#!/bin/bash
# ==============================================================================================
# ━━━ AI Retrieval Server ━━━
# ==============================================================================================
#
# PURPOSE
# ==============================================================================================
# Starts ai_serve.js, the retrieval-only HTTP bridge that lets Open-WebUI — which runs in its
# own container and cannot see Varaverk's filesystem — search the AI index for grounding
# context.
#
# ==============================================================================================
#
# OPERATIONAL MODEL
# ==============================================================================================
# Mirrors Arrs_Stack/start_webhook_listener.sh, because it solves the same problem: a caller
# outside Unraid's nginx needs to reach Varaverk, and nginx applies auth_request to everything
# it serves. Run from ARRAY_START_SCRIPTS and exec's node, so the process this script becomes
# is the server itself — no PID file to go stale.
#
# Retrieval only. Generation stays in ai_query.sh; Open-WebUI has its own model loaded and
# generates from the chunks this returns.
#
# ==============================================================================================
#
# DESIGN PRINCIPLES
# ==============================================================================================
# Every precondition is checked before exec, not after. A failure at array start should name
# its cause in the log rather than surface as an exec error once the setup has already run.
#
# Disabled is a first-class state. AI_HTTP_PORT=0 or AI_ENABLED=false exits 0 without warning,
# so a host that does not want the bridge is not a host reporting a failed start script.
#
# The index is not built here. This serves an index; ai_index.sh creates one. A server that
# silently indexed on boot would turn a restart into an unbounded embedding run.
#
# ==============================================================================================
#
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Root Required
#   Writes the generated secret back into master.conf and logs under /var/log/varaverk.
#
# Refuses to Serve a Missing Index
#   The endpoint would answer every query with a retrieval error and Open-WebUI would render
#   it as "nothing found" — indistinguishable from a corpus that genuinely lacks the answer.
#   Exits with a message naming ai_index.sh instead.
#
# Secret Generated Once, and Verified Persisted
#   An unset AI_HTTP_SECRET is generated with openssl and written to master.conf. If the
#   write-back cannot be confirmed the start is failed: a secret that exists only in this
#   process changes on every restart, silently breaking the tool registered in Open-WebUI.
#   Same failure mode, and same guard, as the webhook listener's secret.
#
# Single Instance
#   acquire_lock "continuous" — an array stop/start without a reboot leaves the old node
#   process holding the port, and a second bind would fail with EADDRINUSE and log a false
#   failure against array_started.sh.
#
# Binds Only Where It Must
#   Defaults to 0.0.0.0 because the caller is a container on the docker bridge and cannot
#   reach a loopback-bound socket. That is the reason the secret exists, and why the served
#   surface is a single read-only verb over documentation already in git.
#
# ==============================================================================================
#
# CONFIGURATION
# ==============================================================================================
#   AI_ENABLED              master.conf — false exits without starting
#   AI_HTTP_PORT            master.conf — 0 disables the bridge
#   AI_HTTP_SECRET          master.conf — auto-generated on first start if empty
#   AI_HTTP_BIND            master.conf — bind address, default 0.0.0.0
#   AI_INDEX_DB             master.conf — index served
#   <HOST>_OLLAMA_URL       host conf   — embedding endpoint
#   <HOST>_OLLAMA_EMBED_MODEL host conf — embedding model
#
# ==============================================================================================
#
# RUNTIME MODES
# ==============================================================================================
#   start_ai_server.sh      exec's the server in the foreground; run from ARRAY_START_SCRIPTS
#
# ==============================================================================================

set -uo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ECOSYSTEM_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"

source "$ECOSYSTEM_ROOT/load_config.sh"

if [[ "$EUID" -ne 0 ]]; then
    error "Must be run as root"
    exit 1
fi

if [[ "${AI_ENABLED:-false}" != "true" ]]; then
    echo "[ai_serve] AI_ENABLED is not true — retrieval bridge disabled"
    exit 0
fi

[[ "${AI_HTTP_PORT:-0}" -eq 0 ]] && {
    echo "[ai_serve] AI_HTTP_PORT=0 — retrieval bridge disabled"
    exit 0
}

if ! command -v node >/dev/null 2>&1; then
    error "node not found — required to run ai_serve.js"
    notify "AI retrieval bridge failed to start on $(hostname) — node not installed" \
        "AI Retrieval" "warning"
    exit 1
fi

detect_hosts

_url_var="${MY_ID}_OLLAMA_URL"
_emb_var="${MY_ID}_OLLAMA_EMBED_MODEL"
OLLAMA_URL="${!_url_var:-}"
EMBED_MODEL="${!_emb_var:-nomic-embed-text}"
DB="${AI_INDEX_DB:-${DATA_DIR}/ai_index.db}"

if [[ -z "$OLLAMA_URL" ]]; then
    error "${MY_ID}_OLLAMA_URL is empty — cannot embed queries"
    exit 1
fi

# Serving an absent index answers every question with a retrieval error, which Open-WebUI
# renders as "nothing found" — the same thing an empty corpus looks like.
if [[ ! -f "$DB" ]]; then
    error "No index at $DB — run AI/ai_index.sh first"
    notify "AI retrieval bridge not started on $(hostname) — index missing" \
        "AI Retrieval" "warning"
    exit 1
fi

acquire_lock "continuous"

if [[ -z "${AI_HTTP_SECRET:-}" ]]; then
    if ! command -v openssl >/dev/null 2>&1; then
        error "openssl not found — cannot generate AI_HTTP_SECRET"
        exit 1
    fi

    GENERATED=$(openssl rand -hex 32)
    MASTER_CONF="$ECOSYSTEM_ROOT/Configurations/master.conf"
    sed -i "s/AI_HTTP_SECRET=\"\"/AI_HTTP_SECRET=\"$GENERATED\"/" "$MASTER_CONF"
    AI_HTTP_SECRET="$GENERATED"

    # A secret held only in this process would differ on the next start, silently breaking
    # the tool already registered in Open-WebUI. Same guard as the webhook listener.
    if ! grep -q "AI_HTTP_SECRET=\"$GENERATED\"" "$MASTER_CONF" 2>/dev/null; then
        error "Generated AI_HTTP_SECRET but could not persist it to $MASTER_CONF"
        error "Set AI_HTTP_SECRET manually — a non-persisted secret changes on every restart"
        notify "AI retrieval secret not persisted on $(hostname)" "AI Retrieval" "warning"
        exit 1
    fi

    echo "[ai_serve] Generated AI_HTTP_SECRET — add it to the Open-WebUI tool"
fi

mkdir -p /var/log/varaverk

exec node "$ECOSYSTEM_ROOT/AI/ai_serve.js" \
    "$AI_HTTP_PORT" "$AI_HTTP_SECRET" "${AI_HTTP_BIND:-0.0.0.0}" \
    "$DB" "$OLLAMA_URL" "$EMBED_MODEL" \
    >> /var/log/varaverk/ai_serve.log 2>&1