* security(auth): per-IP rate limit on auth endpoints + generalize last-admin guard Closes #45 and #151. #45 — every auth endpoint was unthrottled (login, magic-link, token, bootstrap), leaving us open to password brute-force and SMTP email-bombing. Wires slowapi (new dep) into the middleware chain with per-route limits: 10/min on login + token, 5/min on send-link, 3/min on bootstrap. Returns 429 with Retry-After: 60 once exceeded. Per-IP key respects the leftmost X-Forwarded-For hop (Caddy in front of the app strips client-supplied XFF). Operator escape hatch: AGNES_AUTH_RATELIMIT_ENABLED=0. Test suite disables the limiter via autouse conftest fixture so existing auth tests that hammer endpoints in tight loops are unaffected. #151 — DELETE /api/admin/users/{id}/memberships/{group_id} and the mirror DELETE /api/admin/groups/{group_id}/members/{user_id} only guarded against self-removal as last admin. Generalizes to refuse removing anyone from the seeded Admin group when they are the only remaining active admin (mirrors the existing count_admins(active_only=True) <= 1 check on delete_user / update_user). Recovery from zero admins requires direct DB access, so this closes a path where a scheduler/bootstrap actor that bypasses normal admin checks could otherwise empty the group. * security(auth): throttle remaining email-bombing + token-confirm endpoints Address code-review gap on PR #165 — the first commit covered /send-link but missed two endpoints with the IDENTICAL email-bombing surface: - POST /auth/password/reset — sends reset mail, anti-enum response - POST /auth/password/setup/request — sends setup mail, anti-enum response Both now share the 5/min limit with /send-link. Also add 10/min to the token-confirm surfaces — high-entropy tokens but partial leaks via logs / referer have surfaced before, and unbounded guess rate would let an attacker exhaust the keyspace adjacent to a leaked prefix: - POST /auth/email/verify - GET /auth/email/verify — closes the click-through bypass - POST /auth/password/reset/confirm - POST /auth/password/setup/confirm Doc fix: rate_limit.py module docstring + CHANGELOG entry no longer claim "disable without a redeploy" (misleading). The Limiter constructor freezes `enabled` from env at import time, matching every other Agnes env knob — operators set the flag and bounce the container. Tests: 4 new cases in test_auth_rate_limit.py covering /reset, /setup/request, /reset/confirm, GET /verify. Full suite: 2583 passed, 32 skipped, 0 failed. * security(auth): throttle JSON /auth/password/setup — closes form-throttle bypass Second code-review pass on PR #165 caught a fifth gap: POST /auth/password/setup (JSON variant, kept for backward compat) consumes the same setup_token as the web form /setup/confirm but was unthrottled — an attacker brute-forcing the token just switches from the form path to the JSON path and resumes at unbounded RPS. Apply the same 10/min limit and signature shape used on /setup/confirm. Also extend CHANGELOG note about the JSON-variant bypass for future operators reading the security entry. Test: 1 new case (test_password_setup_json_rate_limited_after_10_requests), 9 rate-limit tests + 28 password-flow tests + 41 auth-provider tests pass, no regressions. * chore(release): cut 0.30.1 — auth security hardening (rate limit + last-admin guard)
267 lines
10 KiB
Python
267 lines
10 KiB
Python
"""Email magic link auth provider for FastAPI."""
|
|
|
|
import logging
|
|
import os
|
|
import secrets
|
|
from datetime import datetime, timedelta, timezone
|
|
from urllib.parse import quote
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException, Request
|
|
from fastapi.responses import RedirectResponse
|
|
from pydantic import BaseModel
|
|
import duckdb
|
|
|
|
from app.auth.jwt import create_access_token
|
|
from app.auth.access import is_user_admin
|
|
from app.auth.dependencies import _get_db, is_local_dev_mode
|
|
from app.auth.rate_limit import limiter as _rate_limiter
|
|
from src.repositories.users import UserRepository
|
|
|
|
|
|
def _role_label(user: dict, conn: duckdb.DuckDBPyConnection) -> str:
|
|
"""Display label for the response payload only — `admin` if the user is
|
|
in the Admin system group, otherwise `user`. Authorization at runtime
|
|
checks `is_user_admin` directly; this label is purely cosmetic."""
