scene-actor-extraction/tests/test_track_gallery.cpp

// TRACES: UT-005 | AR-018, AR-019, AR-024, AR-026 | SR-005, SR-001
//
// Unit tests for TrackGallery (gallery/track_gallery.hpp): per-film gallery
// expansion driven by track continuity. Pure, GPU-free, model-free — exercises
// the AR-018 banded admission at both bounds, the promotion-time coherence
// gate, the diversity-buffer eviction policy, plurality ownership, and
// idempotent promotion, all through the public interface.
//
// The band is defined in PROBABILITY space (AR-024), so every case below states
// its own cosine → probability map. It has to: set_calibration is now mandatory
// and there is no header default to inherit.
//
// There used to be one — `max(0, cosine)` — and it was the reason this comment
// was originally needed. Under it the two spaces coincided, so a test that
// forgot to name the mapping still passed, and a gate that silently reverted to
// raw cosine passed with it. The default is gone rather than merely discouraged,
// which is why identity_cal below is now an explicit choice a case makes and not
// a restatement of what would have happened anyway.
#include <catch2/catch_test_macros.hpp>
#include <catch2/matchers/catch_matchers_floating_point.hpp>

#include "config.hpp"
#include "gallery/track_gallery.hpp"
#include "types.hpp"

#include <algorithm>
#include <stdexcept>
#include <array>
#include <cmath>
#include <vector>

namespace {

constexpr float kPi = 3.14159265358979323846f;

// The band as the tests drive it. Kept in one place so a change to the shipped
// defaults does not silently invalidate the arithmetic in each case.
constexpr float kBandLo = 0.90f;
constexpr float kBandHi = 0.95f;

// Identity map: probability == cosine, so a case can place an embedding at an
// exact probability. cosine_similarity is a bare dot product over unit vectors
// (types.hpp), so the placements below are bit-exact, not approximate.
float identity_cal(float c) { return c; }

// Unit-norm embedding pointing along one axis. Cosine sim to another one-hot is
// 0, to itself 1.
Embedding one_hot(int slot) {
    Embedding e{};
    e[slot] = 1.0f;
    return e;
}

// TRACES: AR-026 | SR-001
// The annex is a contiguous row-major matrix, not a vector of structs, so that
// the matcher can hand whole blocks of new rows to the GEMM path. Tests that
// want to compare one promoted view read it back through this.
Embedding annex_view(const TrackGallery& tg, int row) {
    const float* p = tg.annex_row(row);
    Embedding e{};
    std::copy(p, p + 512, e.begin());
    return e;
}

// Unit-norm embedding in the plane of axes i,j at cosine `cos_t` from axis i.
// Cosine sim to one_hot(i) is exactly cos_t.
Embedding at_sim(int i, int j, float cos_t) {
    Embedding e{};
    e[i] = cos_t;
    e[j] = std::sqrt(std::max(0.f, 1.f - cos_t * cos_t));
    return e;
}

// A spoke: shares axis 0 with every other spoke, and is otherwise unique. Any
// two DISTINCT spokes have cosine similarity exactly cos_t², so one constant
// places a whole mutually-in-band store. A spoke against itself is 1.0 — above
// the band's ceiling, i.e. redundant, which is the intended reading.
Embedding spoke(int k, float cos_t) { return at_sim(0, k, cos_t); }

// cos_t chosen so pairwise similarity between distinct spokes is 0.9197 —
// comfortably inside [0.90, 0.95], clear of both bounds.
constexpr float kSpokeCos = 0.959f;

// Two embeddings `deg` apart in the plane of axes 0,1. Cosine is cos(deg), so a
// chain of these can step through the band while its endpoints fall outside it.
Embedding on_circle(float deg) {
    Embedding e{};
    e[0] = std::cos(deg * kPi / 180.f);
    e[1] = std::sin(deg * kPi / 180.f);
    return e;
}

