0.32.1: backup/restore fixes (audit findings, all paths live-verified)

- backup_filename() crashed with NameError (bare now()) since 0.8.0 —
  broke every scheduled backup at the upload step, agent backup download
  and the central remote-backup/push endpoints. The local manual path
  worked only because the router had its own copy (now an alias).
- restore: the manifest stack_id from an uploaded backup is now slugified
  too — a crafted '../../...' id could previously escape STACKS_DIR.
- create_backup no longer starts a previously-stopped stack (stop/restart
  only when the stack was actually running).
- overwrite-restore wipes the existing volume contents before extracting,
  so files created since the backup no longer survive underneath it.

Verified end-to-end: full/config backup contents (compose, .env, .secrets,
bind dirs, extras, volume tars), delete→restore round-trip incl. volume
data, rename restore with volume re-prefixing, 409 conflict + overwrite,
traversal guard, scheduled run + retention prune + restore-from against
real MinIO, and the complete remote-agent cycle (download/push/restore).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

backend/routers/backups.py

@@ -29,10 +29,7 @@ def _ip(request: Request) -> str:
     return request.client.host if request.client else "unknown"
 
 
-def _backup_filename(stack_id: str, include_volumes: bool) -> str:
-    date = compose_service.now().strftime("%Y%m%d-%H%M%S")
-    suffix = "full" if include_volumes else "config"
-    return f"backup-{stack_id}-{suffix}-{date}.tar.gz"
+_backup_filename = backup_service.backup_filename
 
 
 @router.get("/{stack_id}/backup")

backend/services/backup_service.py

@@ -53,7 +53,7 @@ def backup_basename(stack_id: str, prefix: Optional[str] = None) -> str:
 
 
 def backup_filename(stack_id: str, include_volumes: bool, prefix: Optional[str] = None) -> str:
-    date = now().strftime("%Y%m%d-%H%M%S")
+    date = compose_service.now().strftime("%Y%m%d-%H%M%S")
     suffix = "full" if include_volumes else "config"
     return f"{backup_basename(stack_id, prefix)}-{suffix}-{date}.tar.gz"
 
@@ -99,10 +99,22 @@ def _export_volume(full_name: str) -> bytes:
 def _restore_volume(full_name: str, labels: dict, tar_bytes: bytes) -> None:
     client = get_client()
     _ensure_helper_image(client)
+    existed = True
     try:
         safe_call(client.volumes.get, full_name)
     except DockerError:
+        existed = False
         safe_call(client.volumes.create, name=full_name, labels=labels or {})
+    if existed:
+        # Restore means "back to the snapshot": clear the current contents so
+        # files created/kept since the backup don't survive underneath it.
+        safe_call(
+            client.containers.run,
+            settings.BACKUP_HELPER_IMAGE,
+            ["sh", "-c", "find /v -mindepth 1 -delete"],
+            volumes={full_name: {"bind": "/v", "mode": "rw"}},
+            remove=True,
+        )
     container = safe_call(
         client.containers.create,
         settings.BACKUP_HELPER_IMAGE,
@@ -159,14 +171,16 @@ async def create_backup(
 
     volumes = _compose_volumes(stack_id) if include_volumes else []
 
-    # For a consistent volume snapshot, stop the stack first.
+    # For a consistent volume snapshot, stop the stack first — but only if it
+    # is actually running, so backing up a stopped stack doesn't start it.
     stopped = False
     if include_volumes and stop_first and volumes:
-        try:
-            await compose_service.stop(stack_id)
-            stopped = True
-        except Exception as exc:  # noqa: BLE001
-            logger.warning("Could not stop %s before backup: %s", stack_id, exc)
+        if compose_service.compute_status(stack_id) not in ("stopped", "unknown"):
+            try:
+                await compose_service.stop(stack_id)
+                stopped = True
+            except Exception as exc:  # noqa: BLE001
+                logger.warning("Could not stop %s before backup: %s", stack_id, exc)
 
     try:
         manifest = {
@@ -247,9 +261,12 @@ def restore_backup(
 ) -> dict:
     """Restore a backup. Returns {stack_id, name, volumes_restored}."""
     manifest = read_manifest(tar_path)
-    stack_id = target_id or manifest.get("stack_id")
-    if not stack_id:
+    raw_id = target_id or manifest.get("stack_id") or ""
+    if not raw_id.strip():
         raise BackupError("Backup manifest has no stack id")
+    # Slugify whichever id we end up using — the manifest comes from an
+    # uploaded file, so its stack_id must never be able to escape STACKS_DIR.
+    stack_id = compose_service.slugify(raw_id)
 
     directory = compose_service.stack_dir(stack_id)
     exists = os.path.isdir(directory)

backend/version.py

@@ -1,3 +1,3 @@
 """Single source of truth for the StackPilot release version."""
 
-APP_VERSION = "0.32.0"
+APP_VERSION = "0.32.1"

frontend/package.json

@@ -1,7 +1,7 @@
 {
   "name": "stackpilot-frontend",
   "private": true,
-  "version": "0.32.0",
+  "version": "0.32.1",
   "type": "module",
   "scripts": {
     "dev": "vite",