#!/usr/bin/env bash
# Serve the FastFlowLM (FLM) sight+sound endpoint — frank-npu.
#
# Runs `flm serve <tag>` on the XDNA2 NPU (50 TOPS, Dankclaw). The NPU is a
# single-lane device: generations serialize in FIFO order, so this is a
# background/triage endpoint, not an interactive multi-user chat. The NPU
# draws from the unified RAM pool shared with frank-dragoon (the iGPU
# llama.cpp service); see serverAppConfigs-docs/LLM/frank-npu.md
# for the memory budget and the model-selection tradeoff.
#
# NOTE: FLM requires unlimited memlock. The unit sets LimitMEMLOCK=infinity.
# NOTE: an unknown model tag does NOT 404 — /v1/chat/completions answers HTTP 200 with a
# flat {"error":"Failed to load <tag> model!"} body and no choices; /v1/completions returns a
# nested OpenAI-shaped server_error (code 500) also under HTTP 200. Client model IDs must be the exact FLM registry
# tag (e.g. gemma4-it:e4b), never a service alias. Custom tags only resolve
# when FLM_CONFIG_PATH points at the user registry that carries them and their
# kernels are symlinked into /home/dank/.config/flm/xclbins/<PackName>.
set -euo pipefail

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

# --- defaults (used when the env file does not set them) -------------------
: "${FLM_BIN:=/usr/bin/flm}"
: "${FLM_MODEL:=gemma4-it:e4b}"
: "${FLM_HOST:=0.0.0.0}"
: "${FLM_PORT:=7771}"
: "${FLM_PMODE:=turbo}"
: "${FLM_ASR:=0}"
: "${FLM_CTX_LEN:=131072}"

# The user registry is a superset of the system registry (it carries the
# custom tags too), and its model_path resolves relative to the registry file,
# so exports keep a tag swap in the env file from needing script edits.
export FLM_CONFIG_PATH="${FLM_CONFIG_PATH:-/home/dank/.config/flm/model_list.json}"
export FLM_XCLBIN_PATH="${FLM_XCLBIN_PATH:-/home/dank/.config/flm/xclbins}"

if [[ ! -x "$FLM_BIN" ]]; then
    echo "missing flm binary: $FLM_BIN" >&2
    exit 1
fi

# --- optional flags ----------------------------------------------------------
OPT_ARGS=()
if [[ "${FLM_ASR}" != "0" ]]; then
    OPT_ARGS+=(--asr "${FLM_ASR}")
fi
if [[ "${FLM_CTX_LEN}" != "-1" ]]; then
    OPT_ARGS+=(--ctx-len "${FLM_CTX_LEN}")
fi

exec "$FLM_BIN" serve "$FLM_MODEL" \
    --host "$FLM_HOST" \
    -p "$FLM_PORT" \
    --pmode "$FLM_PMODE" \
    "${OPT_ARGS[@]}"