Config expand_cfg() {
    Config cfg;
    cfg.expand_gallery           = true;
    cfg.expand_buffer_size       = 3;
    cfg.expand_band_lo           = kBandLo;
    cfg.expand_band_hi           = kBandHi;
    cfg.expand_min_anchor_frames = 3;
    return cfg;
}

const cv::Mat kNoCrop;  // debug dumping off → crop unused

}  // namespace

TEST_CASE("disabled: no annex growth when expand_gallery is off", "[track_gallery]") {
    // expand_gallery defaults to true (see config.hpp) as of the rep4 bake-off —
    // set it explicitly false here since this test exercises the disabled path,
    // not whatever the struct's current default happens to be.
    Config cfg;
    cfg.expand_gallery = false;
    TrackGallery tg(cfg);
    REQUIRE_FALSE(tg.enabled());
    for (int f = 0; f < 10; ++f)
        tg.observe(1, one_hot(1), /*actor*/ 0, /*sim*/ 0.2f, /*accept*/ true, kNoCrop);
    CHECK(tg.annex_size() == 0);
}

// ── AR-018: the band ─────────────────────────────────────────────────────────

TEST_CASE("band bounds come from config, not a hardcoded default", "[track_gallery][AR-018]") {
    // The bounds were declared in Config and read nowhere, so the gate ran at
    // whatever the header happened to initialise. Drive them somewhere the
    // defaults are not and require the gate to follow.
    Config cfg = expand_cfg();
    cfg.expand_band_lo = 0.40f;
    cfg.expand_band_hi = 0.60f;
    TrackGallery tg(cfg);
    tg.set_calibration(identity_cal);

    tg.observe(1, one_hot(0), 0, 0.30f, true, kNoCrop);
    // P = 0.50: inside the configured band, far below the shipped default lo.
    tg.observe(1, at_sim(0, 1, 0.50f), 0, 0.30f, true, kNoCrop);
    CHECK(tg.band_rejected() == 0);

    // P = 0.92: inside the shipped default band, above the configured ceiling.
    tg.observe(1, at_sim(0, 2, 0.92f), 0, 0.30f, true, kNoCrop);
    CHECK(tg.band_rejected() == 1);
}

TEST_CASE("band admits at each bound exactly", "[track_gallery][AR-018]") {
    // The verification plan asks for the bounds themselves, not a point safely
    // inside them: an off-by-one in the comparison is invisible anywhere else.
    // Both bounds are inclusive.
    SECTION("lower bound exactly") {
        TrackGallery tg(expand_cfg());
        tg.set_calibration(identity_cal);
        tg.observe(1, one_hot(0), 0, 0.30f, true, kNoCrop);
        tg.observe(1, at_sim(0, 1, kBandLo), 0, 0.30f, true, kNoCrop);
        CHECK(tg.band_rejected() == 0);
    }
    SECTION("upper bound exactly") {
        TrackGallery tg(expand_cfg());
        tg.set_calibration(identity_cal);
        tg.observe(1, one_hot(0), 0, 0.30f, true, kNoCrop);
        tg.observe(1, at_sim(0, 1, kBandHi), 0, 0.30f, true, kNoCrop);
        CHECK(tg.band_rejected() == 0);
    }
}

TEST_CASE("store never admits below the lower bound", "[track_gallery][AR-018]") {
    // The lower bound is the poisoning guard: an embedding unlike everything
    // already on the track is evidence the track is not one person.
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    tg.observe(1, one_hot(0), 0, 0.30f, true, kNoCrop);

    tg.observe(1, at_sim(0, 1, kBandLo - 0.01f), 0, 0.30f, true, kNoCrop);
    CHECK(tg.band_rejected() == 1);

    tg.observe(1, one_hot(400), 0, 0.30f, true, kNoCrop);   // orthogonal: P = 0
    CHECK(tg.band_rejected() == 2);
}

