Organize Iris support files

scripts/headless.conf

@@ -0,0 +1,14 @@
+# The compositor `scripts/run-headless.sh` starts, because this machine has no
+# display. Nothing here is meant to be looked at directly; `grim` is.
+#
+# No Xwayland: winit talks Wayland natively, and starting an X server is a
+# second thing to go wrong for no gain. (`emu`'s config forces it because the
+# Android emulator's renderer speaks GLX.)
+xwayland disable
+
+# A desktop-shaped output, since this is the desktop half of the port. Larger
+# than the window an example opens, so nothing is scaled or clipped.
+output HEADLESS-1 mode 1920x1200@60Hz
+
+default_border none
+focus_follows_mouse no

scripts/reference/fling_spline_reference.py

@@ -0,0 +1,151 @@
+#!/usr/bin/env python3
+"""AOSP's fling spline, transcribed independently of the Rust port.
+
+This exists so the numbers in `sense.rs`'s `the_spline_matches_aosps_own_table`
+and `a_flick_decelerates_the_way_aosp_says_it_does` are not the Rust code
+grading its own homework. Every test iris's fling had before 2026-09-07
+compared the curve with itself -- monotonic, signed, integrates to the closed
+form -- and all of them passed while `distance_fraction(t)` was returning
+exactly `t` (see `android_fling_spline`'s doc comment). Numbers checked into a
+test have to come from somewhere else, and this is the somewhere else.
+
+Transcribed by hand from, and only from:
+
+  * frameworks/base `core/java/android/widget/OverScroller.java`,
+    `SplineOverScroller`'s static initialiser, `getSplineDeceleration`,
+    `getSplineFlingDistance`, `getSplineFlingDuration` and `update`.
+  * androidx.compose.animation:animation:1.12.0 `SplineBasedDecay.kt`
+    (`computeSplineInfo`, `AndroidFlingSpline.flingPosition`) and
+    `FlingCalculator.kt` (`computeDeceleration`, `flingDistance`,
+    `flingDuration`, `FlingInfo.position`/`velocity`). The two agree line for
+    line, which is why iris ports one curve rather than two.
+
+Run it with no arguments; it prints the table entries and the (velocity,
+density, t) points the Rust tests assert on.
+"""
+
+NB_SAMPLES = 100
+INFLEXION = 0.35
+START_TENSION = 0.5
+END_TENSION = 1.0
+P1 = START_TENSION * INFLEXION
+P2 = 1.0 - END_TENSION * (1.0 - INFLEXION)
+
+SCROLL_FRICTION = 0.015
+TUNING = 0.84
+GRAVITY_EARTH = 9.80665
+INCHES_PER_METER = 39.37
+
+import math
+
+DECELERATION_RATE = math.log(0.78) / math.log(0.9)
+
+
+def spline_positions():
+    """SPLINE_POSITION: distance fraction at each of 101 even time steps."""
+    position = [0.0] * (NB_SAMPLES + 1)
+    x_min = 0.0
+    for i in range(NB_SAMPLES):
+        alpha = i / NB_SAMPLES
+        x_max = 1.0
+        while True:
+            x = x_min + (x_max - x_min) / 2.0
+            coef = 3.0 * x * (1.0 - x)
+            tx = coef * ((1.0 - x) * P1 + x * P2) + x * x * x
+            if abs(tx - alpha) < 1e-5:
+                break
+            if tx > alpha:
+                x_max = x
+            else:
+                x_min = x
+        position[i] = coef * ((1.0 - x) * START_TENSION + x * END_TENSION) + x * x * x
+    position[NB_SAMPLES] = 1.0
+    return position
+
+
+POSITION = spline_positions()
+
+
+def fling_sample(t):
+    """(distance fraction, velocity fraction) at time fraction `t`."""
