webmail-client/backend/tests/sync/test_backfill_window.py

"""Sync-window backfill strategies at account setup (SPEC §12 M2): all (recent
first, then remainder), 3months (windowed), new (no history, watermark only)."""

from __future__ import annotations

import uuid
from collections.abc import AsyncIterator
from datetime import UTC, date, datetime, timedelta
from email.message import EmailMessage

from sqlalchemy import func, select
from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
from sqlalchemy.pool import NullPool

from app.config import get_settings
from app.identity.passwords import hash_password
from app.models import Account, Mailbox, Message, User
from app.providers.base import RemoteMailbox, RemoteMessage
from app.sync import engine as sync_engine


def _raw(mid: str) -> bytes:
    m = EmailMessage()
    m["Subject"] = "hi"
    m["From"] = "me@example.com"
    m["To"] = "bob@example.com"
    m["Message-ID"] = mid
    m["Date"] = "Mon, 09 Mar 2026 08:36:37 +0100"
    m.set_content("body")
    return m.as_bytes()


class _FakeProvider:
    gmail_labels_supported = False

    def __init__(self) -> None:
        self.backfill_calls: list[tuple[str, date | None, date | None]] = []
        self.count_calls: list[tuple[str, date | None]] = []
        self.newest_calls: list[str] = []

    async def list_mailboxes(self) -> list[RemoteMailbox]:
        return [RemoteMailbox(path="INBOX", special_use="inbox", uidvalidity=1)]

    async def message_count(self, mailbox: str, *, since: date | None = None) -> int:
        self.count_calls.append((mailbox, since))
        return 3

    async def newest_uid(self, mailbox: str) -> int:
        self.newest_calls.append(mailbox)
        return 42

    async def backfill(  # type: ignore[no-untyped-def]
        self, mailbox, *, newest_first=True, batch_size=200, since=None, before=None
    ) -> AsyncIterator[list[RemoteMessage]]:
        self.backfill_calls.append((mailbox, since, before))
        # Distinct UID per pass so recent + remainder both persist a row.
        uid = 100 if since is not None else 50
        yield [
            RemoteMessage(
                uid=uid,
                raw=_raw(f"<{mailbox}-{uid}@x.com>"),
                flags=frozenset(),
                internal_date=datetime.now(UTC),
            )
        ]

    async def close(self) -> None:
        return None


async def _seed(sm: async_sessionmaker, window: str) -> tuple[uuid.UUID, uuid.UUID]:  # type: ignore[type-arg]
    session = sm()
    user = User(handle=f"bf{uuid.uuid4().hex[:8]}@test.local", password_hash=hash_password("pw"))
    session.add(user)
    await session.flush()
    account = Account(
        user_id=user.id,
        email="me@example.com",
        imap_config={},
        smtp_config={},
        secret_ct=b"",
        discovery_src="manual",
        sync_window=window,
    )
    session.add(account)
    await session.commit()
    aid = account.id
    await session.close()
    return user.id, aid


async def test_window_new_sets_watermark_and_skips_backfill(monkeypatch) -> None:  # type: ignore[no-untyped-def]
    engine = create_async_engine(get_settings().database_url, poolclass=NullPool)
    sm = async_sessionmaker(engine, expire_on_commit=False)
    _uid, account_id = await _seed(sm, "new")
    fake = _FakeProvider()
    monkeypatch.setattr(sync_engine, "build_provider", lambda _a: fake)
    try:
        count = await sync_engine.bootstrap_and_backfill(account_id)
        assert count == 0
        assert fake.backfill_calls == []  # no history fetched
        assert fake.newest_calls == ["INBOX"]

        session = sm()
        acct = await session.get(Account, account_id)
        assert acct is not None and acct.state == "live" and acct.backfill_total == 0
        mb = await session.scalar(select(Mailbox).where(Mailbox.account_id == account_id))
        assert mb is not None and mb.last_seen_uid == 42  # moved to the tip
        msgs = await session.scalar(
            select(func.count()).select_from(Message).where(Message.mailbox_id == mb.id)
        )
        assert msgs == 0  # nothing imported
        await session.close()
    finally:
        await engine.dispose()


async def test_window_all_imports_recent_then_remainder(monkeypatch) -> None:  # type: ignore[no-untyped-def]
    engine = create_async_engine(get_settings().database_url, poolclass=NullPool)
    sm = async_sessionmaker(engine, expire_on_commit=False)
    _uid, account_id = await _seed(sm, "all")
    fake = _FakeProvider()
    monkeypatch.setattr(sync_engine, "build_provider", lambda _a: fake)
    try:
        await sync_engine.bootstrap_and_backfill(account_id)

        # Two passes per mailbox: recent window (since set), then the older
        # remainder (before set) — the "usable fast, then fill in" strategy.
        cutoff = date.today() - timedelta(days=sync_engine._RECENT_DAYS)
        assert fake.backfill_calls == [("INBOX", cutoff, None), ("INBOX", None, cutoff)]
        assert fake.count_calls == [("INBOX", None)]  # denominator = whole mailbox

        session = sm()
        acct = await session.get(Account, account_id)
        assert acct is not None and acct.state == "live"
        assert acct.backfill_total == 3 and acct.backfill_done == 2
        mb = await session.scalar(select(Mailbox).where(Mailbox.account_id == account_id))
        assert mb is not None
        msgs = await session.scalar(
            select(func.count()).select_from(Message).where(Message.mailbox_id == mb.id)
        )
        assert msgs == 2  # one from each pass
        await session.close()
    finally:
        await engine.dispose()


async def test_window_3months_single_dated_pass(monkeypatch) -> None:  # type: ignore[no-untyped-def]
    engine = create_async_engine(get_settings().database_url, poolclass=NullPool)
    sm = async_sessionmaker(engine, expire_on_commit=False)
    _uid, account_id = await _seed(sm, "3months")
    fake = _FakeProvider()
    monkeypatch.setattr(sync_engine, "build_provider", lambda _a: fake)
    try:
        await sync_engine.bootstrap_and_backfill(account_id)

        since = date.today() - timedelta(days=sync_engine._WINDOW_DAYS["3months"])
        assert fake.backfill_calls == [("INBOX", since, None)]  # single windowed pass
        assert fake.count_calls == [("INBOX", since)]  # denominator counts the window
        await engine.dispose()
    finally:
        pass