Files
siftlode/backend/app/email.py
T
peter dc221338be fix(logs): keep what a person typed out of the backend log lines
The E22 redactor is a safety net over addresses and credential params, and every
one of these call sites was leaning on it to do the whole job. What it does not
cover went in whole, and what it does cover came out as a constant.

Not covered, so a real leak:
- routes/search.py logged the raw search term at ERROR. The privacy policy shipped
  in 0.88.0 says a search string is kept only at Teljes/TRACE, with the user's own
  consent. The ERROR line now carries the shape of the failure (source, candidate
  and collected counts) and the term follows on a TRACE line, which nothing emits
  unless that consent is in force.
- downloads/backfill.py logged the full source URL at INFO — a row of the user's
  download history. Now the asset id and the host.
- youtube/client.py logged the upstream error body, which is prose that quotes the
  request back. Every failing YouTube call now goes through one _upstream_failure()
  that logs the API's `reason` code, keeps the body for the same consented TRACE
  line, and raises a YouTubeError carrying `reason` as a field — callers put that
  error in log lines of their own (routes/channels.py) and in a 422 answered to the
  user, so the body must not travel in it either.

Covered, so merely useless: routes/auth.py named the account by an address that
reached both sinks as `[email]`, and app/email.py printed recipient lists that read
as `['[email]']`. Both now carry the uid (or a count) and a reason code, which is
also the first half of E22.5 S4's failed-sign-in coverage.

routes/channels.py branched on the text of that error message to recognise an
already-existing subscription. It now branches on `exc.reason`, with the substring
check kept beside it for a body that carried no reason at all.

tests/test_log_pii.py pins the call sites and the family: a source-level contract
test walks every log call in app/ and fails on an argument naming user-typed
content unless the line says why it is safe (`# log-pii-ok: <why>`). Eight sites
carry that marker today, each with its reason. Gate 8/8 green; all five cases
mutation-checked.
2026-09-18 00:49:43 +02:00