+    t = min(max(t, 0.0), 1.0)
+    index = int(t * NB_SAMPLES)
+    if index >= NB_SAMPLES:
+        return 1.0, 0.0
+    t_inf = index / NB_SAMPLES
+    t_sup = (index + 1) / NB_SAMPLES
+    velocity_coef = (POSITION[index + 1] - POSITION[index]) / (t_sup - t_inf)
+    return POSITION[index] + (t - t_inf) * velocity_coef, velocity_coef
+
+
+def physical_coefficient(density):
+    return GRAVITY_EARTH * INCHES_PER_METER * density * 160.0 * TUNING
+
+
+def deceleration(velocity, density):
+    return math.log(
+        INFLEXION * abs(velocity) / (SCROLL_FRICTION * physical_coefficient(density))
+    )
+
+
+def fling_distance(velocity, density):
+    l = deceleration(velocity, density)
+    return (
+        SCROLL_FRICTION
+        * physical_coefficient(density)
+        * math.exp(DECELERATION_RATE / (DECELERATION_RATE - 1.0) * l)
+    )
+
+
+def fling_duration_s(velocity, density):
+    l = deceleration(velocity, density)
+    return math.exp(l / (DECELERATION_RATE - 1.0))
+
+
+def position_at(velocity, density, t_seconds):
+    d = fling_duration_s(velocity, density)
+    return fling_distance(velocity, density) * fling_sample(t_seconds / d)[0]
+
+
+def velocity_at(velocity, density, t_seconds):
+    d = fling_duration_s(velocity, density)
+    return fling_sample(t_seconds / d)[1] * fling_distance(velocity, density) / d
+
+
+if __name__ == "__main__":
+    print("SPLINE_POSITION at a few indices (index: value)")
+    for i in (0, 1, 10, 25, 50, 75, 99, 100):
+        print(f"  {i:3}: {POSITION[i]:.6f}")
+    print()
+    print("distance/velocity fraction at time fractions")
+    for t in (0.0, 0.1, 0.25, 0.5, 0.75, 0.9, 1.0):
+        d, v = fling_sample(t)
+        print(f"  t={t:<5} distance={d:.6f} velocity={v:.6f}")
+    print()
+    # 2.55 is Iris's Pixel 9 Pro XL (docs/bench/iris-phone-v2-2026-09-06.md);
+    # 2.75 is this checkout's emulator.
+    for density in (2.55, 2.75):
+        # 15250 is `app/touch/flick-120hz.touch`'s own
+        # release velocity (velocity_reference.py), so `phone_screen.rs`
+        # can bound the fling it produces from *here* rather than from the
+        # `FlingCalculator` under test (docs/REVIEW-2026-09-07.md's T1).
+        for velocity in (5000.0, 11064.0, 15250.0):
+            dur = fling_duration_s(velocity, density)
+            print(
+                f"density={density} v={velocity}: "
+                f"distance={fling_distance(velocity, density):.3f}px "
+                f"duration={dur:.4f}s"
+            )
+            # Deliberately not round fractions. The velocity coefficient is
+            # piecewise *constant* across each of the 100 samples, so it
+            # steps at t = k/100 and a test asserting on 0.75 is asserting
+            # on which side of a discontinuity the last float landed --
+            # which is genuinely different between Python and Rust and says
+            # nothing about the curve.
+            for frac in (0.125, 0.335, 0.505, 0.755):
+                t = frac * dur
+                print(
+                    f"    t={frac:>4} of duration ({t:.4f}s): "
+                    f"pos={position_at(velocity, density, t):.3f}px "
+                    f"vel={velocity_at(velocity, density, t):.3f}px/s"
+                )

scripts/reference/velocity_reference.py

@@ -0,0 +1,288 @@
+#!/usr/bin/env python3
+"""Compose's touch velocity tracker, transcribed independently of the Rust port.
+
+Same reason `fling_spline_reference.py` exists: the numbers checked into
+`sense.rs`'s velocity tests must not be numbers the Rust produced. The old
+estimator -- total motion over the sample span, an average -- passed every test
+it had, because every one of those tests asserted the average's own definition
+back at it. An average cannot tell an accelerating flick from a steady drag, and
+that is exactly what Iris reported from the phone on 2026-09-07: "flinging now
+actually works but is slower than Compose's immediately after releasing the
+flick".
+
+Transcribed by hand from, and only from, the `-sources.jar` of
+**androidx.compose.ui:ui-android:1.12.0** and
+**androidx.compose.foundation:foundation-android:1.12.0**
+(dl.google.com/dl/android/maven2), read 2026-09-07:
+
+  * `androidx/compose/ui/input/pointer/util/VelocityTracker.kt` --
+    `VelocityTracker1D.calculateVelocity`, `polyFitLeastSquares`,
+    `calculateImpulseVelocity`, `kineticEnergyToVelocity`, and the constants
+    `HistorySize = 20`, `HorizonMilliseconds = 100`,
+    `AssumePointerMoveStoppedMilliseconds = 40`.
+  * `androidx/compose/ui/input/pointer/util/PlatformVelocityTracker.kt` --
+    `Lsq2VelocityTracker`, which is what the 2D `VelocityTracker` delegates to.
+  * `androidx/compose/ui/input/pointer/util/PlatformVelocityTracker.android.kt`
+    -- the `AndroidComposeUiFlags.isFrameworkVelocityTrackerEnabled` fork.
+  * `androidx/compose/ui/AndroidComposeUiFlags.android.kt` -- that flag's
+    default, which is `false`.
