open-standards/aac/aac-rs/third_party/moonshine-wasm/vendor.sh

#!/usr/bin/env bash
# ============================================================================
# vendor.sh — put the on-device voice runtime (Moonshine WASM) on the app's
# own site.
#
#   third_party/moonshine-wasm/vendor.sh <site-dir> [cache-dir]
#
# Writes <site-dir>/vendor/moonshine-wasm-<version>-<revision>/ (and removes
# any other vendor/moonshine-wasm-* there):
#   moonshine.mjs, moonshine.wasm   from @moonshine-ai/moonshine-wasm on npm
#   voice-worker.js                 this directory's worker (the app's own)
#   LICENSE.txt, NOTICE.txt         this directory's licence and notice
#   THIRD_PARTY/                    licences of the code linked into the wasm
#
# The app never imports these URLs directly. When someone downloads a neural
# voice, src/neural_voice.rs stores the three runtime files in the model
# store (SHA-256 checked, kept across app updates) and neural_tts.js runs
# them from there, in a worker, offline. The TypeScript layer of the npm
# package is not vendored: it downloads from Moonshine's CDN, which the app
# must never do.
#
# The version and revision come from MOONSHINE_VERSION and
# MOONSHINE_VENDOR_REV in crates/aac-web/src/neural_voice.rs, and each
# runtime file's size and SHA-256 from RUNTIME_FILES there. This script fails
# loudly on any drift: another version asked for than pinned here, an npm
# tarball that is not the pinned one, a vendored file that differs from the
# Rust pin, or a directory whose bytes differ from VENDOR_DIGEST. Changed
# bytes need a new revision, because browsers and the model store treat the
# directory's URLs as immutable.
#
# Idempotent; downloads are cached in cache-dir (default ~/.cache/aac-rs).
# ============================================================================
set -euo pipefail

HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
AAC="$(cd "$HERE/../.." && pwd)"
SITE="${1:?usage: vendor.sh <site-dir> [cache-dir]}"
CACHE="${2:-${XDG_CACHE_HOME:-$HOME/.cache}/aac-rs}"

NV="$AAC/crates/aac-web/src/neural_voice.rs"
MS_VERSION="$(sed -n 's/^pub const MOONSHINE_VERSION: &str = "\([^"]*\)";$/\1/p' "$NV")"
MS_REV="$(sed -n 's/^pub const MOONSHINE_VENDOR_REV: &str = "\([^"]*\)";$/\1/p' "$NV")"
[ -n "$MS_VERSION" ] || { echo "✗ MOONSHINE_VERSION not found in $NV" >&2; exit 1; }
[ -n "$MS_REV" ] || { echo "✗ MOONSHINE_VENDOR_REV not found in $NV" >&2; exit 1; }
DIR="moonshine-wasm-$MS_VERSION-$MS_REV"