343 lines
15 KiB
Python

"""Outbound email for onboarding (access requests + approval notices).
Gmail SMTP + App Password by default. Deliberately fail-soft: if SMTP isn't configured
or a send errors, we log and return False so the caller can fall back to in-app
notifications — email is never load-bearing for the app's core flow.
Fail-soft must not mean invisible, though: every drop also leaves an in-app notice in the admins'
inbox (see `_alert_admins`). An instance whose SMTP was never filled in silently swallows
verification links, password resets and access-request notices, and the operator's first clue used
to be a person telling them nothing arrived.
"""
import html
import logging
import re
import smtplib
import ssl
from email.message import EmailMessage
from email.utils import formatdate
from sqlalchemy import select
from sqlalchemy.orm import Session
from app import mailtext, sysconfig
from app.config import settings
from app.db import SessionLocal
from app.models import User
from app.notifications import create_notification
from app.ratelimit import RateLimiter
log = logging.getLogger("siftlode.email")
# One admin notice an hour per reason. A relay that is down fails every send, and the inbox must
# stay readable; the log keeps the full record either way.
_alert_throttle = RateLimiter(max_events=1, window_seconds=3600)
def _alert_admins(reason: str, subject: str, recipients: list[str]) -> None:
"""Record an in-app notice that a message did NOT go out. Best effort in every direction: it
opens its own session (callers are often background tasks), swallows its own errors, and never
reports failure to the caller — this is the fallback path, it must not become a new way to
break a send."""
if not _alert_throttle.allow(reason):
return
try:
with SessionLocal() as db:
admins = (
db.execute(
select(User.id).where(
User.role == "admin",
User.is_active.is_(True),
User.is_suspended.is_(False),
)
)
.scalars()
.all()
)
if not admins:
# Nothing was recorded, so don't let this cost the next hour of alerts on the very
# path whose job is to stop drops going unseen. Same on the failure branch below.
_alert_throttle.reset()
return
for uid in admins:
create_notification(
db,
user_id=uid,
type="email_undelivered",
# English fallback; the inbox renders a translated version from `data`.
title="Email could not be sent",
body=subject,
data={"reason": reason, "subject": subject, "recipients": recipients},
commit=False,
)
db.commit()
except Exception:
_alert_throttle.reset()
log.exception("Could not record the undelivered-email notice (%r)", subject)
def _read_smtp(db: Session) -> dict:
return {
"host": sysconfig.get_str(db, "smtp_host"),
"port": sysconfig.get_int(db, "smtp_port"),
"user": sysconfig.get_str(db, "smtp_user"),
"password": sysconfig.get_str(db, "smtp_password"),
"from": sysconfig.get_str(db, "smtp_from"),
}
def _smtp(db: Session | None = None) -> dict:
"""Effective SMTP config (admin DB override over env defaults). Opens its own short session when
the caller has none, because email is usually sent from a BackgroundTask outside a request's db.
A caller that IS inside a request should pass its session: reading the password decrypts a Fernet
value, and /api/me polls this for every admin tab."""
if db is not None:
return _read_smtp(db)
with SessionLocal() as own:
return _read_smtp(own)
def email_enabled(db: Session | None = None) -> bool:
c = _smtp(db)
return bool(c["host"] and c["user"] and c["password"])
def _admin_contact() -> str | None:
return next(iter(sorted(settings.admin_email_set)), None)
# A bare URL in a text/plain mail is only clickable if the CLIENT decides to linkify it. Gmail,
# Outlook and Apple Mail do; plenty of lighter web clients render the body verbatim and leave the
# link as dead text — which, for a verification or password-reset mail, is the whole message. So
# every mail also carries an HTML alternative built from the SAME plain body (below), rather than
# per-template HTML that would have to be kept in sync with it.
#
# `[^\s<]` stops at whitespace and at the `<` of any following markup; the trailing-punctuation trim
# keeps a sentence-final period out of the href. `;` and `:` are deliberately NOT trimmed — escaping
# turns `&` into `&amp;`, so a query string can legitimately end in a semicolon.
_URL_RE = re.compile(r"https?://[^\s<]+")
def _html_body(text: str) -> str:
"""Render a plain-text mail body as minimal HTML: escaped, blank-line-separated paragraphs, with
real links. Escaping happens FIRST and the linkifier then runs over the escaped text — bodies
interpolate untrusted values (a requester's email address, the operator contact), so no caller
can inject markup, and `&` inside a URL is already `&amp;` by the time it reaches the href, which
is what an HTML attribute wants anyway."""
def _anchor(m: re.Match[str]) -> str:
url = m.group(0)
trail = ""
while url and url[-1] in ".,!?)":
url, trail = url[:-1], url[-1] + trail
if not url:
return trail
return f'<a href="{url}">{url}</a>{trail}'
paragraphs = [p for p in html.escape(text).split("\n\n") if p.strip()]
rendered = "".join(
f"<p>{_URL_RE.sub(_anchor, p).replace(chr(10), '<br>')}</p>" for p in paragraphs
)
# Inline styles only — many clients drop <style> blocks. No images, no external CSS, no tracking:
# the HTML part exists to make the link clickable, not to become a template to maintain.
return (
'<html><body style="margin:0;padding:16px;font-family:system-ui,-apple-system,'
"'Segoe UI',sans-serif;font-size:15px;line-height:1.6\">"
f'<div style="max-width:560px">{rendered}</div>'
"</body></html>"
)
def _send(to: list[str], subject: str, body: str, reply_to: str | None = None) -> bool:
recipients = [e for e in to if e]
if not recipients:
return False
c = _smtp()
if not (c["host"] and c["user"] and c["password"]):
# The count, not the addresses: `redact_text` rewrites every one of them to `[email]`
# before either sink sees the line, so the list only ever printed as noise. The subject
# stays — the templates are static, and the one that interpolates (`admin_new_request`)
# interpolates an address, which the same redactor covers.
log.info(
"SMTP not configured; skipping email %r to %d recipient(s)",
subject,
len(recipients), # log-pii-ok: how many, not who
)
_alert_admins("not_configured", subject, recipients)
return False
msg = EmailMessage()
msg["Subject"] = subject
msg["From"] = c["from"] or c["user"]
msg["To"] = ", ".join(recipients)
# A real Date and a Reply-To (so it's a conversation, not a no-reply blast) both
# nudge spam filters the right way; reputation still does most of the work.
msg["Date"] = formatdate(localtime=True)
if reply_to:
msg["Reply-To"] = reply_to
# text/plain stays the primary part (it is the source of truth, and a text-only client still
# gets the full message); the HTML alternative below is what makes the link clickable everywhere.
msg.set_content(body)
msg.add_alternative(_html_body(body), subtype="html")
