siftlode/backend/app/routes/playlists.py

"""Playlists: per-user named, ordered collections of videos from the shared catalog. Local
CRUD (create / rename / delete, add / remove / reorder items) plus YouTube two-way sync —
mirror the user's own YouTube playlists in (`/sync-youtube`) and push/revert local edits back
out (`/{id}/push-plan`, `/{id}/revert-youtube`), behind the optional write scope."""

from fastapi import APIRouter, Depends, HTTPException
from pydantic import BaseModel, Field
from sqlalchemy import func, select, and_
from sqlalchemy.exc import IntegrityError
from sqlalchemy.orm import Session, aliased

from app import quota
from app.auth import current_user, has_read_scope, has_write_scope, require_write_scope
from app.db import get_db
from app.feedquery import feed_columns, serialize
from app.models import Channel, Playlist, PlaylistItem, User, Video, VideoState
from app.sync.playlists import (
    merge_playlist,
    plan_merge,
    recompute_dirty,
    repull_playlist,
    sync_user_playlists,
)
from app.ratelimit import RateLimiter
from app.routes._common import get_or_404, owned_or_404, youtube_refusal
from app.youtube.client import YouTubeClient, YouTubeError

router = APIRouter(prefix="/api/playlists", tags=["playlists"])

# SEC-14, same reasoning as the sync module's limiter: a playlist pull lists every playlist the
# caller owns and then every item in each, against the instance-wide YouTube budget. Its own
# limiter rather than a shared one — spending the manual subscription-import allowance must not
# also close the playlist button, and vice versa.
#
# It guards EVERY route that spends under QuotaAction.PLAYLISTS_PULL, not just the bulk one: a
# scripted loop over the single-playlist re-pull drains the same shared budget, and limiting one of
# two routes with the same quota action is the asymmetric fix this codebase keeps re-learning.
# Deliberately NOT on the push side (`push-plan` / `push`): those run on every push attempt,
# including the no-op "already up to date" path, so a 3-per-10-minute allowance would refuse
# legitimate work. Their exposure is tracked as SEC-18 instead.
_playlist_pull_limiter = RateLimiter(max_events=3, window_seconds=600)


def _check_pull_cooldown(user: User) -> None:
    """Shared gate so the two PLAYLISTS_PULL routes cannot drift apart again."""
    if not _playlist_pull_limiter.allow(str(user.id)):
        raise HTTPException(status_code=429, detail={"code": "sync_cooldown"})


def _refused(status: int, reason: str) -> HTTPException:
    """A playlist action the server refuses, as a reason the UI translates
    (`playlists.errors.<reason>`) — a bare English detail reached the Hungarian UI verbatim."""
    return HTTPException(status_code=status, detail={"code": "playlist", "reason": reason})


def _touch(pl: Playlist) -> None:
    """Bump the playlist's `updated_at` for an edit that only writes `playlist_items`.

    `UpdatedAtMixin`'s `onupdate` fires on an UPDATE of the PLAYLIST row, and add / remove /
    reorder / move write the item rows instead — so without this the rail's "recently changed"
    sort would only ever see renames. The assignment is what makes the column mean "last time
    this list changed", which is what the rail promises the reader.

    The DATABASE's clock, like the mixin's own `onupdate`: one sort key written from two clocks
    (this process's and Postgres's) could order a rename and an item edit the wrong way round."""
    pl.updated_at = func.now()


def _next_playlist_position(db: Session, user_id: int) -> int:
    """Append position for a new playlist in this user's rail."""
    return (
        db.scalar(
            select(func.coalesce(func.max(Playlist.position), -1)).where(
                Playlist.user_id == user_id
            )
        )
        + 1
    )


def _next_item_position(db: Session, playlist_id: int) -> int:
    """Append position for a new item at the end of a playlist. Locks the playlist row first: two
    adds (two tabs, the rail and the page) otherwise both read the same max and land on one
    position, and the list's order between them is then arbitrary."""
    db.execute(select(Playlist.id).where(Playlist.id == playlist_id).with_for_update())
    return (
        db.scalar(
            select(func.coalesce(func.max(PlaylistItem.position), -1)).where(
                PlaylistItem.playlist_id == playlist_id
            )
        )
        + 1
    )


