller, not in this function; see module doc). District granularity
/// (2,048 m spacing) with the matching District cutoff (2,048 m, admits every
/// existing octave band — the "today's shipped cutoff" case) and the same
/// spacing UNCUT (cutoff 0) for comparison.
#[test]
#[ignore]
fn bench_square_window_production_fn_district_spacing() {
    let hm = bench_hm();
    let ta = bench_ta(&hm);
    let rn = bench_river_network(&hm);
    let params = bench_params();
    let climate = ClimateConstants::default();
    let seed = SeedChain::root(99).derive(SeedDomain::Body, 1);

    println!("\n=== T-1178 square-window production-fn bench (District spacing) ===");
    println!("  {}\n", rayon_threads_report());

    // side values chosen to land on/near the ticket's named cell counts:
    //   576^2  = 331,776  (~330K, the 5x5-px-per-gridunit fallback)
    //  1440^2  = 2,073,600 (~2.07M, the 1920x1080 midpoint)
    //  2880^2  = 8,294,400 (~8.3M, the 3840x2160 1x1 ideal)
    let side_targets: [u32; 3] = [576, 1440, 2880];
    let min_wl_m = scale::DISTRICT_M as u32; // 2,048 m — the shipped District cutoff band

    for &side in &side_targets {
        let n = side; // District granularity: side == n
        let cells = (side as u64) * (side as u64);

        // Warm-up call (allocator/page-fault warm-up not counted).
        let _ = build_district_window_layer(
            seed,
            "bench",
            &params,
            &ta,
            &rn,
            (0, 0),
            n,
            &climate,
            WindowGranularity::District,
            min_wl_m,
        );

        let t0 = Instant::now();
        let layer = build_district_window_layer(
            seed,
            "bench",
            &params,
            &ta,
            &rn,
            (0, 0),
            n,
            &climate,
            WindowGranularity::District,
            min_wl_m,
        );
        let elapsed = t0.elapsed();
        std::hint::black_box(layer.elev_q.len());

        let ms = elapsed.as_secs_f64() * 1000.0;
        let ns_per_cell = elapsed.as_secs_f64() * 1e9 / cells as f64;
        println!(
            "  side={side:>5} n={n:>5} cells={cells:>10} (target ~{}): \
             {ms:>9.2} ms warm, {ns_per_cell:>7.1} ns/cell ({:.3} us/cell)",
            match cells {
                c if c < 500_000 => "330K",
                c if c < 4_000_000 => "2.07M",
                _ => "8.3M",
            },
            ns_per_cell / 1000.0
        );
    }
    println!();
}

/// Single-thread comparison at the SAME square shapes — builds a 1-thread
/// Rayon pool via `install()` so the SAME `build_district_window_layer` body
/// runs its `into_par_iter()` on exactly one worker, isolating the
/// parallel-speedup number from a hand-rolled serial loop that might not
/// match the real per-cell overhead exactly.
#[test]
#[ignore]
fn bench_square_window_production_fn_district_spacing_single_thread() {
    let hm = bench_hm();
    let ta = bench_ta(&hm);
    let rn = bench_river_network(&hm);
    let params = bench_params();
    let climate = ClimateConstants::default();
    let seed = SeedChain::root(99).derive(SeedDomain::Body, 1);

    println!("\n=== T-1178 square-window production-fn bench, SINGLE THREAD (District spacing) ===\n");

    // 8.3M cells single-thread is the ~12s-class case the design doc
    // extrapolated (§7); 330K/2.07M included for the full comparison table.
    // Skipped: none — this is the case that must NOT be assumed cheap.
    let side_targets: [u32; 3] = [576, 1440, 2880];
    let min_wl_m = scale::DISTRICT_M as u32;

    let pool = rayon::ThreadPoolBuilder::new()
        .num_threads(1)
        .build()
        .expect("build single-thread rayon pool");

    for &side in &side_targets {
        let n = side;
        let cells = (side as u64) * (side as u64);

        pool.install(|| {
            let _ = build_district_window_layer(
                seed,
                "bench",
                &params,
                &ta,
                &rn,
                (0, 0),
                n,
                &climate,
                WindowGranularity::District,
                min_wl_m,
            );
        });

        let t0 = Instant::now();
        let layer = pool.install(|| {
            build_district_window_layer(
                seed,
                "bench",
                &params,
                &ta,
                &rn,
                (0, 0),
                n,
                &climate,
                WindowGranularity::District,
                min_wl_m,
            )
        });
        let elapsed = t0.elapsed();
        std::hint::black_box(layer.elev_q.len());

        let ms = elapsed.as_secs_f64() * 1000.0;
        let ns_per_cell = elapsed.as_secs_f64() * 1e9 / cells as f64;
        println!(
            "  side={side:>5} n={n:>5} cells={cells:>10} (1 thread): \
             {ms:>9.2} ms, {ns_per_cell:>7.1} ns/cell ({:.3} us/cell)",
            ns_per_cell / 1000.0
        );
    }
    println!();
}

