read.markets/app/models.py

"""SQLAlchemy models for Cassandra.

Schema rationale lives in /home/gg/.claude/plans/ok-i-think-this-tidy-lake.md.
All datetimes are tz-aware UTC (see app.db.utcnow).
"""
from __future__ import annotations

from datetime import datetime, date

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

from app.db import Base, utcnow


class Quote(Base):
    __tablename__ = "quotes"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    symbol: Mapped[str] = mapped_column(String(128), nullable=False)
    source: Mapped[str] = mapped_column(String(32), nullable=False)
    label: Mapped[str] = mapped_column(String(128), default="")
    group_name: Mapped[str] = mapped_column(String(64), nullable=False)
    price: Mapped[float | None] = mapped_column(Float)
    currency: Mapped[str | None] = mapped_column(String(8))
    as_of: Mapped[str | None] = mapped_column(String(16))      # provider date string
    changes: Mapped[dict | None] = mapped_column(JSON)         # {"1d": x, "1m": y, ...}
    error: Mapped[str | None] = mapped_column(String(255))
    fetched_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)

    __table_args__ = (
        Index("ix_quotes_symbol_fetched", "symbol", "fetched_at"),
        Index("ix_quotes_group", "group_name"),
    )


class QuoteDaily(Base):
    """Daily rollup — sparkline source. PK on (symbol, date)."""
    __tablename__ = "quotes_daily"
    symbol: Mapped[str] = mapped_column(String(64), primary_key=True)
    date: Mapped[date] = mapped_column(Date, primary_key=True)
    close: Mapped[float | None] = mapped_column(Float)
    high: Mapped[float | None] = mapped_column(Float)
    low: Mapped[float | None] = mapped_column(Float)
    source: Mapped[str] = mapped_column(String(32))


class Headline(Base):
    __tablename__ = "headlines"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    source: Mapped[str] = mapped_column(String(64), nullable=False)
    category: Mapped[str] = mapped_column(String(32), nullable=False)
    title: Mapped[str] = mapped_column(String(512), nullable=False)
    url: Mapped[str] = mapped_column(String(1024), nullable=False)
    published_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
    fetched_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    fingerprint: Mapped[str] = mapped_column(String(40), nullable=False)  # sha1 of normalised title
    # Semantic content tags from app.services.news_tagging. NULL = not yet
    # tagged; the next news_job run picks it up. Each entry is one of the
    # values in news_tagging.TAG_VOCABULARY.
    tags: Mapped[list[str] | None] = mapped_column(JSON, nullable=True)

    __table_args__ = (
        UniqueConstraint("fingerprint", name="uq_headlines_fingerprint"),
        Index("ix_headlines_published", "published_at"),
        Index("ix_headlines_category_published", "category", "published_at"),
    )


class Feed(Base):
    """Persisted feed state; bootstrapped from default.toml on first startup."""
    __tablename__ = "feeds"
    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
    category: Mapped[str] = mapped_column(String(32), nullable=False)
    name: Mapped[str] = mapped_column(String(64), nullable=False)
    url: Mapped[str] = mapped_column(String(1024), nullable=False)
    enabled: Mapped[bool] = mapped_column(Boolean, default=True)
    consecutive_failures: Mapped[int] = mapped_column(Integer, default=0)
    last_success_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))

    __table_args__ = (
        UniqueConstraint("category", "name", name="uq_feeds_cat_name"),
    )


class StrategicLog(Base):
    __tablename__ = "strategic_logs"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    generated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, index=True)
    model: Mapped[str] = mapped_column(String(64), nullable=False)
    anchor_date: Mapped[str | None] = mapped_column(String(16))
    prompt_version: Mapped[int] = mapped_column(Integer, default=1)
    tone: Mapped[str | None] = mapped_column(String(16))         # NOVICE|INTERMEDIATE|PRO
    analysis: Mapped[str | None] = mapped_column(String(16))     # DRY|SPECULATIVE
    content: Mapped[str] = mapped_column(Text, nullable=False)
    prompt_tokens: Mapped[int | None] = mapped_column(Integer)
    completion_tokens: Mapped[int | None] = mapped_column(Integer)
    cost_usd: Mapped[float | None] = mapped_column(Float)


