#!/usr/bin/env bash
# Download the frank-tts-engine payload: the two GGUF files the arm A engine
# (qwentts.cpp `tts-server`, dankclaw/voiceservice/Containerfile.engine) loads
# once at startup — Serveurperso/Qwen3-TTS-GGUF's **1.7 B base talker at
# Q4_K_M** and the **12 Hz tokenizer at Q8_0**. Public repo — no auth header,
# and never a token on the command line (world-readable in /proc/<pid>/cmdline).
#
# THE BASE VARIANT IS MANDATORY, NOT A PREFERENCE. The engine refuses every
# voice registration unless the loaded model reports type "base"
# (tools/tts-server.cpp, register_voice): on a customvoice or voicedesign talker
# the cloned-voice product does not exist. The 0.6 B talker (628,905,056 B for
# its Q4_K_M) also exists and is NOT the decided artifact — 1.7 B is what live
# output was measured with on 2026-10-18.
#
# Fresh downloads, no resume (the same rule the frank-zealot fetcher learned the
# hard way: `curl -C -` once produced an oversized file on a multi-GB payload);
# -f/--fail-with-body so an HTTP error is never a success; then exact byte count
# and sha256 against the Hub's own LFS oid. This repo IS LFS, so the sha values
# below are the pointer oids the Hub publishes — verified at fetch, not
# computed locally. Idempotent: a complete, correctly-hashed file is skipped,
# and `--verify-only` reports without downloading (that is the mode the deployer
# and the runbook use to answer "are the weights there?").
#
# Both files together are 1.4 GiB and the engine mmaps them: peak RSS measured
# 5.7 GiB with both resident. Nothing here is deleted on a swap — the previous
# talker stays on disk, because the rollback for a bad engine build is to point
# QWENTTS_MODEL at a different file, not to re-download 1.4 GiB under pressure.
#
# Usage:
#   scripts/download-frank-tts-engine-qwentts.sh [DEST_DIR] [--verify-only]
# Default DEST_DIR is the host directory the frank-tts-engine unit mounts
# read-only at /models.
set -euo pipefail

DEST=""
VERIFY_ONLY=0
for arg in "$@"; do
    case "$arg" in
        --verify-only) VERIFY_ONLY=1 ;;
        *) DEST="$arg" ;;
    esac
done
DEST="${DEST:-/home/dank/models/Qwen3-TTS-GGUF}"

# repo | hub-name | dest-name | bytes | sha256 (Hub LFS oid, resolved 2026-10-18)
FILES=(
  "Serveurperso/Qwen3-TTS-GGUF|qwen-talker-1.7b-base-Q4_K_M.gguf|qwen-talker-1.7b-base-Q4_K_M.gguf|1219245248|ea393ebaf2167ea23ce9fc18b093822851358a950d7075cd47ab4f6ce23e887d"
  "Serveurperso/Qwen3-TTS-GGUF|qwen-tokenizer-12hz-Q8_0.gguf|qwen-tokenizer-12hz-Q8_0.gguf|291150624|1883beeed99348fc35e23dd225e9082f93f6f8c109330a33d935baa8acdbfd94"
)

mkdir -p "$DEST"
status=0
for entry in "${FILES[@]}"; do
  IFS='|' read -r repo hubname destname size sha <<<"$entry"
  url="https://huggingface.co/${repo}/resolve/main/${hubname}"
  f="$DEST/$destname"
  have=0
  if [[ -f "$f" ]] && [[ "$(stat -c%s "$f")" == "$size" ]]; then
    if sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
      have=1
    fi
  fi
  if (( have )); then
    echo "OK        $destname"
    continue
  fi
  if (( VERIFY_ONLY )); then
    echo "MISSING   $destname"
    status=1
    continue
  fi
  echo "FETCHING  $destname (from $repo)"
  tmp="$f.part"
  curl -fsSL --fail-with-body -o "$tmp" "$url"
  mv "$tmp" "$f"
  if [[ "$(stat -c%s "$f")" != "$size" ]]; then
    echo "SIZE FAIL $destname ($(stat -c%s "$f") != $size)"
    status=1
    continue
  fi
  if ! sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
    echo "SHA FAIL  $destname"
    status=1
    continue
  fi
  echo "VERIFIED  $destname"
done
if (( status == 0 )); then
  echo "DOWNLOAD_DONE $DEST"
else
  echo "DOWNLOAD_FAILED $DEST" >&2
fi
exit "$status"