+  * `androidx/compose/foundation/gestures/Draggable.kt` -- `sendDragStart` /
+    `sendDragEvent` / `sendDragStopped`, i.e. *which* samples a touch drag
+    feeds the tracker and where the maximum-velocity clamp is applied.
+  * `androidx/compose/foundation/gestures/DifferentialVelocityTracker.kt` and
+    `NonTouchScrollingLogic.kt` -- the Impulse strategy's only caller.
+  * `androidx/compose/foundation/gestures/Scrollable.kt` --
+    `DefaultFlingBehavior.performFling`, for the minimum-velocity question.
+
+**Which strategy a touch fling actually uses, since this was the surprise.**
+`Strategy.Impulse` is *not* it. `scrollable`/`draggable` release through
+`DragGestureNode.sendDragStopped`, which calls the 2D `VelocityTracker`; on
+Android that is `Lsq2VelocityTracker` (the framework-tracker flag defaults to
+false), which is two `VelocityTracker1D(strategy = Lsq2)` -- a degree-2
+least-squares fit over **absolute positions**, whose velocity is the fitted
+polynomial's derivative at the newest sample. Impulse is reached only through
+`DifferentialVelocityTracker`, whose sole caller is `NonTouchScrollingLogic`:
+mouse wheel and trackpad, never a finger. So this script transcribes Lsq2 and
+iris ports Lsq2. `calculate_impulse_velocity` is here anyway, unused by the
+printed points, because ruling it out by reading is cheaper than ruling it out
+again next time somebody remembers "Compose uses impulse".
+
+**Which samples a touch drag feeds it.** `sendDragStart` adds the DOWN change;
+every subsequent MOVE, historical samples included, is added by `sendDragEvent`.
+The **UP position is never added**: `Lsq2VelocityTracker.addPointerInputChange`
+wraps its two `addPosition` calls in `if (!event.changedToUpIgnoreConsumed())`,
+and all the UP branch does is reset the tracker when more than 40ms have passed
+since the last MOVE (b/238654963). So a finger that stops before lifting reads
+as a stop, not as a decelerating tail. Positions are the raw event positions,
+so the touch slop is inside the motion the tracker sees even though the list
+never scrolled by it.
+
+Two of Compose's samples iris does *not* reproduce, both noted rather than
+copied: pre-slop MOVEs (iris's `DragArbiter` is `Undecided` then too, so it
+feeds none either -- these agree), and the single MOVE that *crosses* the slop,
+which Compose drops because `sendDragStart` adds only the DOWN. iris feeds that
+one, since it is a real measured position and dropping it would be copying a
+quirk of where Compose happens to split its state machine.
+
+**The clamps.** Maximum: `sendDragStopped` passes
+`LocalViewConfiguration.maximumFlingVelocity`, which on Android is
+`ViewConfiguration.getScaledMaximumFlingVelocity()` -- 8000 dp/s. Minimum:
+there is **none** on this path. `ViewConfiguration.minimumFlingVelocity`
+exists in Compose's `ViewConfiguration` interface but its only use in either
+artifact is `NestedScrollInteropConnection`, for View interop.
+`DefaultFlingBehavior.performFling` guards with `abs(initialVelocity) > 1f`
+and says why in its own comment: "we need it since spline curve gives us
+NaNs". 1 px/s, not 50 dp/s.
+
+Run it with no arguments; it prints the sample sets and the velocities the
+Rust tests assert on.
+"""
+
+import math
+
+HISTORY_SIZE = 20
+HORIZON_MILLISECONDS = 100.0
+ASSUME_POINTER_MOVE_STOPPED_MILLISECONDS = 40.0
+MIN_SAMPLE_SIZE_LSQ2 = 3
+
+MAXIMUM_FLING_VELOCITY_DP_S = 8000.0
+# DefaultFlingBehavior.performFling's own threshold, in the units of the
+# positions fed to the tracker -- pixels per second here.
+FLING_MINIMUM_PX_S = 1.0
+
+
+def poly_fit_least_squares(x, y, sample_count, degree):
+    """`polyFitLeastSquares`: Gram-Schmidt QR, coefficients low order first."""