# ─── Pins ────────────────────────────────────────────────────────────────────
# The npm release, by its registry integrity (npm view
# @moonshine-ai/[email protected] dist.integrity, read 2026-09-29).
PINNED_VERSION="0.1.5"
NPM_INTEGRITY="sha512-b90GVFkbuQQthW8wZFU/dvJpnnsISHSSxs/p6Xv/NMfaHotLhRp0e9Risy5/np6QSF3SFust3jGE3Uj2LdecmQ=="
# What vendor/$VENDOR_PINNED holds, as a sha256 over its sorted file list and
# each file's sha256. Re-pin only together with a new MOONSHINE_VENDOR_REV.
VENDOR_PINNED="moonshine-wasm-0.1.5-aac2"
VENDOR_DIGEST="a1102edb2e06645107aa8cb38c2774820f4fad3e9f76c0945ac8600ad3801537"
# Licences of the code linked into moonshine.wasm, from Moonshine's
# core/third-party/ at the commit below and ONNX Runtime's own notices at the
# version Moonshine builds (scripts/ort-build-common.sh: ORT_VERSION 1.23.2).
MS_COMMIT="234f60faa0eb388b01cdf7e60aca232af37aefda"
MS_RAW="https://raw.githubusercontent.com/moonshine-ai/moonshine/$MS_COMMIT/core/third-party"
THIRD_PARTY=(
  "onnxruntime-LICENSE.txt|$MS_RAW/onnxruntime/LICENSE.txt|2f07c72751aed99790b8a4869cf2311df85a860b22ded05fa22803587a48922c"
  "onnxruntime-ThirdPartyNotices.txt|https://raw.githubusercontent.com/microsoft/onnxruntime/v1.23.2/ThirdPartyNotices.txt|e9e90971a8e75a9a8ac0c6412e29c1202d079998389915aa485f46c816c3b4cc"
  "Eigen-COPYING.MPL2|$MS_RAW/Eigen/COPYING.MPL2|fab3dd6bdab226f1c08630b1dd917e11fcb4ec5e1e020e2c16f83a0a13863e85"
  "kaldi-native-fbank-LICENSE|$MS_RAW/kaldi-native-fbank/LICENSE|cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30"
  "kissfft-COPYING|$MS_RAW/kissfft/COPYING|a2840585f8411be8e6826a31ef15ae65c950bd74a2437a73b013398a934ad0c6"
  "nlohmann-LICENSE.MIT|$MS_RAW/nlohmann/LICENSE.MIT|86b998c792894ccb911a1cb7994f7a9652894e7a094c0b5e45be2f553f45cf14"
  "utf-8-LICENSE.txt|$MS_RAW/utf-8/LICENSE.txt|c9bff75738922193e67fa726fa225535870d2aa1059f91452c411736284ad566"
  "utf8proc-LICENSE.md|$MS_RAW/utf8proc/LICENSE.md|3b510150d34f248a221bb88e1d811238d6c6c18b51231822c42974c39bb07256"
)

[ "$MS_VERSION" = "$PINNED_VERSION" ] || {
  echo "✗ neural_voice.rs asks for Moonshine WASM $MS_VERSION, but vendor.sh is pinned to $PINNED_VERSION —" >&2
  echo "  check the new release (licence, no GPL, no network use), then re-pin PINNED_VERSION and NPM_INTEGRITY" >&2
  exit 1
}
[ "$DIR" = "$VENDOR_PINNED" ] || {
  echo "✗ neural_voice.rs asks for $DIR, but vendor.sh is pinned to $VENDOR_PINNED — vendor it, check it, and re-pin VENDOR_PINNED and VENDOR_DIGEST" >&2
  exit 1
}

sha256() { shasum -a 256 "$1" | cut -c1-64; }
fsize() { wc -c < "$1" | tr -d ' '; }

echo "▸ vendoring Moonshine WASM $MS_VERSION ($DIR)"
mkdir -p "$CACHE"

# Tell (but do not fail) when npm has a newer release to review.
LATEST="$(npm view @moonshine-ai/moonshine-wasm version 2>/dev/null || true)"
if [ -n "$LATEST" ] && [ "$LATEST" != "$MS_VERSION" ]; then
  echo "  note: npm's latest @moonshine-ai/moonshine-wasm is $LATEST (pinned: $MS_VERSION)"
fi

# npm package: fetched and checked against the pinned integrity beside the
# cache entry, then moved in whole, so an interrupted run never leaves half a
# package that looks complete.
MS_PKG="$CACHE/moonshine-wasm-$MS_VERSION/package"
if [ ! -f "$MS_PKG/package.json" ]; then
  TMP="$(mktemp -d "$CACHE/moonshine-wasm.XXXXXX")"
  (cd "$TMP" && npm pack --silent "@moonshine-ai/moonshine-wasm@$MS_VERSION" >/dev/null)
  TGZ="$(ls "$TMP"/*.tgz)"
  GOT="sha512-$(openssl dgst -sha512 -binary "$TGZ" | base64 | tr -d '\n')"
  [ "$GOT" = "$NPM_INTEGRITY" ] || {
    rm -rf "$TMP"
    echo "✗ @moonshine-ai/moonshine-wasm@$MS_VERSION from npm is not the pinned tarball (got $GOT)" >&2
    exit 1
  }
  (cd "$TMP" && tar xzf "$TGZ")
  rm -rf "$CACHE/moonshine-wasm-$MS_VERSION"
  mv "$TMP" "$CACHE/moonshine-wasm-$MS_VERSION"
fi
grep -q "\"version\": \"$MS_VERSION\"" "$MS_PKG/package.json" || { echo "✗ cached moonshine-wasm is not $MS_VERSION" >&2; exit 1; }
grep -q '"license": "MIT"' "$MS_PKG/package.json" || { echo "✗ moonshine-wasm $MS_VERSION no longer declares MIT — review it" >&2; exit 1; }

