Unreachable mail servers: send retries in Scheduled, real action retries, account health

Sending: a send the server could not take (unreachable, timeout, 4xx) is no
longer failed at once. It waits in Scheduled ("retrying") and is tried again
after 1, 2, 5, 10, 30 min, then hourly, for 24 hours — on the server, so it
works with the browser closed. A permanent refusal (5xx, wrong password) is
"failed" at once, with the server's reason. GET /outbox lists both;
POST /outbox/{id}/retry (Retry now) and /cancel (Edit, Delete) act on them,
and they are left out of Drafts. Mail delivered but not filed in Sent now
counts as sent, and a conditional claim keeps two jobs from sending one
message twice. The app says when a send failed and when it finally went.

Actions: arq retries a job only on Retry, never on a plain exception, so the
"retry x5, then revert" for flags and moves never happened. Flag, move,
archive, restore, delete and empty-folder jobs now raise Retry while the
server is unreachable (~24 hours of growing gaps), skip a change a later one
replaced, stop at the first connection failure instead of 20 s per message,
and delete/empty keep the rows until the server has the messages gone.

Account health: 3 failed connections in a row mark an account unreachable
(amber in the sidebar and Settings, cleared on the next success); 3 refused
sign-ins stop its syncing as auth_failed until the password is entered
again, so the provider does not lock the account. Sync loops back off 30 s
doubling to 10 min and log one line per expected failure; a refused
connection fails at once with its reason (the connect task is kept), and a
silently dead IDLE connection is noticed within ~11 min instead of ~29.

Also: the empty reading pane is clipped to its width when dragged very
narrow; tests no longer leave live accounts and outbox rows in the database.

Migration 0021: outbox attempts / next_attempt_at / retry_until, accounts
sync_error / sync_error_since.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

backend/tests/sync/test_acceptance.py

@@ -44,7 +44,9 @@ async def connections(monkeypatch) -> AsyncIterator[dict[uuid.UUID, int]]:  # ty
     """Patch the runner's loops; yield a live (hot-tier IDLE) connection count."""
     conns: dict[uuid.UUID, int] = defaultdict(int)
 
-    async def fake_live_loop(account_id: uuid.UUID, folder: str, stop: asyncio.Event) -> None:
+    async def fake_live_loop(
+        account_id: uuid.UUID, folder: str, stop: asyncio.Event, health: object = None
+    ) -> None:
         conns[account_id] += 1  # one persistent IDLE connection while alive (hot)
         try:
             await stop.wait()
@@ -52,13 +54,19 @@ async def connections(monkeypatch) -> AsyncIterator[dict[uuid.UUID, int]]:  # ty
             conns[account_id] -= 1
 
     async def fake_secondary(
-        account_id: uuid.UUID, stop: asyncio.Event | None = None, interval: float | None = None
+        account_id: uuid.UUID,
+        stop: asyncio.Event | None = None,
+        interval: float | None = None,
+        health: object = None,
     ) -> None:
         assert stop is not None
         await stop.wait()
 
     async def fake_poll_all(
-        account_id: uuid.UUID, interval: float, stop: asyncio.Event | None = None
+        account_id: uuid.UUID,
+        interval: float,
+        stop: asyncio.Event | None = None,
+        health: object = None,
     ) -> None:
         assert stop is not None  # warm/cold: no persistent connection, just wait
         await stop.wait()