def _add_item(db: Session, pl: Playlist, video_id: str, *, mark_dirty: bool) -> bool:
    """Append a video to a playlist if not already present (idempotent). Returns whether it
    was added. `mark_dirty` recomputes the YouTube-sync dirty flag (skip for Watch later)."""
    exists = db.scalar(
        select(PlaylistItem).where(
            PlaylistItem.playlist_id == pl.id, PlaylistItem.video_id == video_id
        )
    )
    if exists is not None:
        return False
    db.add(
        PlaylistItem(playlist_id=pl.id, video_id=video_id, position=_next_item_position(db, pl.id))
    )
    if mark_dirty:
        recompute_dirty(db, pl)
    _touch(pl)
    db.flush()  # the handler commits (CLAUDE.md: helpers flush)
    return True


def _remove_item(db: Session, pl: Playlist, video_id: str, *, mark_dirty: bool) -> bool:
    """Remove a video from a playlist if present (idempotent). Returns whether it was removed.
    `mark_dirty` recomputes the YouTube-sync dirty flag (skip for Watch later)."""
    item = db.scalar(
        select(PlaylistItem).where(
            PlaylistItem.playlist_id == pl.id, PlaylistItem.video_id == video_id
        )
    )
    if item is None:
        return False
    db.delete(item)
    if mark_dirty:
        recompute_dirty(db, pl)
    _touch(pl)
    db.flush()  # the handler commits (CLAUDE.md: helpers flush)
    return True


def _summary(
    pl: Playlist,
    count: int,
    total_duration: int = 0,
    has_video: bool | None = None,
    cover: str | None = None,
) -> dict:
    out = {
        "id": pl.id,
        "name": pl.name,
        "kind": pl.kind,
        "source": pl.source,
        "yt_playlist_id": pl.yt_playlist_id,
        "dirty": pl.dirty,
        "item_count": count,
        "total_duration_seconds": total_duration,
        "cover_thumbnail": cover,
        # When this list last CHANGED (rename, add/remove/move/reorder) — the rail's
        # "recently changed first" sort reads it. See _touch for why it isn't automatic.
        "updated_at": pl.updated_at,
    }
    if has_video is not None:
        out["has_video"] = has_video
    return out


@router.get("")
def list_playlists(
    contains: str | None = None,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> list[dict]:
    """The user's playlists (newest custom order). With `contains=<video_id>`, each entry
    also reports whether that video is already in it — used by the add-to-playlist popover."""
    pls = (
        db.execute(
            select(Playlist)
            .where(Playlist.user_id == user.id)
            .order_by(Playlist.position, Playlist.created_at)
        )
        .scalars()
        .all()
    )
    if not pls:
        return []
    ids = [p.id for p in pls]
    counts = dict(
        db.execute(
            select(PlaylistItem.playlist_id, func.count())
            .where(PlaylistItem.playlist_id.in_(ids))
            .group_by(PlaylistItem.playlist_id)
        ).all()
    )
    durations = dict(
        db.execute(
            select(
                PlaylistItem.playlist_id,
                func.coalesce(func.sum(Video.duration_seconds), 0),
            )
            .join(Video, Video.id == PlaylistItem.video_id)
            .where(PlaylistItem.playlist_id.in_(ids))
            .group_by(PlaylistItem.playlist_id)
        ).all()
    )
    member: set[int] = set()
    if contains:
        member = set(
            db.execute(
                select(PlaylistItem.playlist_id).where(
                    PlaylistItem.playlist_id.in_(ids),
                    PlaylistItem.video_id == contains,
                )
            )
            .scalars()
            .all()
        )
    # Batch the cover thumbnails (first item per playlist by position) in ONE window query
    # instead of a per-playlist SELECT inside _summary (the old N+1).
    rn = (
        func.row_number()
        .over(
            partition_by=PlaylistItem.playlist_id,
            order_by=PlaylistItem.position,
        )
        .label("rn")
    )
    first_items = (
        select(
            PlaylistItem.playlist_id.label("pid"),
            Video.thumbnail_url.label("thumb"),
            rn,
        )
        .join(Video, Video.id == PlaylistItem.video_id)
        .where(PlaylistItem.playlist_id.in_(ids))
        .subquery()
    )
    covers = dict(
        db.execute(
            select(first_items.c.pid, first_items.c.thumb).where(first_items.c.rn == 1)
        ).all()
    )
    return [
        _summary(
            p,
            counts.get(p.id, 0),
            durations.get(p.id, 0),
            (p.id in member) if contains else None,
            covers.get(p.id),
        )
        for p in pls
    ]