/// Real-body cross-check: the same square sweep, but on the committed GJ1c
/// heightmap/TerrainAnalysis (not the synthetic gradient) and with the real
/// river network live (courses ON, window centred on real river geometry —
/// not an empty network, and not a window that happens to cull every course
/// out) — confirms the synthetic-fixture numbers above are not an artifact of
/// a trivial gradient body or an empty river network's near-zero
/// course-culling cost. Window centring follows `bench_course_cost_on_vs_off`
/// (`zoom_ladder_bench.rs`)'s exact technique: convert a real river cell to
/// world metres via the same `pixel_to_world_m`-equivalent formula, then to
/// the covering `DistrictPos`, so the window is genuinely near GJ1c's rivers
/// rather than at the arbitrary world origin (which measured courses_in_window=0
/// on a first attempt — corrected here). Run at the 330K shape only
/// (real-body I/O + full sweep would duplicate the synthetic-fixture table
/// for no new signal at the larger sizes — the per-cell RATE is what's being
/// cross-checked, not re-measuring 8.3M twice).
#[test]
#[ignore]
fn bench_square_window_production_fn_gj1c_real_body_crosscheck() {
    let (hm, ta) = gj1c_fixture();
    let dr = drainage::analyze(&hm.data, hm.width, hm.height, hm.sea_level);
    let rn = dr.river_network.clone();
    let params = BodyParams {
        hydrosphere: Some("ocean".into()),
        atmosphere: Some("breathable".into()),
        planet_class: Some("temperate".into()),
        body_radius_km: Some(6371.0),
        ..Default::default()
    };
    let climate = ClimateConstants::default();
    let seed = SeedChain::root(0xC0FFEE_u64).derive(SeedDomain::Body, 7);

    assert!(
        !rn.river_cells.is_empty(),
        "GJ1c at production working resolution must have river cells for this bench to be meaningful"
    );

    // Same centring technique as zoom_ladder_bench.rs's bench_course_cost_on_vs_off.
    let river_cell = rn.river_cells[rn.river_cells.len() / 2];
    let r_km = params.body_radius_km.unwrap();
    let world_pos = (
        river_cell.1 as f64 / ta.w as f64 * (std::f64::consts::TAU * r_km * 1000.0),
        (river_cell.0 as f64 / (ta.h - 1) as f64 - 0.5) * (std::f64::consts::PI * r_km * 1000.0),
    );
    let center: (i32, i32) = (
        (world_pos.0 / scale::DISTRICT_M as f64).floor() as i32,
        (world_pos.1 / scale::DISTRICT_M as f64).floor() as i32,
    );

    println!("\n=== T-1178 GJ1c real-body cross-check (District spacing, courses ON) ===");
    println!("  window centred at district {center:?} (river cell {river_cell:?})");
    println!("  {}\n", rayon_threads_report());

    let side = 576u32; // ~330K cells
    let n = side;
    let cells = (side as u64) * (side as u64);
    let min_wl_m = scale::DISTRICT_M as u32;

    let _ = build_district_window_layer(
        seed,
        "GJ1c",
        &params,
        &ta,
        &rn,
        center,
        n,
        &climate,
        WindowGranularity::District,
        min_wl_m,
    );

    let t0 = Instant::now();
    let layer = build_district_window_layer(
        seed,
        "GJ1c",
        &params,
        &ta,
        &rn,
        center,
        n,
        &climate,
        WindowGranularity::District,
        min_wl_m,
    );
    let elapsed = t0.elapsed();

    let ms = elapsed.as_secs_f64() * 1000.0;
    let ns_per_cell = elapsed.as_secs_f64() * 1e9 / cells as f64;
    println!(
        "  side={side} n={n} cells={cells} courses_in_window={}: \
         {ms:.2} ms, {ns_per_cell:.1} ns/cell ({:.3} us/cell)",
        layer.courses.len(),
        ns_per_cell / 1000.0
    );
    println!();
}

