Mangalord/vision-manager/manager.sh

#!/usr/bin/env bash
# vision-manager — start/stop the mangalord-vision (llama.cpp) container by
# name according to the analysis backlog in Postgres.
#
# Why this exists: llama-server has no idle-unload and pins ~4.4 GiB. On the
# 8 GiB box vision must only run while there is analysis work. This sidecar is
# the SINGLE owner of the vision lifecycle and the only component with Docker
# access (scoped through docker-socket-proxy) — the internet-facing backend
# never gets the socket. See VISION-AUTOSCALE.md.
#
# It is deliberately dumb: a poll loop with psql + curl + docker. No web
# surface, no state beyond an in-memory idle timer. If it dies, vision keeps
# running (harmless RAM); a MAX_UPTIME backstop bounds that.
set -euo pipefail

# ---- Config (all overridable via env) --------------------------------------
: "${DATABASE_URL:?DATABASE_URL must be set (use the read-only vision_manager role)}"
VISION_CONTAINER="${VISION_CONTAINER:-mangalord-vision}"
VISION_HEALTH_URL="${VISION_HEALTH_URL:-http://mangalord-vision:8000/health}"
# DOCKER_HOST points at the scoped docker-socket-proxy by default.
export DOCKER_HOST="${DOCKER_HOST:-tcp://docker-socket-proxy:2375}"

POLL_INTERVAL="${POLL_INTERVAL:-20}"        # seconds between backlog checks
STOP_DEBOUNCE="${STOP_DEBOUNCE:-600}"       # idle seconds before stopping vision
START_HEALTH_TIMEOUT="${START_HEALTH_TIMEOUT:-300}"  # max wait for /health 200
HEALTH_POLL_INTERVAL="${HEALTH_POLL_INTERVAL:-5}"    # poll cadence while warming
HEALTH_TIMEOUT="${HEALTH_TIMEOUT:-5}"                # per-probe curl timeout, seconds
MAX_UPTIME="${MAX_UPTIME:-0}"               # >0: force-stop after N idle-or-not seconds running (backstop); 0 disables
# When >0, refuse to start vision while a crawl is running (Chromium + vision
# together OOM the 8 GiB box). Set to 0 on roomier hosts.
RESPECT_CRAWL_MUTEX="${RESPECT_CRAWL_MUTEX:-1}"

PSQL=(psql "$DATABASE_URL" -At -v ON_ERROR_STOP=1)

log() { echo "[vision-manager] $(date -u +%FT%TZ) $*"; }

# ---- Queries ---------------------------------------------------------------
# Pending analysis work: pending OR currently-leased analyze_page jobs. Note
# the queue column is `state` (not `status`) and the kind lives in the JSONB
# payload — see backend/migrations/0012_crawler.sql.
pending_analysis() {
  "${PSQL[@]}" -c \
    "SELECT count(*) FROM crawler_jobs
      WHERE payload->>'kind' = 'analyze_page'
        AND state IN ('pending','running');" 2>/dev/null || echo "ERR"
}

# A crawl is in-flight if any non-analyze job is currently running.
crawl_running() {
  "${PSQL[@]}" -c \
    "SELECT count(*) FROM crawler_jobs
      WHERE payload->>'kind' <> 'analyze_page'
        AND state = 'running';" 2>/dev/null || echo "ERR"
}

# ---- Docker helpers --------------------------------------------------------
# `docker inspect .State.Running` → true/false; empty if the container is
# absent (defined elsewhere and not yet created) — treated as not-running.
vision_running() {
  docker inspect -f '{{.State.Running}}' "$VISION_CONTAINER" 2>/dev/null || echo "false"
}

vision_ready() {
  curl -fsS -m "$HEALTH_TIMEOUT" -o /dev/null "$VISION_HEALTH_URL" 2>/dev/null
}

