feat(mqtt): add device health telemetry and migrate to v2 topic spec

Two efforts that landed together because the v2 topic work extends
tables the health-telemetry effort added days earlier in the same
files/functions, making them impractical to separate cleanly:

Health/diagnostics telemetry (schema, Jul 13-17):
- New Postgres tables: device_alert_events, device_boot_events,
  device_ping_samples, device_diagnostics_reports, plus a `source`
  column on device_logs to distinguish log origins
- Query/service layer in pg_mqtt.py and database/__init__.py for
  inserting and listing this history, plus a "latest metrics" endpoint
  combining most-recent diagnostics + ping RTT per device
- mqtt/router.py gains list endpoints for alert/boot/ping/diagnostics
  history, consumed by the upcoming Health tab

MQTT v2 topic migration (Sep 21):
- Heartbeat payload flattened per vesper_mqtt_topic_spec_v2.md, adding
  rssi/free_heap/state/ok fields
- Command replies move to control/ack, device-initiated events to
  control/reports; mqtt/client.py subscribes to the new topic set and
  runs a ping_loop (wired up in main.py) for RTT sampling
- mqtt/logger.py and pg_mqtt.py updated to parse and persist the new
  payload shape alongside the legacy fields for backwards compatibility

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
2026-09-21 18:24:36 +03:00
co-authored by Claude Sonnet 5
parent e5d556fee1
commit 7c533b9245
12 changed files with 1456 additions and 55 deletions
+111 -6
View File
@@ -1,11 +1,14 @@
from fastapi import APIRouter, Depends, Query, WebSocket, WebSocketDisconnect
from typing import Optional
from typing import Optional, List
from auth.models import TokenPayload
from auth.dependencies import require_permission
from mqtt.models import (
MqttCommandRequest, CommandSendResponse, MqttStatusResponse,
DeviceMqttStatus, LogListResponse, HeartbeatListResponse,
CommandListResponse, HeartbeatEntry,
CommandListResponse, HeartbeatEntry, AlertEventEntry,
AlertEventListResponse, BootEventListResponse, PingSampleListResponse,
DiagnosticsReportListResponse, LatestMetricsResponse,
LatestDiagnosticsEntry, LatestPingEntry, DeviceReportListResponse,
)
from mqtt.client import mqtt_manager
import database as db
@@ -19,6 +22,8 @@ async def get_all_device_status(
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
heartbeats = await db.get_latest_heartbeats()
alert_events = await db.get_latest_alert_events()
alert_by_serial = {a["device_serial"]: a for a in alert_events}
now = datetime.now(timezone.utc)
devices = []
for hb in heartbeats:
@@ -31,11 +36,14 @@ async def get_all_device_status(
except (ValueError, TypeError):
seconds_ago = 9999
alert_event = alert_by_serial.get(hb["device_serial"])
devices.append(DeviceMqttStatus(
device_serial=hb["device_serial"],
online=seconds_ago < 90,
last_heartbeat=HeartbeatEntry(**hb),
seconds_since_heartbeat=seconds_ago,
last_alert_event=AlertEventEntry(**alert_event) if alert_event else None,
))
return MqttStatusResponse(
devices=devices,
@@ -43,6 +51,21 @@ async def get_all_device_status(
)
@router.get("/latest-metrics", response_model=LatestMetricsResponse)
async def get_latest_metrics(
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
# Fleet-wide "last known" CPU temp + ping RTT, one query each — used by
# DeviceList to render optional columns without polling any device.
# Uptime/firmware/RSSI don't need this: they're already in /mqtt/status.
diag_reports = await db.get_latest_diagnostics_reports()
ping_samples = await db.get_latest_ping_samples()
return LatestMetricsResponse(
diagnostics=[LatestDiagnosticsEntry(**d) for d in diag_reports],
pings=[LatestPingEntry(**p) for p in ping_samples],
)
@router.post("/command/{device_serial}", response_model=CommandSendResponse)
async def send_command(
device_serial: str,
@@ -81,14 +104,18 @@ async def send_command(
async def get_device_logs(
device_serial: str,
level: Optional[str] = Query(None, description="Filter: INFO, WARN, ERROR"),
min_level: bool = Query(False, description="If true, level is a floor — also includes higher-severity levels"),
search: Optional[str] = Query(None),
source: Optional[List[str]] = Query(None, description="Filter by source: log, info. Repeat param to include several."),
limit: int = Query(100, ge=1, le=1000),
offset: int = Query(0, ge=0),
since: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/after this time"),