|
|
return "admin" if is_user_admin(user["id"], conn) else "user"
|
|
|
|
logger = logging.getLogger(__name__)
|
|
router = APIRouter(prefix="/auth/email", tags=["auth"])
|
|
|
|
MAGIC_LINK_EXPIRY = 3600 # 1 hour
|
|
|
|
|
|
class MagicLinkRequest(BaseModel):
|
|
email: str
|
|
|
|
|
|
class MagicLinkVerify(BaseModel):
|
|
email: str
|
|
token: str
|
|
|
|
|
|
def is_available() -> bool:
|
|
# In dev mode the link is rendered to logs + response, so the provider is "available"
|
|
# even without SMTP/SendGrid. Keeps the login UI showing the magic-link option.
|
|
if is_local_dev_mode():
|
|
return True
|
|
return bool(os.environ.get("SMTP_HOST") or os.environ.get("SENDGRID_API_KEY"))
|
|
|
|
|
|
def _has_email_transport() -> bool:
|
|
return bool(os.environ.get("SMTP_HOST") or os.environ.get("SENDGRID_API_KEY"))
|
|
|
|
|
|
def _build_magic_link(email: str, token: str) -> str:
|
|
# URL-encode email: a literal '+' in a query string decodes to space per
|
|
# application/x-www-form-urlencoded, which would break addresses like
|
|
# "user+tag@gmail.com" on the GET /verify side.
|
|
server_url = os.environ.get("SERVER_URL", "http://localhost:8000")
|
|
return f"{server_url}/auth/email/verify?email={quote(email, safe='')}&token={token}"
|
|
|
|
|
|
@router.post("/send-link")
|
|
@_rate_limiter.limit("5/minute")
|
|
async def send_magic_link(
|
|
request: Request,
|
|
body: MagicLinkRequest,
|
|
conn: duckdb.DuckDBPyConnection = Depends(_get_db),
|
|
):
|
|
"""Send a magic link to the user's email.
|
|
|
|
When SMTP/SendGrid is not configured, or LOCAL_DEV_MODE=1, the link is
|
|
logged to stderr and returned in the response body so a developer can
|
|
click it without an email transport.
|
|
"""
|
|
repo = UserRepository(conn)
|
|
user = repo.get_by_email(body.email)
|
|
|
|
# Always return success to prevent email enumeration
|
|
if not user:
|
|
return {"message": "If this email is registered, you will receive a login link."}
|
|
|
|
# Generate token
|
|
token = secrets.token_urlsafe(32)
|
|
repo.update(
|
|
id=user["id"],
|
|
reset_token=token,
|
|
reset_token_created=datetime.now(timezone.utc),
|
|
)
|
|
|
|
link = _build_magic_link(body.email, token)
|
|
send_error: str | None = None
|
|
if _has_email_transport():
|
|
try:
|
|
_send_email(body.email, token)
|
|
except Exception as e:
|
|
send_error = str(e)
|
|
logger.error("Failed to send magic link email to %s: %s", body.email, e)
|
|
|
|
# Dev fallback: expose the link in logs + response so you can click it without SMTP.
|
|
# Scoped strictly to LOCAL_DEV_MODE so test and production behavior are unchanged.
|
|
if is_local_dev_mode():
|
|
logger.warning("=" * 60)
|
|
logger.warning("Magic link for %s (LOCAL_DEV_MODE fallback):", body.email)
|
|
logger.warning(" %s", link)
|
|
logger.warning("=" * 60)
|
|
response: dict = {
|
|
"message": "Magic link generated (LOCAL_DEV_MODE) — click dev_link to log in.",
|
|
"dev_link": link,
|
|
}
|
|
if send_error:
|
|
response["send_error"] = send_error
|
|
return response
|
|
|
|
return {"message": "If this email is registered, you will receive a login link."}
|
|
|
|
|
|
def _consume_token(conn: duckdb.DuckDBPyConnection, email: str, token: str) -> dict:
|
|
"""Validate & consume a magic-link token atomically. Returns the user dict or raises 401.