TEST_CASE("store never admits above the upper bound", "[track_gallery][AR-018]") {
    // The upper bound is the redundancy guard: another look at a pose the store
    // already covers teaches the annex nothing and costs a slot.
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    tg.observe(1, one_hot(0), 0, 0.30f, true, kNoCrop);

    tg.observe(1, at_sim(0, 1, kBandHi + 0.01f), 0, 0.30f, true, kNoCrop);
    CHECK(tg.band_rejected() == 1);

    tg.observe(1, one_hot(0), 0, 0.30f, true, kNoCrop);     // identical: P = 1
    CHECK(tg.band_rejected() == 2);
}

TEST_CASE("band thresholds probability, not cosine", "[track_gallery][AR-018][AR-024]") {
    // The invariant's actual claim, and the one a raw-cosine gate passes by
    // accident under an identity calibration. With a calibration that shifts by
    // +0.10, two embeddings get the OPPOSITE verdict from the one their bare
    // cosines would earn — so admission here can only come from the calibrated
    // value having been used.
    TrackGallery tg(expand_cfg());
    tg.set_calibration([](float c) { return c + 0.10f; });

    tg.observe(1, one_hot(0), 0, 0.30f, true, kNoCrop);

    // cosine 0.84 (below lo, would be refused raw) → P = 0.94, inside the band.
    tg.observe(1, at_sim(0, 1, 0.84f), 0, 0.30f, true, kNoCrop);
    CHECK(tg.band_rejected() == 0);

    // cosine 0.92 (inside the band, would be admitted raw) → P = 1.02, above it.
    tg.observe(1, at_sim(0, 2, 0.92f), 0, 0.30f, true, kNoCrop);
    CHECK(tg.band_rejected() == 1);
}

TEST_CASE("a two-person track never poisons the annex", "[track_gallery][AR-018]") {
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    // Two orthogonal identities under one track ID — a track-ID collision.
    // The band refuses the outsider at the door, so the store never becomes
    // two-person in the first place.
    tg.observe(3, spoke(1, kSpokeCos), 0, 0.30f, true, kNoCrop);
    tg.observe(3, spoke(2, kSpokeCos), 0, 0.30f, true, kNoCrop);
    tg.observe(3, one_hot(400),        0, 0.30f, true, kNoCrop);  // orthogonal outlier

    CHECK(tg.band_rejected() == 1);          // refused at the door
    REQUIRE(tg.annex_size() > 0);       // the legitimate views still promote
    for (int i = 0; i < tg.annex_size(); ++i)
        CHECK(cosine_similarity(annex_view(tg, i), one_hot(400)) < 0.5f);
}

TEST_CASE("a track that drifts through the band is refused at promotion",
          "[track_gallery][AR-018]") {
    // `admit` compares a newcomer against its CLOSEST existing member, so a
    // gradual drift chains past it: each step is in-band while the endpoints are
    // strangers. This is the shape a collision takes over a slow pan, and the
    // reason the lower bound is re-asked across every pair before promotion.
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);

    tg.observe(5, on_circle(0.f),  0, 0.30f, true, kNoCrop);
    tg.observe(5, on_circle(25.f), 0, 0.30f, true, kNoCrop);   // P=0.906 vs 0°  → in band
    tg.observe(5, on_circle(50.f), 0, 0.30f, true, kNoCrop);   // P=0.906 vs 25° → in band

    CHECK(tg.band_rejected() == 0);   // every step passed the door...
    // ...but 0° and 50° are P=0.643 apart, below the floor: the whole track goes.
    CHECK(tg.annex_size() == 0);
}

// ── AR-019: ownership and promotion ──────────────────────────────────────────

TEST_CASE("confirmed track promotes its store", "[track_gallery][AR-019]") {
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    REQUIRE(tg.enabled());

