From 57ae338cdb02359b939995070966dbf60bd0fcf8 Mon Sep 17 00:00:00 2001
From: Eric Wagoner <ewagoner@gmail.com>
Date: Sat, 10 Oct 2026 17:44:43 -0400
Subject: [PATCH] The rollup and the backup check in once, when they end, with
 the run's duration

The rollup finishes in two seconds on the shared host, and its "in progress"
and "ok" check-ins reached Sentry in either order; when "ok" landed first,
the late start was never closed and the monitor reported a timeout ten
minutes later. One check-in at the end cannot race, and a run that hangs
still shows: nothing arrives and the night is marked missed.

Fixes TAFL-1

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GwFKMuQnPAEHJ5yA1q4orh
---
 deploy/hnefatafl-backup.sh | 8 ++++++--
 deploy/hnefatafl-rollup.sh | 8 ++++++--
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/deploy/hnefatafl-backup.sh b/deploy/hnefatafl-backup.sh
index ea1d6a0..2e2ab13 100755
--- a/deploy/hnefatafl-backup.sh
+++ b/deploy/hnefatafl-backup.sh
@@ -14,9 +14,14 @@ LOG="/var/log/hnefatafl/backup.log"
 STAMP=$(date +%Y-%m-%d)
 mkdir -p "$(dirname "$LOG")"
 CRON_URL=$(cat /root/.hnefatafl-sentry-cron 2>/dev/null || true)
+# One check-in, when the run ends, carrying its duration: a start and a
+# finish sent seconds apart can reach Sentry in either order, and a start
+# that lands second is never closed. A run that never ends sends nothing,
+# and Sentry marks the night missed.
+START=$SECONDS
 checkin() {
   [ -n "$CRON_URL" ] && curl -sf -o /dev/null -X POST -H "Content-Type: application/json" \
-    -d "{\"status\":\"$1\",\"monitor_config\":{\"schedule\":{\"type\":\"crontab\",\"value\":\"$SCHEDULE\"},\"checkin_margin\":30,\"max_runtime\":10,\"timezone\":\"UTC\"}}" \
+    -d "{\"status\":\"$1\",\"duration\":$((SECONDS - START)),\"monitor_config\":{\"schedule\":{\"type\":\"crontab\",\"value\":\"$SCHEDULE\"},\"checkin_margin\":30,\"max_runtime\":10,\"timezone\":\"UTC\"}}" \
     "$CRON_URL" || true
 }
 
@@ -27,7 +32,6 @@ fi
 
 {
   echo "=== $(date -Is) backup start"
-  checkin in_progress
   if rclone sync "$SRC" "spaces:$BUCKET/$PREFIX/current" --exclude 'rollup.jsonl' 2>&1 &&
      rclone copy "$SRC" "spaces:$BUCKET/$PREFIX/snapshots/$STAMP" 2>&1; then
     checkin ok
diff --git a/deploy/hnefatafl-rollup.sh b/deploy/hnefatafl-rollup.sh
index decf154..96db08a 100755
--- a/deploy/hnefatafl-rollup.sh
+++ b/deploy/hnefatafl-rollup.sh
@@ -16,13 +16,17 @@ DAY="${1:-$(date -u -d 'yesterday' +%Y-%m-%d)}"
 SCHEDULE="12 0 * * *"
 CRON_URL=$(cat /root/.hnefatafl-sentry-cron-rollup 2>/dev/null || true)
 # The check-in carries the schedule: Sentry keeps a monitor only once told its shape.
+# One check-in, when the run ends, carrying its duration: a start and a
+# finish sent seconds apart can reach Sentry in either order, and a start
+# that lands second is never closed. A run that never ends sends nothing,
+# and Sentry marks the night missed.
+START=$SECONDS
 checkin() {
   [ -n "$CRON_URL" ] && curl -sf -o /dev/null -X POST -H "Content-Type: application/json" \
-    -d "{\"status\":\"$1\",\"monitor_config\":{\"schedule\":{\"type\":\"crontab\",\"value\":\"$SCHEDULE\"},\"checkin_margin\":30,\"max_runtime\":10,\"timezone\":\"UTC\"}}" \
+    -d "{\"status\":\"$1\",\"duration\":$((SECONDS - START)),\"monitor_config\":{\"schedule\":{\"type\":\"crontab\",\"value\":\"$SCHEDULE\"},\"checkin_margin\":30,\"max_runtime\":10,\"timezone\":\"UTC\"}}" \
     "$CRON_URL" || true
 }
 mkdir -p "$(dirname "$LOG")"
-checkin in_progress
 if python3 - "$DAY" "$OUT" <<'PY' >> "$LOG" 2>&1
 import datetime, glob, json, os, shutil, sys
 sys.path.insert(0, "/usr/local/lib/hnefatafl")