+    if degree < 1:
+        raise ValueError("The degree must be at positive integer")
+    if sample_count == 0:
+        raise ValueError("At least one point must be provided")
+
+    truncated_degree = sample_count - 1 if degree >= sample_count else degree
+    m = sample_count
+    n = truncated_degree + 1
+
+    a = [[0.0] * m for _ in range(n)]
+    for h in range(m):
+        a[0][h] = 1.0
+        for i in range(1, n):
+            a[i][h] = a[i - 1][h] * x[h]
+
+    q = [[0.0] * m for _ in range(n)]
+    r = [[0.0] * n for _ in range(n)]
+    for j in range(n):
+        w = q[j]
+        w[:] = a[j][:m]
+        for i in range(j):
+            z = q[i]
+            dot = sum(w[h] * z[h] for h in range(m))
+            for h in range(m):
+                w[h] -= dot * z[h]
+        norm = math.sqrt(sum(v * v for v in w))
+        inverse_norm = 1.0 / max(norm, 1e-6)
+        for h in range(m):
+            w[h] *= inverse_norm
+        for i in range(n):
+            r[j][i] = 0.0 if i < j else sum(w[h] * a[i][h] for h in range(m))
+
+    coefficients = [0.0] * n
+    for i in range(n - 1, -1, -1):
+        c = sum(q[i][h] * y[h] for h in range(m))
+        for j in range(n - 1, i, -1):
+            c -= r[i][j] * coefficients[j]
+        coefficients[i] = c / r[i][i]
+    return coefficients
+
+
+def kinetic_energy_to_velocity(kinetic_energy):
+    sign = 0.0 if kinetic_energy == 0.0 else math.copysign(1.0, kinetic_energy)
+    return sign * math.sqrt(2 * abs(kinetic_energy))
+
+
+def calculate_impulse_velocity(data_points, time, sample_count, is_data_differential):
+    """`calculateImpulseVelocity` -- not on the touch path; see the module doc."""
+    work = 0.0
+    start = sample_count - 1
+    next_time = time[start]
+    for i in range(start, 0, -1):
+        current_time = next_time
+        next_time = time[i - 1]
+        if current_time == next_time:
+            continue
+        if is_data_differential:
+            delta = -data_points[i - 1]
+        else:
+            delta = data_points[i] - data_points[i - 1]
+        v_curr = delta / (current_time - next_time)
+        v_prev = kinetic_energy_to_velocity(work)
+        work += (v_curr - v_prev) * abs(v_curr)
+        if i == start:
+            work = work * 0.5
+    return kinetic_energy_to_velocity(work)
+
+
+def calculate_velocity(samples):
+    """`VelocityTracker1D.calculateVelocity` with `Strategy.Lsq2`.
+
+    `samples` is `(time_millis, position)` oldest first, at most the last
+    `HISTORY_SIZE` of which the circular buffer would still be holding.
+    Returns units per second.
+    """
+    held = samples[-HISTORY_SIZE:]
+    if not held:
+        return 0.0
+
+    data_points = []
+    time = []
+    newest_time, _ = held[-1]
+    previous_time = newest_time
+    for sample_time, sample_position in reversed(held):
+        age = float(newest_time - sample_time)
+        delta = abs(float(sample_time - previous_time))
+        # Lsq2 walks back sample to sample; only the non-differential
+        # Impulse branch compares every sample against the newest one.
+        previous_time = sample_time
+        if age > HORIZON_MILLISECONDS or delta > ASSUME_POINTER_MOVE_STOPPED_MILLISECONDS:
+            break
+        data_points.append(sample_position)
+        time.append(-age)
+        if len(data_points) == HISTORY_SIZE:
+            break
+
+    if len(data_points) < MIN_SAMPLE_SIZE_LSQ2:
+        return 0.0
+    try:
+        coefficients = poly_fit_least_squares(time, data_points, len(data_points), 2)
+    except ValueError:
+        return 0.0
+    # The 2nd coefficient is the fitted polynomial's derivative at x = 0,
+    # which is the newest sample's timestamp. units/ms -> units/s.
+    return coefficients[1] * 1000.0
+
+
+def clamped(velocity, maximum):
+    """`VelocityTracker1D.calculateVelocity(maximumVelocity)`."""
+    if velocity == 0.0 or math.isnan(velocity):
+        return 0.0
+    return min(velocity, maximum) if velocity > 0 else max(velocity, -maximum)
+
+
+def average(samples):
+    """The estimator being replaced: total motion over the span."""
+    if len(samples) < 2:
+        return 0.0
+    span = (samples[-1][0] - samples[0][0]) / 1000.0
+    if span <= 0.0:
+        return 0.0
+    return (samples[-1][1] - samples[0][1]) / span
+
+
+
+# 1. `app/touch/flick-120hz.touch`, as `DragGesture` feeds it:
+#    the DOWN position, then one position per MOVE. The UP at t=20 adds no
+#    sample (see the module doc), which is why the finger sitting still for its
+#    last 4ms does not drag the estimate down. y only; the flick is vertical.
+FLICK_120HZ = [(0, 1000.0), (4, 1040.0), (8, 1086.0), (12, 1138.0), (16, 1196.0)]
+
+# 2. A steady drag: 5px every 10ms for 100ms. A constant-velocity fit and an
+#    average must agree here -- this is the case that cannot tell the two
+#    estimators apart, which is why it is not the only one.
+STEADY_DRAG = [(i * 10, float(i * 5)) for i in range(11)]
+
+# 3. A flick that accelerates into the release: 10ms apart, deltas doubling.
+#    This is the case the average gets wrong, and the negative control for
+#    the port -- reverting to the average must fail this test and only this
+#    kind of test.
+ACCELERATING_FLICK = [(0, 0.0), (10, 2.0), (20, 6.0), (30, 14.0), (40, 30.0), (50, 54.0)]
+
+# 4. The two edges of the sample walk, checked here so the Rust asserts
+#    Compose's answer rather than iris's own reading of the rule.
+#    (a) An old, fast burst outside the 100ms horizon, then a slow steady
+#        drag: the burst must not leak into the estimate.
+OLD_BURST_THEN_STEADY = [(0, 0.0)] + [(10 + i * 10, 1000.0 + i) for i in range(11)]
+STOPPED_BEFORE_RELEASE = [(0, 0.0), (4, 40.0), (8, 90.0), (12, 150.0), (60, 152.0)]
+
+TWO_MOVE_FRAMES = [(0, 0.0), (8, 100.0), (16, 220.0)]
+#    ... and one move frame, which Compose cannot fit either.
+ONE_MOVE_FRAME = [(0, 0.0), (8, 100.0)]
+
+PHONE_DENSITY = 2.55
+
+
+def report(name, samples):
+    v = calculate_velocity(samples)
+    print(f"{name}:")
+    print(f"  samples (t_ms, position): {samples}")
+    print(f"  Lsq2 (Compose's touch path):    {v:.4f} px/s")
+    print(f"  average (the old estimator):    {average(samples):.4f} px/s")
+    print(f"  impulse (non-touch, for ref):   ", end="")
+    held = list(reversed(samples[-HISTORY_SIZE:]))
+    newest = held[0][0]
+    print(
+        f"{calculate_impulse_velocity([p for _, p in held], [-(newest - t) for t, _ in held], len(held), False) * 1000.0:.4f} px/s"
+    )
+    print()
+
+
+if __name__ == "__main__":
+    print("Compose 1.12.0 touch velocity: VelocityTracker1D, Strategy.Lsq2,")
+    print("non-differential (positions), HistorySize=20, Horizon=100ms,")
+    print("AssumePointerMoveStopped=40ms, minSampleSize=3.\n")
+    report("flick-120hz.touch", FLICK_120HZ)
+    report("steady drag (5px/10ms)", STEADY_DRAG)
+    report("accelerating flick (deltas 2,4,8,16,24 per 10ms)", ACCELERATING_FLICK)
+
+    report("old burst then steady 1px/10ms", OLD_BURST_THEN_STEADY)
+    report("stopped 48ms before release", STOPPED_BEFORE_RELEASE)
+    report("press and two move frames", TWO_MOVE_FRAMES)
+    report("press and one move frame", ONE_MOVE_FRAME)
+
+    print("Clamps:")
+    print(f"  maximum: {MAXIMUM_FLING_VELOCITY_DP_S} dp/s")
+    print(
+        f"           = {MAXIMUM_FLING_VELOCITY_DP_S * PHONE_DENSITY:.1f} px/s at the phone's density {PHONE_DENSITY}"
+    )
+    print(f"  minimum: none on the fling path; DefaultFlingBehavior skips |v| <= {FLING_MINIMUM_PX_S} px/s")
+    print()
+    print("Two samples only (a press and one move, the phone's 120Hz worst case):")
+    print(f"  Lsq2 needs 3 and answers {calculate_velocity(FLICK_120HZ[:2]):.4f} px/s")

scripts/report_to_touch.py

@@ -0,0 +1,94 @@
+#!/usr/bin/env python3
+"""Turns `iris::input` debug lines -- from a phone's diagnostics report, or
+from a report the layer-1 harness produced with tracing on
+(`iris::diagnostics::set_trace(true)`) -- back into a `TouchScript` file
+`iris::harness::Harness::replay` can play back at layer 1.
+
+Why this exists: `docs/RUST.md`'s "Three test layers" box says the cheapest
+layer that can answer a question wins, and a gesture that misbehaves on
+Iris's phone is otherwise only describable in words. `iris::sense::
+log_input_event`'s one line per platform event (Android's on_touch_event
+once per `MotionEvent`, with historical samples inline; winit's once per
+pointer `WindowEvent`; the harness's `touch`, once per script line) already
+carries everything a `.touch` file's `t_ms action x y` needs -- this just
+reads it back out and reconstructs the samples in order, expanding each
+event's inline historical samples into their own `move` lines first (they
+are always intermediate positions of a move, and Android documents them as
+oldest first, which is also the order they appear in the line).
