siftlode/backend/app/models.py

from datetime import date, datetime

from sqlalchemy import (
    BigInteger,
    Boolean,
    Date,
    DateTime,
    Float,
    ForeignKey,
    Integer,
    JSON,
    String,
    Text,
    UniqueConstraint,
    func,
)
from sqlalchemy.orm import Mapped, mapped_column, relationship

from app.db import Base


class User(Base):
    __tablename__ = "users"

    id: Mapped[int] = mapped_column(primary_key=True)
    google_sub: Mapped[str] = mapped_column(String(64), unique=True, index=True)
    email: Mapped[str] = mapped_column(String(320), unique=True, index=True)
    display_name: Mapped[str | None] = mapped_column(String(255))
    avatar_url: Mapped[str | None] = mapped_column(String(1024))
    role: Mapped[str] = mapped_column(String(16), default="user", server_default="user")
    # The single shared "demo" account: signed into without Google OAuth (via a whitelisted
    # email on the login page), has no OAuth token / YouTube scope, and its per-user state is
    # shared by everyone who enters this way. Exactly one such row is expected.
    is_demo: Mapped[bool] = mapped_column(
        Boolean, default=False, server_default="false", index=True
    )
    # Free-form UI preferences (theme, color scheme, font scale, default filters…).
    preferences: Mapped[dict | None] = mapped_column(JSON)
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )

    token: Mapped["OAuthToken | None"] = relationship(
        back_populates="user", uselist=False, cascade="all, delete-orphan"
    )
    subscriptions: Mapped[list["Subscription"]] = relationship(
        back_populates="user", cascade="all, delete-orphan"
    )


class OAuthToken(Base):
    __tablename__ = "oauth_tokens"

    id: Mapped[int] = mapped_column(primary_key=True)
    user_id: Mapped[int] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), unique=True
    )
    # Refresh token encrypted at rest (Fernet). Access token is short-lived and low risk.
    refresh_token_enc: Mapped[str | None] = mapped_column(String)
    access_token: Mapped[str | None] = mapped_column(String)
    expiry: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    scopes: Mapped[str | None] = mapped_column(String)
    updated_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now(), onupdate=func.now()
    )

    user: Mapped["User"] = relationship(back_populates="token")


class Invite(Base):
    """Access-request / whitelist row. Source of truth for who may sign in; the env
    ALLOWED_EMAILS/ADMIN_EMAILS act only as a bootstrap fallback (see auth.is_allowed)."""

    __tablename__ = "invites"

    id: Mapped[int] = mapped_column(primary_key=True)
    email: Mapped[str] = mapped_column(String(320), unique=True, index=True)
    # pending | approved | denied
    status: Mapped[str] = mapped_column(
        String(16), default="pending", server_default="pending"
    )
    note: Mapped[str | None] = mapped_column(Text)
    requested_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )
    decided_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    decided_by: Mapped[str | None] = mapped_column(String(320))  # admin email


class DemoWhitelist(Base):
    """Emails that may enter the shared demo account from the login page (no Google OAuth).
    A hidden, admin-curated list of "keys to the same door" — every entry logs into the one
    shared demo user. Distinct from Invite (which gates real Google sign-in)."""

    __tablename__ = "demo_whitelist"

    id: Mapped[int] = mapped_column(primary_key=True)
    email: Mapped[str] = mapped_column(String(320), unique=True, index=True)
    note: Mapped[str | None] = mapped_column(Text)
    added_by: Mapped[str | None] = mapped_column(String(320))  # admin email
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )


class Channel(Base):
    """A YouTube channel. Shared across all users (one channel's videos are the same
    for everyone), so its expensive metadata is fetched and stored only once."""

    __tablename__ = "channels"

    id: Mapped[str] = mapped_column(String(32), primary_key=True)  # "UC..." channel id
    title: Mapped[str | None] = mapped_column(String(255))
    handle: Mapped[str | None] = mapped_column(String(255))
    description: Mapped[str | None] = mapped_column(Text)
    thumbnail_url: Mapped[str | None] = mapped_column(String(1024))
    uploads_playlist_id: Mapped[str | None] = mapped_column(String(64))
    subscriber_count: Mapped[int | None] = mapped_column(BigInteger)
    video_count: Mapped[int | None] = mapped_column(BigInteger)
    topic_categories: Mapped[list | None] = mapped_column(JSON)
    default_language: Mapped[str | None] = mapped_column(String(16))
    country: Mapped[str | None] = mapped_column(String(8))

    # Sync bookkeeping.
    details_synced_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    recent_synced_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    last_rss_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    backfill_cursor: Mapped[str | None] = mapped_column(String(128))
    backfill_done: Mapped[bool] = mapped_column(
        Boolean, default=False, server_default="false"
    )
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )

    videos: Mapped[list["Video"]] = relationship(back_populates="channel")
    subscriptions: Mapped[list["Subscription"]] = relationship(back_populates="channel")


class Subscription(Base):
    """Per-user link to a channel, with the user's own priority/visibility overrides."""

