Files
deer-flow/backend/app/gateway/routers/auth.py
greatmengqi 27b66d6753 feat(auth): authentication module with multi-tenant isolation (RFC-001)
Introduce an always-on auth layer with auto-created admin on first boot,
multi-tenant isolation for threads/stores, and a full setup/login flow.

Backend
- JWT access tokens with `ver` field for stale-token rejection; bump on
  password/email change
- Password hashing, HttpOnly+Secure cookies (Secure derived from request
  scheme at runtime)
- CSRF middleware covering both REST and LangGraph routes
- IP-based login rate limiting (5 attempts / 5-min lockout) with bounded
  dict growth and X-Forwarded-For bypass fix
- Multi-worker-safe admin auto-creation (single DB write, WAL once)
- needs_setup + token_version on User model; SQLite schema migration
- Thread/store isolation by owner; orphan thread migration on first admin
  registration
- thread_id validated as UUID to prevent log injection
- CLI tool to reset admin password
- Decorator-based authz module extracted from auth core

Frontend
- Login and setup pages with SSR guard for needs_setup flow
- Account settings page (change password / email)
- AuthProvider + route guards; skips redirect when no users registered
- i18n (en-US / zh-CN) for auth surfaces
- Typed auth API client; parseAuthError unwraps FastAPI detail envelope

Infra & tooling
- Unified `serve.sh` with gateway mode + auto dep install
- Public PyPI uv.toml pin for CI compatibility
- Regenerated uv.lock with public index

Tests
- HTTP vs HTTPS cookie security tests
- Auth middleware, rate limiter, CSRF, setup flow coverage
2026-04-08 00:31:43 +08:00

