#!/usr/bin/env bash
# Serve the Qwen3.8-27B pipeline-parallel RPC worker on Dankserver.
#
# Runs ggml-rpc-server from the b10433 CUDA+RPC build and exposes the RTX
# 3090 as a remote device for the head on Dankclaw.
#
# Tunables come from frank-pp-worker.env in this directory unless the
# FRANK_PP_WORKER_ENV_FILE environment variable overrides that path.
#
# Security note (upstream): the RPC server is "fragile and insecure". No
# authentication, no encryption. Keep it on the trusted LAN only.
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ENV_FILE="${FRANK_PP_WORKER_ENV_FILE:-$SCRIPT_DIR/frank-pp-worker.env}"
if [[ -f "$ENV_FILE" ]]; then
    set -a
    # shellcheck disable=SC1090
    source "$ENV_FILE"
    set +a
fi

# --- defaults (used when the env file does not set them) -------------------
: "${RPC_BIND:=192.168.0.235}"
: "${RPC_PORT:=50052}"
: "${DEVICE:=CUDA0}"
: "${THREADS:=7}"
: "${CACHE:=1}"
: "${WORKER_BIN:=/home/dank/llama-cpp-rpc/build/bin/ggml-rpc-server}"

if [[ ! -x "$WORKER_BIN" ]]; then
    echo "missing worker binary: $WORKER_BIN" >&2
    echo "Build it: cd /home/dank/llama-cpp-rpc && cmake -B build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON -DGGML_CUDA_FA_ALL_QUANTS=ON -DGGML_RPC=ON -DCMAKE_BUILD_TYPE=Release && cmake --build build --config Release -- -j 8" >&2
    exit 1
fi

ARGS=()
if [[ "${CACHE}" == "1" ]]; then
    ARGS+=(--cache)
fi

exec "$WORKER_BIN" \
    --host "$RPC_BIND" \
    --port "$RPC_PORT" \
    --device "$DEVICE" \
    --threads "$THREADS" \
    "${ARGS[@]}"