class CreatePlaylistIn(BaseModel):
    name: str


# Shared by the two "add a video" endpoints (Watch-later shortcut + explicit add-to-playlist).
class VideoRefIn(BaseModel):
    video_id: str


@router.post("")
def create_playlist(
    body: CreatePlaylistIn,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    name = body.name.strip()
    if not name:
        raise _refused(400, "name_required")
    pl = Playlist(user_id=user.id, name=name, position=_next_playlist_position(db, user.id))
    db.add(pl)
    db.commit()
    return _summary(pl, 0)


def _watch_later(db: Session, user: User) -> Playlist:
    """The user's built-in Watch later playlist, created on first use."""
    pl = db.scalar(
        select(Playlist).where(Playlist.user_id == user.id, Playlist.kind == "watch_later")
    )
    if pl is None:
        pl = Playlist(
            user_id=user.id,
            name="Watch later",
            kind="watch_later",
            position=_next_playlist_position(db, user.id),
        )
        db.add(pl)
        db.flush()  # the id, for the item the caller adds next; the handler commits
    return pl


@router.post("/watch-later")
def add_watch_later(
    body: VideoRefIn,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    """Bookmark shortcut: add a video to the built-in Watch later playlist."""
    video_id = body.video_id
    get_or_404(db, Video, video_id, what="video")
    pl = _watch_later(db, user)
    _add_item(db, pl, video_id, mark_dirty=False)
    db.commit()
    return {"ok": True, "saved": True, "playlist_id": pl.id}


@router.delete("/watch-later/{video_id}")
def remove_watch_later(
    video_id: str,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    pl = db.scalar(
        select(Playlist).where(Playlist.user_id == user.id, Playlist.kind == "watch_later")
    )
    if pl is not None:
        _remove_item(db, pl, video_id, mark_dirty=False)
        db.commit()
    return {"ok": True, "saved": False}


@router.post("/sync-youtube")
def sync_youtube(
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    """Pull the user's YouTube playlists into local mirrors now (read-only direction).
    Also runs automatically on the scheduler; this is the manual 'sync now'."""
    if not has_read_scope(user):
        raise _refused(403, "youtube_read_scope")
    _check_pull_cooldown(user)
    try:
        with quota.attribute(user.id, quota.QuotaAction.PLAYLISTS_PULL):
            return {"ok": True, **sync_user_playlists(db, user)}
    except YouTubeError as exc:
        db.rollback()
        raise youtube_refusal(exc)


@router.post("/{playlist_id}/revert-youtube")
def revert_youtube(
    playlist_id: int,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    """Reset one YouTube-linked playlist to its current YouTube state, discarding local
    edits (and clearing the dirty flag). The user-facing 'undo all my changes' for a list
    once the in-session undo history is gone."""
    pl = owned_or_404(db, Playlist, playlist_id, user, what="playlist")
    if not pl.yt_playlist_id:
        raise _refused(400, "not_on_youtube")
    if not has_read_scope(user):
        raise _refused(403, "youtube_read_scope")
    _check_pull_cooldown(user)
    try:
        with quota.attribute(user.id, quota.QuotaAction.PLAYLISTS_PULL):
            return {"ok": True, **repull_playlist(db, user, pl)}
    except YouTubeError as exc:
        db.rollback()
        raise youtube_refusal(exc)


def _pushable(db: Session, user: User, playlist_id: int) -> Playlist:
    """A local playlist the user may push to YouTube (create or update). The built-in
    Watch later and read-only YouTube mirrors are never pushable."""
    pl = owned_or_404(db, Playlist, playlist_id, user, what="playlist")
    if pl.kind == "watch_later":
        raise _refused(400, "watch_later_not_pushable")
    return pl


