Files
server-26/drb-c2-core/app/main.py
T
Logan CusanoandClaude Opus 5 a3681ea698
Build & Deploy / Build & push images (push) Successful in 4m5s
Build & Deploy / Deploy to VM (push) Successful in 1m59s
Stamp org_id everywhere and gate every route that leaked across tenants
The previous commit shipped Firestore rules that reference an org_id claim
nothing issues yet, and an org_id filter nothing writes yet - this is the
commit that makes both real. Backend half of SAAS_PLAN.md B2/B2b/B2c.

Data model: organizations/{org_id} and org_members/{uid} are new
collections (models.py OrganizationRecord/OrgMember). org_id is now an
Optional field on NodeRecord, SystemRecord, CallRecord, IncidentRecord,
AlertRule, and AlertEvent - optional because every existing document
predates it; scripts/backfill_org_id.py (written, not run - it touches
production Firestore and Firebase Auth claims) is what closes that gap
later. plan_id/subscription_status/stripe_* on OrganizationRecord are
deliberately None: no billing or pricing model has been decided, so this is
a seam, not a promise. app/internal/tenancy.py holds FOUNDING_ORG_ID, the
org every pre-tenancy document and every legacy enrollment path resolves
into.

Where org_id comes from, end to end: a customer's node enrolls with a
per-org token (new enrollment_tokens/{token_hash} collection, minted via
POST /org/enrollment-tokens - new routers/org.py) instead of the old
fleet-wide ENROLLMENT_TOKEN, which still works as a fallback that resolves
to FOUNDING_ORG_ID so an already-deployed node's .env doesn't start failing
today. The node's org_id then flows onto every call it produces
(mqtt_handler.py's call_start/call_end, upload.py's /upload handler all
resolve it from the node doc), and onto every incident correlated from
those calls (incident_correlator.py's _create_incident/_create_master_incident).

That last one is the part that isn't just a read filter: _build_context's
`all_active = collection_list("incidents", status="active")` fed every
correlation candidate - fast-path talkgroup match, unit-continuity,
disambiguation - from the entire incidents collection, unscoped. Without
scoping it to the call's own org_id, a call from org A could link into an
incident org B already owns, which is a cross-tenant data merge at
correlation time, not just an over-broad read. Same shape of bug in
alerter.py: rule matching pulled every enabled alert_rule regardless of
org, so org A's keyword rule could fire (and POST org A's Discord webhook)
on org B's radio traffic. Both now resolve org_id from the call doc itself
rather than threading a new parameter through every caller.

Every list/get route gained org scoping via a new resolve_caller_org_id()
helper in internal/auth.py, which handles the three credential shapes those
routes accept (service key, node api_key, Firebase user) uniformly and
returns None (unrestricted) for the service key and platform admins -
preserving today's single-org behaviour exactly while closing the leak for
everyone else: GET /nodes, /systems, /calls, /incidents, /alerts,
/alert-rules. Write routes for nodes/systems (approve, create, delete, etc.)
deliberately stay platform-admin-only for now rather than being loosened to
org-owner/operator - that's a real gap called out in SAAS_PLAN.md 2.4's
"should be" column, but it's a separate authorization redesign the 12-item
build order doesn't actually enumerate, and doing it half-considered here
risked being exactly the "half-applied filter is worse than none" failure
mode the plan warns about. Today's founding org keeps working unchanged;
loosening node/system management to org owners is follow-up work, flagged
rather than guessed at.

Also closed the four spend/access-attack routes SAAS_PLAN.md B2c called out
by file and line: POST /calls/{id}/reprocess is now admin-only (was any
signed-in viewer looping the Whisper+Gemini pipeline for free - DEFERRED.md
had this as a live, independent-of-SaaS exploit) plus a per-call rate
limiter as a second guard; POST /alerts/{id}/acknowledge now checks the
alert's org_id; GET /admin/features moved from require_firebase_token to
require_admin_token; and trips.py's four unauthenticated mutation routes
(create_trip, update_trip_tags, create_event, update_event) are now
restricted to the founding org (or the bot's service key, or a platform
admin) - trips has no org_id of its own and isn't getting one, since
[[trips-feature-intentional]] says it's an internal utility riding along on
this stack, not a tenant-scoped product surface.

New public-but-scoped seam: POST /auth/signup (routers/links.py, alongside
the existing /auth/link* routes) provisions an organizations doc and an
owner org_members doc for a just-created Firebase user, then sets their
org_id/org_role claims - idempotent, so a double-submit doesn't create two
orgs. This is the only route that turns "has a Firebase account" into "can
read anything," which is what the frontend AuthProvider no-claim guard
(next commit) is built around.

Also new: GET/PATCH /org for the organization profile (closes the disabled
"Save changes" button noted in DEFERRED.md - there was no organizations
concept to save into before this), and POST /waitlist (public, source-IP
rate-limited, not coupled to any plan or tier - the commercial model is
still an open decision per SAAS_PLAN.md section 6).

Verified: all touched files py_compile clean; c2-core pytest is 69
passed / 10 failed, matching the documented pre-existing baseline exactly
(DEFERRED.md - mqtt_handler/node_sweeper test-vs-code drift, unrelated to
this change) - no new failures. flake8 --max-line-length=120 shows no new
violations in any touched file (checked each new E501/E221/E30x against
`git diff` to confirm it predates this commit); c2-core has no CI lint gate
regardless (CLAUDE.md - flake8 only runs in Client CI).

