This commit was merged in pull request #811.
This commit is contained in:
@@ -109,6 +109,225 @@ restore_snapshot() {
|
||||
}
|
||||
cleanup_snapshot() { [[ -n "$SNAPSHOT_DIR" && -d "$SNAPSHOT_DIR" ]] && rm -rf "$SNAPSHOT_DIR"; SNAPSHOT_DIR=""; }
|
||||
|
||||
# ─── durable operator-config snapshot (#791 PR2) ─────────────────────────────
|
||||
# A SECOND, independent safety layer, distinct from SNAPSHOT_DIR above:
|
||||
# • SNAPSHOT_DIR is ephemeral (/tmp, deleted on success) and mirrors the WHOLE
|
||||
# target for CRASH rollback if the sync aborts mid-write.
|
||||
# • DURABLE_SNAPSHOT_DIR is RETAINED, holds only the operator-owned surface, and
|
||||
# lives OUTSIDE the framework tree and any repo. It exists for the failure the
|
||||
# crash-rollback cannot see: a sync that finishes "successfully" yet a
|
||||
# manifest/logic bug let it modify an operator file. verify_operator_surface()
|
||||
# (post-sync) heals from it; `mosaic restore` recovers from it days later.
|
||||
# Path convention is mirrored in packages/mosaic/src/commands/restore.ts — keep
|
||||
# the two in sync (there is no shared code across the bash/TS boundary).
|
||||
DURABLE_SNAPSHOT_DIR=""
|
||||
backup_root() { printf '%s/mosaic/backups' "${XDG_STATE_HOME:-$HOME/.local/state}"; }
|
||||
|
||||
# Relative paths that a migration INTENTIONALLY removes from the target (e.g. the
|
||||
# legacy bin/ tree). Such a path is operator-classified by the manifest (unknown⇒
|
||||
# operator), so the durable snapshot captures it — but its post-migration absence
|
||||
# is correct, NOT a manifest bug. run_migrations() records each removal here so
|
||||
# verify_operator_surface() does not "heal" it back and silently undo the
|
||||
# migration (which would then be skipped forever once the version is stamped).
|
||||
MIGRATION_REMOVED_PATHS=()
|
||||
|
||||
# True (0) if $1 (a path relative to TARGET_DIR) equals or lives under a path a
|
||||
# migration deliberately removed this run.
|
||||
is_migration_removed() {
|
||||
local rel="$1" removed
|
||||
for removed in ${MIGRATION_REMOVED_PATHS[@]+"${MIGRATION_REMOVED_PATHS[@]}"}; do
|
||||
[[ -n "$removed" ]] || continue
|
||||
[[ "$rel" == "$removed" || "$rel" == "$removed"/* ]] && return 0
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
# True (0) if any parent directory of $1 (relative to TARGET_DIR) is a symlink.
|
||||
# Restoring THROUGH a symlinked ancestor would let cp write snapshot contents —
|
||||
# possibly secrets — outside the target (CWE-59), so the verify net refuses it.
|
||||
has_symlinked_parent() {
|
||||
local rel="$1" dir p seg
|
||||
dir="$(dirname "$rel")"
|
||||
[[ "$dir" == "." ]] && return 1
|
||||
p="$TARGET_DIR"
|
||||
local IFS='/'
|
||||
for seg in $dir; do
|
||||
[[ -n "$seg" ]] || continue
|
||||
p="$p/$seg"