// ---------------------------------------------------------------------------
// T-1178 (Measurement ②) — real 16:9 rectangular canvases, replica loop.
// ---------------------------------------------------------------------------

/// Row-chunked derive over a REAL (non-square) canvas rectangle, mirroring
/// `build_district_window_layer`'s internal loop shape cell-for-cell (see
/// module doc for the explicit diff against the real function). Returns
/// (elapsed, per_cell_ns).
#[allow(clippy::too_many_arguments)]
fn rect_window_replica(
    seed: SeedChain,
    body_id: &str,
    params: &BodyParams,
    ta: &TerrainAnalysis,
    climate: &ClimateConstants,
    cols: u32,
    rows: u32,
    step_m: f64,
    min_wavelength_m: f64,
) -> (std::time::Duration, f64) {
    use rayon::prelude::*;

    let cells = (cols as u64) * (rows as u64);
    let t0 = Instant::now();

    // One Rayon task per row (matches build_district_window_layer's own
    // chunking granularity exactly — row-chunked, not per-cell).
    let row_results: Vec<u64> = (0..rows)
        .into_par_iter()
        .map(|row| {
            let mut row_acc: u64 = 0;
            for col in 0..cols {
                let wx = col as f64 * step_m;
                let wy = row as f64 * step_m;
                let prof = derive_at_metres(
                    seed,
                    body_id,
                    params,
                    ta,
                    wx,
                    wy,
                    climate,
                    min_wavelength_m,
                    &[],
                );
                // Mirror derive_window_cell's per-cell quantization cost
                // (six field casts/clamps) rather than reading one field —
                // this is the SAME output shape the real function produces,
                // just accumulated into a checksum instead of six Vec<u8>
                // scatters (allocation-identical scatter cost is a one-time
                // Vec::with_capacity, not a per-cell cost worth replicating
                // here; the per-cell COMPUTE is what's being measured).
                let morphology = prof.morphology_zone as u8;
                let elev_q = prof.elev_q.clamp(0, 100) as u8;
                let moisture_q = prof.moisture_q.clamp(0, 100) as u8;
                let vegetation = prof.vegetation_class as u8;
                let glaciation = prof.glaciation_grade as u8;
                row_acc ^= morphology as u64
                    ^ elev_q as u64
                    ^ moisture_q as u64
                    ^ vegetation as u64
                    ^ glaciation as u64;
            }
            std::hint::black_box(row_acc)
        })
        .collect();

    let checksum: u64 = row_results.into_iter().fold(0, |a, b| a ^ b);
    std::hint::black_box(checksum);

    let elapsed = t0.elapsed();
    let ns_per_cell = elapsed.as_secs_f64() * 1e9 / cells as f64;
    (elapsed, ns_per_cell)
}

/// The three named real step-canvas shapes (768x432 / 1920x1080 / 3840x2160),
/// District spacing + District cutoff, through the row-chunked replica loop.
/// This is the DIRECT answer to "does 4,096-cell par_iter throughput hold at
/// real canvas sizes" for the actual non-square shapes the workshop brief
/// names, cross-checked against the square production-fn numbers above.
#[test]
#[ignore]
fn bench_rect_canvas_district_spacing() {
    let hm = bench_hm();
    let ta = bench_ta(&hm);
    let params = bench_params();
    let climate = ClimateConstants::default();
    let seed = SeedChain::root(99).derive(SeedDomain::Body, 1);
    let min_wl_m = scale::DISTRICT_M as f64;

    println!("\n=== T-1178 real 16:9 canvas bench, replica row-chunked loop (District spacing) ===");
    println!("  {}\n", rayon_threads_report());

    let shapes: [(u32, u32, &str); 3] = [
        (768, 432, "768x432 (5x5px/gridunit fallback, ~330K)"),
        (1920, 1080, "1920x1080 (midpoint, ~2.07M)"),
        (3840, 2160, "3840x2160 (1x1 ideal, ~8.3M)"),
    ];

    for (cols, rows, label) in shapes {
        let cells = (cols as u64) * (rows as u64);
        let (elapsed, ns_per_cell) = rect_window_replica(
            seed, "bench", &params, &ta, &climate, cols, rows, min_wl_m, min_wl_m,
        );
        let ms = elapsed.as_secs_f64() * 1000.0;
        println!(
            "  {label}: cells={cells:>10} {ms:>9.2} ms warm, {ns_per_cell:>7.1} ns/cell \
             ({:.3} us/cell)",
            ns_per_cell / 1000.0
        );
    }
    println!();
}