|
|
|
|
Uses a "compare-and-swap" pattern: instead of setting reset_token to NULL
|
|
directly, we first set it to a unique CONSUMED marker that identifies THIS
|
|
consumption attempt, then verify that OUR marker was written. Two concurrent
|
|
verifies will both try to write their marker, but only one will succeed
|
|
(the WHERE clause checks the original token value); the loser's UPDATE is
|
|
a no-op, and the loser sees the winner's marker and fails.
|
|
|
|
DuckDB doesn't expose affected-row count, so the marker is the only way
|
|
to distinguish "I won the race" from "someone else won."
|
|
"""
|
|
# Compute the TTL cutoff in Python — DuckDB doesn't support
|
|
# parameterized INTERVAL arithmetic (?, INTERVAL) in all builds.
|
|
cutoff = datetime.now(timezone.utc) - timedelta(seconds=MAGIC_LINK_EXPIRY)
|
|
|
|
# Unique marker for this consumption attempt — lets us detect who won
|
|
# the race without relying on DuckDB rowcount (which returns -1).
|
|
consume_id = f"CONSUMED:{secrets.token_hex(16)}"
|
|
|
|
# Step 1: Atomic compare-and-swap. Only succeeds if the token still
|
|
# matches the original value and hasn't expired. On success, writes
|
|
# OUR consume_id instead of NULL so we can verify ownership.
|
|
# DuckDB raises TransactionContext Error on concurrent row conflicts —
|
|
# catch and treat as "someone else won the race."
|
|
try:
|
|
conn.execute(
|
|
"UPDATE users SET reset_token = ?, reset_token_created = NULL "
|
|
"WHERE email = ? AND reset_token = ? AND reset_token_created IS NOT NULL "
|
|
"AND reset_token_created >= ?",
|
|
[consume_id, email, token, cutoff],
|
|
)
|
|
except Exception as exc:
|
|
err = str(exc).lower()
|
|
if "conflict" in err or "transaction" in err:
|
|
raise HTTPException(status_code=401, detail="Invalid or expired link")
|
|
raise
|
|
|
|
# Step 2: Verify that OUR consume_id was written. If a concurrent
|
|
# request won the race, we'll see THEIR consume_id (or NULL if they
|
|
# already cleared it in step 3) — either way, we fail.
|
|
row = conn.execute(
|
|
"SELECT reset_token FROM users WHERE email = ?",
|
|
[email],
|
|
).fetchone()
|
|
if not row or row[0] != consume_id:
|
|
raise HTTPException(status_code=401, detail="Invalid or expired link")
|
|
|
|
# Step 3: Clear the consumed marker. Safe to do unconditionally —
|
|
# only the winner reaches here, and the marker is transient.
|
|
# If this UPDATE fails (DB error), the marker persists but the user
|
|
# can still request a new magic link — not a lockout.
|
|
try:
|
|
conn.execute(
|
|
"UPDATE users SET reset_token = NULL WHERE email = ? AND reset_token = ?",
|
|
[email, consume_id],
|
|
)
|
|
except Exception:
|
|
logger.warning("Failed to clear CONSUMED marker for %s — marker will persist", email)
|
|
|
|
# Fetch the user (token is now cleared, but we need the rest of the fields).
|
|
# CAS already validated token + expiry atomically, so no further checks
|
|
# needed — re-running them now would always fail because reset_token was
|
|
# NULL'd in step 3.
|
|
repo = UserRepository(conn)
|
|
user = repo.get_by_email(email)
|
|
if not user:
|
|
raise HTTPException(status_code=401, detail="Invalid link")
|
|
return user
|
|
|
|
|
|
@router.post("/verify")
|
|
@_rate_limiter.limit("10/minute")
|
|
async def verify_magic_link(
|
|
request: Request,
|
|
body: MagicLinkVerify,
|
|
conn: duckdb.DuckDBPyConnection = Depends(_get_db),
|
|
):
|
|
"""Verify a magic link token and issue JWT (JSON API for programmatic clients).