    __tablename__ = "subscriptions"
    __table_args__ = (UniqueConstraint("user_id", "channel_id", name="uq_user_channel"),)

    id: Mapped[int] = mapped_column(primary_key=True)
    user_id: Mapped[int] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), index=True
    )
    channel_id: Mapped[str] = mapped_column(
        ForeignKey("channels.id", ondelete="CASCADE"), index=True
    )
    # YouTube's subscription resource id, needed to unsubscribe via the API.
    yt_subscription_id: Mapped[str | None] = mapped_column(String(128))
    priority: Mapped[int] = mapped_column(Integer, default=0, server_default="0")
    hidden: Mapped[bool] = mapped_column(Boolean, default=False, server_default="false")
    # Per-user opt-in to full-history (deep) backfill of this channel. Default off so a
    # new user's unique channels don't trigger a big shared-quota burst; the deep
    # scheduler only picks up channels at least one user has requested.
    deep_requested: Mapped[bool] = mapped_column(
        Boolean, default=False, server_default="false"
    )
    subscribed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )

    user: Mapped["User"] = relationship(back_populates="subscriptions")
    channel: Mapped["Channel"] = relationship(back_populates="subscriptions")


class Video(Base):
    """A YouTube video. Shared across users; per-user state lives elsewhere."""

    __tablename__ = "videos"

    id: Mapped[str] = mapped_column(String(16), primary_key=True)  # video id
    channel_id: Mapped[str] = mapped_column(
        ForeignKey("channels.id", ondelete="CASCADE"), index=True
    )
    title: Mapped[str | None] = mapped_column(Text)
    description: Mapped[str | None] = mapped_column(Text)
    published_at: Mapped[datetime | None] = mapped_column(
        DateTime(timezone=True), index=True
    )
    thumbnail_url: Mapped[str | None] = mapped_column(String(1024))
    duration_seconds: Mapped[int | None] = mapped_column(Integer)
    view_count: Mapped[int | None] = mapped_column(BigInteger)
    like_count: Mapped[int | None] = mapped_column(BigInteger)
    category_id: Mapped[int | None] = mapped_column(Integer)
    topic_categories: Mapped[list | None] = mapped_column(JSON)
    default_language: Mapped[str | None] = mapped_column(String(16))
    detected_language: Mapped[str | None] = mapped_column(String(16))
    is_short: Mapped[bool] = mapped_column(
        Boolean, default=False, server_default="false", index=True
    )
    # Whether the youtube.com/shorts/<id> probe has run for this video.
    shorts_probed: Mapped[bool] = mapped_column(
        Boolean, default=False, server_default="false", index=True
    )
    # none | live | upcoming | premiere | was_live
    live_status: Mapped[str] = mapped_column(
        String(16), default="none", server_default="none", index=True
    )
    enriched_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    # videos.list?part=status fields (populated during enrichment); used by the
    # maintenance/validation job to decide whether a video is playable anywhere.
    embeddable: Mapped[bool | None] = mapped_column(Boolean)
    privacy_status: Mapped[str | None] = mapped_column(String(16))  # public|unlisted|private
    upload_status: Mapped[str | None] = mapped_column(String(16))  # processed|failed|rejected|deleted
    # Maintenance/validation lifecycle. last_checked_at drives the rolling re-validation
    # (least-recently-checked first); unavailable_since marks a video as currently
    # unplayable (hidden from the feed immediately, hard-deleted after a grace period);
    # unavailable_reason records why (deleted|private|paywalled|abandoned|stuck_live).
    last_checked_at: Mapped[datetime | None] = mapped_column(
        DateTime(timezone=True), index=True
    )
    unavailable_since: Mapped[datetime | None] = mapped_column(
        DateTime(timezone=True), index=True
    )
    unavailable_reason: Mapped[str | None] = mapped_column(String(24))
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )

    channel: Mapped["Channel"] = relationship(back_populates="videos")


class Tag(Base):
    """A label. System tags (user_id NULL) are computed automatically and shared by all
    users; user tags (user_id set) are personal. category groups them in the UI."""