No new environment variables. Firestore composite indexes for the queries
this introduces were already shipped in the previous commit
(infra/firestore/firestore.indexes.json).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-18 20:28:37 -04:00

123 lines
5.9 KiB
Python

import asyncio
from contextlib import asynccontextmanager
from fastapi import FastAPI, Depends
from fastapi.middleware.cors import CORSMiddleware
from app.internal.logger import logger
from app.internal.mqtt_handler import mqtt_handler
from app.internal.node_sweeper import sweeper_loop
from app.internal.summarizer import summarizer_loop
from app.internal.vocabulary_learner import vocabulary_induction_loop
from app.internal.recorrelation_sweep import recorrelation_loop
from app.config import settings
from app.internal.auth import (
require_firebase_token,
require_service_or_firebase_token,
require_node_service_or_firebase_token,
)
from app.routers import nodes, systems, calls, upload, tokens, incidents, alerts, admin, trips, places, links, users
from app.routers import enrollment, media, org, waitlist
from app.internal import dynsec
from app.internal import firestore as fstore
async def _release_orphaned_tokens():
"""Release all in-use tokens on startup — voice connections don't survive server restarts."""
def _find():
from app.internal.firestore import db
return [d for d in db.collection("bot_tokens").where("in_use", "==", True).stream()]
results = await asyncio.to_thread(_find)
for doc in results:
await fstore.doc_update("bot_tokens", doc.id, {
"in_use": False,
"assigned_node_id": None,
"assigned_at": None,
})
if results:
logger.info(f"Released {len(results)} orphaned token(s) on startup.")
@asynccontextmanager
async def lifespan(app: FastAPI):
logger.info("DRB C2 Core starting.")
await _release_orphaned_tokens()
# dynsec bootstrap + reconcile — must happen before mqtt_handler.connect()
# so that by the time the app is serving requests, c2-core's own dynsec
# client/roles exist and every already-approved node's dynsec client
# matches Firestore (see app/internal/dynsec.py "TWO-SOURCES-OF-TRUTH").
# Non-fatal by design: if the broker or MQTT_DYNSEC_ADMIN_PASS isn't
# reachable/configured yet (e.g. first-ever deploy, mosquitto still
# starting), log loudly and keep booting rather than crash-looping
# c2-core itself — mqtt_handler.connect() below has its own retry loop
# and node approval/reissue endpoints fail loudly on their own if dynsec
# calls fail later, so nothing here is silently swallowed forever.
try:
await dynsec.ensure_roles_and_c2core_grant()
await dynsec.reconcile_all()
except dynsec.DynsecError as e:
logger.error(f"dynsec bootstrap/reconcile failed — node approval/reissue will fail until this is resolved: {e}")
await mqtt_handler.connect()
sweeper_task = asyncio.create_task(sweeper_loop())
summarizer_task = asyncio.create_task(summarizer_loop())
induction_task = asyncio.create_task(vocabulary_induction_loop())
recorrelation_task = asyncio.create_task(recorrelation_loop())
yield # --- app running ---
logger.info("DRB C2 Core shutting down.")
sweeper_task.cancel()
summarizer_task.cancel()
induction_task.cancel()
recorrelation_task.cancel()
await mqtt_handler.disconnect()
app = FastAPI(title="DRB C2 Core", lifespan=lifespan)
app.add_middleware(
CORSMiddleware,
allow_origins=settings.cors_origins,
allow_methods=["*"],
allow_headers=["*"],
allow_credentials=True,
)
app.include_router(nodes.router, dependencies=[Depends(require_service_or_firebase_token)])
# systems is the one router edge nodes read directly (system_cacher.py builds
# the OP25 config from it), so its gate also accepts a per-node api_key. The
# write routes inside carry their own require_admin_token, so nodes get read
# access only.
app.include_router(systems.router, dependencies=[Depends(require_node_service_or_firebase_token)])
app.include_router(calls.router, dependencies=[Depends(require_service_or_firebase_token)])
app.include_router(tokens.router, dependencies=[Depends(require_service_or_firebase_token)])
app.include_router(incidents.router, dependencies=[Depends(require_service_or_firebase_token)])
app.include_router(alerts.router, dependencies=[Depends(require_service_or_firebase_token)])
app.include_router(trips.router, dependencies=[Depends(require_service_or_firebase_token)])
app.include_router(places.router, dependencies=[Depends(require_service_or_firebase_token)])
app.include_router(upload.router) # auth is per-node, handled inline
app.include_router(admin.router) # auth is per-endpoint (read: firebase, write: admin)
app.include_router(users.router) # auth: admin only
app.include_router(links.router) # auth is per-endpoint (generate: firebase, resolve: service key)
app.include_router(enrollment.router) # public; auth is the enrollment/pickup-secret tokens, checked inline
app.include_router(org.router) # auth is per-endpoint (read: firebase, write: org owner)
app.include_router(waitlist.router) # public — no auth, source-IP rate limited inline
# public by necessity — an <audio src> can't send a bearer token, so the
# short-lived HMAC in the URL is the credential. Checked inline in media.py.
app.include_router(media.router)
# NOTE: there used to be an app.routers.mqtt_auth router here (an HTTP
# backend for the mosquitto-go-auth plugin). That plugin's upstream project
# is archived (no CVE patches) and was rejected for an internet-facing
# broker — see MQTT-PUBLIC-AUTH-PLAN.md. MQTT auth is now mosquitto's own
# built-in dynamic-security plugin (app/internal/dynsec.py talks to it over
# MQTT control topics, not HTTP), so there is nothing at /internal/mqtt/*
# anymore. Caddy's Caddyfile.j2 still 404s /internal/* on api.<domain> as
# defence in depth even though nothing calls it today — cheap insurance
# against a future /internal/* route being added and forgotten there.
@app.get("/health")
async def health():
return {"ok": True, "mqtt_connected": mqtt_handler.is_connected}