qonto-assistant/src/qonto_assistant/app.py
tegwick 1f0f979e36 QONTO-WP-0004-T04: live flex-auth + tenant-engine authorization gate
Replaces the config-only QONTO_ASSISTANT_ENFORCE_SCOPE cached-claim
check with two live-checked facts, per docs/SecurityPractice.md #4:

1. flex-auth POST /v1/check on finance.qonto.read for the calling
   actor/tenant (FlexAuthCheckClient, modeled on tenant-engine's own
   client for the same API). Registration lives in the flex-auth repo
   (examples/qonto-assistant/) -- rules + embedded tests verified with
   flex-auth test-policy/load-registry/check, and a live flex-auth
   serve hit by this exact client over real HTTP (not a mock).
2. tenant-engine's live capability-role lookup
   (GET /tenants/{id}/roles/live), denying unless the tenant currently
   holds one of QONTO_TENANT_ENGINE_REQUIRED_ROLES (default VEN,CUS) --
   optional and additive to the flex-auth check.

Both clients fail closed by construction (unreachable/malformed/non-2xx
all deny, never grant), matching FlexAuthCheckClient's existing
fail-closed philosophy elsewhere in the fleet. LiveAuthorizationGate
combines both and is wired into CapabilityService._execute ahead of
the internal policy kernel; off by default (no QONTO_FLEX_AUTH_URL
set) so existing deployments are unaffected until configured.

Verified beyond mocked unit tests: ran a real `flex-auth serve` loaded
with the registered policy, and a real tenant-engine instance seeded
with a VEN grant for tenant:friendly:binky, and exercised this repo's
actual FlexAuthCheckClient/TenantEngineClient/LiveAuthorizationGate
against both live processes over real HTTP -- allow for the correct
tenant, live_authz_denied for a mismatched tenant.

28 new unit tests (flex_auth_client, tenant_engine_client,
live_authorization_gate + CapabilityService integration). Full suite
-> 80 passed; REST/MCP smokes and compileall still clean.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-24 00:19:04 +02:00