|
||||
[[ -L "$p" ]] && return 0
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
# Emit (NUL-delimited, into file $1) the operator-owned relative paths that exist
|
||||
# under TARGET_DIR, classified via the shared manifest (deny-wins; unknown⇒
|
||||
# operator). Returns non-zero if the filesystem walk itself failed — we must
|
||||
# NEVER snapshot from a truncated scan (a `< <(find …)` process substitution
|
||||
# would hide that error; capture-then-check does not — cf. #791 blocker-D1).
|
||||
enumerate_operator_files() {
|
||||
local out="$1" scan abs rel
|
||||
scan="$(mktemp)"
|
||||
if ! find "$TARGET_DIR" -type f -print0 > "$scan"; then
|
||||
rm -f "$scan"
|
||||
return 1 # OP-SCAN-GUARD
|
||||
fi
|
||||
: > "$out"
|
||||
while IFS= read -r -d '' abs; do
|
||||
rel="${abs#"$TARGET_DIR"/}"
|
||||
# Not operator config: version marker and any VCS metadata.
|
||||
case "$rel" in .framework-version|.git|.git/*) continue ;; esac
|
||||
manifest_is_framework "$rel" || printf '%s\0' "$rel" >> "$out"
|
||||
done < "$scan"
|
||||
rm -f "$scan"
|
||||
}
|
||||
|
||||
# Retain only the newest MOSAIC_BACKUP_RETENTION (default 5) snapshots. The
|
||||
# pre-update-<UTC-ts> names sort lexicographically = chronologically, so a
|
||||
# reverse sort is newest-first. Pruning failures are non-fatal (they only leave
|
||||
# extra old backups); the enclosing find's status is still honored, not swallowed.
|
||||
prune_durable_snapshots() {
|
||||
local root keep list d i=0
|
||||
root="$(backup_root)"
|
||||
keep="${MOSAIC_BACKUP_RETENTION:-5}"
|
||||
[[ "$keep" =~ ^[0-9]+$ ]] && (( keep >= 1 )) || keep=5
|
||||
list="$(mktemp)"
|
||||
if ! find "$root" -maxdepth 1 -type d -name 'pre-update-*' > "$list"; then
|
||||
rm -f "$list"; return 0
|
||||
fi
|
||||
# Newest-first ordering needs `sort` (`-o` writes back in place — no `mv`
|
||||
# dependency); if it is somehow unavailable, leave the backups untouched rather
|
||||
# than risk pruning in an undefined order.
|
||||
if ! LC_ALL=C sort -r -o "$list" "$list" 2>/dev/null; then
|
||||
rm -f "$list"; return 0
|
||||
fi
|
||||
while IFS= read -r d; do
|
||||
[[ -n "$d" ]] || continue
|
||||
i=$((i + 1))
|
||||
(( i > keep )) && rm -rf "$d"
|
||||
done < "$list"
|
||||
rm -f "$list"
|
||||
}
|
||||
|
||||
# Take the durable pre-update snapshot BEFORE any mutation. Fail-OPEN: the durable
|
||||
# snapshot is a recovery bonus on top of the manifest (which already keeps the
|
||||
# sync out of operator paths) and the crash-rollback — so an un-writable backup
|
||||
# location warns and continues rather than blocking the upgrade. Everything it
|
||||
# creates is private (umask 077 + explicit 0700 dirs / 0600 files): the snapshot
|
||||
# mirrors operator config, which may hold secrets, and must never be world-readable.
|
||||
make_durable_snapshot() {
|
||||
is_existing_install || return 0
|
||||
local root ts dir list rel src dst count=0 old_umask
|
||||
root="$(backup_root)"
|
||||
# Fail-open if we cannot even stamp a timestamp: the durable snapshot is a
|
||||
# recovery bonus and must never be the thing that aborts an upgrade.
|
||||
ts="$(date -u +%Y%m%dT%H%M%SZ 2>/dev/null || true)"
|
||||
if [[ -z "$ts" ]]; then
|
||||
warn "Durable snapshot skipped: no UTC timestamp available (upgrade continues)."
|
||||
return 0
|
||||
fi
|
||||
# umask 077 makes every dir/file the snapshot creates private from birth (it
|
||||
# mirrors operator config, which may hold secrets). It is PROCESS-global, so we
|
||||
# save and restore it around exactly this block — otherwise every later sync
|
||||
# copy and new framework dir would inherit 0600/0700 instead of 0644/0755.
|
||||
old_umask="$(umask)"
|
||||
umask 077
|
||||
if ! mkdir -p "$root"; then
|
||||
umask "$old_umask"
|
||||
warn "Durable snapshot skipped: cannot create backup dir $root (upgrade continues; operator files remain manifest-protected)."