until: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/before this time"),
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
logs, total = await db.get_logs(
device_serial, level=level, search=search,
limit=limit, offset=offset,
device_serial, level=level, search=search, source=source,
min_level=min_level, limit=limit, offset=offset, since=since, until=until,
)
return LogListResponse(logs=logs, total=total)
@@ -96,12 +123,14 @@ async def get_device_logs(
@router.get("/heartbeats/{device_serial}", response_model=HeartbeatListResponse)
async def get_device_heartbeats(
device_serial: str,
limit: int = Query(100, ge=1, le=1000),
limit: int = Query(100, ge=1, le=5000),
offset: int = Query(0, ge=0),
since: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/after this time"),
until: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/before this time"),
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
heartbeats, total = await db.get_heartbeats(
device_serial, limit=limit, offset=offset,
device_serial, limit=limit, offset=offset, since=since, until=until,
)
return HeartbeatListResponse(heartbeats=heartbeats, total=total)
@@ -119,6 +148,82 @@ async def get_device_commands(
return CommandListResponse(commands=commands, total=total)
@router.get("/alert-events/{device_serial}", response_model=AlertEventListResponse)
async def get_device_alert_events(
device_serial: str,
limit: int = Query(100, ge=1, le=1000),
offset: int = Query(0, ge=0),
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
events, total = await db.get_alert_events(
device_serial, limit=limit, offset=offset,
)
return AlertEventListResponse(events=events, total=total)
@router.get("/boot-events/{device_serial}", response_model=BootEventListResponse)
async def get_device_boot_events(
device_serial: str,
limit: int = Query(100, ge=1, le=2000),
offset: int = Query(0, ge=0),
since: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/after this time"),
until: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/before this time"),
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
events, total = await db.get_boot_events(
device_serial, limit=limit, offset=offset, since=since, until=until,
)
return BootEventListResponse(events=events, total=total)
@router.get("/ping-samples/{device_serial}", response_model=PingSampleListResponse)
async def get_device_ping_samples(
device_serial: str,
limit: int = Query(200, ge=1, le=5000),
offset: int = Query(0, ge=0),
since: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/after this time"),
until: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/before this time"),
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
samples, total = await db.get_ping_samples(
device_serial, limit=limit, offset=offset, since=since, until=until,
)
return PingSampleListResponse(samples=samples, total=total)
@router.get("/diagnostics-reports/{device_serial}", response_model=DiagnosticsReportListResponse)
async def get_device_diagnostics_reports(
device_serial: str,
limit: int = Query(200, ge=1, le=5000),
offset: int = Query(0, ge=0),
since: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/after this time"),
until: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/before this time"),
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
reports, total = await db.get_diagnostics_reports(
device_serial, limit=limit, offset=offset, since=since, until=until,
)
return DiagnosticsReportListResponse(reports=reports, total=total)
@router.get("/reports/{device_serial}", response_model=DeviceReportListResponse)
async def get_device_reports(
device_serial: str,
limit: int = Query(200, ge=1, le=2000),
offset: int = Query(0, ge=0),
since: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/after this time"),
until: Optional[datetime] = Query(None, description="ISO timestamp — only rows at/before this time"),
_user: TokenPayload = Depends(require_permission("mqtt", "view")),
):
"""Critical, unsolicited board-initiated events from control/reports
(currently only bell_overload). History/audit only — the tablets are the
real-time consumer of this data, not the console."""
reports, total = await db.get_reports(
device_serial, limit=limit, offset=offset, since=since, until=until,
)
return DeviceReportListResponse(reports=reports, total=total)
@router.websocket("/ws")
async def mqtt_websocket(websocket: WebSocket):
"""Live MQTT data stream. Auth via query param: ?token=JWT"""