233 lines
8.8 KiB
Python

from __future__ import annotations
from collections.abc import AsyncIterator, Callable
from contextlib import AsyncExitStack, asynccontextmanager, suppress
import logging
from uuid import uuid4
import uvicorn
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse
from starlette.concurrency import run_in_threadpool
from qonto_assistant import __version__
from qonto_assistant.audit import AuditLogger
from qonto_assistant.auth import actor_claims_from_request
from qonto_assistant.config import Settings
from qonto_assistant.credentials import build_credential_provider
from qonto_assistant.errors import QontoAssistantError, UpstreamError
from qonto_assistant.flex_auth_client import FlexAuthCheckClient
from qonto_assistant.key_cape_auth import KeyCapeTokenVerifier
from qonto_assistant.live_authorization import LiveAuthorizationGate
from qonto_assistant.mcp_auth import BearerTokenAuthMiddleware
from qonto_assistant.mcp_server import create_mcp_server
from qonto_assistant.policy import PolicyEngine
from qonto_assistant.qonto_client import FixtureQontoClient, QontoClient
from qonto_assistant.rate_limits import ConcurrencyLimiter, RateLimiter
from qonto_assistant.security_watch import DenyEscalationTracker
from qonto_assistant.service import CapabilityService
from qonto_assistant.tenant_engine_client import TenantEngineClient
def create_app(
*,
settings: Settings | None = None,
service: CapabilityService | None = None,
audit_logger: AuditLogger | None = None,
rate_limiter: RateLimiter | None = None,
concurrency_limiter: ConcurrencyLimiter | None = None,
key_cape_verifier: KeyCapeTokenVerifier | None = None,
) -> FastAPI:
settings = settings or Settings.from_env()
audit_logger = audit_logger or AuditLogger()
service = service or _build_service(
settings=settings,
audit_logger=audit_logger,
rate_limiter=rate_limiter,
concurrency_limiter=concurrency_limiter,
)
if key_cape_verifier is None and settings.key_cape_jwks_url:
key_cape_verifier = KeyCapeTokenVerifier(
jwks_url=settings.key_cape_jwks_url,
issuer=settings.key_cape_issuer,
audience=settings.key_cape_audience,
required=settings.key_cape_required,
default_lane=settings.default_actor_lane,
timeout_seconds=settings.key_cape_timeout_seconds,
cache_seconds=settings.key_cape_cache_seconds,
)
mcp_server = create_mcp_server(settings=settings, service=service, key_cape_verifier=key_cape_verifier)
mcp_app = mcp_server.streamable_http_app()
if settings.mcp_auth_token:
mcp_app.add_middleware(BearerTokenAuthMiddleware, token=settings.mcp_auth_token)
@asynccontextmanager
async def lifespan(_: FastAPI) -> AsyncIterator[None]:
async with AsyncExitStack() as stack:
await stack.enter_async_context(mcp_app.router.lifespan_context(mcp_app))
yield
with suppress(Exception):
service.client.close()
app = FastAPI(title="qonto-assistant", version=__version__, lifespan=lifespan)
app.state.settings = settings
app.state.service = service
app.mount("/mcp", mcp_app)
@app.exception_handler(QontoAssistantError)
def handle_qonto_error(_: Request, exc: QontoAssistantError) -> JSONResponse:
body = {"error_code": exc.error_code, "detail": exc.message}
if isinstance(exc, UpstreamError) and exc.upstream_status is not None:
body["upstream_status"] = exc.upstream_status
return JSONResponse(status_code=exc.status_code, content=body)
@app.get("/v1/health")
async def health() -> dict[str, str]:
return {
"status": "ok",
"service": settings.service_name,
"version": __version__,
"policy_file": str(settings.policy_file),
}
@app.get("/v1/accounts")
async def get_accounts(request: Request) -> JSONResponse:
claims = actor_claims_from_request(request, settings, key_cape_verifier=key_cape_verifier)
request_id = _request_id(request)
payload = await run_in_threadpool(service.get_accounts, claims=claims, request_id=request_id)
return JSONResponse(content=payload, headers={"X-Request-ID": request_id})
@app.get("/v1/transactions")
async def get_transactions(
request: Request,
account_slug: str | None = None,
page: int = 1,
page_size: int = 50,
window_days: int = 31,
status: str | None = "completed",
side: str | None = None,
) -> JSONResponse:
claims = actor_claims_from_request(request, settings, key_cape_verifier=key_cape_verifier)
request_id = _request_id(request)
payload = await run_in_threadpool(
service.list_transactions,
claims=claims,
request_id=request_id,
account_slug=account_slug,
page=page,
page_size=page_size,
window_days=window_days,
status=status,
side=side,
)
return JSONResponse(content=payload, headers={"X-Request-ID": request_id})
@app.get("/v1/snapshot")
async def get_snapshot(
request: Request,
window_days: int = 31,
page_size: int = 50,
) -> JSONResponse:
claims = actor_claims_from_request(request, settings, key_cape_verifier=key_cape_verifier)
request_id = _request_id(request)
payload = await run_in_threadpool(
service.get_snapshot,
claims=claims,
request_id=request_id,
window_days=window_days,
page_size=page_size,
)
return JSONResponse(content=payload, headers={"X-Request-ID": request_id})
return app
def _request_id(request: Request) -> str:
existing = getattr(request.state, "request_id", None)
if existing:
return existing
request.state.request_id = request.headers.get("x-request-id", str(uuid4()))
return request.state.request_id
def _build_service(
*,
settings: Settings,
audit_logger: AuditLogger,
rate_limiter: RateLimiter | None,
concurrency_limiter: ConcurrencyLimiter | None,
) -> CapabilityService:
policy = PolicyEngine.from_file(
settings.policy_file,
required_scope=settings.required_scope,
enforce_scope=settings.enforce_scope,
)
if settings.qonto_fixture_dir is not None:
client = FixtureQontoClient(fixture_dir=settings.qonto_fixture_dir)
else:
credential_provider = build_credential_provider(settings)
client = QontoClient(
base_url=settings.qonto_base_url,
organization_path=settings.qonto_organization_path,
transactions_path=settings.qonto_transactions_path,
auth_mode=settings.qonto_auth_mode,
timeout_seconds=settings.qonto_timeout_seconds,
max_retries=settings.qonto_max_retries,
credential_provider=credential_provider,
)
return CapabilityService(
client=client,
policy=policy,
audit_logger=audit_logger,
rate_limiter=rate_limiter
or RateLimiter(
limit=settings.rate_limit_requests,
window_seconds=settings.rate_limit_window_seconds,
),
concurrency_limiter=concurrency_limiter
or ConcurrencyLimiter(limit=settings.max_concurrency),
deny_escalation_tracker=(
DenyEscalationTracker(
threshold=settings.deny_escalation_threshold,
window_seconds=settings.deny_escalation_window_seconds,
lockout_seconds=settings.deny_escalation_lockout_seconds,
)
if settings.deny_escalation_enabled
else None
),
live_authorization_gate=_build_live_authorization_gate(settings),
)
def _build_live_authorization_gate(settings: Settings) -> LiveAuthorizationGate | None:
if not settings.flex_auth_base_url:
return None
tenant_engine_client = (
TenantEngineClient(
base_url=settings.tenant_engine_base_url,
timeout_seconds=settings.tenant_engine_timeout_seconds,
)
if settings.tenant_engine_base_url
else None
)
return LiveAuthorizationGate(
flex_auth_client=FlexAuthCheckClient(
base_url=settings.flex_auth_base_url,
timeout_seconds=settings.flex_auth_timeout_seconds,
),
tenant_engine_client=tenant_engine_client,
required_tenant_roles=settings.tenant_engine_required_roles,
)
def main() -> None:
settings = Settings.from_env()
logging.basicConfig(level=logging.INFO, format="%(message)s")
uvicorn.run(
"qonto_assistant.app:create_app",
factory=True,
host=settings.host,
port=settings.port,
reload=False,
)