/// Single-thread version of the same three rectangles (cutoff-matched) —
/// completes the parallel-speedup comparison for the real canvas shapes.
#[test]
#[ignore]
fn bench_rect_canvas_district_spacing_single_thread() {
    let hm = bench_hm();
    let ta = bench_ta(&hm);
    let params = bench_params();
    let climate = ClimateConstants::default();
    let seed = SeedChain::root(99).derive(SeedDomain::Body, 1);
    let min_wl_m = scale::DISTRICT_M as f64;

    println!("\n=== T-1178 real 16:9 canvas bench, SINGLE THREAD (District spacing) ===\n");

    let pool = rayon::ThreadPoolBuilder::new()
        .num_threads(1)
        .build()
        .expect("build single-thread rayon pool");

    let shapes: [(u32, u32, &str); 3] = [
        (768, 432, "768x432 (~330K)"),
        (1920, 1080, "1920x1080 (~2.07M)"),
        (3840, 2160, "3840x2160 (~8.3M)"),
    ];

    for (cols, rows, label) in shapes {
        let cells = (cols as u64) * (rows as u64);
        let (elapsed, ns_per_cell) = pool.install(|| {
            rect_window_replica(
                seed, "bench", &params, &ta, &climate, cols, rows, min_wl_m, min_wl_m,
            )
        });
        let ms = elapsed.as_secs_f64() * 1000.0;
        println!(
            "  {label}: cells={cells:>10} {ms:>9.2} ms, {ns_per_cell:>7.1} ns/cell \
             ({:.3} us/cell)",
            ns_per_cell / 1000.0
        );
    }
    println!();
}

// ---------------------------------------------------------------------------
// T-1154 (Measurement ③) — block (128 m) and tile-adjacent spacing.
// ---------------------------------------------------------------------------

/// Per-cell derive cost at Block (128 m) and Tile-adjacent (1 m, 4 m)
/// spacing, with the matching octave cutoff active — the ladder rungs
/// `atlas-zoom-ladder-t1143.md` §2 marks "not estimated". Uses the SAME
/// 64x64 = 4,096-cell sweep shape as `zoom_ladder_bench.rs`'s District/
/// Quarter sweeps so the per-cell rate is directly comparable across every
/// rung on one table.
///
/// `MIN_WL_BANDS_M` (the request-facing quantized cutoff set,
/// `layer_proxy.rs:451`) bottoms out at 1,024 m (Quarter's own band) — there
/// is NO existing wire-facing band for Block or Tile. This bench calls
/// `derive_at_metres` directly with a cutoff value no real window request can
/// carry today (same "call the underlying function, not the wire path"
/// discipline as the T-1178 benches above), matching each spacing to its OWN
/// Nyquist floor (cutoff = spacing) the same way the existing District/
/// Quarter sweeps do.
#[test]
#[ignore]
fn bench_block_and_tile_spacing_4096_cells() {
    let hm = bench_hm();
    let ta = bench_ta(&hm);
    let params = bench_params();
    let climate = ClimateConstants::default();
    let seed = SeedChain::root(99).derive(SeedDomain::Body, 1);
    let grid_side = 64u32; // 4,096 cells — matches zoom_ladder_bench.rs's shape

    println!("\n=== T-1154 block/tile-spacing derive_at_metres benchmark (4,096-cell sweep) ===");
    println!(
        "grid: {grid_side}x{grid_side} = {} cells/sweep\n",
        grid_side * grid_side
    );

    let block_m = scale::BLOCK_M as f64; // 128 m
    let tile_4m = 4.0_f64; // coarsest "tile-adjacent" spacing named in the ticket
    let tile_1m = 1.0_f64; // the literal voxel/tile spacing (D-243)

