feat(reader): a Google Takeout export becomes watch state and Watch later

The YouTube API reads neither a user's watch history nor their Watch later list, so the Takeout
export is the only way in. `POST /api/takeout` takes one file of it (watch-history.json or
Watch later-videos.csv, told apart by content), keeps its videos in `takeout_items` and queues the
user's `takeout_import` run, whose outcome reaches their inbox.

The run marks watched the known videos the Shorts probe has cleared, at the Takeout time; a Short
is not marked, and a state the user set here (watched, hidden, or changed after that time) wins, by
the upsert's own condition. A video the catalog does not know yet waits with no outcome. Watch later
videos are fetched if unknown and appended oldest first.

An ad-hoc run can now ask for a completion notice (`run_ad_hoc(..., notify=True)`).

backend/app/reader/service.py

@@ -15,7 +15,17 @@ from sqlalchemy.orm import Session
 
 from app.models import User
 from app.reader import queries
-from app.reader.models import ChannelTag, Playlist, PlaylistItem, SavedView, Tag, VideoState
+from app.reader.models import (
+    ChannelTag,
+    Playlist,
+    PlaylistItem,
+    SavedView,
+    Tag,
+    TakeoutItem,
+    TakeoutKind,
+    TakeoutOutcome,
+    VideoState,
+)
 from app.sync.playlists import lock_playlists, recompute_dirty
 from app.userscope import owned_by
 
@@ -495,3 +505,113 @@ def detach_user_tag(db: Session, user: User, channel_id: str, tag_id: int) -> No
     if row is not None:
         db.delete(row)
         db.flush()
+
+
+# --- Google Takeout --------------------------------------------------------------------------
+
+_TAKEOUT_BATCH = 1000
+
+
+def stage_takeout(
+    db: Session, user: User, kind: TakeoutKind, rows: dict[str, tuple[datetime, str | None]]
+) -> None:
+    """Keep the videos of one Takeout file, `{video id: (time, channel id)}`, for the import job.
+    A second upload of the same export, or a newer one, adds what is new: a video already kept keeps
+    the later time, and a row the import has settled keeps its outcome."""
+    values = [
+        {"user_id": user.id, "kind": kind, "video_id": vid, "at": at, "channel_id": channel}
+        for vid, (at, channel) in rows.items()
+    ]
+    for start in range(0, len(values), _TAKEOUT_BATCH):
+        stmt = pg_insert(TakeoutItem).values(values[start : start + _TAKEOUT_BATCH])
+        db.execute(
+            stmt.on_conflict_do_update(
+                constraint="uq_takeout_item",
+                set_={
+                    "at": func.greatest(TakeoutItem.at, stmt.excluded.at),
+                    "channel_id": func.coalesce(stmt.excluded.channel_id, TakeoutItem.channel_id),
+                },
+            )
+        )
+    db.flush()
+
+
+def _settle(db: Session, ids: list[int], outcome: TakeoutOutcome) -> None:
+    for start in range(0, len(ids), _TAKEOUT_BATCH):
+        db.execute(
+            update(TakeoutItem)
+            .where(TakeoutItem.id.in_(ids[start : start + _TAKEOUT_BATCH]))
+            .values(outcome=outcome)
+        )
+
+
+def apply_takeout_watched(db: Session, user: User) -> dict[str, int]:
+    """Mark watched what the user watched on YouTube, for the videos the catalog knows and has probed
+    for Shorts; the rest wait. `watched_at` is the Takeout time. A Short is not marked (swiping one
+    past is not watching it), and a state the user set here wins: watched or hidden, or anything
+    changed after the Takeout time. The upsert's own condition is that rule, so a state set while
+    the import runs wins too."""
+    short: list[int] = []
+    todo: dict[str, tuple[int, datetime]] = {}
+    for row_id, video_id, at, is_short in queries.takeout_watched_ready(db, user):
+        if is_short:
+            short.append(row_id)
+        else:
+            todo[video_id] = (row_id, at)
+    marked: set[str] = set()
+    items = list(todo.items())
+    now = datetime.now(timezone.utc)
+    for start in range(0, len(items), _TAKEOUT_BATCH):
+        stmt = pg_insert(VideoState).values(
+            [
+                {"user_id": user.id, "video_id": vid, "status": "watched", "watched_at": at}
+                for vid, (_, at) in items[start : start + _TAKEOUT_BATCH]
+            ]
+        )
+        marked.update(
+            db.execute(
+                stmt.on_conflict_do_update(
+                    constraint="uq_user_video",
+                    set_={
+                        "status": "watched",
+                        "watched_at": stmt.excluded.watched_at,
+                        "updated_at": now,
+                    },
+                    where=(VideoState.status == "new")
+                    & (VideoState.updated_at < stmt.excluded.watched_at),
+                ).returning(VideoState.video_id)
+            ).scalars()
+        )
+    kept = [row_id for vid, (row_id, _) in items if vid not in marked]
+    _settle(db, [todo[vid][0] for vid in marked], TakeoutOutcome.WATCHED)
+    _settle(db, kept, TakeoutOutcome.KEPT)
+    _settle(db, short, TakeoutOutcome.SHORT)
+    db.flush()
+    return {"watched": len(marked), "kept": len(kept), "shorts": len(short)}
+
+
+def apply_takeout_watch_later(db: Session, user: User) -> dict[str, int]:
+    """Put the videos of the user's YouTube Watch later list into theirs here, oldest first, after
+    what it already holds. Called once the catalog has fetched what it could: a video still unknown
+    is one YouTube no longer has."""
+    waiting = queries.takeout_waiting(db, user, TakeoutKind.WATCH_LATER)
+    if not waiting:
+        return {}
+    known = queries.known_video_ids(db, [vid for _, vid in waiting])
+    pl = watch_later(db, user)
+    done: dict[TakeoutOutcome, list[int]] = {o: [] for o in TakeoutOutcome}
+    for row_id, vid in waiting:
+        if vid not in known:
+            done[TakeoutOutcome.MISSING].append(row_id)
+        elif add_item(db, pl, vid, mark_dirty=False):
+            done[TakeoutOutcome.ADDED].append(row_id)
+        else:
+            done[TakeoutOutcome.PRESENT].append(row_id)
+    for outcome, ids in done.items():
+        _settle(db, ids, outcome)
+    db.flush()
+    return {
+        "watch_later_added": len(done[TakeoutOutcome.ADDED]),
+        "watch_later_present": len(done[TakeoutOutcome.PRESENT]),
+        "watch_later_missing": len(done[TakeoutOutcome.MISSING]),
+    }