+
+Usage:
+    report_to_touch.py < report.txt > replay.touch
+    report_to_touch.py report.txt > replay.touch
+
+Only lines containing "iris input: action=..." are read; everything else in
+the report (insets, frame timings, drag-release summaries) is ignored, so
+this can be pointed at Copy report's whole clipboard text directly.
+"""
+
+import re
+import sys
+
+# The message half of `sense::log_input_event`'s format string, prefix-
+# agnostic: a real report line also carries the ring's own
+# `HH:MM:SS.mmm LEVEL target:` header (`LogLine::format`) or, forwarded
+# through `ai_server::client_log`, a `[<source> <clock> #<seq>]` tag ahead
+# of that -- neither of which this needs to understand, since `search`
+# (not `match`) finds the marker wherever it starts.
+LINE_RE = re.compile(
+    r"iris input: action=(?P<action>\w+) x=(?P<x>-?[0-9.]+) y=(?P<y>-?[0-9.]+) "
+    r"t=(?P<t>[0-9]+)ms history=(?P<hist>[0-9]+)(?P<rest>.*)$"
+)
+HIST_RE = re.compile(r"(?P<t>[0-9]+):(?P<x>-?[0-9.]+),(?P<y>-?[0-9.]+)")
+
+
+def _fmt(value: float) -> str:
+    """The number as `TouchScript::parse`'s own `f32::parse` would round-trip
+    it -- an integer without a trailing `.0` where the source was one
+    (every coordinate here is a physical pixel), `{:g}` otherwise so a
+    fractional value from a real device is not silently truncated."""
+    if value == int(value):
+        return str(int(value))
+    return f"{value:g}"
+
+
+def convert(lines):
+    """Every `iris::input` line, oldest first, expanded to one `(t_ms,
+    action, x, y)` tuple per touch sample -- a historical sample is always
+    an intermediate `move`, and the event's own sample keeps its real
+    action (`down`/`move`/`up`/`cancel`)."""
+    rows = []
+    for line in lines:
+        m = LINE_RE.search(line)
+        if not m:
+            continue
+        hist_count = int(m.group("hist"))
+        hist_matches = list(HIST_RE.finditer(m.group("rest")))
+        if len(hist_matches) != hist_count:
+            print(
+                f"report_to_touch: {line.strip()!r} says history={hist_count} but "
+                f"holds {len(hist_matches)} samples -- skipped",
+                file=sys.stderr,
+            )
+            continue
+        for hm in hist_matches:
+            rows.append(
+                (int(hm.group("t")), "move", float(hm.group("x")), float(hm.group("y")))
+            )
+        rows.append(
+            (int(m.group("t")), m.group("action"), float(m.group("x")), float(m.group("y")))
+        )
+    return rows
+
+
+def main():
+    if len(sys.argv) > 2:
+        print("usage: report_to_touch.py [report.txt] < report.txt", file=sys.stderr)
+        return 2
+    text = open(sys.argv[1]) if len(sys.argv) == 2 else sys.stdin
+    for t_ms, action, x, y in convert(text):
+        print(f"{t_ms} {action} {_fmt(x)} {_fmt(y)}")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/run-bench.sh

@@ -0,0 +1,25 @@
+#!/bin/sh
+# Runs iris's on-demand benchmark suite.
+# Never run by `cargo test`; run this by hand or before/after a layout
+# change. Always release -- see AGENTS.md's own rule against reading a
+# frame time from a debug build.
+#
+#   ./scripts/run-bench.sh            # everything
+#   ./scripts/run-bench.sh list       # just the CPU-only message-list scenarios
+#   ./scripts/run-bench.sh images     # just the GPU bind-group-creation scenario
+set -eu
+scripts=$(cd "$(dirname "$0")" && pwd)
+root=$(cd "$scripts/.." && pwd)
+cd "$root"
+
+what="${1:-all}"
+
+if [ "$what" = "all" ] || [ "$what" = "list" ]; then
+    echo "=== message_list (CPU-only, no window) ==="
+    cargo bench --bench message_list
+fi
+
+if [ "$what" = "all" ] || [ "$what" = "images" ]; then
+    echo "=== bench_images (real wgpu device, via run-headless.sh) ==="
+    timeout 60 "$scripts/run-headless.sh" bench_images --seconds 4 2>&1 | grep "^BENCH_IMAGES"
+fi

scripts/run-headless.sh

@@ -0,0 +1,198 @@
+#!/bin/sh
+# Run an iris example on this machine, which has no display.