# Third-party licence texts: fetched to a temporary name and moved in only
# once their hash matches.
TP_CACHE="$CACHE/moonshine-wasm-third-party"
mkdir -p "$TP_CACHE"
for entry in "${THIRD_PARTY[@]}"; do
  IFS='|' read -r name url want <<< "$entry"
  f="$TP_CACHE/$name"
  if [ ! -f "$f" ] || [ "$(sha256 "$f")" != "$want" ]; then
    rm -f "$f"
    curl -fsSL "$url" -o "$f.tmp"
    [ "$(sha256 "$f.tmp")" = "$want" ] || { rm -f "$f.tmp"; echo "✗ $name ($url) does not match its pinned sha256" >&2; exit 1; }
    mv "$f.tmp" "$f"
  fi
done

rm -rf "$SITE"/vendor/moonshine-wasm-*
MS="$SITE/vendor/$DIR"
mkdir -p "$MS/THIRD_PARTY"
cp "$MS_PKG/dist/moonshine.mjs" "$MS_PKG/dist/moonshine.wasm" "$MS/"
cp "$HERE/voice-worker.js" "$HERE/LICENSE.txt" "$HERE/NOTICE.txt" "$MS/"
for entry in "${THIRD_PARTY[@]}"; do
  IFS='|' read -r name _ _ <<< "$entry"
  cp "$TP_CACHE/$name" "$MS/THIRD_PARTY/$name"
done

# The runtime must never reach another site. (moonshine.mjs only fetches its
# own wasm, same origin; the app hands it the bytes anyway.)
if grep -nE 'https?://' "$MS/moonshine.mjs" "$MS/voice-worker.js"; then
  echo "✗ the voice runtime names another site — review it" >&2; exit 1
fi

# Each runtime file must be exactly what neural_voice.rs pins (RUNTIME_FILES):
# the app downloads it by that size and SHA-256.
PINS="$(sed -n 's/^ *RuntimeFile { name: "\([^"]*\)", bytes: \([0-9_]*\), sha256: "\([0-9a-f]*\)" },$/\1 \2 \3/p' "$NV" | tr -d '_')"
[ "$(printf '%s\n' "$PINS" | grep -c .)" = 3 ] || { echo "✗ RUNTIME_FILES in $NV should pin 3 files" >&2; exit 1; }
while read -r name bytes want; do
  f="$MS/$name"
  [ -s "$f" ] || { echo "✗ vendored runtime is missing $name" >&2; exit 1; }
  got_bytes="$(fsize "$f")"; got="$(sha256 "$f")"
  if [ "$got_bytes" != "$bytes" ] || [ "$got" != "$want" ]; then
    echo "✗ vendor/$DIR/$name is $got_bytes bytes, sha256 $got;" >&2
    echo "  neural_voice.rs RUNTIME_FILES pins $bytes bytes, sha256 $want." >&2
    echo "  Changed bytes need a new MOONSHINE_VENDOR_REV (a new URL), then new pins there and here." >&2
    exit 1
  fi
done <<< "$PINS"

DIGEST="$(cd "$MS" && find . -type f | LC_ALL=C sort | while IFS= read -r f; do printf '%s %s\n' "$f" "$(sha256 "$f")"; done | shasum -a 256 | cut -c1-64)"
[ "$DIGEST" = "$VENDOR_DIGEST" ] || {
  echo "✗ vendor/$DIR differs from what was pinned (got $DIGEST)." >&2
  echo "  Its URLs are cached as immutable: bump MOONSHINE_VENDOR_REV in neural_voice.rs," >&2
  echo "  then set VENDOR_PINNED and VENDOR_DIGEST in $HERE/vendor.sh." >&2
  exit 1
}
echo "✓ vendor/$DIR ($(du -sh "$MS" | cut -f1))"