start_vision() {
  log "starting $VISION_CONTAINER"
  # Idempotent: starting an already-running container is a docker no-op.
  if ! docker start "$VISION_CONTAINER" >/dev/null 2>&1; then
    log "ERROR: docker start failed (is $VISION_CONTAINER defined on this host?)"
    return 1
  fi
  local waited=0
  while ! vision_ready; do
    if [ "$waited" -ge "$START_HEALTH_TIMEOUT" ]; then
      log "WARNING: $VISION_CONTAINER not healthy after ${START_HEALTH_TIMEOUT}s; leaving it running"
      return 1
    fi
    sleep "$HEALTH_POLL_INTERVAL"
    waited=$((waited + HEALTH_POLL_INTERVAL))
  done
  log "$VISION_CONTAINER healthy after ~${waited}s"
}

stop_vision() {
  log "stopping $VISION_CONTAINER (idle ${STOP_DEBOUNCE}s)"
  if docker stop "$VISION_CONTAINER" >/dev/null 2>&1; then
    return 0
  fi
  log "WARNING: docker stop failed; will retry next tick"
  return 1
}

# ---- Main loop -------------------------------------------------------------
log "started: container=$VISION_CONTAINER health=$VISION_HEALTH_URL poll=${POLL_INTERVAL}s debounce=${STOP_DEBOUNCE}s docker_host=$DOCKER_HOST"

idle_for=0       # seconds the queue has been empty while vision is running
up_for=0         # seconds vision has been running (for MAX_UPTIME backstop)
crawl_deferred=0 # 1 while a start is held off by the crawl mutex (log on flip only)

while true; do
  pending="$(pending_analysis)"
  running="$(vision_running)"

  # Treat anything non-numeric (the "ERR" sentinel, or a stray psql notice on
  # stdout) as "query failed" — never feed it to `-gt`, which under
  # `set -e` would otherwise exit-2 and kill the loop.
  case "$pending" in
    ''|*[!0-9]*)
      log "WARNING: backlog query failed (got '${pending}'); will retry next tick"
      sleep "$POLL_INTERVAL"
      continue
      ;;
  esac

  if [ "$running" = "true" ]; then
    up_for=$((up_for + POLL_INTERVAL))
  else
    up_for=0
  fi

  if [ "$pending" -gt 0 ]; then
    idle_for=0
    if [ "$running" != "true" ]; then
      if [ "$RESPECT_CRAWL_MUTEX" != "0" ] && [ "$(crawl_running)" != "0" ]; then
        # Log once per deferral episode, not every poll, so a long crawl
        # doesn't flood the log.
        if [ "$crawl_deferred" != "1" ]; then
          log "deferring start: $pending analysis job(s) pending but a crawl is running (RAM mutex)"
          crawl_deferred=1
        fi
      else
        crawl_deferred=0
        start_vision || true
      fi
    else
      crawl_deferred=0
    fi
  else
    crawl_deferred=0
    # No work. Debounce the stop so bursty enqueues don't thrash the load
    # cycle, and own the stop on our OWN timer (never wait for a backend
    # "drained" signal — leak safety).
    if [ "$running" = "true" ]; then
      idle_for=$((idle_for + POLL_INTERVAL))
      if [ "$idle_for" -ge "$STOP_DEBOUNCE" ]; then
        # Only reset the timers if the stop actually took; otherwise let them
        # keep counting so we retry on the next tick rather than waiting out
        # another full debounce window.
        if stop_vision; then
          idle_for=0
          up_for=0
        fi
      fi
    else
      idle_for=0
    fi
  fi

  # Backstop: bound how long vision can stay up regardless of debounce state.
  if [ "$MAX_UPTIME" -gt 0 ] && [ "$running" = "true" ] && [ "$up_for" -ge "$MAX_UPTIME" ]; then
    log "MAX_UPTIME ${MAX_UPTIME}s reached; force-stopping $VISION_CONTAINER"
    if stop_vision; then
      idle_for=0
      up_for=0
    fi
  fi

  sleep "$POLL_INTERVAL"
done