Captioneer/scripts/smoke/desktop-smoke.sh

#!/usr/bin/env bash
# Manual desktop smoke test.
#
# Boots a headless Wayland compositor (sway) inside the captioneer-dev
# Distrobox, routes synthesized speech through a temporary PipeWire null
# sink, runs the real captioneer-desktop binary against it, and fails on
# diagnostics errors or missing captions.
#
# Usage (from the repository root, on the host):
#   ./scripts/download-models.sh        # once
#   ./scripts/distrobox/build.sh        # produce build/captioneer-desktop
#   ./scripts/smoke/desktop-smoke.sh
#
# Environment:
#   CAPTIONEER_SMOKE_MODE      vad (default) or fixed
#   CAPTIONEER_SMOKE_SPEECH_S  seconds of speech to play (default 20)
set -Eeuo pipefail

script_dir="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"
repo_root="$(cd -- "$script_dir/../.." && pwd -P)"

# ---------------------------------------------------------------------------
# Host phase: prepare the Distrobox and re-execute this script inside it.
# ---------------------------------------------------------------------------
if [[ -z "${CAPTIONEER_SMOKE_INNER:-}" && -z "${CONTAINER_ID:-}" ]]; then
  # shellcheck source=scripts/distrobox/common.sh
  source "$repo_root/scripts/distrobox/common.sh"
  prepare_distrobox

  [[ -x "$repo_root/build/captioneer-desktop" ]] \
    || die "build/captioneer-desktop is missing; run ./scripts/distrobox/build.sh first"
  [[ -d "$repo_root/models/parakeet-tdt-v2" ]] \
    || die "models/parakeet-tdt-v2 is missing; run ./scripts/download-models.sh first"
  [[ -f "$repo_root/models/silero_vad_v5.onnx" ]] \
    || die "models/silero_vad_v5.onnx is missing; run ./scripts/download-models.sh first"

  # shellcheck disable=SC2016 # Positional parameters expand inside the container.
  # shellcheck disable=SC2154 # container_name is defined by common.sh above.
  exec distrobox enter --no-workdir --name "$container_name" -- \
    bash -lc 'CAPTIONEER_SMOKE_INNER=1 exec bash "$1"' captioneer-smoke \
    "$repo_root/scripts/smoke/desktop-smoke.sh"
fi

# ---------------------------------------------------------------------------
# Inner phase: runs inside the Distrobox.
# ---------------------------------------------------------------------------
# shellcheck source=scripts/smoke/lib.sh
source "$script_dir/lib.sh"

smoke_mode="${CAPTIONEER_SMOKE_MODE:-vad}"
speech_seconds="${CAPTIONEER_SMOKE_SPEECH_S:-20}"

# On-demand smoke dependencies; kept out of common.sh so normal builds stay lean.
smoke_packages=(sway espeak-ng)
missing_packages=()
for package in "${smoke_packages[@]}"; do
  rpm -q "$package" >/dev/null 2>&1 || missing_packages+=("$package")
done
if (( ${#missing_packages[@]} > 0 )); then
  smoke_log "installing smoke dependencies: ${missing_packages[*]}"
  sudo dnf install -y "${missing_packages[@]}"
fi

cd -- "$repo_root"
workdir="$repo_root/build/smoke/$(date +%Y%m%d-%H%M%S)"
mkdir -p "$workdir/transcripts"
smoke_log "work directory: $workdir"

trap smoke_cleanup EXIT

smoke_setup_audio "$workdir"
wayland_socket="$(smoke_start_compositor "$workdir")"
smoke_log "nested compositor ready on $wayland_socket"

