thermograph/accounts/models.py
Emi Griffith f504f7bda9 Containerize the app and move the databases to PostgreSQL 18 (#220)
Run Thermograph as a docker-compose stack (app + Postgres 18) and standardize the
data layer on Postgres, while keeping the test suite on SQLite.

- accounts/db.py: DSN-driven engines. On Postgres, a per-worker read-write +
  read-only asyncpg pair (the RO engine pins read-only transactions, used by the
  pure-GET endpoints) plus a sync psycopg engine for the notifier thread; the
  SQLite path is preserved for tests/local (selected when THERMOGRAPH_DATABASE_URL
  is unset). models.py: boolean server_default -> sa.false().
- store.py / metrics.py: dialect-flexible — Postgres UNLOGGED tables via psycopg
  when configured, else the existing raw-sqlite3 paths byte-for-byte; sync
  interfaces and every fail-soft contract preserved.
- Alembic (backend/alembic/) manages the accounts schema; the container entrypoint
  runs `alembic upgrade head` before uvicorn (4 workers). migrate_accounts_to_pg.py
  copies the accounts data SQLite->PG through the ORM (UUID/bool/JSON coerced),
  skips access_token, and resets identity sequences.
- Dockerfile + docker-compose.yml: app image (uvicorn, 4 workers, loopback 8137)
  and a Postgres 18 db (2 CPUs) running pg_duckdb (deploy/db/) so the parquet
  climate cache is queryable in-DB via read_parquet('/parquet/cache/*.parquet').
- deploy.sh/thermograph.service rewired to manage the compose stack; env example,
  Makefile targets (up/down/db-up), and deploy/POSTGRES-MIGRATION.md cutover runbook.

Tests stay on SQLite (dialect fallback) — 323 pass. The full Postgres stack was
verified via docker compose: alembic migrations, register/login, the RO endpoint,
store/metrics round-trips, and the accounts data migration.
2026-07-20 06:28:23 +00:00