+#
+#   ./scripts/run-headless.sh tabs [-- cargo args]
+#   ./scripts/run-headless.sh tabs --shot /tmp/tabs.png --seconds 4
+#   ./scripts/run-headless.sh phone --phone --dir ../app --shot /tmp/p.png
+#   ./scripts/run-headless.sh phone --phone --dir ../app \
+#       --replay ../app/touch/flick-120hz.touch --shot /tmp/p.png
+#
+# `--dir DIR` names the workspace to build in, defaulting to `iris/`. The
+# app's examples -- the phone-sized transcript
+# screen and everything else that is about *this product* -- live in
+# `app/`, which is a workspace of its own; `replay-touch` is still
+# built from iris, since it is part of the rig rather than of either app.
+#
+# `--phone` is layer 2 of docs/RUST.md's "Three test layers": the output
+# and the window take Iris's phone's own size and density (1080x2424 at
+# `content_scale` 2.55, from docs/bench/iris-phone-v2-2026-09-06.md,
+# carried in `ai_app::ui::fixture::PHONE_*`), and `IRIS_SCALE` hands that
+# density to iris the way `DisplayMetrics.density` does on Android
+# (`iris::desktop::content_scale`). So a screenshot from here and one
+# from the phone are the same layout at the same density, and what
+# differs is only the renderer. Without it the output stays desktop-
+# shaped, which is what every other example wants.
+#
+# `--replay FILE` drives one of the `.touch` recordings the headless
+# tests use (`app/touch/`) into the window through
+# `rig-input`'s `replay-touch` -- one recording, both layers. With
+# `--shot` it also writes `<shot>-before.png` from just before the
+# gesture, since "the list moved" is a claim about two pictures.
+#
+# `--bin` runs a real crate binary instead of an example (E4's
+# `ai-app-desktop`, which is a window a person runs, not a demo) --
+# `cargo build --bin NAME` instead of `--example NAME`, and
+# `target/debug/NAME` instead of `target/debug/examples/NAME`. Its own
+# argv (the CLI flags a real binary takes, as opposed to `cargo build`'s
+# own flags after `--`) comes through `$RUN_HEADLESS_ARGS`, word-split on
+# purpose -- an example never needed one, so there was nowhere to plumb it
+# through positionally without disturbing the existing `-- cargo args`
+# convention above.
+#
+# The VM has a real GPU and no display (the `this-machine-graphics` skill
+# says what it is and how it fails), so what is missing here is only a
+# compositor to give winit a surface. So: a headless sway, the same trick
+# `emu` uses for the Android emulator, and `grim` to see the result.
+#
+# It is deliberately *not* `emu`'s compositor. sway tiles, so adding a window
+# to the one an emulator is sitting in resizes that emulator's window, and a
+# peer session's `emu up` could join at any moment. This one has its own
+# socket and its own runtime directory and goes away with the machine.
+set -eu
+
+scripts=$(cd "$(dirname "$0")" && pwd)
+root=$(cd "$scripts/.." && pwd)
+workdir="$root"
+cd "$root"
+run="${XDG_RUNTIME_DIR:-/tmp}/iris-headless"
+seconds=3
+shot=""
+replay=""
+example=""
+kind=example
+phone=no
+
+# The phone Iris runs the bench on. Not typed from memory: these are
+# `ai_app::ui::fixture::PHONE_WIDTH`/`PHONE_HEIGHT`/`PHONE_SCALE`, which
+# in turn come from her own reports -- keep the three in step.
+PHONE_MODE=1080x2424@120Hz
+PHONE_SCALE=2.55
+DESKTOP_MODE=1920x1200@60Hz
+
+while [ $# -gt 0 ]; do
+    case "$1" in
+        --shot) shot=$2; shift 2 ;;
+        --seconds) seconds=$2; shift 2 ;;
+        --bin) kind=bin; shift ;;
+        --phone) phone=yes; shift ;;
+        --replay) replay=$2; shift 2 ;;
+        --dir) workdir=$(cd "$2" && pwd); shift 2 ;;
+        --) shift; break ;;
+        *) example=$1; shift ;;
+    esac
+done
+[ -n "$example" ] || { echo "usage: $0 NAME [--bin] [--phone] [--dir DIR] [--replay TOUCH] [--shot PNG] [--seconds N] [-- cargo args]" >&2; exit 2; }
+[ -z "$replay" ] || [ -f "$replay" ] || { echo "run-headless: no touch script at $replay" >&2; exit 2; }
+
+mkdir -p "$run"
+export SWAYSOCK="$run/sway.sock"
+
+# Named rather than left to sway's pid-based default, so a second run reuses
+# this compositor instead of starting another beside it.
