bonaminandClaude Sonnet 5
7c533b9245
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>
74 lines
3.4 KiB
Python
74 lines
3.4 KiB
Python
"""device diagnostics reports
|
|
|
|
Adds device_diagnostics_reports — structured storage for the firmware's
|
|
diagnostics_report MQTT event (vesper/{uid}/status/info, type="diagnostics_report"),
|
|
published every 5 minutes. Cleanly separate from device_boot_events (one row per
|
|
boot, event-driven) and heartbeats (one row every 30s, transport/liveness facts):
|
|
this table is periodic health telemetry — CPU temperature (min/max/avg over the
|
|
5-minute window), WiFi reconnect count + last disconnect reason, OTA/firmware
|
|
check state, and per-task stack high-water marks (bytes free).
|
|
|
|
stack_high_water is stored as a JSON-encoded TEXT column rather than flattened
|
|
columns — unlike the other three groups (fixed field sets), the set of
|
|
monitored tasks is open-ended on the firmware side (see project-vesper's
|
|
Telemetry::registerTaskForStackMonitoring), so a fixed column per task would
|
|
need a migration every time a task is added. TEXT (not JSONB) matches this
|
|
codebase's existing convention for JSON blobs stored via raw SQL — see
|
|
commands.command_payload / response_payload.
|
|
|
|
Revision ID: a7b8c9d0e1f2
|
|
Revises: f6a7b8c9d0e1
|
|
Create Date: 2026-07-17 00:00:00.000000
|
|
"""
|
|
from typing import Sequence, Union
|
|
import sqlalchemy as sa
|
|
from alembic import op
|
|
|
|
revision: str = "a7b8c9d0e1f2"
|
|
down_revision: Union[str, None] = "f6a7b8c9d0e1"
|
|
branch_labels: Union[str, Sequence[str], None] = None
|
|
depends_on: Union[str, Sequence[str], None] = None
|
|
|
|
|
|
def upgrade() -> None:
|
|
op.create_table(
|
|
"device_diagnostics_reports",
|
|
sa.Column("id", sa.BigInteger(), primary_key=True, autoincrement=True),
|
|
sa.Column("device_serial", sa.String(128), nullable=False),
|
|
|
|
# cpu_temp — omitted by firmware (all null here) if no samples were
|
|
# taken yet this window (e.g. very first report shortly after boot).
|
|
sa.Column("cpu_temp_avg", sa.Float(), nullable=True),
|
|
sa.Column("cpu_temp_min", sa.Float(), nullable=True),
|
|
sa.Column("cpu_temp_max", sa.Float(), nullable=True),
|
|
sa.Column("cpu_temp_samples", sa.Integer(), nullable=True),
|
|
|
|
# wifi_reconnects — this-boot-only lifetime count, not device lifetime.
|
|
sa.Column("wifi_reconnect_count", sa.Integer(), nullable=True),
|
|
sa.Column("wifi_last_disconnect_reason", sa.String(64), nullable=True),
|
|
sa.Column("wifi_last_disconnect_uptime_ms", sa.BigInteger(), nullable=True),
|
|
|
|
# ota
|
|
sa.Column("ota_current_version", sa.String(32), nullable=True),
|
|
sa.Column("ota_update_available", sa.Boolean(), nullable=True),
|
|
sa.Column("ota_available_version", sa.String(32), nullable=True),
|
|
sa.Column("ota_last_check_uptime_ms", sa.BigInteger(), nullable=True),
|
|
sa.Column("ota_last_error", sa.String(32), nullable=True),
|
|
|
|
# stack_high_water — open-ended task set, see module docstring.
|
|
sa.Column("stack_high_water", sa.Text(), nullable=True),
|
|
|
|
sa.Column("received_at", sa.DateTime(timezone=True), nullable=False,
|
|
server_default=sa.func.now()),
|
|
)
|
|
op.create_index(
|
|
"idx_device_diagnostics_reports_serial_received",
|
|
"device_diagnostics_reports",
|
|
["device_serial", sa.text("received_at DESC")],
|
|
)
|
|
|
|
|
|
def downgrade() -> None:
|
|
op.drop_index("idx_device_diagnostics_reports_serial_received", table_name="device_diagnostics_reports")
|
|
op.drop_table("device_diagnostics_reports")
|