|
||||
return 0
|
||||
fi
|
||||
chmod 700 "$root" 2>/dev/null || true
|
||||
dir="$root/pre-update-$ts"
|
||||
if [[ -e "$dir" ]]; then # same-second re-run: disambiguate
|
||||
local n=1; while [[ -e "$dir-$n" ]]; do n=$((n + 1)); done; dir="$dir-$n"
|
||||
fi
|
||||
if ! mkdir -p "$dir"; then
|
||||
umask "$old_umask"
|
||||
warn "Durable snapshot skipped: cannot create $dir (upgrade continues)."
|
||||
return 0
|
||||
fi
|
||||
chmod 700 "$dir"
|
||||
list="$(mktemp)"
|
||||
if ! enumerate_operator_files "$list"; then
|
||||
umask "$old_umask"
|
||||
warn "Durable snapshot skipped: could not enumerate operator files (upgrade continues)."
|
||||
rm -f "$list"; rmdir "$dir" 2>/dev/null || true
|
||||
return 0
|
||||
fi
|
||||
while IFS= read -r -d '' rel; do
|
||||
src="$TARGET_DIR/$rel"; dst="$dir/$rel"
|
||||
[[ -f "$src" ]] || continue
|
||||
mkdir -p "$(dirname "$dst")"
|
||||
if ! cp "$src" "$dst"; then
|
||||
warn "Durable snapshot: could not copy operator file '$rel' (skipped)."
|
||||
continue
|
||||
fi
|
||||
chmod 600 "$dst" 2>/dev/null || true
|
||||
count=$((count + 1))
|
||||
done < "$list"
|
||||
rm -f "$list"
|
||||
# Tighten every dir the copy created (mkdir -p honors umask, but be explicit).
|
||||
find "$dir" -type d -exec chmod 700 {} + 2>/dev/null || true
|
||||
umask "$old_umask" # UMASK-RESTORE-NORMAL — restore before the upgrade proper resumes (see above)
|
||||
DURABLE_SNAPSHOT_DIR="$dir"
|
||||
ok "Durable pre-update snapshot: $count operator file(s) saved to $dir (recover with: mosaic restore --list)"
|
||||
prune_durable_snapshots
|
||||
}
|
||||
|
||||
# Post-sync safety net: a keep-mode upgrade must NEVER modify an operator file.
|
||||
# Compare every file in the durable snapshot to its current target counterpart;
|
||||
# any that changed (or vanished) was touched by a framework bug — restore it from
|
||||
# the snapshot and warn loudly. This does NOT abort: the framework itself synced
|
||||
# correctly; we only heal the operator collateral. Runs after the restore trap is
|
||||
# disarmed so its corrective copies can't spuriously trip a full rollback, and
|
||||
# every step is guarded so `set -e` cannot exit silently mid-heal (cf. blocker-D2).
|
||||
verify_operator_surface() {
|
||||
[[ -n "$DURABLE_SNAPSHOT_DIR" && -d "$DURABLE_SNAPSHOT_DIR" ]] || return 0
|
||||
local scan snap rel cur healed=0
|
||||
scan="$(mktemp)"
|
||||
if ! find "$DURABLE_SNAPSHOT_DIR" -type f -print0 > "$scan"; then
|
||||
rm -f "$scan"
|
||||
warn "Post-upgrade verify skipped: could not enumerate the pre-update snapshot at $DURABLE_SNAPSHOT_DIR."
|
||||
return 0
|
||||
fi
|
||||
while IFS= read -r -d '' snap; do
|
||||
rel="${snap#"$DURABLE_SNAPSHOT_DIR"/}"
|
||||
cur="$TARGET_DIR/$rel"
|
||||
# A migration may legitimately delete an operator-classified path (e.g. legacy
|
||||
# bin/). Its absence is intended — do not heal it back, or the migration is
|
||||
# silently undone and never re-runs once the version is stamped (#791 PR2).
|
||||
is_migration_removed "$rel" && continue # MIGRATION-SKIP-GUARD
|
||||
if [[ ! -e "$cur" ]] || ! cmp -s "$snap" "$cur"; then
|
||||
# Never restore THROUGH a symlink: an operator path swapped for a link would
|
||||
# otherwise let cp write snapshot contents (possibly secrets) outside the
|
||||
# target (CWE-59). Refuse a symlinked parent; drop a symlinked leaf and write
|
||||
# a real file in its place.
|
||||
if has_symlinked_parent "$rel"; then
|
||||
warn "Operator path '$rel' has a symlinked parent under $TARGET_DIR; refusing to restore through it (possible tampering) — recover it manually from $DURABLE_SNAPSHOT_DIR."
