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

200 lines
7.2 KiB
Python

from datetime import datetime, timezone, timedelta
from fastapi import APIRouter, BackgroundTasks, HTTPException, Query, Depends
from pydantic import BaseModel
from typing import Optional
from app.internal import firestore as fstore
from app.internal.auth import (
require_admin_token,
require_service_or_firebase_token,
resolve_caller_org_id,
reprocess_limiter,
)
from app.internal.storage import gcs_uri_for_call, with_playback_url
class TranscriptUpdate(BaseModel):
transcript: str
router = APIRouter(prefix="/calls", tags=["calls"])
@router.get("")
async def list_calls(
node_id: Optional[str] = Query(None),
status: Optional[str] = Query(None),
system_id: Optional[str] = Query(None),
decoded: dict = Depends(require_service_or_firebase_token),
):
filters = {}
if node_id:
filters["node_id"] = node_id
if status:
filters["status"] = status
if system_id:
filters["system_id"] = system_id
org_id = await resolve_caller_org_id(decoded)
if org_id is not None: # service key / platform admin stay unrestricted
filters["org_id"] = org_id
calls = await fstore.collection_list("calls", **filters)
# audio_url is not stored — it's a short-lived signed link minted per read.
return [with_playback_url(c) for c in calls]
@router.get("/{call_id}")
async def get_call(call_id: str, decoded: dict = Depends(require_service_or_firebase_token)):
call = await fstore.doc_get("calls", call_id)
if not call:
raise HTTPException(404, f"Call '{call_id}' not found.")
org_id = await resolve_caller_org_id(decoded)
if org_id is not None and call.get("org_id") != org_id:
raise HTTPException(404, f"Call '{call_id}' not found.")
return with_playback_url(call)
@router.post("/{call_id}/reprocess")
async def reprocess_call(
call_id: str,
background_tasks: BackgroundTasks,
_: dict = Depends(require_admin_token),
):
"""
Re-run the full intelligence pipeline (transcription -> extraction ->
correlation) for a call. Admin-only (SAAS_PLAN.md B2c) — this was
previously gated only by "any valid Firebase token", which meant any
signed-in viewer could loop it and burn the owner's OpenAI/Gemini
credits (DEFERRED.md, calls.py:42). The rate limiter below is a second
guard against the same thing happening from a compromised/careless
admin session, not the primary fix.
"""
call = await fstore.doc_get("calls", call_id)
if not call:
raise HTTPException(404, f"Call '{call_id}' not found.")
reprocess_limiter.check(call_id)
from app.routers.upload import _run_intelligence_pipeline
gcs_uri = gcs_uri_for_call(call)
background_tasks.add_task(
_run_intelligence_pipeline,
call_id=call_id,
node_id=call.get("node_id"),
system_id=call.get("system_id"),
talkgroup_id=call.get("talkgroup_id"),
talkgroup_name=call.get("talkgroup_name"),
gcs_uri=gcs_uri,
)
return {"ok": True, "call_id": call_id}
@router.post("/close-stale")
async def close_stale_calls(
older_than_minutes: int = Query(30, ge=1, le=1440, description="Close active calls started more than this many minutes ago."),
dry_run: bool = Query(False, description="If true, return what would be closed without writing."),
_: dict = Depends(require_admin_token),
):
"""
Find and close calls stuck in 'active' status — e.g. because a node rebooted
before sending an end-call event. Returns the list of affected call IDs.
"""
cutoff = datetime.now(timezone.utc) - timedelta(minutes=older_than_minutes)
active_calls = await fstore.collection_list("calls", status="active")
stale = []
for call in active_calls:
started_raw = call.get("started_at")
if not started_raw:
continue
if isinstance(started_raw, datetime):
started = started_raw if started_raw.tzinfo else started_raw.replace(tzinfo=timezone.utc)
else:
try:
started = datetime.fromisoformat(str(started_raw).replace("Z", "+00:00"))
except Exception:
continue
if started < cutoff:
stale.append(call)
if not dry_run:
now_iso = datetime.now(timezone.utc).isoformat()
for call in stale:
await fstore.doc_set("calls", call["call_id"], {
"status": "ended",
"ended_at": now_iso,
})
return {
"dry_run": dry_run,
"older_than_minutes": older_than_minutes,
"count": len(stale),
"call_ids": [c["call_id"] for c in stale],
}
@router.patch("/{call_id}/transcript")
async def patch_transcript(
call_id: str,
body: TranscriptUpdate,
background_tasks: BackgroundTasks,
_: dict = Depends(require_admin_token),
):
"""Overwrite a call's transcript and re-run intelligence extraction."""
call = await fstore.doc_get("calls", call_id)
if not call:
raise HTTPException(404, f"Call '{call_id}' not found.")
# Save user correction as transcript_corrected; leave original transcript intact.
# Clear stale intelligence fields so re-extraction runs fresh.
await fstore.doc_set("calls", call_id, {
"transcript_corrected": body.transcript,
"tags": [],
"severity": "unknown",
"location": None,
"units": [],
"vehicles": [],
"embedding": None,
})
# Unlink from ALL current incidents so re-correlation starts clean.
# Handles both old single incident_id and new incident_ids list.
old_ids: list[str] = call.get("incident_ids") or (
[call["incident_id"]] if call.get("incident_id") else []
)
for old_incident_id in old_ids:
old_incident = await fstore.doc_get("incidents", old_incident_id)
if old_incident:
remaining = [c for c in (old_incident.get("call_ids") or []) if c != call_id]
if remaining:
await fstore.doc_set("incidents", old_incident_id, {
"call_ids": remaining,
"summary_stale": True,
})
else:
await fstore.doc_set("incidents", old_incident_id, {
"call_ids": [],
"status": "resolved",
"summary_stale": True,
})
await fstore.doc_set("calls", call_id, {"incident_ids": [], "incident_id": None})
# Learn from the correction: diff original → corrected and add new tokens to vocabulary
system_id = call.get("system_id")
original_text = call.get("transcript_corrected") or call.get("transcript") or ""
if system_id and original_text:
from app.internal.vocabulary_learner import learn_from_correction
await learn_from_correction(system_id, original_text, body.transcript)
from app.routers.upload import _run_extraction_pipeline
background_tasks.add_task(
_run_extraction_pipeline,
call_id=call_id,
node_id=call.get("node_id"),
system_id=call.get("system_id"),
talkgroup_id=call.get("talkgroup_id"),
talkgroup_name=call.get("talkgroup_name"),
transcript=body.transcript,
segments=call.get("segments"),
preserve_transcript_correction=True,
)
return {"ok": True, "call_id": call_id}