agnes-the-ai-analyst/app/auth/providers/email.py
ZdenekSrotyr e9d7af3cce feat(rbac+marketplace): RBAC v13 + Claude Code marketplace + #81/#83/#44 hardening
This squashes 13 commits from ma/staging plus a small docstring translation
into a single coherent unit. Three workstreams.

== RBAC v13 redesign ==
- Drops core.viewer/analyst/km_admin/admin hierarchy and the
  internal_roles / group_mappings / user_role_grants / plugin_access tables.
- Replaced by user_group_members + resource_grants. Atomic v12→v13 backfill
  wrapped in BEGIN/COMMIT; ROLLBACK leaves schema_version at 12 for retry.
- Two authorization primitives in app.auth.access:
    require_admin                        — Admin-group god-mode
    require_resource_access(rt, "{path}") — entity-scoped grants
  Single DB lookup per request; no session cache; no implies BFS.
- /admin/access UI (single page) replaces /admin/role-mapping +
  /admin/plugin-access. CLI `da admin group/grant *` replaces
  `da admin role/mapping/grant-role/revoke-role/effective-roles`.
- ResourceType.TABLE listing-only — admins can record table grants,
  runtime enforcement still flows through legacy dataset_permissions
  (migration plan in docs/TODO-rbac-data-enforcement.md).

== Claude Code marketplace ==
- Aggregated /marketplace.zip + /marketplace.git/* (PAT-gated,
  RBAC-filtered, content-addressed cache via dulwich).
- Admin god-mode dropped on the marketplace surface — admins curate
  their own view via grants like everyone else.
- Bare-repo cache materializes per RBAC-filtered ETag; stale entries
  not pruned in this iteration (disclaimed in git_backend.py docstring).

== #81 #83 #44 security/ops hardening ==
- #81 Group A — orchestrator ATTACH allow-listing (extension/url/alias).
- #81 Group B — Keboola extractor 3-state exit codes:
    0 success / 1 total fail / 2 PARTIAL fail
  Sync API logs PARTIAL FAILURE alert on exit 2. Operators with binary
  alerting must teach it the new partial signal.
- #81 Group C — schema v10 view_ownership; rejects silent overwrite
  of a prior connector's view name on collision.
- #81 Group D — extractor-side identifier validation.
- #83 — Jira webhook fail-closed when JIRA_WEBHOOK_SECRET unset
  + path-traversal fix.
- #44 — entire /api/scripts/* surface is admin-only (planted-script +
  sandbox-bypass risk closed).

== Web UI polish + deploy fix ==
- /admin/access: live grant-count badges (no stale snapshot revert),
  shared-header CSS link added to /catalog and /admin/{tables,permissions},
  per-resource-type colored stripes.
- docker-compose.host-mount.yml: bind,rbind so dual-disk hosts don't
  silently shadow sub-mounts and write state to the wrong disk.

== OSS vendor-neutralization (waves 1+2) ==
- scripts/grpn/ → scripts/ops/. Customer-specific identifiers
  (project IDs, internal hostnames, dev/prod VM IPs, brand names)
  replaced with placeholders across code, docs, Terraform, Caddyfile,
  OAuth probe, and planning docs. Downstream infra repos that copied
  scripts/grpn/agnes-tls-rotate.sh or agnes-auto-upgrade.sh must
  update the path.

== Translation ==
- src/repositories/user_groups.py::ensure_system docstring translated
  from Czech to English for codebase consistency.

Co-authored-by: Mina Rustamyan <mina@keboola.com>
2026-04-28 14:25:04 +02:00

205 lines
7.4 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
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 src.repositories.users import UserRepository
def _role_label(user: dict, conn: duckdb.DuckDBPyConnection) -> str:
if is_user_admin(user["id"], conn):
return "admin"
return user.get("role") or "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")
async def send_magic_link(
request: 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(request.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(request.email, token)
send_error: str | None = None
if _has_email_transport():
try:
_send_email(request.email, token)
except Exception as e:
send_error = str(e)
logger.error("Failed to send magic link email to %s: %s", request.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):", request.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. Returns the user dict or raises 401."""
repo = UserRepository(conn)
user = repo.get_by_email(email)
if not user:
raise HTTPException(status_code=401, detail="Invalid link")
if user.get("reset_token") != token:
raise HTTPException(status_code=401, detail="Invalid or expired link")
created = user.get("reset_token_created")
if created:
if isinstance(created, str):
created = datetime.fromisoformat(created)
# DuckDB returns TIMESTAMP as offset-naive; we stored it as UTC, so assume UTC.
if created.tzinfo is None:
created = created.replace(tzinfo=timezone.utc)
if (datetime.now(timezone.utc) - created).total_seconds() > MAGIC_LINK_EXPIRY:
raise HTTPException(status_code=401, detail="Link expired")
# Clear token (one-time use)
repo.update(id=user["id"], reset_token=None, reset_token_created=None)
return user
@router.post("/verify")
async def verify_magic_link(
request: MagicLinkVerify,
conn: duckdb.DuckDBPyConnection = Depends(_get_db),
):
"""Verify a magic link token and issue JWT (JSON API for programmatic clients)."""
user = _consume_token(conn, request.email, request.token)
role_label = _role_label(user, conn)
jwt_token = create_access_token(user["id"], user["email"], role_label)
return {"access_token": jwt_token, "token_type": "bearer", "email": user["email"], "role": role_label}
@router.get("/verify")
async def verify_magic_link_get(
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.
"""
user = _consume_token(conn, email, token)
jwt_token = create_access_token(user["id"], user["email"], _role_label(user, conn))
# 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)