+if ! swaymsg -t get_version >/dev/null 2>&1; then
+    rm -f "$SWAYSOCK"
+    WLR_BACKENDS=headless WLR_LIBINPUT_NO_DEVICES=1 LIBSEAT_BACKEND=noop \
+        setsid sway -c "$scripts/headless.conf" >"$run/sway.log" 2>&1 &
+    i=0
+    while [ $i -lt 20 ]; do
+        swaymsg -t get_version >/dev/null 2>&1 && break
+        i=$((i + 1)); sleep 0.5
+    done
+    swaymsg -t get_version >/dev/null 2>&1 || {
+        echo "run-headless: compositor did not start; see $run/sway.log" >&2
+        exit 1
+    }
+fi
+
+rm -f "$run/display"
+swaymsg exec -- "sh -c 'printf %s \"\$WAYLAND_DISPLAY\" > $run/display'" >/dev/null
+i=0
+while [ $i -lt 20 ]; do
+    [ -s "$run/display" ] && break
+    i=$((i + 1)); sleep 0.5
+done
+[ -s "$run/display" ] || { echo "run-headless: could not read WAYLAND_DISPLAY" >&2; exit 1; }
+WAYLAND_DISPLAY=$(cat "$run/display")
+export WAYLAND_DISPLAY
+
+echo "run-headless: $WAYLAND_DISPLAY (sway $(swaymsg -t get_version --raw | sed -n 's/.*"human_readable":"\([^"]*\)".*/\1/p'))" >&2
+
+# Set every run rather than only when it changes: this compositor is
+# reused across runs (see the socket comment above), so a desktop-shaped
+# run after a phone-shaped one would otherwise inherit the phone's output
+# and silently screenshot the wrong size.
+if [ "$phone" = yes ]; then
+    mode=$PHONE_MODE
+    export IRIS_SCALE="$PHONE_SCALE"
+    echo "run-headless: phone-shaped output $PHONE_MODE at IRIS_SCALE=$PHONE_SCALE" >&2
+else
+    mode=$DESKTOP_MODE
+fi
+swaymsg output HEADLESS-1 mode "$mode" >/dev/null
+# The extent `replay-touch` positions against, so a script's coordinates
+# are the output's own pixels.
+out_w=${mode%x*}
+out_h=${mode#*x}; out_h=${out_h%@*}
+
+# Built before the app starts, so a compile error is not reported as a
+# window that failed to move.
+[ -z "$replay" ] || (cd "$root" && cargo build --bin replay-touch -p rig-input) >&2
+
+cd "$workdir"
+if [ "$kind" = bin ]; then
+    cargo build --bin "$example" "$@" >&2
+    bin="$workdir/target/debug/$example"
+else
+    cargo build --example "$example" "$@" >&2
+    bin="$workdir/target/debug/examples/$example"
+fi
+
+# shellcheck disable=SC2086 -- deliberately word-split: this is the
+# binary's own argv, not a single path.
+"$bin" ${RUN_HEADLESS_ARGS:-} >"$run/$example.log" 2>&1 &
+pid=$!
+trap 'kill "$pid" 2>/dev/null || true' EXIT INT TERM
+
+# Wait for the window to be mapped rather than for a number of seconds. A
+# fixed sleep took an all-black screenshot the first time this ran, when sway
+# had started in the same invocation and had not composited its output yet --
+# which is indistinguishable from an app that draws nothing.
+i=0
+while [ $i -lt 40 ]; do
+    kill -0 "$pid" 2>/dev/null || break
+    swaymsg -t get_tree --raw 2>/dev/null | grep -q "\"pid\":$pid," && break
+    i=$((i + 1)); sleep 0.25
+done
+
+i=0
+while [ $i -lt "$((seconds * 2))" ]; do
+    kill -0 "$pid" 2>/dev/null || break
+    i=$((i + 1)); sleep 0.5
+done
+
+if [ -n "$replay" ] && kill -0 "$pid" 2>/dev/null; then
+    if [ -n "$shot" ]; then
+        grim "${shot%.png}-before.png"
+        echo "run-headless: wrote ${shot%.png}-before.png (before the gesture)" >&2
+    fi
+    "$root/target/debug/replay-touch" "$out_w" "$out_h" "$replay"
+    # A fling outlives the finger: the gesture's own last sample is not
+    # when the list stops. Long enough for Android's spline to settle
+    # (`FlingCalculator::duration` tops out around a second and a half).
+    sleep 2
+fi
+
+if kill -0 "$pid" 2>/dev/null; then
+    [ -n "$shot" ] && grim "$shot" && echo "run-headless: wrote $shot" >&2
+    kill "$pid" 2>/dev/null || true
+    wait "$pid" 2>/dev/null || true
+    status=0
+else
+    wait "$pid" 2>/dev/null || status=$?
+    echo "run-headless: $example exited early (status ${status:-0})" >&2
+    status=${status:-1}
+fi
+
+echo "--- $example output ---" >&2
+cat "$run/$example.log" >&2
+exit "$status"