    for (label, step_m, cutoff_m) in [
        ("block (128m), cutoff=128m", block_m, block_m),
        ("tile-adjacent (4m), cutoff=4m", tile_4m, tile_4m),
        ("tile (1m), cutoff=1m", tile_1m, tile_1m),
    ] {
        let n_cells = (grid_side * grid_side) as u64;
        let t0 = Instant::now();
        for row in 0..grid_side {
            for col in 0..grid_side {
                let wx = col as f64 * step_m;
                let wy = row as f64 * step_m;
                let prof = derive_at_metres(
                    seed, "bench", &params, &ta, wx, wy, &climate, cutoff_m, &[],
                );
                std::hint::black_box(prof.elev_q);
            }
        }
        let elapsed = t0.elapsed();
        let per_cell_ns = elapsed.as_secs_f64() * 1e9 / n_cells as f64;
        println!(
            "  {label:<32}: {:>8.2} ms total, {:>7.1} ns/cell ({:.3} us/cell)",
            elapsed.as_secs_f64() * 1000.0,
            per_cell_ns,
            per_cell_ns / 1000.0
        );
    }
    println!();
}

/// The realistic deep-step canvas: at the ~10 px-per-1m-tile bottom-out on a
/// 2,160-px SMALLER axis (a 1920x1080 viewport, portrait-safe on the smaller
/// dimension per the brief's "viewport's smaller axis" convention), the
/// world extent covered is `1080 px / 10 px-per-tile = 108 tiles = 108 m` on
/// the smaller axis, `1920 / 10 = 192 m` on the larger — a 192m x 108m
/// window at 1 m spacing. Re-stated against the ticket's own worked example
/// (2160 px smaller axis, ~216m x ~384m) for the 3840x2160 canvas instead:
/// `2160/10 = 216 m` (smaller axis), `3840/10 = 384 m` (larger axis) — EXACT
/// geometry used below, matching the ticket's stated numbers precisely.
///
/// At 1 m spacing that is a 216x384 CELL grid (1 world-metre per gridunit,
/// 10 screen px per gridunit) = 82,944 cells — the ticket's "~83K cells"
/// figure, confirmed exactly (216 * 384 = 82,944).
#[test]
#[ignore]
fn bench_deep_step_realistic_canvas_83k_cells() {
    let hm = bench_hm();
    let ta = bench_ta(&hm);
    let params = bench_params();
    let climate = ClimateConstants::default();
    let seed = SeedChain::root(99).derive(SeedDomain::Body, 1);

    // Geometry: 3840x2160 canvas, 10 px per 1m tile, smaller axis 2160.
    // world extent: 216 m (smaller/rows) x 384 m (larger/cols), 1 m spacing.
    let rows = 216u32; // world metres on the smaller (2160px/10) axis
    let cols = 384u32; // world metres on the larger (3840px/10) axis
    let cells = (rows as u64) * (cols as u64);
    assert_eq!(cells, 82_944, "geometry must match the ticket's stated ~83K cells exactly");

    let step_m = 1.0_f64;
    let cutoff_m = 1.0_f64; // Nyquist-matched to 1 m spacing

    println!("\n=== T-1154 deep-step realistic-canvas bench (216m x 384m @ 1m spacing) ===");
    println!(
        "  geometry: 3840x2160 canvas @ 10px/tile, smaller axis 2160 -> 216m, larger axis 3840 -> 384m"
    );
    println!("  cells = 216 * 384 = {cells}");
    println!("  {}\n", rayon_threads_report());

    // Parallel, through the SAME row-chunked replica loop T-1178 uses (this
    // is the production par_iter SHAPE, not the exact function, for the same
    // reason as the T-1178 rectangular benches: no square-only production fn
    // covers a non-square metre-spacing window).
    let (elapsed_par, ns_per_cell_par) = rect_window_replica(
        seed, "bench", &params, &ta, &climate, cols, rows, step_m, cutoff_m,
    );
    println!(
        "  PARALLEL (row-chunked): {:.2} ms, {:.1} ns/cell ({:.3} us/cell)",
        elapsed_par.as_secs_f64() * 1000.0,
        ns_per_cell_par,
        ns_per_cell_par / 1000.0
    );

    // Single-thread comparison.
    let pool = rayon::ThreadPoolBuilder::new()
        .num_threads(1)
        .build()
        .expect("build single-thread rayon pool");
    let (elapsed_seq, ns_per_cell_seq) = pool.install(|| {
        rect_window_replica(
            seed, "bench", &params, &ta, &climate, cols, rows, step_m, cutoff_m,
        )
    });
    println!(
        "  SINGLE-THREAD:           {:.2} ms, {:.1} ns/cell ({:.3} us/cell)",
        elapsed_seq.as_secs_f64() * 1000.0,
        ns_per_cell_seq,
        ns_per_cell_seq / 1000.0
    );
    println!(
        "  speedup: {:.2}x\n",
        elapsed_seq.as_secs_f64() / elapsed_par.as_secs_f64()
    );
}

