iris/run-headless.sh

#!/bin/sh
# Run an iris example on this machine, which has no display.
#
#   ./run-headless.sh tabs [-- cargo args]
#   ./run-headless.sh tabs --shot /tmp/tabs.png --seconds 4
#   ./run-headless.sh phone --phone --dir ../app-rust --shot /tmp/p.png
#   ./run-headless.sh phone --phone --dir ../app-rust \
#       --replay ../app-rust/touch/flick-120hz.touch --shot /tmp/p.png
#
# `--dir DIR` names the workspace to build in, defaulting to `iris/` (this
# script's own directory). The app's examples -- the phone-sized transcript
# screen and everything else that is about *this product* -- live in
# `app-rust/`, 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-rust/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

here=$(cd "$(dirname "$0")" && pwd)
workdir="$here"
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 "$SWAYSOCK"
    WLR_BACKENDS=headless WLR_LIBINPUT_NO_DEVICES=1 LIBSEAT_BACKEND=noop \
        setsid sway -c "$here/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 "$replay" ] || (cd "$here" && 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 ${shot%.png}-before.png (before the gesture)" >&2
    fi
    "$here/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"