class IndicatorSummary(Base):
    """Short AI-generated read for one indicator group, regenerated hourly.
    The latest row per group_name is what the dashboard renders."""
    __tablename__ = "indicator_summaries"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    group_name: Mapped[str] = mapped_column(String(64), nullable=False)
    generated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    model: Mapped[str] = mapped_column(String(64), nullable=False)
    tone: Mapped[str | None] = mapped_column(String(16))
    analysis: Mapped[str | None] = mapped_column(String(16))
    prompt_version: Mapped[int] = mapped_column(Integer, default=1)
    content: Mapped[str] = mapped_column(Text, nullable=False)
    prompt_tokens: Mapped[int | None] = mapped_column(Integer)
    completion_tokens: Mapped[int | None] = mapped_column(Integer)
    cost_usd: Mapped[float | None] = mapped_column(Float)

    __table_args__ = (Index("ix_indsumm_group_generated", "group_name", "generated_at"),)


class AICall(Base):
    """Cost ledger for OpenRouter calls. Feeds the monthly cap check."""
    __tablename__ = "ai_calls"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    called_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, index=True)
    model: Mapped[str] = mapped_column(String(64), nullable=False)
    prompt_tokens: Mapped[int | None] = mapped_column(Integer)
    completion_tokens: Mapped[int | None] = mapped_column(Integer)
    cost_usd: Mapped[float | None] = mapped_column(Float)
    status: Mapped[str] = mapped_column(String(16), default="ok")
    error: Mapped[str | None] = mapped_column(String(512))


# Portfolio / PortfolioSnapshot / Position removed in Phase G —
# holdings live in the browser, the server stores only the anonymous
# ticker universe + public market data.


class User(Base):
    """A user account. Authentication is e-mail-only via one-time codes
    (see EmailOTP) — no passwords. Possessing an active session cookie
    means the user proved control of `email` at session creation time, so
    a separate `email_verified` flag would be redundant."""
    __tablename__ = "users"
    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
    email: Mapped[str] = mapped_column(String(255), nullable=False)
    tier: Mapped[str] = mapped_column(String(16), default="free")  # free | paid | enterprise
    settings_json: Mapped[dict | None] = mapped_column(JSON)
    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    last_login_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    # Referrals (Phase D.1). The code is unique + URL-safe; generated on
    # first need rather than at row creation so existing accounts get one
    # the next time they hit /settings.
    referral_code: Mapped[str | None] = mapped_column(String(16), nullable=True)
    referred_by_user_id: Mapped[int | None] = mapped_column(
        ForeignKey("users.id", ondelete="SET NULL"), nullable=True,
    )
    # Paid-tier credit window (Phase D.2). Null = no credit. When set and
    # > now(), the user gets paid-tier features regardless of `tier`.
    # Populated by admin CLI (manual grants) or Paddle webhook (D.3).
    credit_until: Mapped[datetime | None] = mapped_column(
        DateTime(timezone=True), nullable=True,
    )

    __table_args__ = (
        UniqueConstraint("email", name="uq_users_email"),
        UniqueConstraint("referral_code", name="uq_users_referral_code"),
    )


class PortfolioSync(Base):
    """Opt-in encrypted backup of a user's pie. Stored as opaque bytes:
    the client encrypts the pie with a PIN-derived key (AES-GCM), and the
    server wraps that ciphertext again with a per-user key derived from
    PORTFOLIO_SYNC_PEPPER + user_id (also AES-GCM). A DB-only leak yields
    nothing usable without the env-only pepper; a pepper-only leak still
    leaves the attacker brute-forcing the PIN through PBKDF2(600k).

    One row per user. Absent row = sync disabled for that user. The
    fetch_window_* fields drive a sliding-window rate limit on GET so the
    pepper-leak threat model can't degenerate into an unthrottled brute
    force against the inner PBKDF2."""
    __tablename__ = "portfolio_sync"
    user_id: Mapped[int] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), primary_key=True,
    )
    outer_ciphertext: Mapped[bytes] = mapped_column(LargeBinary, nullable=False)
    outer_nonce: Mapped[bytes] = mapped_column(LargeBinary, nullable=False)
    version: Mapped[int] = mapped_column(SmallInteger, nullable=False, default=1)
    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    fetch_window_start: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    fetch_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
    # 8-byte HKDF fingerprint of the pepper that wrapped this row. A
    # mismatch against the current pepper means the row is orphaned
    # (pepper was rotated) — distinct from genuine GCM corruption.
    pepper_fp: Mapped[bytes | None] = mapped_column(LargeBinary(length=8))


