fix(deploy): the sidecars' downloads try again within the hour after a failed round

A failed BRouter segment or listing, a failed tile cut or an unwritable folder waited the whole refresh period, 30 days without routes or a map; they try again after an hour, doubling to a day. Photon's failed download backs off from a day to a week, and a dead Photon is noticed within a minute. The downloads' network is an ordinary bridge the three share, as the comments now say.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Tizian 「ティツィアーン」 <raisondetredev@pm.me>

deploy/maps/tiles.sh

@@ -3,7 +3,9 @@
 # newest of Protomaps' daily builds of the planet, cut to MAP_REGION (`west,south,
 # east,north` in degrees; by default Europe's, the box BRouter's segments cover) at
 # zooms 0 to 15, into /tiles/europe.pmtiles; again every MAP_REFRESH_DAYS days (30)
-# where a newer build has come. The cut is written into /tiles/next/ and moved over
+# where a newer build has come; after a round where the builds' list or the cut
+# failed, again in an hour, the wait doubling up to a day while rounds keep failing.
+# The cut is written into /tiles/next/ and moved over
 # the old one, so the server never reads half a file; until it is done, the old one
 # serves. Both at once take twice a cut's room.
 set -eu
@@ -12,9 +14,13 @@ builds=https://build-metadata.protomaps.dev/builds.json
 region=${MAP_REGION:--25,35,45,75}
 days=${MAP_REFRESH_DAYS:-30}
 cd /tiles
-mkdir -p next
 
 refresh() {
+  complete=0
+  if ! mkdir -p next; then
+    echo "/tiles/next can't be made; the tiles stay as they are." >&2
+    return 0
+  fi
   build=$(curl -fsS "$builds" | grep -o '"key": *"[0-9]\{8\}\.pmtiles"' |
     grep -o '[0-9]\{8\}\.pmtiles' | sort | tail -n 1) || build=
   if [ -z "$build" ]; then
@@ -23,6 +29,7 @@ refresh() {
   fi
   if [ -e europe.build ] && [ "$(cat europe.build)" = "$build" ]; then
     echo "The tiles are $build's, the newest."
+    complete=1
     return 0
   fi
   rm -f next/europe.pmtiles
@@ -31,13 +38,33 @@ refresh() {
     mv next/europe.pmtiles europe.pmtiles
     echo "$build" >europe.build
     echo "The tiles are $build's now, $(du -h europe.pmtiles | cut -f1)."
+    complete=1
   else
     rm -f next/europe.pmtiles
     echo "The cut of $build failed; the tiles stay as they are." >&2
   fi
 }
 
+# Seconds to wait after the $1th incomplete round in a row: $2, doubling up to $3.
+backoff() {
+  pause=$2 n=1
+  while [ "$n" -lt "$1" ] && [ "$pause" -lt "$3" ]; do
+    pause=$((pause * 2)) n=$((n + 1))
+  done
+  if [ "$pause" -gt "$3" ]; then pause=$3; fi
+  echo "$pause"
+}
+
+failures=0
 while :; do
   refresh
-  sleep $((days * 86400))
+  if [ "$complete" -eq 1 ]; then
+    failures=0
+    sleep $((days * 86400))
+  else
+    failures=$((failures + 1))
+    pause=$(backoff "$failures" 3600 86400)
+    echo "The round wasn't complete; trying again in $((pause / 60)) minutes." >&2
+    sleep "$pause"
+  fi
 done