Files
stackpilot/backend/routers/auth.py
T
menzeljandClaude Opus 5 09bed274eb
CI / check (push) Successful in 7m4s
CI / build-and-push (push) Successful in 1m47s
Lock stacks during compose runs, cache stats, persist runtime state (0.47.0)
F7 — Nothing stopped two compose operations landing on the same stack. There
was a busy flag, but is_busy() was only ever read to colour the status column;
no lifecycle handler consulted it before acting. Two tabs, or auto-update
picking up a stack somebody had just clicked, both ran pull + up -d against the
same project and raced over recreating containers.

Lifecycle calls, the two deploy WebSockets and the auto-update pass now take a
real lock; a second caller gets 409 (or an error frame and close 4409) and
auto-update skips and retries next cycle. The lock is a row rather than a set
in one worker's memory, so it holds across workers and across a restart, and it
carries an expiry — a worker killed mid-deploy would otherwise strand the stack
with no fix short of editing the database.

F10 — /api/stacks/stats sampled every running container on every call, one
blocking daemon request each, and both the dashboard and the stacks list poll
it every five seconds. Two tabs on a 40-container host meant a sustained ~16
samples a second. Cached for 4s behind a lock so concurrent callers share one
sweep, the same shape dashboard_service already used for its fleet aggregate.

F11 — Three module dicts assumed exactly one uvicorn worker without saying so
and were lost on restart. The busy set is the lock above. The image update
cache is now mirrored to SQLite, so a restart shows the badges immediately
instead of blanking them for up to an hour, and the already-notified marks come
back with them rather than re-announcing the same updates. The login rate
limiter is a table, so it cannot be cleared by getting the process to restart
and no longer multiplies by the worker count.

The constraint that shaped this: compose_service and update_service are shared
with the agent, which has no database. Neither may import one. So the lock is a
separate service the central app enforces at its own entry points, and update
persistence is an opt-in callback the central app registers in its lifespan —
the agent registers nothing and behaves exactly as before. A test asserts
update_service never imports the database, since that is the kind of thing a
later change breaks silently.

Both new nets were checked by reverting the fix: dropping the lock from
_lifecycle fails six tests, removing the stats cache fails the one that names
the behaviour.

Also wires up cache pruning in the same sweep — without it both the dict and
the table grew one entry per image tag ever run, for the life of the install.

31 new tests (729 total).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dk43rmEeRfYi5wsLDbmfyG
2026-08-31 13:43:39 +02:00