backend/tests/sync/test_account_health.py

@@ -0,0 +1,127 @@
+"""An account whose mail server is unreachable, or refuses the password."""
+
+from __future__ import annotations
+
+import uuid
+from collections.abc import AsyncIterator
+
+import aiosmtplib
+import pytest_asyncio
+from aioimaplib import aioimaplib
+from sqlalchemy import delete
+
+from app.db import session_scope
+from app.identity.passwords import hash_password
+from app.models import Account, User
+from app.providers.base import (
+    ProviderAuthError,
+    ProviderConnectError,
+    ProviderRejectedError,
+)
+from app.providers.imap_smtp.provider import _smtp_error
+from app.sync.health import AUTH_GIVE_UP_AFTER, UNREACHABLE_AFTER, AccountHealth, is_temporary
+
+
+@pytest_asyncio.fixture
+async def account_id() -> AsyncIterator[uuid.UUID]:
+    async with session_scope() as session:
+        user = User(
+            handle=f"hl{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={"host": "imap.example.com", "port": 993, "tls": "ssl"},
+            smtp_config={"host": "smtp.example.com", "port": 465, "tls": "ssl"},
+            secret_ct=b"",
+            discovery_src="manual",
+            state="live",
+        )
+        session.add(account)
+        await session.flush()
+        user_id, aid = user.id, account.id
+    try:
+        yield aid
+    finally:
+        async with session_scope() as session:
+            await session.execute(delete(User).where(User.id == user_id))
+
+
+async def _account(aid: uuid.UUID) -> Account:
+    async with session_scope() as session:
+        account = await session.get(Account, aid)
+        assert account is not None
+        return account
+
+
+def test_what_counts_as_temporary() -> None:
+    assert is_temporary(ProviderConnectError("cannot connect"))
+    assert is_temporary(TimeoutError())
+    assert is_temporary(ConnectionResetError())
+    assert is_temporary(aioimaplib.CommandTimeout("uid move"))
+    # After the connection drops, aioimaplib refuses commands this way.
+    assert is_temporary(aioimaplib.Abort("command UID illegal in state LOGOUT"))
+    assert not is_temporary(aioimaplib.Abort("server has not MOVE capability"))
+    assert not is_temporary(ProviderAuthError("bad password"))
+    assert not is_temporary(ProviderRejectedError("550 no such user"))
+    assert not is_temporary(ValueError("bug"))
+
+
+def test_smtp_errors_say_whether_to_retry() -> None:
+    assert isinstance(_smtp_error(aiosmtplib.SMTPConnectError("refused")), ProviderConnectError)
+    assert isinstance(_smtp_error(aiosmtplib.SMTPServerDisconnected("gone")), ProviderConnectError)
+    assert isinstance(
+        _smtp_error(aiosmtplib.SMTPResponseException(451, "try later")), ProviderConnectError
+    )
+    assert isinstance(
+        _smtp_error(aiosmtplib.SMTPResponseException(554, "rejected")), ProviderRejectedError
+    )
+    assert isinstance(
+        _smtp_error(aiosmtplib.SMTPAuthenticationError(535, "bad credentials")), ProviderAuthError
+    )
+    refused = aiosmtplib.SMTPRecipientsRefused(
+        [aiosmtplib.SMTPRecipientRefused(550, "no such user", "x@example.com")]
+    )
+    assert isinstance(_smtp_error(refused), ProviderRejectedError)
+    greylisted = aiosmtplib.SMTPRecipientsRefused(
+        [aiosmtplib.SMTPRecipientRefused(450, "greylisted", "x@example.com")]
+    )
+    assert isinstance(_smtp_error(greylisted), ProviderConnectError)
+
+
+async def test_unreachable_after_failures_in_a_row_then_clears(account_id: uuid.UUID) -> None:
+    health = AccountHealth(account_id)
+    for _ in range(UNREACHABLE_AFTER - 1):
+        await health.failed(ProviderConnectError("cannot connect"))
+    assert (await _account(account_id)).sync_error is None  # a blip is not an outage
+
+    await health.failed(ProviderConnectError("cannot connect"))
+    account = await _account(account_id)
+    assert account.sync_error == "unreachable" and account.sync_error_since is not None
+    assert account.state == "live"  # still synced: retried until it answers
+
+    await health.ok()
+    account = await _account(account_id)
+    assert account.sync_error is None and account.sync_error_since is None
+
+
+async def test_mark_survives_a_restart_and_clears_on_success(account_id: uuid.UUID) -> None:
+    first = AccountHealth(account_id)
+    for _ in range(UNREACHABLE_AFTER):
+        await first.failed(ProviderConnectError("cannot connect"))
+    # A new worker knows nothing of the mark, yet its first success clears it.
+    await AccountHealth(account_id).ok()
+    assert (await _account(account_id)).sync_error is None
+
+
+async def test_refused_sign_in_stops_syncing(account_id: uuid.UUID) -> None:
+    health = AccountHealth(account_id)
+    for _ in range(AUTH_GIVE_UP_AFTER - 1):
+        await health.failed(ProviderAuthError("AUTHENTICATIONFAILED"))
+    assert (await _account(account_id)).state == "live"
+
+    await health.failed(ProviderAuthError("AUTHENTICATIONFAILED"))
+    account = await _account(account_id)
+    assert account.state == "auth_failed" and "AUTHENTICATIONFAILED" in account.state_detail

backend/tests/sync/test_backfill_window.py

@@ -8,7 +8,7 @@ from collections.abc import AsyncIterator
 from datetime import UTC, date, datetime, timedelta
 from email.message import EmailMessage
 
-from sqlalchemy import func, select
+from sqlalchemy import delete, func, select
 from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
 from sqlalchemy.pool import NullPool
 
@@ -16,7 +16,9 @@ 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.redis_client import get_redis
 from app.sync import engine as sync_engine
+from app.sync import leases
 
 
 def _raw(mid: str) -> bytes:
@@ -89,6 +91,16 @@ async def _seed(sm: async_sessionmaker, window: str) -> tuple[uuid.UUID, uuid.UU
     return user.id, aid
 
 
+async def _cleanup(sm: async_sessionmaker, user_id: uuid.UUID, account_id: uuid.UUID) -> None:  # type: ignore[type-arg]
+    """Remove the seeded user — backfill sets its account live, and left behind a
+    running dev worker would keep trying to sync it."""
+    await leases.mark_not_live(get_redis(), account_id)
+    session = sm()
+    await session.execute(delete(User).where(User.id == user_id))
+    await session.commit()
+    await session.close()
+
+
 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)
@@ -112,6 +124,7 @@ async def test_window_new_sets_watermark_and_skips_backfill(monkeypatch) -> None
         assert msgs == 0  # nothing imported
         await session.close()
     finally:
+        await _cleanup(sm, _uid, account_id)
         await engine.dispose()
 
 
@@ -142,6 +155,7 @@ async def test_window_all_imports_recent_then_remainder(monkeypatch) -> None:  #
         assert msgs == 2  # one from each pass
         await session.close()
     finally:
+        await _cleanup(sm, _uid, account_id)
         await engine.dispose()
 
 
@@ -157,6 +171,6 @@ async def test_window_3months_single_dated_pass(monkeypatch) -> None:  # type: i
         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
+        await _cleanup(sm, _uid, account_id)
+        await engine.dispose()