# ---------------------------------------------------------------------------
# Launch the desktop application.
# ---------------------------------------------------------------------------
env \
  WAYLAND_DISPLAY="$wayland_socket" \
  GDK_BACKEND=wayland \
  GSK_RENDERER=cairo \
  ./build/captioneer-desktop \
  --no-config \
  --start-captions=true \
  --output=both \
  --stderr-diagnostics=true \
  --caption-log=true \
  --caption-log-dir="$workdir/transcripts" \
  --models-dir=models \
  --mode="$smoke_mode" \
  --model-auto-restart=false \
  > "$workdir/captioneer.stdout.log" \
  2> "$workdir/captioneer.stderr.log" &
SMOKE_APP_PID=$!
smoke_log "captioneer-desktop started (pid $SMOKE_APP_PID, mode $smoke_mode)"

stderr_log="$workdir/captioneer.stderr.log"

if ! smoke_wait_for_line "$stderr_log" "Model worker ready" 60; then
  smoke_fail "model worker did not become ready within 60s"
fi
if ! smoke_wait_for_line "$stderr_log" "Capturing from:" 30; then
  smoke_fail "audio capture did not start within 30s"
fi

if (( ${#SMOKE_FAILURES[@]} == 0 )); then
  smoke_log "playing synthesized speech for ${speech_seconds}s"
  smoke_play_speech "$workdir" "$speech_seconds"
  wait "$SMOKE_PLAYER_PID" 2>/dev/null || true
  SMOKE_PLAYER_PID=""
  # Allow VAD finalization (500ms pause) and transcript flush to settle.
  sleep 4
fi

smoke_stop_app
app_exit=0
if smoke_wait_for_exit "$SMOKE_APP_PID" 20; then
  wait "$SMOKE_APP_PID" 2>/dev/null || app_exit=$?
else
  smoke_fail "application did not exit within 20s of SIGINT"
  kill -KILL "$SMOKE_APP_PID" 2>/dev/null || true
  app_exit=137
fi
SMOKE_APP_PID=""

# ---------------------------------------------------------------------------
# Assertions.
# ---------------------------------------------------------------------------
if (( app_exit == 0 )); then
  smoke_pass "clean shutdown (exit 0)"
else
  smoke_fail "application exited with status $app_exit"
fi

if grep -q "Model worker ready" "$stderr_log"; then
  smoke_pass "model worker started"
fi
if grep -q "Capturing from:" "$stderr_log"; then
  smoke_pass "audio capture attached to a monitor source"
fi

if grep -E " ERROR " "$stderr_log" > "$workdir/errors.txt"; then
  smoke_fail "diagnostics contain ERROR lines (see errors.txt)"
else
  smoke_pass "no ERROR diagnostics"
fi

mapfile -t caption_files < <(find "$workdir/transcripts" -type f -size +0c 2>/dev/null)
if (( ${#caption_files[@]} > 0 )); then
  smoke_pass "caption log contains recognized speech"
else
  smoke_fail "no captions were recognized; inspect $workdir and consider CAPTIONEER_SMOKE_MODE=fixed"
fi

# ---------------------------------------------------------------------------
# Report.
# ---------------------------------------------------------------------------
report="$workdir/report.txt"
{
  printf 'Captioneer desktop smoke report\n'
  printf 'Date:        %s\n' "$(date --rfc-3339=seconds)"
  printf 'Mode:        %s\n' "$smoke_mode"
  printf 'Compositor:  sway headless (%s)\n' "$wayland_socket"
  printf 'Sink:        %s\n' "$SMOKE_SINK_NAME"
  printf 'App exit:    %s\n' "$app_exit"
  printf '\n--- Key diagnostics ---\n'
  grep -E " (ERROR|WARNING) |Model worker ready|Capturing from:|Shutting down" \
    "$stderr_log" 2>/dev/null || printf '(none)\n'
  printf '\n--- Caption transcript excerpt ---\n'
  if (( ${#caption_files[@]} > 0 )); then
    head -n 10 "${caption_files[@]}" 2>/dev/null
  else
    printf '(empty)\n'
  fi
  printf '\n--- Result ---\n'
  if (( ${#SMOKE_FAILURES[@]} == 0 )); then
    printf 'PASS\n'
  else
    printf 'FAIL:\n'
    printf '  - %s\n' "${SMOKE_FAILURES[@]}"
  fi
} > "$report"

cat "$report"
smoke_log "full report: $report"

if (( ${#SMOKE_FAILURES[@]} > 0 )); then
  exit 1
fi
exit 0