340 lines
12 KiB
Python

"""Authentication routes + first-launch setup wizard."""
from __future__ import annotations
from datetime import datetime, timedelta, timezone
from fastapi import APIRouter, Depends, HTTPException, Request, Response, status
from sqlmodel import Session, delete, select
import auth as auth_mod
from database import get_session
from models.runtime_state import LoginAttempt
from models.user import (
LoginRequest,
RefreshRequest,
TokenPair,
User,
UserCreate,
UserRead,
UserUpdate,
)
from config import settings
from services import audit_service
router = APIRouter(prefix="/api/auth", tags=["auth"])
# Login rate limit: max 10 attempts per minute per client IP.
#
# Kept in the database rather than a module dict. In memory it reset on every
# restart — so an attacker could clear their own budget by getting the process
# to restart — and with more than one uvicorn worker each worker enforced its
# own limit, multiplying the real allowance by the worker count.
#
# The IP is only meaningful because uvicorn runs with --proxy-headers; without
# that every request looks like it comes from the frontend container and this
# would throttle all users together.
_RATE_LIMIT = 10
_RATE_WINDOW = timedelta(seconds=60)
#: Attempts older than this are deleted while we are in the table anyway.
_RATE_RETENTION = timedelta(hours=1)
def _check_rate_limit(session: Session, ip: str) -> None:
now = datetime.now(timezone.utc)
session.exec(delete(LoginAttempt).where(LoginAttempt.at < now - _RATE_RETENTION))
recent = session.exec(
select(LoginAttempt).where(
LoginAttempt.ip == ip, LoginAttempt.at >= now - _RATE_WINDOW
)
).all()
if len(recent) >= _RATE_LIMIT:
session.commit()
raise HTTPException(
status_code=status.HTTP_429_TOO_MANY_REQUESTS,
detail="Too many login attempts, slow down.",
)
session.add(LoginAttempt(ip=ip, at=now))
session.commit()
#: The refresh cookie is scoped to the two endpoints that consume it, so it is
#: not attached to every API call the way a "/" cookie would be.
REFRESH_COOKIE = "stackpilot_refresh"
REFRESH_COOKIE_PATH = "/api/auth"
def _issue(
user: User, response: Response, request: Request, in_body: bool = False
) -> TokenPair:
"""Mint a token pair, putting the refresh token in an httpOnly cookie.
Keeping the long-lived token out of JavaScript's reach means a successful
XSS can no longer walk off with 30 days of access — it is limited to
whatever it can do in the live page. The short-lived access token still
goes to the client, which holds it in memory only.
``in_body`` returns it in the response as well, for scripted clients that
have no cookie jar.
"""
refresh = auth_mod.create_refresh_token(user)
response.set_cookie(
REFRESH_COOKIE,
refresh,
max_age=settings.REFRESH_TOKEN_EXPIRE_DAYS * 24 * 3600,
httponly=True,
# Lax rather than Strict so following a link into StackPilot keeps you
# signed in; the cookie is only ever read by same-site POSTs anyway.
samesite="lax",
# Only when the request actually arrived over TLS — marking it Secure on
# a plain-HTTP homelab deployment would make the browser drop it and
# nobody could stay signed in. request.url.scheme is trustworthy here
# because uvicorn runs with --proxy-headers.
secure=request.url.scheme == "https",
path=REFRESH_COOKIE_PATH,
)
return TokenPair(
access_token=auth_mod.create_access_token(user),
refresh_token=refresh if in_body else None,
)
@router.get("/needs-setup")
def needs_setup(session: Session = Depends(get_session)) -> dict:
"""First-launch wizard check: True if no users exist yet."""
return {"needs_setup": not auth_mod.users_exist(session)}
@router.post("/setup", response_model=TokenPair)
def setup(
body: UserCreate,
request: Request,
response: Response,
in_body: bool = False,
session: Session = Depends(get_session),
) -> TokenPair:
if auth_mod.users_exist(session):
raise HTTPException(status_code=400, detail="Setup already completed")
user = User(
username=body.username,
hashed_password=auth_mod.hash_password(body.password),
role="admin",
)
session.add(user)
session.commit()
session.refresh(user)
audit_service.record(
session, user=user.username, action="user.setup", target=user.username
)
return _issue(user, response, request, in_body)
@router.post("/login", response_model=TokenPair)
def login(
body: LoginRequest,
request: Request,
response: Response,
in_body: bool = False,
session: Session = Depends(get_session),
) -> TokenPair:
ip = request.client.host if request.client else "unknown"
_check_rate_limit(session, ip)
user = auth_mod.authenticate(session, body.username, body.password)
if not user:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Incorrect username or password",
)
audit_service.record(
session, user=user.username, action="auth.login", target=user.username, ip=ip
)
return _issue(user, response, request, in_body)
@router.post("/refresh", response_model=TokenPair)
def refresh(
request: Request,
response: Response,
body: RefreshRequest | None = None,
in_body: bool = False,
session: Session = Depends(get_session),
) -> TokenPair:
"""Exchange a refresh token for a fresh pair.
Reads the httpOnly cookie; a body is accepted as a fallback for clients
that cannot hold one. The token is re-validated against the live user, so a
password reset or a disabled account takes effect here too rather than at
the end of the token's 30-day life.
"""
token = request.cookies.get(REFRESH_COOKIE) or (body.refresh_token if body else None)
if not token:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail="No refresh token"
)
