US06-03: Preserve Offline Identity and Review Evidence (#79)

photo_pipeline/services/archives.py

@@ -28,7 +28,11 @@ Blocker codes: ``no_library_root``, ``location_offline``, ``wrong_volume``,
 ``unsafe_destination``, ``destination_not_writable``, ``manifest_unwritable``,
 ``insufficient_capacity``, ``backup_unavailable``, ``lock_conflict``,
 ``rename_pending``, ``empty_scope``, ``destination_collision``,
-``upload_unverified``, ``bytes_changed``, ``file_missing``.
+``upload_unverified``, ``bytes_changed``, ``file_missing``, ``preview_unavailable``.
+
+Preflight also *creates* the durable comparison preview of every asset in scope
+(US06-03): it is the evidence duplicate review falls back on once the original is
+on a medium that may be offline, so it has to exist before the original leaves.
 
 Like upload preflight, the confirmation token is *derived* from the report rather
 than stored: any change to the scope, the bytes, the destination, or the blockers
@@ -59,14 +63,16 @@ from photo_pipeline.models import ArchiveLocation, Asset, UploadBatch, UploadIte
 from photo_pipeline.path_policy import PathPolicyError, is_excluded, normalize_root, resolve_within
 from photo_pipeline.services.albums import album_label
 from photo_pipeline.services.archive_journal import ArchiveJournal
+from photo_pipeline.services.availability import MARKER_NAME, read_marker as _read_marker
+from photo_pipeline.services.availability import refresh as refresh_availability
 from photo_pipeline.services.hashing import sha256_file
 from photo_pipeline.services.jobs import JobService
 from photo_pipeline.services.rename_journal import RenameJournal
+from photo_pipeline.services.thumbnails import ThumbnailService
 from photo_pipeline.services.upload_reports import VERIFIED
 
 PREFLIGHT_VERSION = 1
 TOKEN_PREFIX = f"v{PREFLIGHT_VERSION}"
-MARKER_NAME = ".photo-pipeline-archive.json"
 MANIFEST_NAME = "archive-manifest.json"
 
 # Upload outcomes that prove Immich holds these exact bytes. ``skipped``/``failed``/
@@ -163,7 +169,10 @@ class ArchiveService:
                     location.capabilities = json.dumps(probe["capabilities"])
                 reports.append(self._location_report(location, probe=probe))
             session.commit()
-            return reports
+        # A medium that just appeared or vanished changes what is readable, so the
+        # archived assets are re-derived from the same probe (US06-03).
+        refresh_availability(self._session_factory)
+        return reports
 
     # ── preflight ─────────────────────────────────────────────────────────────
 
@@ -420,7 +429,10 @@ class ArchiveService:
 
     def _album(self, name: str, rows: list[dict], root: Path, *, reachable: bool) -> dict:
         folder = Path(rows[0]["path"]).parent
-        items = sorted((_item(row) for row in rows), key=lambda item: item["current_path"])
+        items = sorted(
+            (self._with_preview(_item(row)) for row in rows),
+            key=lambda item: item["current_path"],
+        )
         blocked = [item for item in items if item["blockers"]]
         blockers: list[dict] = []
 
@@ -456,6 +468,30 @@ class ArchiveService:
             "assets": items,
         }
 
+    def _with_preview(self, item: dict) -> dict:
+        """Create the durable comparison preview while the original is still here.
+
+        This is the last moment it can be made: once the file is archived and the
+        medium leaves, only the retained preview can answer "is this new photo the
+        same picture?". An original that cannot be decoded at all has no preview to
+        keep — its hashes and metadata stay the evidence — but a preview that fails
+        for any other reason blocks the archive (concept §9).
+        """
+        preview = self._previews().ensure_protected(item["asset_id"])
+        item["preview"] = preview
+        if preview["state"] == "unavailable" and not item["blockers"]:
+            item["blockers"].append(
+                _issue(
+                    "preview_unavailable",
+                    f"a durable comparison preview of {item['current_path']} could not be "
+                    f"created ({preview['error_code']})",
+                )
+            )
+        return item
+
+    def _previews(self) -> ThumbnailService:
+        return ThumbnailService(self._session_factory, self._config)
+
 
 # ── internals ────────────────────────────────────────────────────────────────
 
@@ -512,13 +548,6 @@ def _transfer_method(folder: Path, root: Path) -> str:
     return "copy_verify_remove"
 
 
-def _read_marker(root: Path) -> dict | None:
-    try:
-        return json.loads((root / MARKER_NAME).read_text(encoding="utf-8"))
-    except (OSError, ValueError):
-        return None
-
-
 def _probe_write(path: Path, payload: bytes, *, keep: bool = False) -> str | None:
     """Write ``payload`` to ``path``; return the failure detail or ``None``."""
     try: