move_detect/server/tests/DeviceHealthWatchTest.php

<?php
declare(strict_types=1);
namespace App\Tests;

use App\Alert\DeviceHealthWatch;
use App\Tests\Support\{InMemoryEventRepository, InMemoryDeviceRepository, InMemoryDeviceMetricRepository};
use PHPUnit\Framework\TestCase;

/**
 * The two events nobody produced.
 *
 * These tests pin the behaviour that makes them trustworthy rather than noisy: a fault must be
 * filed ONCE per outage (not once per cron tick), a slow node must be degraded for a sustained
 * period before it counts, and a node that has never been installed must stay silent.
 */
final class DeviceHealthWatchTest extends TestCase
{
    private const NOW = 1_700_000_000;

    private function devices(array $rows): InMemoryDeviceRepository
    {
        return new InMemoryDeviceRepository([], [], [], $rows);
    }

    private function device(string $id, ?int $heartbeat, ?string $site = 'site-a'): array
    {
        return ['device_id' => $id, 'name' => $id, 'site' => $site,
                'last_fps' => null, 'last_temp' => null, 'last_throttle' => null,
                'config_version' => 1, 'reported_config_version' => 1,
                'last_heartbeat_at' => $heartbeat];
    }

    /** @param array<int,array> $points [tsOffsetFromNow => metric fields] */
    private function metrics(string $deviceId, array $points): InMemoryDeviceMetricRepository
    {
        $repo = new InMemoryDeviceMetricRepository();
        foreach ($points as $offset => $fields) {
            $repo->append($deviceId, $fields, self::NOW - $offset);
        }
        return $repo;
    }

    // --- device_fault ---------------------------------------------------------------------

    public function testSilentDeviceFilesDeviceFault(): void
    {
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 600)]),
            new InMemoryDeviceMetricRepository()
        );

        $filed = $watch->run(self::NOW);

        self::assertCount(1, $filed);
        self::assertSame('device_fault', $filed[0]['event_type']);
        $row = $events->find($filed[0]['event_id']);
        self::assertSame('warning', $row['severity']);
        self::assertSame(DeviceHealthWatch::DEVICE_CAMERA, $row['camera_id']);
        self::assertSame('site-a', $row['site']);
        self::assertSame(600, $row['metrics']['silent_s']);
    }

    public function testHealthyHeartbeatFilesNothing(): void
    {
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 20)]),
            $this->metrics('pi-01', [20 => ['fps' => 12.0, 'cameras_erroring' => 0]])
        );

        self::assertSame([], $watch->run(self::NOW));
    }

    public function testOutageFilesOnceAcrossRepeatedRuns(): void
    {
        // The cron runs every minute. An hour-long outage must leave ONE event, not sixty.
        $events = new InMemoryEventRepository();
        $devices = $this->devices([$this->device('pi-01', self::NOW - 600)]);
        $watch = new DeviceHealthWatch($events, $devices, new InMemoryDeviceMetricRepository());

        $first = $watch->run(self::NOW);
        $second = $watch->run(self::NOW + 60);
        $third = $watch->run(self::NOW + 120);

        self::assertCount(1, $first);
        self::assertSame([], $second);
        self::assertSame([], $third);
    }

    public function testRecoveredThenFailedAgainIsASecondEvent(): void
    {
        $events = new InMemoryEventRepository();
        $devices = $this->devices([$this->device('pi-01', self::NOW - 600)]);
        $watch = new DeviceHealthWatch($events, $devices, new InMemoryDeviceMetricRepository());
        self::assertCount(1, $watch->run(self::NOW));

        // The node came back (new heartbeat) and then went silent again.
        $devices->statusRows = [$this->device('pi-01', self::NOW + 1000)];
        self::assertCount(1, $watch->run(self::NOW + 2000));
    }

    public function testNeverInstalledDeviceIsNotAFault(): void
    {
        // A provisioned row that has never reported is an uninstalled node. Alarming here would
        // make every new site's first day a wall of red.
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-new', null), $this->device('pi-zero', 0)]),
            new InMemoryDeviceMetricRepository()
        );

        self::assertSame([], $watch->run(self::NOW));
    }

    public function testSilentDeviceDoesNotAlsoFileDegraded(): void
    {
        // A node that is gone must not be reported twice for one failure.
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 600)]),
            $this->metrics('pi-01', [900 => ['fps' => 1.0], 700 => ['fps' => 1.0]])
        );

        $filed = $watch->run(self::NOW);
        self::assertCount(1, $filed);
        self::assertSame('device_fault', $filed[0]['event_type']);
    }

    // --- monitoring_degraded --------------------------------------------------------------

    public function testSustainedLowFpsFilesDegraded(): void
    {
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 10)]),
            $this->metrics('pi-01', [
                800 => ['fps' => 12.0],   // healthy anchor
                600 => ['fps' => 3.0],
                300 => ['fps' => 3.0],
                10  => ['fps' => 3.0],
            ])
        );

        $filed = $watch->run(self::NOW);

        self::assertCount(1, $filed);
        self::assertSame('monitoring_degraded', $filed[0]['event_type']);
        $row = $events->find($filed[0]['event_id']);
        self::assertSame(['low_fps'], $row['metrics']['reasons']);
        self::assertSame(590, $row['metrics']['degraded_s']);
    }

    public function testBriefDipDoesNotFileDegraded(): void
    {
        // One slow heartbeat is a hiccup. Requiring a sustained run is what separates this event
        // from noise the operator learns to ignore.
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 10)]),
            $this->metrics('pi-01', [
                200 => ['fps' => 12.0],
                100 => ['fps' => 12.0],
                10  => ['fps' => 3.0],
            ])
        );

        self::assertSame([], $watch->run(self::NOW));
    }

    public function testRecoveredFpsFilesNothingEvenAfterALongBadRun(): void
    {
        // The latest heartbeat is what decides. A node that already recovered must not alarm.
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 10)]),
            $this->metrics('pi-01', [
                900 => ['fps' => 2.0],
                600 => ['fps' => 2.0],
                10  => ['fps' => 12.0],
            ])
        );

        self::assertSame([], $watch->run(self::NOW));
    }

    public function testErroringCameraIsDegradedEvenAtFullFps(): void
    {
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 10)]),
            $this->metrics('pi-01', [
                800 => ['fps' => 12.0, 'cameras_total' => 2, 'cameras_erroring' => 0],
                600 => ['fps' => 12.0, 'cameras_total' => 2, 'cameras_erroring' => 1],
                10  => ['fps' => 12.0, 'cameras_total' => 2, 'cameras_erroring' => 1],
            ])
        );

        $filed = $watch->run(self::NOW);

        self::assertCount(1, $filed);
        $row = $events->find($filed[0]['event_id']);
        self::assertSame(['cameras_erroring'], $row['metrics']['reasons']);
        self::assertSame(1, $row['metrics']['cameras_erroring']);
    }

    public function testThermalThrottleCountsAsDegraded(): void
    {
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 10)]),
            $this->metrics('pi-01', [
                800 => ['fps' => 12.0, 'throttle' => 0],
                600 => ['fps' => 12.0, 'throttle' => 1],
                10  => ['fps' => 12.0, 'throttle' => 1],
            ])
        );

        $filed = $watch->run(self::NOW);

        self::assertCount(1, $filed);
        self::assertSame(['thermal_throttle'],
            $events->find($filed[0]['event_id'])['metrics']['reasons']);
    }

    public function testOngoingDegradationFilesOncePerRunNotPerTick(): void
    {
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 10)]),
            $this->metrics('pi-01', [
                800 => ['fps' => 12.0],
                600 => ['fps' => 3.0],
                10  => ['fps' => 3.0],
            ])
        );

        self::assertCount(1, $watch->run(self::NOW));
        self::assertSame([], $watch->run(self::NOW + 60));
        self::assertSame([], $watch->run(self::NOW + 120));
    }

    public function testMissingFpsIsNotTreatedAsZero(): void
    {
        // A node that cannot read a metric reports NULL. Coercing that to 0 would invent an
        // outage out of a missing reading.
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 10)]),
            $this->metrics('pi-01', [
                600 => ['fps' => null, 'cameras_erroring' => 0],
                10  => ['fps' => null, 'cameras_erroring' => 0],
            ])
        );

        self::assertSame([], $watch->run(self::NOW));
    }

    public function testNoHeartbeatSeriesFilesNothingWhileDeviceIsFresh(): void
    {
        // Fresh heartbeat but no metric rows yet (just installed): nothing to judge.
        $events = new InMemoryEventRepository();
        $watch = new DeviceHealthWatch(
            $events,
            $this->devices([$this->device('pi-01', self::NOW - 5)]),
            new InMemoryDeviceMetricRepository()
        );

        self::assertSame([], $watch->run(self::NOW));
    }

    public function testEachDeviceIsJudgedIndependently(): void
    {
        $events = new InMemoryEventRepository();
        $metrics = new InMemoryDeviceMetricRepository();
        $metrics->append('pi-ok', ['fps' => 12.0], self::NOW - 10);
        $metrics->append('pi-slow', ['fps' => 12.0], self::NOW - 800);
        $metrics->append('pi-slow', ['fps' => 2.0], self::NOW - 600);
        $metrics->append('pi-slow', ['fps' => 2.0], self::NOW - 10);

        $watch = new DeviceHealthWatch($events, $this->devices([
            $this->device('pi-ok', self::NOW - 10),
            $this->device('pi-slow', self::NOW - 10),
            $this->device('pi-dead', self::NOW - 3600),
        ]), $metrics);

        $filed = $watch->run(self::NOW);
        $byDevice = [];
        foreach ($filed as $f) $byDevice[$f['device_id']] = $f['event_type'];

        self::assertSame(['pi-slow' => 'monitoring_degraded', 'pi-dead' => 'device_fault'], $byDevice);
    }

    public function testUuidIsStableAndDistinctPerKindAndDevice(): void
    {
        $a = DeviceHealthWatch::uuidFor('device_fault', 'pi-01', 100);
        self::assertSame($a, DeviceHealthWatch::uuidFor('device_fault', 'pi-01', 100));
        self::assertSame(32, strlen($a));
        self::assertNotSame($a, DeviceHealthWatch::uuidFor('monitoring_degraded', 'pi-01', 100));
        self::assertNotSame($a, DeviceHealthWatch::uuidFor('device_fault', 'pi-02', 100));
        self::assertNotSame($a, DeviceHealthWatch::uuidFor('device_fault', 'pi-01', 101));
    }
}