    __tablename__ = "tags"

    id: Mapped[int] = mapped_column(primary_key=True)
    user_id: Mapped[int | None] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), index=True
    )
    name: Mapped[str] = mapped_column(String(64))
    color: Mapped[str | None] = mapped_column(String(16))
    # language | topic | other
    category: Mapped[str] = mapped_column(
        String(16), default="other", server_default="other"
    )
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )


class ChannelTag(Base):
    """Links a tag to a channel. source='auto' rows are managed by the auto-tagger and
    regenerated freely; source='user' rows are never touched by the system."""

    __tablename__ = "channel_tags"
    __table_args__ = (
        UniqueConstraint("channel_id", "tag_id", "user_id", name="uq_channel_tag"),
    )

    id: Mapped[int] = mapped_column(primary_key=True)
    channel_id: Mapped[str] = mapped_column(
        ForeignKey("channels.id", ondelete="CASCADE"), index=True
    )
    tag_id: Mapped[int] = mapped_column(
        ForeignKey("tags.id", ondelete="CASCADE"), index=True
    )
    # NULL = system/auto link visible to everyone; set = a specific user's link.
    user_id: Mapped[int | None] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE")
    )
    source: Mapped[str] = mapped_column(String(8), default="auto", server_default="auto")
    confidence: Mapped[float | None] = mapped_column(Float)


class VideoState(Base):
    """Per-user watch state for a video. Rows exist only for non-default states; the
    absence of a row means 'new/unseen'."""

    __tablename__ = "video_states"
    __table_args__ = (UniqueConstraint("user_id", "video_id", name="uq_user_video"),)

    id: Mapped[int] = mapped_column(primary_key=True)
    user_id: Mapped[int] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), index=True
    )
    video_id: Mapped[str] = mapped_column(
        ForeignKey("videos.id", ondelete="CASCADE"), index=True
    )
    # new | watched | saved | hidden
    status: Mapped[str] = mapped_column(String(12), default="new", server_default="new")
    watched_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    # Resume position (seconds into the video) for the in-app player. Orthogonal to
    # status: a partially-watched video keeps status "new" but a non-zero position, so
    # it can render a progress bar and match the "in progress" feed filter. 0 = not
    # started / finished (trivially-early and near-finished positions are not stored).
    position_seconds: Mapped[int] = mapped_column(
        Integer, default=0, server_default="0", nullable=False
    )
    progress_updated_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    updated_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now(), onupdate=func.now()
    )


class ApiQuotaUsage(Base):
    """Tracks YouTube Data API units spent per Pacific-time day (the quota resets at
    midnight Pacific). The whole app shares one daily budget."""

    __tablename__ = "api_quota_usage"

    day: Mapped[date] = mapped_column(Date, primary_key=True)
    units_used: Mapped[int] = mapped_column(Integer, default=0, server_default="0")


class QuotaEvent(Base):
    """Per-spend audit log for YouTube API quota attribution. `user_id` is the end-user
    whose action caused the spend; NULL means background/system work (scheduler backfill,
    enrichment, resync). The aggregate budget still lives in ApiQuotaUsage; this is detail."""

    __tablename__ = "quota_events"

    id: Mapped[int] = mapped_column(primary_key=True)
    # SET NULL on user delete: keep the audit trail (it just becomes system-attributed).
    user_id: Mapped[int | None] = mapped_column(
        ForeignKey("users.id", ondelete="SET NULL"), index=True
    )
    action: Mapped[str] = mapped_column(String(40), index=True)
    units: Mapped[int] = mapped_column(Integer)
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now(), index=True
    )


class AppState(Base):
    """Single-row global app state (admin-controlled)."""

    __tablename__ = "app_state"

    id: Mapped[int] = mapped_column(primary_key=True, default=1)
    sync_paused: Mapped[bool] = mapped_column(
        Boolean, default=False, server_default="false"
    )
    # Admin override for the maintenance job's rolling re-validation batch (videos re-checked
    # per run). NULL = use the config/env default (settings.maintenance_revalidate_batch).
    maintenance_revalidate_batch: Mapped[int | None] = mapped_column(Integer)


class SchedulerSetting(Base):
    """Admin override for a scheduler job's run interval (minutes). One row per job id;
    absent = use the env/config default. DB-backed so it's editable from the admin UI at
    runtime without a redeploy (env stays a fallback)."""