@router.get("/{playlist_id}/push-plan")
def push_plan(
    playlist_id: int,
    user: User = Depends(require_write_scope),
    db: Session = Depends(get_db),
) -> dict:
    """Dry run: what a two-way 'Sync to YouTube' merge would do (what each side gains/loses) +
    the quota estimate, so the UI can show a confirm. For a linked playlist this reads the live
    YouTube state (cheap, 1 unit/page). Write scope is required — syncing is a YouTube write."""
    pl = _pushable(db, user, playlist_id)
    try:
        with quota.attribute(user.id, quota.QuotaAction.PLAYLISTS_PUSH):
            plan = plan_merge(db, user, pl)
    except YouTubeError as exc:
        raise youtube_refusal(exc)
    plan["remaining_today"] = quota.remaining_today(db)
    plan["affordable"] = plan["units_estimate"] <= plan["remaining_today"]
    return plan


@router.post("/{playlist_id}/push")
def push(
    playlist_id: int,
    user: User = Depends(require_write_scope),
    db: Session = Depends(get_db),
) -> dict:
    """Two-way sync a local playlist with YouTube (create it on first push, else 3-way merge so
    neither side loses an item). Refuses if the estimated quota exceeds what's left today, so a
    big sync can't strand half-applied. Write scope required (require_write_scope)."""
    pl = _pushable(db, user, playlist_id)
    try:
        with quota.attribute(user.id, quota.QuotaAction.PLAYLISTS_PUSH):
            # Read the live playlist ONCE (linked playlists only) and share it with both the
            # plan and the merge, halving read-quota and closing the second read→write TOCTOU
            # window. A fresh export (no yt_playlist_id) reads nothing.
            live = None
            if pl.yt_playlist_id:
                with YouTubeClient(db, user) as yt:
                    live = (
                        list(yt.iter_playlist_items_with_ids(pl.yt_playlist_id)),
                        yt.get_playlist_snippet(pl.yt_playlist_id),
                    )
            plan = plan_merge(db, user, pl, live=live)
            if plan["units_estimate"] > quota.remaining_today(db):
                raise _refused(429, "quota_exceeded")
            return {"ok": True, **merge_playlist(db, user, pl, live=live)}
    except YouTubeError as exc:
        db.rollback()
        raise youtube_refusal(exc)


@router.get("/{playlist_id}")
def get_playlist(
    playlist_id: int,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    pl = owned_or_404(db, Playlist, playlist_id, user, what="playlist")
    state = aliased(VideoState)
    rows = db.execute(
        select(*feed_columns(user, state))
        .join(PlaylistItem, PlaylistItem.video_id == Video.id)
        .join(Channel, Channel.id == Video.channel_id)
        .outerjoin(state, and_(state.video_id == Video.id, state.user_id == user.id))
        .where(PlaylistItem.playlist_id == pl.id)
        # `id` breaks a position tie the same way on every read (the renumbering add does too).
        .order_by(PlaylistItem.position, PlaylistItem.id)
    ).all()
    return {
        "id": pl.id,
        "name": pl.name,
        "kind": pl.kind,
        "source": pl.source,
        "yt_playlist_id": pl.yt_playlist_id,
        "dirty": pl.dirty,
        "items": [serialize(r) for r in rows],
    }