    // A track owned by actor 0: every frame accepted, every view mutually
    // in-band (P = 0.9197 between distinct spokes) and gallery-far (0.30).
    for (int k = 1; k <= 3; ++k)
        tg.observe(7, spoke(k, kSpokeCos), 0, 0.30f, true, kNoCrop);

    // 3 accepted frames == min_anchor_frames → confirmed and promoted.
    CHECK(tg.annex_size() == 3);
    for (int actor : tg.annex_actors()) CHECK(actor == 0);
}

TEST_CASE("registry ownership overrides the local tally", "[track_gallery][AR-019]") {
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    // Local accepted-frame plurality says actor 5; the registry's accumulated
    // posterior says actor 9. The registry is authoritative.
    tg.set_owner(11, 9);
    for (int k = 1; k <= 3; ++k)
        tg.observe(11, spoke(k, kSpokeCos), 5, 0.30f, true, kNoCrop);
    REQUIRE(tg.annex_size() > 0);
    for (int actor : tg.annex_actors()) CHECK(actor == 9);
}

TEST_CASE("unconfirmed track (too few accepts) does not promote", "[track_gallery][AR-019]") {
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    // Only 2 accepted frames < min_anchor_frames 3; the third fills the buffer
    // but doesn't count toward ownership.
    tg.observe(4, spoke(1, kSpokeCos), 0, 0.30f, true,  kNoCrop);
    tg.observe(4, spoke(2, kSpokeCos), 0, 0.30f, true,  kNoCrop);
    tg.observe(4, spoke(3, kSpokeCos), 0, 0.30f, false, kNoCrop);
    CHECK(tg.annex_size() == 0);
}

TEST_CASE("plurality actor wins a mixed-vote track", "[track_gallery][AR-019]") {
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    // No registry attached (unit-test path): actor 5 accepted twice, actor 6
    // once → plurality is 5.
    tg.observe(8, spoke(1, kSpokeCos), 5, 0.30f, true, kNoCrop);
    tg.observe(8, spoke(2, kSpokeCos), 5, 0.30f, true, kNoCrop);
    tg.observe(8, spoke(3, kSpokeCos), 6, 0.30f, true, kNoCrop);
    REQUIRE(tg.annex_size() > 0);
    for (int actor : tg.annex_actors()) CHECK(actor == 5);
}

TEST_CASE("promotion is idempotent across a long track", "[track_gallery][AR-019]") {
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    for (int k = 1; k <= 3; ++k)
        tg.observe(9, spoke(k, kSpokeCos), 0, 0.30f, true, kNoCrop);
    const int after_confirm = tg.annex_size();
    REQUIRE(after_confirm > 0);
    // Keep feeding the confirmed track: annex must not grow again.
    for (int f = 0; f < 10; ++f)
        tg.observe(9, spoke(4 + f, kSpokeCos), 0, 0.30f, true, kNoCrop);
    CHECK(tg.annex_size() == after_confirm);
}

TEST_CASE("clear_tracks drops buffers before confirmation", "[track_gallery][AR-019]") {
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);
    // Two accepts, then a cut clears buffers; the third accept starts fresh and
    // can't reach the anchor threshold on its own.
    tg.observe(1, spoke(1, kSpokeCos), 0, 0.30f, true, kNoCrop);
    tg.observe(1, spoke(2, kSpokeCos), 0, 0.30f, true, kNoCrop);
    tg.clear_tracks();
    tg.observe(1, spoke(3, kSpokeCos), 0, 0.30f, true, kNoCrop);
    CHECK(tg.annex_size() == 0);
}

