Files
ZY-Agent/backend/app/gateway/auth_middleware.py
T
2026-06-28 21:25:46 +08:00

197 lines
8.4 KiB
Python

"""Global authentication middleware — fail-closed safety net.
Rejects unauthenticated requests to non-public paths with 401. When a
request passes the cookie check, resolves the JWT payload to a real
``User`` object and stamps it into both ``request.state.user`` and the
``deerflow.runtime.user_context`` contextvar so that repository-layer
owner filtering works automatically via the sentinel pattern.
Fine-grained permission checks remain in authz.py decorators.
"""
import logging
from collections.abc import Callable
from fastapi import HTTPException, Request, Response
from starlette.middleware.base import BaseHTTPMiddleware
from starlette.responses import JSONResponse
from starlette.types import ASGIApp
from app.gateway.auth.api_key_backend import build_api_key_backend
from app.gateway.auth.errors import AuthErrorCode, AuthErrorResponse
from app.gateway.auth.models import ActiveWorkspace
from app.gateway.authz import _ALL_PERMISSIONS, AuthContext
from app.gateway.internal_auth import INTERNAL_AUTH_HEADER_NAME, get_internal_user, is_valid_internal_auth_token
from deerflow.runtime.user_context import reset_current_user, set_current_user
from deerflow.runtime.workspace_context import reset_current_workspace, set_current_workspace
logger = logging.getLogger(__name__)
# Paths that never require authentication.
_PUBLIC_PATH_PREFIXES: tuple[str, ...] = (
"/health",
"/docs",
"/redoc",
"/openapi.json",
)
# Exact auth paths that are public (login/register/status check).
# /api/v1/auth/me, /api/v1/auth/change-password etc. are NOT public.
_PUBLIC_EXACT_PATHS: frozenset[str] = frozenset(
{
"/api/v1/auth/login/local",
"/api/v1/auth/register",
"/api/v1/auth/logout",
"/api/v1/auth/setup-status",
"/api/v1/auth/initialize",
}
)
def _is_public(path: str) -> bool:
stripped = path.rstrip("/")
if stripped in _PUBLIC_EXACT_PATHS:
return True
return any(path.startswith(prefix) for prefix in _PUBLIC_PATH_PREFIXES)
# Data-plane / SDK route prefixes a service principal (API key) may reach.
# Everything else (global control plane: models/mcp/memory/skills/channels/
# agents, plus management/auth endpoints) is denied by default for API keys.
# NOTE: nginx rewrites /api/langgraph/(.*) -> /api/$1 before the gateway, so
# AuthMiddleware never sees /api/langgraph; the SDK surface arrives as
# /api/threads, /api/runs, /api/assistants. assistants.search()/get() is
# required for langgraph-sdk client init, so /api/assistants is allowed.
_DATAPLANE_PREFIXES: tuple[str, ...] = (
"/api/threads",
"/api/v1/threads",
"/api/runs",
"/api/v1/runs",
"/api/assistants",
)
def _is_dataplane_path(path: str) -> bool:
"""True if an API key request may reach this path. Reusable by a future
Pattern B service-token branch."""
return any(path.startswith(prefix) for prefix in _DATAPLANE_PREFIXES)
class AuthMiddleware(BaseHTTPMiddleware):
"""Strict auth gate: reject requests without a valid session.
Two-stage check for non-public paths:
1. Cookie presence — return 401 NOT_AUTHENTICATED if missing
2. JWT validation via ``get_optional_user_from_request`` — return 401
TOKEN_INVALID if the token is absent, malformed, expired, or the
signed user does not exist / is stale
On success, stamps ``request.state.user`` and the
``deerflow.runtime.user_context`` contextvar so that repository-layer
owner filters work downstream without every route needing a
``@require_auth`` decorator. Routes that need per-resource
authorization (e.g. "user A cannot read user B's thread by guessing
the URL") should additionally use ``@require_permission(...,
owner_check=True)`` for explicit enforcement — but authentication
itself is fully handled here.
"""
def __init__(self, app: ASGIApp) -> None:
super().__init__(app)
async def dispatch(self, request: Request, call_next: Callable) -> Response:
if _is_public(request.url.path):
return await call_next(request)
# API key path: "Authorization: Bearer dfk_..." authenticates a
# service account. Resolved principal is mapped to the same
# (user_id, workspace_id) contextvars a human would set (spec D1),
# so all downstream isolation works unchanged.
auth_header = request.headers.get("authorization", "")
if auth_header.startswith("Bearer dfk_"):
token = auth_header[len("Bearer ") :]
backend = build_api_key_backend()
try:
result = await backend.authenticate(token) if backend is not None else None
except Exception:
logger.exception("API key authentication failed unexpectedly")
return JSONResponse(status_code=503, content={"detail": "Authentication service unavailable"})
if result is None:
return JSONResponse(
status_code=401,
content={"detail": AuthErrorResponse(code=AuthErrorCode.TOKEN_INVALID, message="Invalid API key").model_dump()},
)
request.state.user = result.principal
request.state.auth = AuthContext(user=result.principal, permissions=result.permissions)
user_token = set_current_user(result.principal)
ws_token = set_current_workspace(ActiveWorkspace(id=result.workspace_id, role=result.role))
try:
return await call_next(request)
finally:
reset_current_workspace(ws_token)
reset_current_user(user_token)
internal_user = None
if is_valid_internal_auth_token(request.headers.get(INTERNAL_AUTH_HEADER_NAME)):
internal_user = get_internal_user()
# Non-public path: require session cookie
if internal_user is None and not request.cookies.get("access_token"):
return JSONResponse(
status_code=401,
content={
"detail": AuthErrorResponse(
code=AuthErrorCode.NOT_AUTHENTICATED,
message="Authentication required",
).model_dump()
},
)
# Strict JWT validation: reject junk/expired tokens with 401
# right here instead of silently passing through. This closes
# the "junk cookie bypass" gap (AUTH_TEST_PLAN test 7.5.8):
# without this, non-isolation routes like /api/models would
# accept any cookie-shaped string as authentication.
#
# We call the *strict* resolver so that fine-grained error
# codes (token_expired, token_invalid, user_not_found, …)
# propagate from AuthErrorCode, not get flattened into one
# generic code. BaseHTTPMiddleware doesn't let HTTPException
# bubble up, so we catch and render it as JSONResponse here.
from app.gateway.deps import get_current_user_from_request
if internal_user is not None:
user = internal_user
else:
try:
user = await get_current_user_from_request(request)
except HTTPException as exc:
return JSONResponse(status_code=exc.status_code, content={"detail": exc.detail})
# Stamp both request.state.user (for the contextvar pattern)
# and request.state.auth (so @require_permission's "auth is
# None" branch short-circuits instead of running the entire
# JWT-decode + DB-lookup pipeline a second time per request).
request.state.user = user
request.state.auth = AuthContext(user=user, permissions=_ALL_PERMISSIONS)
user_token = set_current_user(user)
# Inject workspace contextvar from the JWT's wid/role claims.
# decode_token has already rejected legacy no-wid tokens upstream,
# so by the time we get here payload.wid is guaranteed non-None
# for cookie-authenticated requests. Internal-auth requests skip
# the workspace contextvar (they don't have a workspace scope —
# the internal user is a system actor).
ws_token = None
payload = getattr(request.state, "auth_payload", None)
if payload is not None and payload.wid is not None:
ws_token = set_current_workspace(ActiveWorkspace(id=payload.wid, role=payload.role or "owner"))
try:
return await call_next(request)
finally:
if ws_token is not None:
reset_current_workspace(ws_token)
reset_current_user(user_token)