304 lines
11 KiB
Python

"""Authentication endpoints."""
import logging
import time
from fastapi import APIRouter, Depends, HTTPException, Request, Response, status
from fastapi.security import OAuth2PasswordRequestForm
from pydantic import BaseModel, EmailStr, Field
from app.gateway.auth import (
UserResponse,
create_access_token,
)
from app.gateway.auth.config import get_auth_config
from app.gateway.auth.errors import AuthErrorCode, AuthErrorResponse
from app.gateway.csrf_middleware import is_secure_request
from app.gateway.deps import get_current_user_from_request, get_local_provider
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/api/v1/auth", tags=["auth"])
# ── Request/Response Models ──────────────────────────────────────────────
class LoginResponse(BaseModel):
"""Response model for login — token only lives in HttpOnly cookie."""
expires_in: int # seconds
needs_setup: bool = False
class RegisterRequest(BaseModel):
"""Request model for user registration."""
email: EmailStr
password: str = Field(..., min_length=8)
class ChangePasswordRequest(BaseModel):
"""Request model for password change (also handles setup flow)."""
current_password: str
new_password: str = Field(..., min_length=8)
new_email: EmailStr | None = None
class MessageResponse(BaseModel):
"""Generic message response."""
message: str
# ── Helpers ───────────────────────────────────────────────────────────────
def _set_session_cookie(response: Response, token: str, request: Request) -> None:
"""Set the access_token HttpOnly cookie on the response."""
config = get_auth_config()
is_https = is_secure_request(request)
response.set_cookie(
key="access_token",
value=token,
httponly=True,
secure=is_https,
samesite="lax",
max_age=config.token_expiry_days * 24 * 3600 if is_https else None,
)
# ── Rate Limiting ────────────────────────────────────────────────────────
# In-process dict — not shared across workers. Sufficient for single-worker deployments.
_MAX_LOGIN_ATTEMPTS = 5
_LOCKOUT_SECONDS = 300 # 5 minutes
# ip → (fail_count, lock_until_timestamp)
_login_attempts: dict[str, tuple[int, float]] = {}
def _get_client_ip(request: Request) -> str:
"""Extract the real client IP for rate limiting.
Uses ``X-Real-IP`` header set by nginx (``proxy_set_header X-Real-IP
$remote_addr``). Nginx unconditionally overwrites any client-supplied
``X-Real-IP``, so the value seen by Gateway is always the TCP peer IP
that nginx observed — it cannot be spoofed by the client.
``request.client.host`` is NOT reliable because uvicorn's default
``proxy_headers=True`` replaces it with the *first* entry from
``X-Forwarded-For``, which IS client-spoofable.
``X-Forwarded-For`` is intentionally NOT used for the same reason.
"""
real_ip = request.headers.get("x-real-ip", "").strip()
if real_ip:
return real_ip
# Fallback: direct connection without nginx (e.g. unit tests, dev).
return request.client.host if request.client else "unknown"
def _check_rate_limit(ip: str) -> None:
"""Raise 429 if the IP is currently locked out."""
record = _login_attempts.get(ip)
if record is None:
return
fail_count, lock_until = record
if fail_count >= _MAX_LOGIN_ATTEMPTS:
if time.time() < lock_until:
raise HTTPException(
status_code=429,
detail="Too many login attempts. Try again later.",
)
del _login_attempts[ip]
_MAX_TRACKED_IPS = 10000
def _record_login_failure(ip: str) -> None:
"""Record a failed login attempt for the given IP."""
# Evict expired lockouts when dict grows too large
if len(_login_attempts) >= _MAX_TRACKED_IPS:
now = time.time()
expired = [k for k, (c, t) in _login_attempts.items() if c >= _MAX_LOGIN_ATTEMPTS and now >= t]
for k in expired:
del _login_attempts[k]
# If still too large, evict cheapest-to-lose half: below-threshold
# IPs (lock_until=0.0) sort first, then earliest-expiring lockouts.
if len(_login_attempts) >= _MAX_TRACKED_IPS:
by_time = sorted(_login_attempts.items(), key=lambda kv: kv[1][1])
for k, _ in by_time[: len(by_time) // 2]:
del _login_attempts[k]
record = _login_attempts.get(ip)
if record is None:
_login_attempts[ip] = (1, 0.0)
else:
new_count = record[0] + 1
lock_until = time.time() + _LOCKOUT_SECONDS if new_count >= _MAX_LOGIN_ATTEMPTS else 0.0
_login_attempts[ip] = (new_count, lock_until)
def _record_login_success(ip: str) -> None:
"""Clear failure counter for the given IP on successful login."""
_login_attempts.pop(ip, None)
# ── Endpoints ─────────────────────────────────────────────────────────────
@router.post("/login/local", response_model=LoginResponse)
async def login_local(
request: Request,
response: Response,
form_data: OAuth2PasswordRequestForm = Depends(),
):
"""Local email/password login."""
client_ip = _get_client_ip(request)
_check_rate_limit(client_ip)
user = await get_local_provider().authenticate({"email": form_data.username, "password": form_data.password})
if user is None:
_record_login_failure(client_ip)
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=AuthErrorResponse(code=AuthErrorCode.INVALID_CREDENTIALS, message="Incorrect email or password").model_dump(),
)
_record_login_success(client_ip)
token = create_access_token(str(user.id), token_version=user.token_version)
_set_session_cookie(response, token, request)
return LoginResponse(
expires_in=get_auth_config().token_expiry_days * 24 * 3600,
needs_setup=user.needs_setup,
)
@router.post("/register", response_model=UserResponse, status_code=status.HTTP_201_CREATED)
async def register(request: Request, response: Response, body: RegisterRequest):
"""Register a new user account (always 'user' role).
Admin is auto-created on first boot. This endpoint creates regular users.
Auto-login by setting the session cookie.
"""
try:
user = await get_local_provider().create_user(email=body.email, password=body.password, system_role="user")
except ValueError:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=AuthErrorResponse(code=AuthErrorCode.EMAIL_ALREADY_EXISTS, message="Email already registered").model_dump(),
)
token = create_access_token(str(user.id), token_version=user.token_version)
_set_session_cookie(response, token, request)
return UserResponse(id=str(user.id), email=user.email, system_role=user.system_role)
@router.post("/logout", response_model=MessageResponse)
async def logout(request: Request, response: Response):
"""Logout current user by clearing the cookie."""
response.delete_cookie(key="access_token", secure=is_secure_request(request), samesite="lax")
return MessageResponse(message="Successfully logged out")
@router.post("/change-password", response_model=MessageResponse)
async def change_password(request: Request, response: Response, body: ChangePasswordRequest):
"""Change password for the currently authenticated user.
Also handles the first-boot setup flow:
- If new_email is provided, updates email (checks uniqueness)
- If user.needs_setup is True and new_email is given, clears needs_setup
- Always increments token_version to invalidate old sessions
- Re-issues session cookie with new token_version
"""
from app.gateway.auth.password import hash_password_async, verify_password_async
user = await get_current_user_from_request(request)
if user.password_hash is None:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=AuthErrorResponse(code=AuthErrorCode.INVALID_CREDENTIALS, message="OAuth users cannot change password").model_dump())
if not await verify_password_async(body.current_password, user.password_hash):
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=AuthErrorResponse(code=AuthErrorCode.INVALID_CREDENTIALS, message="Current password is incorrect").model_dump())
provider = get_local_provider()
# Update email if provided
if body.new_email is not None:
existing = await provider.get_user_by_email(body.new_email)
if existing and str(existing.id) != str(user.id):
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=AuthErrorResponse(code=AuthErrorCode.EMAIL_ALREADY_EXISTS, message="Email already in use").model_dump())
user.email = body.new_email
# Update password + bump version
user.password_hash = await hash_password_async(body.new_password)
user.token_version += 1
# Clear setup flag if this is the setup flow
if user.needs_setup and body.new_email is not None:
user.needs_setup = False
await provider.update_user(user)
# Re-issue cookie with new token_version
token = create_access_token(str(user.id), token_version=user.token_version)
_set_session_cookie(response, token, request)
return MessageResponse(message="Password changed successfully")
@router.get("/me", response_model=UserResponse)
async def get_me(request: Request):
"""Get current authenticated user info."""
user = await get_current_user_from_request(request)
return UserResponse(id=str(user.id), email=user.email, system_role=user.system_role, needs_setup=user.needs_setup)
@router.get("/setup-status")
async def setup_status():
"""Check if admin account exists. Always False after first boot."""
user_count = await get_local_provider().count_users()
return {"needs_setup": user_count == 0}
# ── OAuth Endpoints (Future/Placeholder) ─────────────────────────────────
@router.get("/oauth/{provider}")
async def oauth_login(provider: str):
"""Initiate OAuth login flow.
Redirects to the OAuth provider's authorization URL.
Currently a placeholder - requires OAuth provider implementation.
"""
if provider not in ["github", "google"]:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=f"Unsupported OAuth provider: {provider}",
)
raise HTTPException(
status_code=status.HTTP_501_NOT_IMPLEMENTED,
detail="OAuth login not yet implemented",
)
@router.get("/callback/{provider}")
async def oauth_callback(provider: str, code: str, state: str):
"""OAuth callback endpoint.
Handles the OAuth provider's callback after user authorization.
Currently a placeholder.
"""
raise HTTPException(
status_code=status.HTTP_501_NOT_IMPLEMENTED,
detail="OAuth callback not yet implemented",
)