payload = auth_mod.decode_token(token, "refresh")
user = auth_mod.resolve_token_user(session, payload)
if not user:
response.delete_cookie(REFRESH_COOKIE, path=REFRESH_COOKIE_PATH)
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Session is no longer valid — sign in again",
)
return _issue(user, response, request, in_body)
@router.post("/logout")
def logout(request: Request, response: Response) -> dict:
"""End the session on this device by dropping the refresh cookie.
Deliberately does not bump ``token_version``: signing out on your phone
should not kill the session on your desktop. Use "sign out everywhere"
for that. The access token is held in memory by the client and dies with
the tab; it stays technically valid for the rest of its hour, which is why
it is short-lived.
"""
response.delete_cookie(REFRESH_COOKIE, path=REFRESH_COOKIE_PATH)
return {"ok": True}
@router.post("/logout-everywhere")
def logout_everywhere(
request: Request,
response: Response,
session: Session = Depends(get_session),
user: User = Depends(auth_mod.get_current_user),
) -> dict:
"""Revoke every token this account holds, on every device."""
auth_mod.bump_token_version(user)
session.add(user)
session.commit()
response.delete_cookie(REFRESH_COOKIE, path=REFRESH_COOKIE_PATH)
audit_service.record(
session, user=user.username, action="auth.logout_everywhere",
target=user.username, ip=_ip(request),
)
return {"ok": True}
@router.get("/me", response_model=UserRead)
def me(user: User = Depends(auth_mod.get_current_user)) -> User:
return user
# --------------------------------------------------------------------------- #
# User management (admin only)
# --------------------------------------------------------------------------- #
def _ip(request: Request) -> str:
return request.client.host if request.client else "unknown"
@router.get("/users", response_model=list[UserRead])
def list_users(
session: Session = Depends(get_session),
_admin: User = Depends(auth_mod.require_admin),
) -> list[User]:
return session.exec(select(User).order_by(User.id)).all()
@router.post("/users", response_model=UserRead, status_code=201)
def create_user(
body: UserCreate,
request: Request,
session: Session = Depends(get_session),
admin: User = Depends(auth_mod.require_admin),
) -> User:
if not body.username.strip() or not body.password:
raise HTTPException(status_code=400, detail="Username and password required")
if auth_mod.get_user(session, body.username):
raise HTTPException(status_code=409, detail="Username already exists")
role = body.role if body.role in ("admin", "user") else "user"
user = User(
username=body.username,
hashed_password=auth_mod.hash_password(body.password),
role=role,
)
session.add(user)
session.commit()
session.refresh(user)
audit_service.record(
session, user=admin.username, action="user.create", target=user.username,
detail=f"role={role}", ip=_ip(request),
)
return user
@router.patch("/users/{user_id}", response_model=UserRead)
def update_user(
user_id: int,
body: UserUpdate,
request: Request,
session: Session = Depends(get_session),
admin: User = Depends(auth_mod.require_admin),
) -> User:
user = session.get(User, user_id)
if not user:
raise HTTPException(status_code=404, detail="User not found")
# Guard against locking yourself out / demoting the last admin.
demoting = (body.role is not None and body.role != "admin") or body.is_active is False
if user.role == "admin" and demoting:
other_admins = session.exec(
select(User).where(User.role == "admin", User.is_active == True, User.id != user_id) # noqa: E712
).first()
if not other_admins:
raise HTTPException(status_code=400, detail="Cannot demote or disable the last active admin")
# Any of these three changes what this account is allowed to do, so the
# tokens it already holds must stop working. Without the bump a password
# reset was cosmetic: whoever had the old tokens kept full access for up to
# 30 days, and a demotion or a disable only took effect once they expired.
authority_changed = (
bool(body.password)
or (body.role is not None and body.role != user.role)
or (body.is_active is not None and body.is_active != user.is_active)
)
if body.password:
user.hashed_password = auth_mod.hash_password(body.password)
if body.role is not None:
if body.role not in ("admin", "user"):
raise HTTPException(status_code=400, detail="Invalid role")
user.role = body.role
if body.is_active is not None:
user.is_active = body.is_active
if authority_changed:
auth_mod.bump_token_version(user)
session.add(user)
session.commit()
session.refresh(user)
audit_service.record(
session, user=admin.username, action="user.update", target=user.username,
ip=_ip(request),
)
return user
@router.delete("/users/{user_id}")
def delete_user(
user_id: int,
request: Request,
session: Session = Depends(get_session),
admin: User = Depends(auth_mod.require_admin),
) -> dict:
user = session.get(User, user_id)
if not user:
raise HTTPException(status_code=404, detail="User not found")
if user.id == admin.id:
raise HTTPException(status_code=400, detail="You cannot delete your own account")
if user.role == "admin":
other_admins = session.exec(
select(User).where(User.role == "admin", User.is_active == True, User.id != user_id) # noqa: E712
).first()
if not other_admins:
raise HTTPException(status_code=400, detail="Cannot delete the last active admin")
username = user.username
session.delete(user)
session.commit()
audit_service.record(
session, user=admin.username, action="user.delete", target=username,
ip=_ip(request),
)
return {"ok": True}