Files
server-26/drb-c2-core/app/routers/nodes.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

279 lines
10 KiB
Python

import secrets
from typing import Optional
from fastapi import APIRouter, HTTPException, Depends, Query
from pydantic import BaseModel
from app.models import CommandPayload
from app.internal import firestore as fstore
from app.internal.mqtt_handler import mqtt_handler
from app.internal import dynsec
from app.internal.logger import logger
from app.internal.auth import (
require_admin_token,
require_service_key_or_admin,
require_service_or_firebase_token,
resolve_caller_org_id,
)
from app.routers.tokens import assign_token, release_token
router = APIRouter(prefix="/nodes", tags=["nodes"])
@router.get("")
async def list_nodes(decoded: dict = Depends(require_service_or_firebase_token)):
org_id = await resolve_caller_org_id(decoded)
if org_id is None: # service key or platform admin — unrestricted, matches prior behaviour
return await fstore.collection_list("nodes")
return await fstore.collection_list("nodes", org_id=org_id)
@router.get("/{node_id}")
async def get_node(node_id: str, decoded: dict = Depends(require_service_or_firebase_token)):
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
org_id = await resolve_caller_org_id(decoded)
if org_id is not None and node.get("org_id") != org_id:
raise HTTPException(404, f"Node '{node_id}' not found.")
return node
@router.post("/{node_id}/approve")
async def approve_node(node_id: str, _: dict = Depends(require_admin_token)):
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
api_key = secrets.token_hex(32)
# dynsec FIRST, Firestore second: if the broker rejects/never confirms
# the new client, we must not tell Firestore (and the admin UI) the
# node is approved with a key mosquitto doesn't actually recognise —
# that's exactly the silent-drift the two-sources-of-truth problem
# warns about. See app/internal/dynsec.py.
try:
await dynsec.upsert_node_client(node_id, api_key)
except dynsec.DynsecError as e:
logger.error(f"Approve {node_id!r}: dynsec upsert failed, NOT writing Firestore: {e}")
raise HTTPException(502, f"Could not provision MQTT credentials for node: {e}")
await fstore.doc_set("node_keys", node_id, {"node_id": node_id, "api_key": api_key}, merge=False)
await fstore.doc_update("nodes", node_id, {"approval_status": "approved"})
# TODO(mqtt-cutover): drop this MQTT push once nodes pull their key via
# GET /nodes/{id}/credentials (routers/enrollment.py) exclusively — see
# MQTT-PUBLIC-AUTH-PLAN.md "Rollout order" step 6. Kept for node-26.
mqtt_handler.publish_node_key(node_id, api_key)
return {"ok": True}
@router.delete("/{node_id}", status_code=204)
async def delete_node(node_id: str, _: dict = Depends(require_admin_token)):
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
try:
await dynsec.delete_node_client(node_id)
except dynsec.DynsecError as e:
logger.error(f"Delete {node_id!r}: dynsec deleteClient failed, NOT deleting Firestore docs: {e}")
raise HTTPException(502, f"Could not revoke MQTT credentials for node: {e}")
await fstore.doc_delete("node_keys", node_id)
await fstore.doc_delete("nodes", node_id)
@router.post("/{node_id}/reject")
async def reject_node(node_id: str, _: dict = Depends(require_admin_token)):
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
await fstore.doc_update("nodes", node_id, {"approval_status": "rejected"})
return {"ok": True}
@router.post("/{node_id}/command")
async def send_command(
node_id: str,
cmd: CommandPayload,
_: dict = Depends(require_service_key_or_admin),
):
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
payload = cmd.model_dump(exclude_none=True)
if cmd.action == "discord_join":
# Resolve system doc once — used for preferred token and presence name.
system_doc = None
system_id = node.get("assigned_system_id")
if system_id:
system_doc = await fstore.doc_get_cached("systems", system_id)
# Explicit preferred_token_id in the request beats the system-level preference.
preferred = payload.pop("preferred_token_id", None) or (system_doc or {}).get("preferred_token_id")
token = await assign_token(node_id, preferred_token_id=preferred)
if not token:
raise HTTPException(503, "No Discord bot tokens available in the pool.")
payload["token"] = token
# Pass system name so the bot can set its Discord presence on join.
system_name = (system_doc or {}).get("name")
if system_name:
payload["system_name"] = system_name
elif cmd.action == "discord_leave":
await release_token(node_id)
if not mqtt_handler.send_command(node_id, payload):
raise HTTPException(503, "MQTT broker unavailable — command not delivered.")
return {"ok": True}
@router.post("/{node_id}/reissue-key")
async def reissue_node_key(node_id: str, _: dict = Depends(require_admin_token)):
"""Generate a new API key for the node and push it via MQTT (retained).