class RenamePlaylistIn(BaseModel):
    name: str | None = None


@router.patch("/{playlist_id}")
def rename_playlist(
    playlist_id: int,
    body: RenamePlaylistIn,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    pl = owned_or_404(db, Playlist, playlist_id, user, what="playlist")
    if "name" in body.model_fields_set:
        name = (body.name or "").strip()
        if not name:
            raise _refused(400, "name_required")
        if name != pl.name:
            pl.name = name
            recompute_dirty(db, pl)
    db.commit()
    # One aggregate for count + duration (outer join so an empty playlist still returns 0),
    # plus a single cover lookup — was 3 separate round-trips.
    count, total = db.execute(
        select(
            func.count(PlaylistItem.id),
            func.coalesce(func.sum(Video.duration_seconds), 0),
        )
        .select_from(PlaylistItem)
        .outerjoin(Video, Video.id == PlaylistItem.video_id)
        .where(PlaylistItem.playlist_id == pl.id)
    ).one()
    cover = db.scalar(
        select(Video.thumbnail_url)
        .join(PlaylistItem, PlaylistItem.video_id == Video.id)
        .where(PlaylistItem.playlist_id == pl.id)
        .order_by(PlaylistItem.position)
        .limit(1)
    )
    return _summary(pl, count or 0, total or 0, cover=cover)


@router.delete("/{playlist_id}")
def delete_playlist(
    playlist_id: int,
    on_youtube: bool = False,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    pl = owned_or_404(db, Playlist, playlist_id, user, what="playlist")
    if pl.kind == "watch_later":
        raise _refused(400, "watch_later_undeletable")
    if on_youtube:
        if not pl.yt_playlist_id:
            raise _refused(400, "not_on_youtube")
        if not has_write_scope(user):
            raise _refused(403, "youtube_editing_off")
        try:
            with quota.attribute(user.id, quota.QuotaAction.PLAYLISTS_DELETE):
                with YouTubeClient(db, user) as yt:
                    yt.delete_playlist(pl.yt_playlist_id)
        except YouTubeError as exc:
            raise youtube_refusal(exc)
    db.delete(pl)  # items cascade
    db.commit()
    return {"deleted": playlist_id}


class AddItemIn(VideoRefIn):
    # Where the video lands among the list's items, in their stored order (0 = first). Omitted, it
    # is appended. The list page's "Undo" of a removal puts the row back where it was with this —
    # ONE request, because append-then-reorder leaves it at the end whenever the second call fails.
    position: int | None = Field(default=None, ge=0)


@router.post("/{playlist_id}/items")
def add_item(
    playlist_id: int,
    body: AddItemIn,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    pl = owned_or_404(db, Playlist, playlist_id, user, what="playlist")
    video_id = body.video_id
    get_or_404(db, Video, video_id, what="video")
    added = _add_item(db, pl, video_id, mark_dirty=False)
    if added and body.position is not None:
        # Renumber the whole list with the new row at `position` (clamped to the end): positions
        # can have gaps after removals, so "index N" is only meaningful over the ordered rows.
        rows = list(
            db.execute(
                select(PlaylistItem)
                .where(PlaylistItem.playlist_id == pl.id)
                .order_by(PlaylistItem.position, PlaylistItem.id)
            ).scalars()
        )
        new = next(r for r in rows if r.video_id == video_id)
        rows.remove(new)
        rows.insert(min(body.position, len(rows)), new)
        for pos, row in enumerate(rows):
            row.position = pos
    recompute_dirty(db, pl)
    db.commit()
    return {"ok": True, "playlist_id": pl.id, "video_id": video_id}


@router.delete("/{playlist_id}/items/{video_id}")
def remove_item(
    playlist_id: int,
    video_id: str,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    pl = owned_or_404(db, Playlist, playlist_id, user, what="playlist")
    _remove_item(db, pl, video_id, mark_dirty=True)
    db.commit()
    return {"ok": True, "playlist_id": pl.id, "video_id": video_id}


class MoveItemIn(BaseModel):
    target_playlist_id: int


@router.post("/{playlist_id}/items/{video_id}/move")
def move_item(
    playlist_id: int,
    video_id: str,
    body: MoveItemIn,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    """Move one video from a playlist into another of the caller's playlists, atomically.