191 lines
9.5 KiB
Python

"""ORM tables for the account domain (data/accounts.sqlite).
``User`` / ``AccessToken`` are fastapi-users' base tables (UUID primary keys);
the access-token table backs a database session strategy, so logins survive a
process restart and are individually revocable. ``Subscription`` and
``Notification`` are our own, keyed to a user and cascading on delete.
"""
import time
import uuid
from fastapi_users_db_sqlalchemy import SQLAlchemyBaseUserTableUUID
from fastapi_users_db_sqlalchemy.access_token import SQLAlchemyBaseAccessTokenTableUUID
from fastapi_users_db_sqlalchemy.generics import GUID
from sqlalchemy import (
JSON,
Boolean,
CheckConstraint,
Float,
ForeignKey,
Index,
Integer,
String,
Text,
UniqueConstraint,
false,
)
from sqlalchemy.orm import Mapped, mapped_column
from accounts.db import Base
class User(SQLAlchemyBaseUserTableUUID, Base):
# Inherits id (UUID), email (unique), hashed_password, is_active,
# is_superuser, is_verified. Optional extras:
display_name: Mapped[str | None] = mapped_column(String(120), nullable=True)
# Linked Discord account id (OAuth2 identify) — the key DM alerts reach the user
# by. NB: create_all only makes this on a fresh DB; an existing prod accounts.db
# needs the manual migration in deploy/migrations/ (no Alembic in this project).
discord_id: Mapped[str | None] = mapped_column(String(32), unique=True, nullable=True)
# Whether to also deliver alerts as a Discord DM. Set True on linking (an active
# opt-in); the user can mute it while staying linked. Same migration caveat.
discord_dm: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False,
server_default=false())
class AccessToken(SQLAlchemyBaseAccessTokenTableUUID, Base):
# Inherits token (PK), user_id (FK -> user.id), created_at. Rows here ARE the
# sessions: DatabaseStrategy looks a cookie's token up in this table.
pass
class Subscription(Base):
__tablename__ = "subscription"
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
user_id: Mapped[uuid.UUID] = mapped_column(
GUID, ForeignKey("user.id", ondelete="CASCADE"), nullable=False
)
# grid.snap(lat, lon)["id"] — the stable per-location key used across the app.
cell_id: Mapped[str] = mapped_column(String(40), nullable=False)
label: Mapped[str | None] = mapped_column(String(200), nullable=True)
lat: Mapped[float] = mapped_column(Float, nullable=False)
lon: Mapped[float] = mapped_column(Float, nullable=False)
# Unusualness cutoff the user picked; the low tail mirrors it at 100-threshold.
threshold: Mapped[int] = mapped_column(Integer, nullable=False)
# Grading metric keys this subscription watches, e.g. ["tmax", "feels", "precip"].
metrics: Mapped[list] = mapped_column(JSON, nullable=False, default=list)
# 'observed' (a recorded day crossed) or 'forecast' (an upcoming day is projected to).
kind: Mapped[str] = mapped_column(String(16), nullable=False, default="observed")
# Also alert the cold/low tail for temperature-like metrics (precip stays one-sided).
two_sided: Mapped[bool] = mapped_column(Boolean, nullable=False, default=True)
active: Mapped[bool] = mapped_column(Boolean, nullable=False, default=True)
# Epoch seconds of the last notification emitted — enforces the weekly cap.
last_notified_at: Mapped[float | None] = mapped_column(Float, nullable=True)
created_at: Mapped[float] = mapped_column(Float, nullable=False, default=time.time)
__table_args__ = (
CheckConstraint("threshold BETWEEN 95 AND 99", name="ck_sub_threshold"),
CheckConstraint("kind IN ('observed','forecast')", name="ck_sub_kind"),
# One observed + one forecast subscription per location per user.
UniqueConstraint("user_id", "cell_id", "kind", name="uq_sub_user_cell_kind"),
Index("idx_sub_user", "user_id"),
Index("idx_sub_active", "active"),
)
class Notification(Base):
__tablename__ = "notification"
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
user_id: Mapped[uuid.UUID] = mapped_column(
GUID, ForeignKey("user.id", ondelete="CASCADE"), nullable=False
)
subscription_id: Mapped[int] = mapped_column(
Integer, ForeignKey("subscription.id", ondelete="CASCADE"), nullable=False
)
event_date: Mapped[str] = mapped_column(String(10), nullable=False) # YYYY-MM-DD
metric: Mapped[str] = mapped_column(String(16), nullable=False)
direction: Mapped[str] = mapped_column(String(4), nullable=False) # 'high' | 'low'
kind: Mapped[str] = mapped_column(String(16), nullable=False, default="observed")
percentile: Mapped[float] = mapped_column(Float, nullable=False)
value: Mapped[float | None] = mapped_column(Float, nullable=True)
grade: Mapped[str | None] = mapped_column(String(40), nullable=True)
title: Mapped[str] = mapped_column(String(200), nullable=False)
body: Mapped[str | None] = mapped_column(Text, nullable=True)
# 'inapp' today; the seam for future 'email' / 'push' delivery.
channel: Mapped[str] = mapped_column(String(16), nullable=False, default="inapp")
created_at: Mapped[float] = mapped_column(Float, nullable=False, default=time.time)
read_at: Mapped[float | None] = mapped_column(Float, nullable=True) # NULL == unread
__table_args__ = (
# The dedup key: a given event (day+metric+direction+kind) notifies a
# subscription at most once, so re-running the evaluator never repeats it.
UniqueConstraint(
"subscription_id", "event_date", "metric", "direction", "kind",
name="uq_notif_event",
),
Index("idx_notif_user_created", "user_id", "created_at"),
Index("idx_notif_user_read", "user_id", "read_at"),
)
class PushSubscription(Base):
"""A single browser/device Web Push registration, owned by a user.
One row per device (a user with a phone + a laptop has two). The `endpoint`
is the push service URL the browser handed us; it's the natural identity, so
re-subscribing from the same device updates the keys in place rather than
duplicating. Rows are pruned when the push service reports the endpoint gone
(404/410) — see notify.py / api_accounts.py.
"""
__tablename__ = "push_subscription"
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
user_id: Mapped[uuid.UUID] = mapped_column(
GUID, ForeignKey("user.id", ondelete="CASCADE"), nullable=False
)
# The push service URL (per-device). Unique — it identifies the device.
endpoint: Mapped[str] = mapped_column(Text, nullable=False)
# The two client keys from PushSubscription.toJSON().keys, used to encrypt the
# payload so only this device can read it.
p256dh: Mapped[str] = mapped_column(String(200), nullable=False)
auth: Mapped[str] = mapped_column(String(100), nullable=False)
# Best-effort label for a future "manage devices" view.
user_agent: Mapped[str | None] = mapped_column(String(300), nullable=True)
created_at: Mapped[float] = mapped_column(Float, nullable=False, default=time.time)
last_used_at: Mapped[float | None] = mapped_column(Float, nullable=True)
__table_args__ = (
UniqueConstraint("endpoint", name="uq_push_endpoint"),
Index("idx_push_user", "user_id"),
)
class PendingDigest(Base):
"""A monthly-digest signup, collected before email delivery is wired up.
The digest form ships ahead of SMTP on purpose: building the list is the
slow part, and making people wait for the mailer would throw away every
signup in the meantime. Rows land here unconfirmed; once delivery is live, a
confirmation pass mails each address and stamps ``confirmed_at``.
Deliberately NOT tied to ``user`` — signing up for the digest must not
require an account, and most subscribers won't have one.
"""
__tablename__ = "pending_digest"
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
# 320 = the practical maximum length of an email address (64 local + @ + 255 domain).
email: Mapped[str] = mapped_column(String(320), nullable=False)
# The place the digest should cover. Optional: an address with no place is
# still a real signup, and the place can be asked for at confirmation time.
place_label: Mapped[str | None] = mapped_column(String(200), nullable=True)
lat: Mapped[float | None] = mapped_column(Float, nullable=True)
lon: Mapped[float | None] = mapped_column(Float, nullable=True)
cell_id: Mapped[str | None] = mapped_column(String(32), nullable=True)
# Where the signup came from (bare referrer domain), for attribution only.
source: Mapped[str | None] = mapped_column(String(64), nullable=True)
created_at: Mapped[float] = mapped_column(Float, nullable=False, default=time.time)
# Set when the address is verified. The double opt-in token is stored as a
# sha256 hash, never in the clear, so a leaked database can't confirm addresses.
token_hash: Mapped[str | None] = mapped_column(String(64), nullable=True)
confirmed_at: Mapped[float | None] = mapped_column(Float, nullable=True)
last_sent_at: Mapped[float | None] = mapped_column(Float, nullable=True)
unsubscribed_at: Mapped[float | None] = mapped_column(Float, nullable=True)
__table_args__ = (
# One row per address: a re-submit updates in place rather than
# duplicating, which is what makes the form idempotent.
UniqueConstraint("email", name="uq_pending_digest_email"),
)