#!/bin/bash
# Unattended wrapper around gdl-sync.py. One argument: the run mode.
#
#   stories   daily      ~6 requests; the only surface that cannot be backfilled
#   full      monthly    every surface, --abort 50 (stops at already-held content)
#   sweep     quarterly  every surface, no abort -- the only run that notices
#                        carousels edited after we archived them
#
# Exits non-zero if the sync does, so cron mails you. Everything is logged.
set -eu

MODE="${1:?usage: gdl-cron.sh stories|full|sweep}"

GDL_HOME="${GDL_HOME:-$HOME/gdl}"
INDEX="${GDL_INDEX:-https://instaarchive.ergosteur.com}"
PUBLISH="${GDL_PUBLISH:-agentapi@10.20.28.200:/volume1/rslsync/sync/Instagram-archive/archives/}"
STAGING="$GDL_HOME/staging-$MODE"
# $$ in the name because two runs in the same SECOND would otherwise share a
# log file, and `tee -a` appends -- which made a test see the previous run.
LOG="$GDL_HOME/logs/$MODE-$(date +%Y%m%d-%H%M%S)-$$.log"

PATH="$HOME/.local/bin:$PATH"; export PATH

# Pacing. These are the values the 2026-08-22 runs used by hand, after the
# scraping warning -- roughly double the caution of gdl-sync.py's own defaults
# (6-10s / 3-6s / 1M). An archive sync has no deadline; being slow is free and
# being restricted is not. Override per-run with GDL_SLEEP_REQUEST etc. if you
# ever need to, but raise them rather than lower them.
SLEEP_REQUEST="${GDL_SLEEP_REQUEST:-12 20}"
SLEEP="${GDL_SLEEP:-5 10}"
RATE="${GDL_RATE:-500K}"

case "$MODE" in
  # --min-interval 8, not the 20h default. The floor exists to stop an ABORTED
  # RESTART re-enumerating profiles -- a minutes-to-hours concern. At 20h the
  # daily timer silently did nothing whenever a manual run had happened the
  # previous afternoon, which is exactly what happened on 2026-08-21: it fired,
  # skipped all six sources and reported success. A stories fetch is one
  # request per profile, so the worst case 8h permits is roughly twelve
  # requests in a day instead of six.
  stories) ARGS="--only stories --min-interval 8" ;;
  full)    ARGS="--only posts,reels,stories,highlights --abort 50" ;;
  # No --abort: the whole point of sweep is enumerating to the end, so it is
  # the only run that notices carousels edited after we archived them.
  sweep)   ARGS="--only posts,reels,stories,highlights" ;;
  *) echo "unknown mode: $MODE" >&2; exit 2 ;;
esac

mkdir -p "$GDL_HOME/logs"

# Staging is wiped every run ON PURPOSE. What we already hold is decided by the
# skip-archive (--download-archive), never by which files happen to be sitting
# in staging, so starting empty is correct -- and it keeps the publish rsync
# to just the new files instead of re-walking gigabytes each time.
rm -rf "$STAGING"

echo "=== $MODE run $(date -Is) ===" | tee -a "$LOG"

# The exit status has to survive the pipe into tee. The left-hand side of a
# pipeline runs in a SUBSHELL, so an `exit` in there sets the subshell's status
# and the script goes on to return tee's, which is always 0. An earlier version
# of this file did exactly that and reported success no matter what the sync
# did -- which is why the shebang is bash: PIPESTATUS is the fix.
# This run's output only. The check below must never see a previous run's
# lines, so it reads this rather than the (appended-to) log.
RUNOUT=$(mktemp)
trap 'rm -f "$RUNOUT"' EXIT

set +e
# shellcheck disable=SC2086
"$GDL_HOME/gdl-sync.py" \
    --index "$INDEX" \
    --staging "$STAGING" \
    --publish "$PUBLISH" \
    --archive-db "$GDL_HOME/artms.db" \
    --urls-file "$GDL_HOME/artms_account_links.txt" \
    --sleep-request $SLEEP_REQUEST \
    --sleep $SLEEP \
    --rate "$RATE" \
    $ARGS --execute 2>&1 | tee -a "$LOG" "$RUNOUT"
status=${PIPESTATUS[0]}
set -e

# A stories run that skipped every source is NOT a success. It means the
# min-interval floor blocked the one surface that cannot be backfilled, and
# without this it looks identical to a clean run: exit 0, "0 step(s) failed".
# Note this is not the same as "no stories today" -- that shows up as sources
# being fetched and returning no results, which is normal and stays quiet.
if [ "$MODE" = "stories" ] && grep -q "sources  : 0 to sync" "$RUNOUT"; then
  echo "WARNING: every stories source was skipped by --min-interval." | tee -a "$LOG" >&2
  echo "         Nothing was fetched. Stories expire in 24h and cannot be" | tee -a "$LOG" >&2
  echo "         backfilled, so this is a real loss, not a quiet no-op." | tee -a "$LOG" >&2
  [ "$status" -eq 0 ] && status=75
fi

echo "=== exit $status at $(date -Is) ===" | tee -a "$LOG"

# Keep the log directory from growing without bound.
ls -1t "$GDL_HOME/logs" | tail -n +30 | while read -r old; do
  rm -f "$GDL_HOME/logs/$old"
done

exit $status