Track snapshot base lineage in Django

src/pobsync_backend/snapshot_discovery.py

@@ -55,6 +55,7 @@ def discover_snapshots(
                     created += 1
                 else:
                     updated += 1
+        resolve_base_links(host=host_config)
 
     return {
         "ok": True,
@@ -66,8 +67,15 @@ def discover_snapshots(
 
 def upsert_snapshot_record(*, host: HostConfig, kind: str, snapshot_dir: Path) -> tuple[SnapshotRecord, bool]:
     meta = read_snapshot_meta(snapshot_dir)
+    base_defaults = _base_defaults_from_meta(meta)
     defaults = {
         "path": str(snapshot_dir),
+        **base_defaults,
+        "base": _resolve_base_record(
+            host=host,
+            kind=base_defaults["base_kind"],
+            dirname=base_defaults["base_dirname"],
+        ),
         "status": str(meta.get("status") or ""),
         "started_at": parse_snapshot_datetime(snapshot_dir.name, meta, "started_at"),
         "ended_at": parse_snapshot_datetime(snapshot_dir.name, meta, "ended_at"),
@@ -81,6 +89,26 @@ def upsert_snapshot_record(*, host: HostConfig, kind: str, snapshot_dir: Path) -
     )
 
 
+def resolve_base_links(*, host: HostConfig | None = None) -> int:
+    snapshot_qs = SnapshotRecord.objects.exclude(base_dirname="").filter(base__isnull=True)
+    if host is not None:
+        snapshot_qs = snapshot_qs.filter(host=host)
+
+    updated = 0
+    for snapshot in snapshot_qs.select_related("host"):
+        base = _resolve_base_record(
+            host=snapshot.host,
+            kind=snapshot.base_kind,
+            dirname=snapshot.base_dirname,
+        )
+        if base is None:
+            continue
+        snapshot.base = base
+        snapshot.save(update_fields=["base"])
+        updated += 1
+    return updated
+
+
 def infer_snapshot_kind(snapshot_path: Path) -> str:
     parent = snapshot_path.parent.name
     if parent == "scheduled":
@@ -92,6 +120,29 @@ def infer_snapshot_kind(snapshot_path: Path) -> str:
     raise ValueError(f"Cannot infer snapshot kind from path: {snapshot_path}")
 
 
+def _base_defaults_from_meta(meta: dict[str, Any]) -> dict[str, Any]:
+    base = meta.get("base")
+    if not isinstance(base, dict):
+        base = {}
+
+    return {
+        "base_kind": _base_value(base.get("kind")),
+        "base_dirname": _base_value(base.get("dirname")),
+        "base_path": _base_value(base.get("path")),
+        "base_snapshot_id": _base_value(base.get("id")),
+    }
+
+
+def _base_value(value: Any) -> str:
+    return value if isinstance(value, str) else ""
+
+
+def _resolve_base_record(*, host: HostConfig, kind: str, dirname: str) -> SnapshotRecord | None:
+    if not kind or not dirname:
+        return None
+    return SnapshotRecord.objects.filter(host=host, kind=kind, dirname=dirname).first()
+
+
 def _parse_iso_z(value: str) -> datetime | None:
     try:
         if value.endswith("Z"):