TEST_CASE("eviction keeps the gallery-far views", "[track_gallery][AR-018]") {
    // Novelty is no longer a threshold — it is this ordering. With the buffer
    // full, a more gallery-far newcomer must displace the best-recognised
    // member, and a less novel one must be dropped rather than displace a
    // better sample.
    Config cfg = expand_cfg();
    cfg.expand_buffer_size       = 2;
    cfg.expand_min_anchor_frames = 4;
    TrackGallery tg(cfg);
    tg.set_calibration(identity_cal);

    tg.observe(6, spoke(1, kSpokeCos), 0, 0.80f, true, kNoCrop);   // well recognised
    tg.observe(6, spoke(2, kSpokeCos), 0, 0.40f, true, kNoCrop);
    tg.observe(6, spoke(3, kSpokeCos), 0, 0.20f, true, kNoCrop);   // novel: evicts the 0.80
    tg.observe(6, spoke(4, kSpokeCos), 0, 0.90f, true, kNoCrop);   // least novel: dropped

    REQUIRE(tg.annex_size() == 2);
    // Survivors are the two most gallery-far views: spokes 2 and 3.
    for (int i = 0; i < tg.annex_size(); ++i) {
        const Embedding view = annex_view(tg, i);
        const bool is_2 = cosine_similarity(view, spoke(2, kSpokeCos)) > 0.99f;
        const bool is_3 = cosine_similarity(view, spoke(3, kSpokeCos)) > 0.99f;
        CHECK((is_2 || is_3));
    }
}

// TRACES: UT-005 | AR-026 | SR-001
// The annex reaches the GEMM path by being drained, not re-read: the matcher
// pushes newly promoted rows into the similarity engine once per frame. Draining
// must therefore be exactly-once — a row handed over twice becomes a duplicate
// gallery entry that quietly doubles an actor's best-of-N chances, and a row
// never handed over is a promotion that silently does nothing.
TEST_CASE("promotions drain exactly once, in matrix order",
          "[track_gallery][AR-026]") {
    TrackGallery tg(expand_cfg());
    tg.set_calibration(identity_cal);

    std::vector<float> emb;
    std::vector<int>   actor;

    CHECK(tg.drain_promotions(emb, actor) == 0);   // nothing promoted yet

    for (int k = 1; k <= 3; ++k)
        tg.observe(7, spoke(k, kSpokeCos), 0, 0.30f, true, kNoCrop);
    REQUIRE(tg.annex_size() == 3);

    const int drained = tg.drain_promotions(emb, actor);
    CHECK(drained == 3);
    CHECK(actor.size() == 3);
    CHECK(emb.size() == 3 * 512);
    for (int a : actor) CHECK(a == 0);

    // Drained rows are the annex rows, in the same order — the engine's row i
    // and flat_actor_[i] have to keep naming the same view.
    for (int i = 0; i < drained; ++i)
        for (int d = 0; d < 512; ++d)
            CHECK(emb[static_cast<size_t>(i) * 512 + d] == tg.annex_row(i)[d]);

    // Draining again yields nothing: the engine already holds these.
    CHECK(tg.drain_promotions(emb, actor) == 0);
    CHECK(actor.size() == 3);

    // A second track promotes, and only its rows are handed over.
    for (int k = 1; k <= 3; ++k)
        tg.observe(8, spoke(k, kSpokeCos), 4, 0.30f, true, kNoCrop);
    CHECK(tg.drain_promotions(emb, actor) == 3);
    CHECK(actor.size() == 6);
    CHECK(actor[5] == 4);
}

// ── AR-024: the calibration is not optional ─────────────────────────────────

/// TRACES: UT-005 | AR-024 | SR-005
TEST_CASE("a null calibration is refused, not silently replaced", "[track_gallery][AR-024]") {
    // The class used to default calibrate_ to max(0, cosine). That made
    // expand_band_lo = 0.90 mean "cosine above 0.9" here and "P(same person)
    // above 0.9" in production — two very different gates, with nothing
    // announcing which one was in force. FaceTrackerFunc already refused to
    // construct without a calibration for exactly this reason; the expansion
    // store now matches it.
    TrackGallery tg(expand_cfg());
    CHECK_THROWS_AS(tg.set_calibration(nullptr), std::invalid_argument);
}