|
||||
continue
|
||||
fi
|
||||
[[ -L "$cur" ]] && rm -f "$cur" # SYMLINK-LEAF-GUARD
|
||||
# Guard mkdir too: under set -e (trap already disarmed) a bare failure would
|
||||
# exit the whole installer before the recovery pointer below is emitted.
|
||||
if ! mkdir -p "$(dirname "$cur")"; then
|
||||
warn "Operator file '$rel' was modified by the upgrade but could NOT be auto-restored (parent dir unavailable) — recover it manually from $DURABLE_SNAPSHOT_DIR."
|
||||
continue
|
||||
fi
|
||||
if cp "$snap" "$cur"; then
|
||||
chmod 600 "$cur" 2>/dev/null || true
|
||||
warn "Operator file was modified by the upgrade and has been restored from the pre-update snapshot: $rel"
|
||||
healed=$((healed + 1))
|
||||
else
|
||||
warn "Operator file '$rel' was modified by the upgrade but could NOT be auto-restored — recover it manually from $DURABLE_SNAPSHOT_DIR."
|
||||
fi
|
||||
fi
|
||||
done < "$scan"
|
||||
rm -f "$scan"
|
||||
if (( healed > 0 )); then
|
||||
warn "$healed operator file(s) were unexpectedly changed by this upgrade and were restored from the pre-update snapshot. A keep-mode upgrade must never modify operator files — this indicates a framework manifest bug; please report it (#791)."
|
||||
fi
|
||||
}
|
||||
|
||||
# Reconcile contract files after sync: framework-owned overwrite (backup-once),
|
||||
# user-seeded seed-if-absent.
|
||||
reconcile_framework_files() {
|
||||
@@ -326,6 +545,10 @@ run_migrations() {
|
||||
# Remove bin/ directory — all executables now live in the npm CLI.
|
||||
# Scripts that were in bin/ are now in tools/_scripts/.
|
||||
if [[ "$from_version" -lt 2 ]]; then
|
||||
# bin/ and the rails symlink are operator-classified by the manifest (unknown⇒
|
||||
# operator) and thus captured in the durable snapshot; record them as
|
||||
# intentional removals so the post-sync verify net does not restore them.
|
||||
MIGRATION_REMOVED_PATHS+=("bin" "rails")
|
||||
if [[ -d "$TARGET_DIR/bin" ]]; then
|
||||
ok "Removing legacy bin/ directory (executables now in npm CLI)"
|
||||
rm -rf "$TARGET_DIR/bin"
|
||||
@@ -383,6 +606,9 @@ fi
|
||||
# not for a validation failure that has touched nothing yet (#791 blocker-1).
|
||||
if [[ "$INSTALL_MODE" == "keep" ]]; then
|
||||
manifest_load
|
||||
# Durable, operator-scoped backup taken BEFORE any mutation (#791 PR2). Kept
|
||||
# outside the framework tree; recovered later via `mosaic restore`. Fail-open.
|
||||
make_durable_snapshot
|
||||
fi
|
||||
|
||||
# Snapshot before any destructive file operation; restore on interrupt/failure.
|
||||
@@ -421,6 +647,10 @@ run_migrations
|
||||
|
||||
# File-system phase complete and consistent — clear the restore trap.
|
||||
trap - ERR INT TERM
|
||||
# Post-sync safety net: heal any operator file a manifest bug let the sync touch,
|
||||
# using the durable pre-update snapshot (#791 PR2). Runs with the trap disarmed so
|
||||
# a corrective copy can't spuriously trigger a full rollback.
|
||||
verify_operator_surface # VERIFY-NET (#791 PR2)
|
||||
cleanup_snapshot
|
||||
|
||||
# Testability / minimal-install hook: stop after the file-system phase, before any
|
||||
|
||||
Reference in New Issue
Block a user