avm/hassio-addons
1
0
Fork 0
mirror of https://github.com/alexbelgium/hassio-addons.git synced 2026-08-16 18:12:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(claude_desktop): address CodeRabbit findings on TokenSave startup hardening

Browse Source 
flock -n silently skipped TokenSave prep on lock contention with no retry until next restart; wait up to 60s instead (kernel releases flock the instant its owner exits, so only a truly stuck lock can't clear within that window).

Quarantine fired on any sync failure after 3 retries, including transient causes (permissions, disk full, missing binary) unrelated to corruption. Now only quarantines when stderr names actual database corruption (SQLite malformed/not-a-database/disk-image wording); other failures leave the index untouched and retry next start.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
alexbelgium
2026-07-15 22:19:01 +02:00
parent 3354af026f
commit b8c7cc3815
1 changed files with 23 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
claude_desktop/rootfs/etc/cont-init.d/82-claude_tools.sh
View File

@@ -203,12 +203,17 @@ if $TOKENSAVE_ENABLED; then
# Prepare the per-repo semantic graph defensively so a hard add-on stop or storage # Prepare the per-repo semantic graph defensively so a hard add-on stop or storage
# hiccup can never leave a broken index that fails every subsequent boot: # hiccup can never leave a broken index that fails every subsequent boot:
# * a startup-scoped flock serializes against an overlapping restart (and any git # * a startup-scoped flock serializes against an overlapping restart (and any git
# post-commit/checkout sync hook that fires mid-boot), so two writers never race; # post-commit/checkout sync hook that fires mid-boot); waits up to 60s for the
# other writer to finish rather than silently skipping, since a held lock clears
# itself the moment its holder exits or dies (the kernel releases flock on exit);
# * an existing index is refreshed with a cheap incremental `sync`, retried a few # * an existing index is refreshed with a cheap incremental `sync`, retried a few
# times because SQLITE_BUSY under lock contention is transient, not corruption; # times because SQLITE_BUSY under lock contention is transient, not corruption;
# * only a genuinely unreadable/malformed index (sync still failing after retries) # * quarantine is reserved for sync failures whose stderr actually names database
# or a half-written one from an interrupted `init` is quarantined and rebuilt, # corruption (SQLite's own "malformed"/"not a database"/"disk image" wording) or
# so the graph self-heals instead of propagating corruption; # a half-written index from an interrupted `init` (sentinel-flagged). Any other
# failure (permissions, disk full, missing binary, ...) leaves the existing index
# untouched and simply retries on the next start — corruption should self-heal,
# a transient environment problem should not nuke a healthy graph;
# * `init` is bracketed by a sentinel file so an interrupted full build is detected # * `init` is bracketed by a sentinel file so an interrupted full build is detected
# as incomplete on the next start and rebuilt rather than trusted. # as incomplete on the next start and rebuilt rather than trusted.
# All file operations run as the abc runtime user because the repo `.tokensave` # All file operations run as the abc runtime user because the repo `.tokensave`
@@ -223,10 +228,13 @@ if $TOKENSAVE_ENABLED; then
initflag="$ts_dir/.init-incomplete" initflag="$ts_dir/.init-incomplete"
mkdir -p "$ts_dir" mkdir -p "$ts_dir"
exec 9>"$lock" exec 9>"$lock"
if ! flock -n 9; then if ! flock -w 60 9; then
echo "TokenSave: index busy for $repo_root; skipping startup sync" >&2 echo "TokenSave: index still locked for $repo_root after 60s; skipping startup sync" >&2
exit 0 exit 0
fi fi
is_corruption() {
printf "%s" "$1" | grep -qiE "malformed|not a database|file is encrypted|disk image|database.*corrupt"
}
quarantine() { quarantine() {
stamp="$(date +%Y%m%d-%H%M%S)" stamp="$(date +%Y%m%d-%H%M%S)"
bdir="$ts_dir/corrupt-$stamp" bdir="$ts_dir/corrupt-$stamp"
@@ -239,14 +247,20 @@ if $TOKENSAVE_ENABLED; then
if [ -f "$db" ] && [ ! -f "$initflag" ]; then if [ -f "$db" ] && [ ! -f "$initflag" ]; then
attempt=1 attempt=1
while :; do while :; do
tokensave sync "$repo_root" && exit 0 sync_err="$(tokensave sync "$repo_root" 2>&1 1>/dev/null)" && exit 0
[ "$attempt" -ge 3 ] && break [ "$attempt" -ge 3 ] && break
echo "TokenSave: sync attempt $attempt failed for $repo_root; retrying" >&2 echo "TokenSave: sync attempt $attempt failed for $repo_root; retrying" >&2
attempt=$((attempt + 1)) attempt=$((attempt + 1))
sleep 2 sleep 2
done done
echo "TokenSave: sync failed after retries for $repo_root; rebuilding index" >&2 if is_corruption "$sync_err"; then
quarantine echo "TokenSave: sync failed after retries for $repo_root (corruption detected); rebuilding index" >&2
quarantine
else
echo "TokenSave: sync failed after retries for $repo_root (no corruption signature); leaving index in place, will retry next start" >&2
echo "TokenSave: last sync error: $sync_err" >&2
exit 1
fi
elif [ -f "$db" ]; then elif [ -f "$db" ]; then
echo "TokenSave: previous init did not finish for $repo_root; rebuilding index" >&2 echo "TokenSave: previous init did not finish for $repo_root; rebuilding index" >&2
quarantine quarantine