|
|
|
|
Rate limited 10/min per IP to slow brute-forcing the 32-byte
|
|
``reset_token`` (the same column doubles as the magic-link token).
|
|
"""
|
|
user = _consume_token(conn, body.email, body.token)
|
|
role_label = _role_label(user, conn)
|
|
jwt_token = create_access_token(user["id"], user["email"])
|
|
return {"access_token": jwt_token, "token_type": "bearer", "email": user["email"], "role": role_label}
|
|
|
|
|
|
@router.get("/verify")
|
|
@_rate_limiter.limit("10/minute")
|
|
async def verify_magic_link_get(
|
|
request: Request,
|
|
email: str,
|
|
token: str,
|
|
conn: duckdb.DuckDBPyConnection = Depends(_get_db),
|
|
):
|
|
"""Click-through variant — verifies token, sets cookie, redirects to /dashboard.
|
|
|
|
This is the URL we embed in outgoing emails (and the dev-fallback link), so
|
|
clicking it in a mail client logs the user in without a separate API call.
|
|
|
|
Rate limited 10/min per IP for the same reason as the POST variant —
|
|
don't let the click-through path bypass the brute-force throttle.
|
|
"""
|
|
user = _consume_token(conn, email, token)
|
|
jwt_token = create_access_token(user["id"], user["email"])
|
|
# secure=False when DOMAIN is unset so the cookie is actually sent on plain HTTP (dev).
|
|
use_secure = os.environ.get("DOMAIN", "") != ""
|
|
response = RedirectResponse(url="/dashboard", status_code=302)
|
|
response.set_cookie(
|
|
key="access_token", value=jwt_token,
|
|
httponly=True, max_age=86400, samesite="lax",
|
|
secure=use_secure,
|
|
)
|
|
return response
|
|
|
|
|
|
def _send_email(email: str, token: str):
|
|
"""Send magic link email via SMTP or SendGrid."""
|
|
link = _build_magic_link(email, token)
|
|
sendgrid_key = os.environ.get("SENDGRID_API_KEY")
|
|
if sendgrid_key:
|
|
import sendgrid
|
|
from sendgrid.helpers.mail import Mail
|
|
sg = sendgrid.SendGridAPIClient(api_key=sendgrid_key)
|
|
message = Mail(
|
|
from_email=os.environ.get("EMAIL_FROM_ADDRESS", "noreply@example.com"),
|
|
to_emails=email,
|
|
subject="Login Link",
|
|
html_content=f'<p>Click to login: <a href="{link}">Login</a></p>',
|
|
)
|
|
sg.send(message)
|
|
return
|
|
|
|
smtp_host = os.environ.get("SMTP_HOST")
|
|
if smtp_host:
|
|
import smtplib
|
|
from email.mime.text import MIMEText
|
|
msg = MIMEText(f"Login link: {link}")
|
|
msg["Subject"] = "Login Link"
|
|
msg["From"] = os.environ.get("SMTP_FROM", "noreply@example.com")
|
|
msg["To"] = email
|
|
with smtplib.SMTP(smtp_host, int(os.environ.get("SMTP_PORT", "587"))) as s:
|
|
if os.environ.get("SMTP_USE_TLS", "true").lower() == "true":
|
|
s.starttls()
|
|
smtp_user = os.environ.get("SMTP_USER")
|
|
if smtp_user:
|
|
s.login(smtp_user, os.environ.get("SMTP_PASSWORD", ""))
|
|
s.send_message(msg)
|