class Referral(Base):
    """One row per captured (referrer, referred) pair. Created at signup
    when the new user supplied a valid `?ref=<code>`. The conversion
    fields (`converted_at`, `credited_at`) stay null until the referred
    user makes their first paid subscription — Phase D.3 fills them in
    via the Paddle webhook."""
    __tablename__ = "referrals"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    referrer_user_id: Mapped[int] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), nullable=False,
    )
    referred_user_id: Mapped[int] = mapped_column(
        ForeignKey("users.id", ondelete="CASCADE"), nullable=False,
    )
    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    converted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    credited_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))

    __table_args__ = (
        UniqueConstraint("referred_user_id", name="uq_referrals_referred"),
        Index("ix_referrals_referrer", "referrer_user_id"),
    )


class EmailOTP(Base):
    """One-time codes for email verification. The plaintext 6-digit code is
    sent in the email; we store an argon2 hash, expiry, attempt count, and
    a used_at timestamp so a single code can't be reused or brute-forced."""
    __tablename__ = "email_otps"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    email: Mapped[str] = mapped_column(String(255), nullable=False)
    code_hash: Mapped[str] = mapped_column(String(255), nullable=False)
    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    expires_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
    attempts: Mapped[int] = mapped_column(Integer, default=0)
    used_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    purpose: Mapped[str] = mapped_column(String(16), default="signup")

    __table_args__ = (Index("ix_otps_email_created", "email", "created_at"),)


class InstrumentMap(Base):
    """Maps T212's tickers/shortnames to Yahoo Finance tickers so we can
    refresh prices via Yahoo after a user uploads a T212 pie CSV.

    Synced periodically from T212's /equity/metadata/instruments endpoint
    via the admin's read-only API key. Each row is one T212 listing.
    Multiple rows can share a shortName (e.g. SHEL on LSE in GBX vs
    SHEL on NYSE in USD); the resolver picks the right one per user."""
    __tablename__ = "instrument_map"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    t212_ticker: Mapped[str] = mapped_column(String(64), nullable=False)
    t212_shortname: Mapped[str] = mapped_column(String(32), nullable=False)
    yahoo_ticker: Mapped[str | None] = mapped_column(String(32))
    name: Mapped[str] = mapped_column(String(128), nullable=False)
    currency: Mapped[str | None] = mapped_column(String(8))
    isin: Mapped[str | None] = mapped_column(String(16))
    instrument_type: Mapped[str | None] = mapped_column(String(16))
    manual: Mapped[bool] = mapped_column(Boolean, default=False)
    last_verified_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)

    __table_args__ = (
        UniqueConstraint("t212_ticker", name="uq_imap_t212_ticker"),
        Index("ix_imap_shortname", "t212_shortname"),
        Index("ix_imap_isin", "isin"),
    )


class TickerUniverse(Base):
    """The set of public tickers Cassandra is currently tracking. Populated
    as the union of all users' holdings, *without user attribution* — once
    a ticker is in the universe, the row carries no signal as to who put
    it there. The /api/universe endpoint returns the entire set (gzipped)
    to every authenticated client, so the request body itself doesn't leak
    which tickers belong to which user.

    Eviction policy: passive aging. last_referenced_at is bumped whenever
    the ticker appears in /api/portfolio/parse or /api/analyze. A nightly
    cron prunes rows older than UNIVERSE_EVICTION_TTL (60 days).
    """
    __tablename__ = "ticker_universe"
    yahoo_ticker: Mapped[str] = mapped_column(String(32), primary_key=True)
    currency: Mapped[str | None] = mapped_column(String(8))
    first_seen_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    last_referenced_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)

    __table_args__ = (Index("ix_universe_last_ref", "last_referenced_at"),)


class JobRun(Base):
    """One row per scheduled-job invocation; powers /api/health + the ops footer."""
    __tablename__ = "job_runs"
    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
    name: Mapped[str] = mapped_column(String(64), nullable=False)
    started_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
    finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
    status: Mapped[str] = mapped_column(String(16), default="running")  # running|success|failed
    error: Mapped[str | None] = mapped_column(Text)
    items_written: Mapped[int | None] = mapped_column(Integer)

    __table_args__ = (Index("ix_jobruns_name_started", "name", "started_at"),)