/// Cutoff sweep AT Block-spacing sample positions, varying the cutoff itself
/// from uncut (0, every octave band in `OCTAVE_WAVELENGTHS_M` [4,096..32,768]
/// AND `VOXEL_OCTAVE_WAVELENGTHS_M` [128..1,024] survives) up through
/// District-coarse (2,048m, truncates nothing extra vs. uncut — every
/// `OCTAVE_WAVELENGTHS_M` entry is still ≥2,048) to Region-coarse (204,800m,
/// truncates EVERY octave in both bands, `enveloped_fbm`'s "every octave cut"
/// empty-sum guard fires).
///
/// **Why "cutoff=128m (Block's own Nyquist floor)" shows ZERO delta vs.
/// uncut** (confirmed by direct read of `enveloped_fbm`,
/// `detail_scatter.rs:198-251`: `if wl < min_wavelength_m { skip }` — a
/// cutoff only skips octaves STRICTLY FINER than itself. At Block's own
/// floor (128m), every entry in BOTH octave arrays is `>= 128m`
/// (`VOXEL_OCTAVE_WAVELENGTHS_M`'s finest is exactly 128m, `>=` not `<`), so
/// nothing is skipped — Block sits at the bottom of the invented-detail
/// octave stack, with nothing finer left to truncate. This is a genuine,
/// verified finding (not a bench bug): **the cutoff mechanism has no
/// truncation work left to do at Block spacing or finer** — every rung from
/// Block down to Tile pays the SAME full per-cell octave-sum cost, because
/// the const octave arrays bottom out at 128m and neither
/// `MOSAIC_OCTAVE_WAVELENGTHS_M` (64/32/16/8m) nor any Tile-specific band is
/// wired into `derive_at_metres`'s call graph (see the module doc's
/// voxel_mosaic finding). The cutoff only pays off at COARSER rungs
/// (District, Quarter, Region) where it truncates the fine end of the octave
/// stack that those rungs' sample density can't resolve anyway.
#[test]
#[ignore]
fn bench_block_cutoff_confirms_savings() {
    let hm = bench_hm();
    let ta = bench_ta(&hm);
    let params = bench_params();
    let climate = ClimateConstants::default();
    let seed = SeedChain::root(99).derive(SeedDomain::Body, 1);
    let grid_side = 64u32;
    let block_m = scale::BLOCK_M as f64;
    let district_m = scale::DISTRICT_M as f64;
    let region_m = scale::REGION_M as f64;

    println!("\n=== T-1154 Block-spacing-position cutoff sweep (varying cutoff value) ===\n");

    for (label, cutoff_m) in [
        ("uncut (cutoff=0)", 0.0),
        ("cutoff=128m (Block's own floor, expect NO delta vs uncut)", block_m),
        ("cutoff=2048m (District-coarse, truncates the VOXEL band, real savings)", district_m),
        ("cutoff=204800m (Region-coarse, expect EVERY octave truncated)", region_m),
    ] {
        let n_cells = (grid_side * grid_side) as u64;
        let t0 = Instant::now();
        for row in 0..grid_side {
            for col in 0..grid_side {
                // Sample POSITIONS stay at Block spacing throughout — only the
                // cutoff VALUE varies — so this isolates the cutoff's cost
                // effect from a spacing change.
                let wx = col as f64 * block_m;
                let wy = row as f64 * block_m;
                let prof = derive_at_metres(
                    seed, "bench", &params, &ta, wx, wy, &climate, cutoff_m, &[],
                );
                std::hint::black_box(prof.elev_q);
            }
        }
        let elapsed = t0.elapsed();
        let per_cell_ns = elapsed.as_secs_f64() * 1e9 / n_cells as f64;
        println!(
            "  {label:<58}: {:>8.2} ms total, {:>7.1} ns/cell ({:.3} us/cell)",
            elapsed.as_secs_f64() * 1000.0,
            per_cell_ns,
            per_cell_ns / 1000.0
        );
    }
    println!();
}