Use this to rotate a key or recover a node whose key was lost."""
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
api_key = secrets.token_hex(32)
try:
await dynsec.upsert_node_client(node_id, api_key)
except dynsec.DynsecError as e:
logger.error(f"Reissue {node_id!r}: dynsec upsert failed, NOT writing Firestore: {e}")
raise HTTPException(502, f"Could not update MQTT credentials for node: {e}")
await fstore.doc_set("node_keys", node_id, {"node_id": node_id, "api_key": api_key}, merge=False)
# TODO(mqtt-cutover): drop this MQTT push once nodes pull their key via
# GET /nodes/{id}/credentials (routers/enrollment.py) exclusively — see
# MQTT-PUBLIC-AUTH-PLAN.md "Rollout order" step 6. Kept for node-26.
mqtt_handler.publish_node_key(node_id, api_key)
return {"ok": True}
@router.post("/{node_id}/config/{system_id}")
async def assign_system(
node_id: str,
system_id: str,
hardware_preset: str = Query("rtl-sdr-v3"),
ppm_override: Optional[float] = Query(None),
_: dict = Depends(require_service_key_or_admin),
):
"""
Assign a system to a node. Fetches the system config from Firestore
and pushes it to the node via MQTT, then marks the node as configured.
"""
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
system = await fstore.doc_get("systems", system_id)
if not system:
raise HTTPException(404, f"System '{system_id}' not found.")
# Include hardware preset, node type, and enforce timeout in the push
push_payload = {
**system,
"hardware_preset": hardware_preset,
"node_type": node.get("node_type", "fixed"),
"enforce_override_timeout": node.get("enforce_override_timeout", True),
}
if ppm_override is not None:
push_payload["ppm_override"] = ppm_override
mqtt_handler.push_config(node_id, push_payload)
# Update Firestore
node_updates = {
"assigned_system_id": system_id,
"configured": True,
"hardware_preset": hardware_preset,
}
if ppm_override is not None:
node_updates["ppm_override"] = ppm_override
await fstore.doc_update("nodes", node_id, node_updates)
return {"ok": True}
class NodeUpdateBody(BaseModel):
node_type: Optional[str] = None
enforce_override_timeout: Optional[bool] = None
@router.patch("/{node_id}")
async def update_node(
node_id: str,
body: NodeUpdateBody,
_: dict = Depends(require_admin_token),
):
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
updates = body.model_dump(exclude_unset=True)
if not updates:
return {"ok": True}
await fstore.doc_update("nodes", node_id, updates)
# Re-push config to apply new node settings locally
updated_node = await fstore.doc_get("nodes", node_id)
assigned_system_id = updated_node.get("assigned_system_id")
if assigned_system_id:
system = await fstore.doc_get("systems", assigned_system_id)
if system:
push_payload = {
**system,
"hardware_preset": updated_node.get("hardware_preset", "rtl-sdr-v3"),
"node_type": updated_node.get("node_type", "fixed"),
"enforce_override_timeout": updated_node.get("enforce_override_timeout", True),
}
if updated_node.get("ppm_override") is not None:
push_payload["ppm_override"] = updated_node["ppm_override"]
mqtt_handler.push_config(node_id, push_payload)
return {"ok": True}
class AckOverrideBody(BaseModel):
timeout_minutes: int = 1440
@router.post("/{node_id}/override/ack")
async def ack_override(
node_id: str,
body: AckOverrideBody,
_: dict = Depends(require_service_key_or_admin),
):
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
from datetime import datetime, timezone, timedelta
new_timeout = datetime.now(timezone.utc) + timedelta(minutes=body.timeout_minutes)
await fstore.doc_update("nodes", node_id, {
"override_timeout_at": new_timeout.isoformat()
})
return {"ok": True, "override_timeout_at": new_timeout.isoformat()}
@router.post("/{node_id}/override/reset")
async def reset_override(
node_id: str,
_: dict = Depends(require_service_key_or_admin),
):
node = await fstore.doc_get("nodes", node_id)
if not node:
raise HTTPException(404, f"Node '{node_id}' not found.")
assigned_system_id = node.get("assigned_system_id")
if assigned_system_id:
system = await fstore.doc_get("systems", assigned_system_id)
if system:
mqtt_handler.push_config(node_id, system)
await fstore.doc_update("nodes", node_id, {
"is_overridden": False,
"override_system_id": None,
"override_timeout_at": None,
})
return {"ok": True}