    ONE transaction on purpose. The obvious client-side shape — add to the target, then remove
    from the source — leaves the video in BOTH lists whenever the second call fails, which is
    exactly the kind of half-applied state this codebase treats as a bug rather than an edge
    case. Idempotent: if the video is already in the target, the source row is simply dropped
    (moving into a list that already has it is a removal, not a duplicate)."""
    src = owned_or_404(db, Playlist, playlist_id, user, what="playlist")
    # Its own reason: "this playlist doesn't exist any more" about a TARGET that is gone was read as
    # the list on screen — which is still there.
    dst = owned_or_404(db, Playlist, body.target_playlist_id, user, what="move_target")
    if src.id == dst.id:
        raise HTTPException(
            status_code=400, detail={"code": "playlist_move", "reason": "same_playlist"}
        )
    item = db.scalar(
        select(PlaylistItem).where(
            PlaylistItem.playlist_id == src.id, PlaylistItem.video_id == video_id
        )
    )
    if item is None:
        # A concurrent edit (another tab, or a YouTube re-pull) already took it out.
        raise HTTPException(
            status_code=404, detail={"code": "playlist_move", "reason": "not_in_playlist"}
        )
    already = db.scalar(
        select(PlaylistItem).where(
            PlaylistItem.playlist_id == dst.id, PlaylistItem.video_id == video_id
        )
    )
    dst_changed = False
    if already is None:
        # Re-parent the existing row rather than delete+insert: `added_at` ("when I saved this")
        # survives the move, and there is no window where the video belongs to neither list. The
        # check above is not a lock: a second tab's add or the scheduler's YouTube merge can insert
        # the same (playlist, video) in between, and uq_playlist_video then refuses the re-parent.
        # That is the already-present outcome arriving late, not a failure — answer it the same way
        # instead of a raw 500.
        try:
            with db.begin_nested():
                item.playlist_id = dst.id
                item.position = _next_item_position(db, dst.id)
                db.flush()
            dst_changed = True
        # silent-ok: the conflict IS the answer — the target already holds the video, which is the
        # idempotent outcome; the savepoint put the row back in the source list, dropped below.
        except IntegrityError:
            pass
    if not dst_changed:
        db.delete(item)
    # The source always changed; the target only when the row landed in it. `_touch` on a target
    # that already had the video promoted an untouched list in the rail's "recently changed" sort.
    recompute_dirty(db, src)
    _touch(src)
    if dst_changed:
        recompute_dirty(db, dst)
        _touch(dst)
    db.commit()
    return {"ok": True, "from_playlist_id": src.id, "to_playlist_id": dst.id, "video_id": video_id}


class ReorderItemsIn(BaseModel):
    video_ids: list[str] = []


@router.put("/{playlist_id}/order")
def reorder_items(
    playlist_id: int,
    body: ReorderItemsIn,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    # Locked: a concurrent add between reading the items and writing the order would collide.
    pl = owned_or_404(db, Playlist, playlist_id, user, what="playlist", lock=True)
    order = body.video_ids
    items = {
        it.video_id: it
        for it in db.execute(
            select(PlaylistItem).where(PlaylistItem.playlist_id == pl.id)
        ).scalars()
    }
    pos = 0
    seen: set[str] = set()
    for vid in order:
        it = items.get(vid)
        if it is not None:
            it.position = pos
            pos += 1
            seen.add(vid)
    # Any items the payload omitted (e.g. added concurrently in another tab) keep their relative
    # order but get fresh trailing positions, so no two items collide on the same position.
    for it in sorted(
        (it for vid, it in items.items() if vid not in seen), key=lambda i: i.position
    ):
        it.position = pos
        pos += 1
    recompute_dirty(db, pl)
    _touch(pl)
    db.commit()
    return {"ok": True, "playlist_id": pl.id, "count": pos}