#!/usr/bin/env bash
# tts-engine-start.sh — the entrypoint of the frank-tts-engine image
# (dankclaw/voiceservice/Containerfile.engine). It exists for one reason: the
# knobs of the arm A engine are command-line flags, while the fleet's knobs
# live in scripts/frank-tts-engine.env and reach the container through
# EnvironmentFile=. This is the translation layer, and nothing else — no
# supervision, no retries, no logging of its own. PID 1 stays the server, so
# `podman stop` and the unit's Restart=always drive it directly.
#
# THE FLAGS THAT ARE NOT HERE, and must stay absent:
#
#   --threads / -t   does not exist in this build. src/backend.h computes the
#                    CPU thread count as std::thread::hardware_concurrency()/2
#                    (the comment there: GEMM shares SIMD units across
#                    hyperthreads), and there is no flag to override it. So a
#                    CPU affinity pin (CPUQuota=, taskset, a cpuset) silently
#                    changes the engine's thread count instead of just its
#                    placement — pinning is deliberately not done anywhere in
#                    this stack. See the env file header for the same warning
#                    aimed at the operator.
#   --device         left at its default. Every GPU backend is compiled out of
#                    the image, so the default device pick can only land on
#                    CPU; naming a device would add a way to be wrong.
#
# Everything defaults to the shape the 2026-10-18 trial measured, so an empty
# environment still boots the decided configuration: 1.7 B talker Q4_K_M with
# the Q8_0 tokenizer, one request at a time, on the private bridge.
set -euo pipefail

# The binary path. Overridable for one reason: the bats seam runs a stub
# instead of a 1.2 GiB model. Operators never set it — the image ships exactly
# one binary at /app/tts-server.
: "${QWENTTS_BIN:=/app/tts-server}"

# Paths are CONTAINER paths (the host directories they come from are named in
# scripts/frank-tts-engine.env and mounted by the Quadlet unit).
: "${QWENTTS_MODEL:=/models/qwen-talker-1.7b-base-Q4_K_M.gguf}"
: "${QWENTTS_CODEC:=/models/qwen-tokenizer-12hz-Q8_0.gguf}"

# Reported by GET /v1/models, and what scripts/frank-tts.env's
# TTS_UPSTREAM_MODEL names. A model id, not a filename: the file name would
# leak a quantization choice into every consumer's config.
: "${QWENTTS_ALIAS:=frank-tts-engine}"

# 0.0.0.0 inside the container is not "public". tts-server defaults to
# 127.0.0.1 (its own usage prints `--host <ip> Listen address (default:
# 127.0.0.1)`), and inside a container netns a loopback bind is reachable by
# nothing outside that namespace — the façade dials this container by its bridge
# address on the private voice network, which is why the address has to be
# broad. The unit PUBLISHES NOTHING (see
# dankclaw/voiceservice/quadlet/frank-tts-engine.container: no PublishPort at
# all, not even 127.0.0.1:8880), so the only namespaces that can reach
# 0.0.0.0:8880 are that bridge and this container's own loopback — and its own
# loopback is exactly where the boot warmer and the health probe speak.
: "${QWENTTS_HOST:=0.0.0.0}"
: "${QWENTTS_PORT:=8880}"

# The language label used when a request omits one. `auto` is the upstream
# default and what the trial ran.
: "${QWENTTS_LANG:=auto}"

# One request at a time. The server-side queue is a serialised FIFO at this
# setting, which is what keeps the measured per-voice timings true; batching
# on a CPU build splits the same cores between two syntheses and the warm RTF
# margin (0.55-0.67 against real time 1.0) disappears. The engine's own
# default is also 1; it is written here because it is a decision, not an
# accident.
: "${QWENTTS_MAX_BATCH:=1}"

# Fail loudly BEFORE binding, so the journal says which artifact is missing
# instead of the unit reporting a container that starts and dies. This is the
# self-healing path: Restart=always re-runs it every RestartSec, and the same
# sentence repeats until the operator fetches the weights
# (scripts/download-frank-tts-engine-qwentts.sh).
for artifact in "$QWENTTS_MODEL" "$QWENTTS_CODEC"; do
    if [[ ! -r "$artifact" ]]; then
        echo "frank-tts-engine: cannot read ${artifact}; run scripts/download-frank-tts-engine-qwentts.sh on the host (the /models mount is read-only and holds the two GGUF files)" >&2
        exit 1
    fi
done

exec "$QWENTTS_BIN" \
    --model "$QWENTTS_MODEL" \
    --codec "$QWENTTS_CODEC" \
    --alias "$QWENTTS_ALIAS" \
    --host "$QWENTTS_HOST" \
    --port "$QWENTTS_PORT" \
    --lang "$QWENTTS_LANG" \
    --max-batch "$QWENTTS_MAX_BATCH"