#!/usr/bin/env bash
# ============================================================================
# Install a dedicated Coqui XTTS-v2 (natural Korean voice) venv at /opt/xtts.
#
# Why a SEPARATE venv (not the brain-bridge /opt/venv or /opt/melo):
#   - Coqui TTS pulls its own heavy torch/transformers stack; isolating it keeps
#     the slim bridge env (numpy<2 for faster-whisper) untouched.
#   - We use python3.11 (installed for the melo layer) because Coqui ships cp311
#     wheels and torch cu128 is available for it.
#
# torch is the CUDA (cu128) build so XTTS runs on the GPU alongside Ollama +
# Whisper. cu128 is the Blackwell (sm_120) wheel verified on this host.
# The worker selects the device via XTTS_DEVICE=cuda (compose).
#
# XTTS-v2 is non-commercial (Coqui Public Model License). COQUI_TOS_AGREED=1
# accepts it non-interactively so the model can load in a headless container.
# ============================================================================
set -euxo pipefail

export DEBIAN_FRONTEND=noninteractive
export COQUI_TOS_AGREED=1

# Install python3.11 if not already present, so this layer is self-contained.
if ! command -v python3.11 >/dev/null 2>&1; then
    apt-get update
    apt-get install -y --no-install-recommends software-properties-common
    add-apt-repository -y ppa:deadsnakes/ppa
    apt-get update
    apt-get install -y --no-install-recommends python3.11 python3.11-venv python3.11-dev
    rm -rf /var/lib/apt/lists/*
fi

python3.11 -m venv /opt/xtts
/opt/xtts/bin/pip install --no-cache-dir --upgrade pip wheel setuptools

# CUDA (cu128) torch first so Coqui's `torch` dep is satisfied with the GPU
# build. Pinned to the Blackwell-verified versions for reproducible rebuilds.
/opt/xtts/bin/pip install --no-cache-dir torch==2.11.0+cu128 torchaudio==2.11.0+cu128 \
    --index-url https://download.pytorch.org/whl/cu128

# Coqui TTS (maintained fork; provides the `TTS` package and XTTS-v2). The
# [codec] extra pulls torchcodec, which torch >=2.9 requires for audio IO
# (without it the import fails with TORCHCODEC_IMPORT_ERROR). torchcodec also
# needs the system FFmpeg shared libs, which are present (ffmpeg apt package).
/opt/xtts/bin/pip install --no-cache-dir "coqui-tts[codec]"

# Pin transformers to the 4.57+ / <5 range. coqui-tts requires >=4.57 but does
# NOT cap the upper bound, and transformers 5.x removed `isin_mps_friendly`
# (used by XTTS's tortoise layer), so an unpinned install pulls 5.x and the
# model import fails with "cannot import name 'isin_mps_friendly'". Pin <5.
/opt/xtts/bin/pip install --no-cache-dir "transformers>=4.57,<5"

# Pre-bake the XTTS-v2 model so the worker starts offline and the first Discord
# turn pays no download cost. The model is cached under TTS_HOME; we pin a
# DEDICATED, non-volume dir (/opt/xtts-cache) AND set it in supervisord, because
# runtime volume mounts (whisper_cache over /root/.cache) must not shadow it.
export TTS_HOME=/opt/xtts-cache
mkdir -p "$TTS_HOME"
COQUI_TOS_AGREED=1 TTS_HOME=/opt/xtts-cache XTTS_SPEAKER="Ana Florence" \
    /opt/xtts/bin/python - <<'PY'
import os
os.environ["COQUI_TOS_AGREED"] = "1"
from TTS.api import TTS

speaker = os.environ.get("XTTS_SPEAKER", "Ana Florence")
model = TTS("tts_models/multilingual/multi-dataset/xtts_v2")  # downloads to TTS_HOME
out = "/tmp/xtts_warm.wav"
model.tts_to_file(text="초기화 워밍업입니다.", speaker=speaker, language="ko", file_path=out)
print("[setup-xtts] warm-up KR synth OK ->", out, "speaker:", speaker)
PY

echo "[setup-xtts] Coqui XTTS-v2 venv ready at /opt/xtts (cache /opt/xtts-cache)"