try:
with smtplib.SMTP(c["host"], c["port"], timeout=20) as s:
s.starttls(context=ssl.create_default_context())
s.login(c["user"], c["password"])
s.send_message(msg)
# log-pii-ok: how many, not who
log.info("Sent email %r to %d recipient(s)", subject, len(recipients))
return True
except Exception:
# log-pii-ok: how many, not who
log.exception("SMTP send failed (%r to %d recipient(s))", subject, len(recipients))
_alert_admins("send_failed", subject, recipients)
return False
def _next_step(verify_link: str | None, has_account: bool, hours: int, lang: str) -> str:
"""What this person actually has to do next, in the one paragraph that carries the whole flow.
Three states, because a mail that guesses wrong sends someone looking for a link that isn't
coming — or worse, tells them to sign in when their address is still unconfirmed and sign-in will
refuse them (E9.5 S4 named that state on screen; the mail must not contradict it).
The link branch is the point of the C option: in the common ordering — approve first, the person
signs up later, or signs up and waits — they would otherwise have to find and open TWO separate
messages. One mail, one click.
"""
if verify_link:
return mailtext.text(
"next_step.verify", lang, link=verify_link, expiry=mailtext.link_expiry(hours, lang)
)
if has_account:
return mailtext.text("next_step.sign_in", lang, app=settings.app_base)
return mailtext.text("next_step.register", lang, app=settings.app_base)
def _reply_contact(lang: str) -> tuple[str | None, str]:
"""The admin address to answer to, and the closing line that names it — empty when no admin
contact is configured, so the mail never promises a reply nobody will read."""
admin = _admin_contact()
return admin, (mailtext.text("contact.reply", lang, admin=admin) if admin else "")
def send_access_approved(
email: str,
lang: str,
verify_link: str | None = None,
has_account: bool = False,
hours: int = 24,
) -> bool:
"""Answer someone who ASKED for access. Sent automatically on approval, because a person who
made a request is owed a reply — unlike the admin-initiated invitation below."""
admin, contact = _reply_contact(lang)
body = mailtext.text(
"access_approved.body",
lang,
next_step=_next_step(verify_link, has_account, hours, lang),
contact=contact,
)
return _send([email], mailtext.text("access_approved.subject", lang), body, reply_to=admin)
def send_access_invitation(
email: str,
lang: str,
verify_link: str | None = None,
has_account: bool = False,
hours: int = 24,
) -> bool:
"""Invite someone the admin let in WITHOUT them asking — sent only when the admin presses send.
Whitelisting an address is opening a door, not knocking on one: the operator has usually already
agreed it with the person, and an address can sit approved for weeks without anyone registering.
So adding to the whitelist stays silent and this is a separate, deliberate act. That is also why
the closing line offers no deadline — nudging is the one thing this mail must not do.
Its language is the one place the app has no signal to read: the admin typed this address in, so
nobody has ever told us how to address its owner. That is why the send button asks (E9.5 S7).
"""
admin, contact = _reply_contact(lang)
body = mailtext.text(
"access_invitation.body",
lang,
next_step=_next_step(verify_link, has_account, hours, lang),
contact=contact,
)
return _send([email], mailtext.text("access_invitation.subject", lang), body, reply_to=admin)
def send_access_denied(email: str, lang: str) -> bool:
admin, contact = _reply_contact(lang)
body = mailtext.text("access_denied.body", lang, contact=contact)
return _send([email], mailtext.text("access_denied.subject", lang), body, reply_to=admin)
def send_role_changed(to: str, lang: str, role: str, operator: str | None) -> bool:
line = mailtext.text(
"role_changed.granted" if role == "admin" else "role_changed.revoked", lang
)
contact = mailtext.text("contact.operator", lang, operator=operator) if operator else ""
body = mailtext.text("role_changed.body", lang, line=line, contact=contact)
return _send([to], mailtext.text("role_changed.subject", lang), body, reply_to=operator)
def send_account_unsuspended(to: str, lang: str, operator: str | None) -> bool:
contact = mailtext.text("contact.operator", lang, operator=operator) if operator else ""
body = mailtext.text("account_unsuspended.body", lang, contact=contact)
return _send([to], mailtext.text("account_unsuspended.subject", lang), body, reply_to=operator)
def send_account_deleted(to: str, lang: str, operator: str | None) -> bool:
contact = mailtext.text("contact.deleted", lang, operator=operator) if operator else ""
body = mailtext.text("account_deleted.body", lang, contact=contact)
return _send([to], mailtext.text("account_deleted.subject", lang), body, reply_to=operator)
def send_account_suspended(to: str, lang: str, operator: str | None) -> bool:
contact = (
mailtext.text("contact.suspended", lang, operator=operator)
if operator
else mailtext.text("contact.suspended_unknown", lang)
)
body = mailtext.text("account_suspended.body", lang, contact=contact)
return _send([to], mailtext.text("account_suspended.subject", lang), body, reply_to=operator)
def send_admin_new_request(admins: list[str], lang: str, requester: str) -> bool:
"""Tell the admins someone is waiting. One call per language group (see
`routes.auth.notify_admins_of_request`) — admins are people with their own UI language, and a
single blast to all of them would have to pick one and be wrong for the rest.
The link deep-links straight to the admin Access-requests page (the SPA reads ?admin=…). The
requester address is spelled out (mail clients auto-link both the URL and the address), and the
reply note is accurate: _send sets Reply-To to the requester, so a reply reaches THEM — not the
sending mailbox. (The old copy said "Settings → Account", which was the wrong menu.)
"""
body = mailtext.text(
"admin_new_request.body",
lang,
requester=requester,
link=f"{settings.app_base}/?admin=access-requests",
)
subject = mailtext.text("admin_new_request.subject", lang, requester=requester)
return _send(admins, subject, body, reply_to=requester)
def send_verify_email(to: str, lang: str, link: str, hours: int = 24) -> bool:
# The body says what the link's rules are. The reset mail always has; this one left the reader to
# discover both by meeting a dead link, which is precisely the silence this epic removes.
body = mailtext.text(
"verify_email.body", lang, link=link, expiry=mailtext.link_expiry(hours, lang)
)
return _send([to], mailtext.text("verify_email.subject", lang), body)
def send_password_reset(to: str, lang: str, link: str) -> bool:
body = mailtext.text("password_reset.body", lang, link=link)
return _send([to], mailtext.text("password_reset.subject", lang), body)
def send_test(to: str, lang: str) -> bool:
return _send([to], mailtext.text("test.subject", lang), mailtext.text("test.body", lang))