    __tablename__ = "scheduler_settings"

    job_id: Mapped[str] = mapped_column(String(40), primary_key=True)
    interval_minutes: Mapped[int] = mapped_column(Integer)


class Playlist(Base):
    """A per-user named, ordered collection of videos from the shared catalog.

    `kind`: 'user' (normal) or 'watch_later' (built-in, undeletable, one per user).
    `source`: 'local' (created here) or 'youtube' (mirrored from the user's YouTube
    playlists). `yt_playlist_id` links a mirrored/exported playlist to its YouTube id.
    `dirty` marks a YouTube-linked playlist with local edits not yet pushed, so the read
    sync won't clobber them. (source/yt_playlist_id/dirty are forward-looking for the YT
    sync phases; the foundation phase only uses local playlists.)"""

    __tablename__ = "playlists"

    id: Mapped[int] = mapped_column(primary_key=True)
    user_id: Mapped[int] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), index=True
    )
    name: Mapped[str] = mapped_column(String(255))
    kind: Mapped[str] = mapped_column(String(16), default="user", server_default="user")
    source: Mapped[str] = mapped_column(
        String(16), default="local", server_default="local"
    )
    yt_playlist_id: Mapped[str | None] = mapped_column(String(64))
    # True when the current items/name differ from `synced_fingerprint` (unpushed edits).
    dirty: Mapped[bool] = mapped_column(Boolean, default=False, server_default="false")
    # SHA-256 of name + ordered video ids as last synced from / pushed to YouTube; the
    # baseline `dirty` is derived against. NULL = no baseline yet (treated as dirty).
    synced_fingerprint: Mapped[str | None] = mapped_column(String)
    position: Mapped[int] = mapped_column(Integer, default=0, server_default="0")
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )
    updated_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now(), onupdate=func.now()
    )

    items: Mapped[list["PlaylistItem"]] = relationship(
        back_populates="playlist",
        cascade="all, delete-orphan",
        order_by="PlaylistItem.position",
    )


class PlaylistItem(Base):
    """A video's membership in a playlist, with its order within that playlist."""

    __tablename__ = "playlist_items"
    __table_args__ = (
        UniqueConstraint("playlist_id", "video_id", name="uq_playlist_video"),
    )

    id: Mapped[int] = mapped_column(primary_key=True)
    playlist_id: Mapped[int] = mapped_column(
        ForeignKey("playlists.id", ondelete="CASCADE"), index=True
    )
    video_id: Mapped[str] = mapped_column(
        ForeignKey("videos.id", ondelete="CASCADE"), index=True
    )
    position: Mapped[int] = mapped_column(Integer, default=0, server_default="0")
    added_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now()
    )

    playlist: Mapped["Playlist"] = relationship(back_populates="items")


class Notification(Base):
    """A durable, server-backed per-user notification (the inbox center, phase 1).

    Distinct from the client-side transient "bell" (toasts kept only in localStorage):
    these survive reloads and devices, and are produced server-side (first producer = the
    maintenance/validation job's batched "N saved/playlisted videos removed" notice). The
    column is named `data` (not `metadata`, which SQLAlchemy's declarative Base reserves):
    a free-form JSON payload (e.g. the list of removed videos) the UI can render. `read`
    and `dismissed` are separate: read clears the unread badge but keeps the row in the
    inbox; dismissed removes it from the default view. Unread rows never auto-expire; read
    ones are trimmed past a soft per-user cap (see app.notifications.trim_read)."""

    __tablename__ = "notifications"

    id: Mapped[int] = mapped_column(primary_key=True)
    user_id: Mapped[int] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), index=True
    )
    type: Mapped[str] = mapped_column(String(32), index=True)  # e.g. "maintenance"
    title: Mapped[str] = mapped_column(String(255))
    body: Mapped[str | None] = mapped_column(Text)
    data: Mapped[dict | None] = mapped_column(JSON)
    read: Mapped[bool] = mapped_column(
        Boolean, default=False, server_default="false", index=True
    )
    dismissed: Mapped[bool] = mapped_column(
        Boolean, default=False, server_default="false"
    )
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), server_default=func.now(), index=True
    )