x1208-exporter/internal/monitor/monitor_test.go

package monitor

import (
	"errors"
	"testing"
	"time"

	"git.mial.net/mokhtar/x1208-exporter/internal/sensor"
)

func shutdownConfig() Config {
	return Config{
		Shutdown:         true,
		Volts:            3.5,
		SOC:              15,
		Samples:          4,
		MinUptimeTicks:   2,
		RequireDischarge: true,
	}
}

// onBattery returns a low reading that falls by 10 mV per step, which is what
// a real discharge looks like.
func onBattery(step int) sensor.Reading {
	return sensor.Reading{
		ACPresent: false,
		Volts:     3.40 - float64(step)*0.01,
		SOC:       10,
		At:        time.Unix(1754661600+int64(step)*30, 0),
	}
}

func onMains() sensor.Reading {
	return sensor.Reading{ACPresent: true, Volts: 4.1, SOC: 100, At: time.Unix(1754661600, 0)}
}

func events(r Result) []Event {
	out := make([]Event, 0, len(r.Logs))
	for _, l := range r.Logs {
		out = append(out, l.Event)
	}
	return out
}

func contains(list []Event, want Event) bool {
	for _, e := range list {
		if e == want {
			return true
		}
	}
	return false
}

// settle runs enough healthy mains ticks to clear the startup inhibition.
func settle(t *testing.T, m *Monitor) {
	t.Helper()
	for i := 0; i <= m.cfg.MinUptimeTicks; i++ {
		if res := m.Tick(onMains(), nil); res.Shutdown {
			t.Fatal("shutdown fired while on mains")
		}
	}
}

func TestHealthyTicksLogNothingAfterStartup(t *testing.T) {
	m := New(Config{})

	first := m.Tick(onMains(), nil)
	if !contains(events(first), EventStartup) {
		t.Error("first tick must log startup")
	}

	for i := 0; i < 5; i++ {
		if res := m.Tick(onMains(), nil); len(res.Logs) != 0 {
			t.Errorf("healthy tick %d logged %v, want nothing", i, events(res))
		}
	}
}

func TestACTransitionLogsOncePerChange(t *testing.T) {
	m := New(Config{})
	m.Tick(onMains(), nil)

	res := m.Tick(onBattery(0), nil)
	if !contains(events(res), EventACChanged) {
		t.Fatal("losing AC must log a transition")
	}
	if res := m.Tick(onBattery(1), nil); len(res.Logs) != 0 {
		t.Errorf("staying on battery logged %v, want nothing", events(res))
	}
	if res := m.Tick(onMains(), nil); !contains(events(res), EventACChanged) {
		t.Error("regaining AC must log a transition")
	}
}

func TestFailedTickKeepsPreviousSampleAndCounts(t *testing.T) {
	m := New(Config{})
	m.Tick(onMains(), nil)

	res := m.Tick(sensor.Reading{}, errors.New("i2c wedged"))
	if res.Healthy {
		t.Error("failed tick must report unhealthy")
	}
	if res.Failures != 1 {
		t.Errorf("failures = %d, want 1", res.Failures)
	}
	if !res.HaveSample || res.Sample.Volts != 4.1 {
		t.Error("failed tick must carry the previous complete sample forward")
	}
	if !contains(events(res), EventErrorEnter) {
		t.Error("first failure must log error_enter")
	}

	if res := m.Tick(sensor.Reading{}, errors.New("still wedged")); contains(events(res), EventErrorEnter) {
		t.Error("a continuing error must not log error_enter again")
	}
	if res := m.Tick(onMains(), nil); !contains(events(res), EventErrorExit) {
		t.Error("recovery must log error_exit")
	}
}

func TestShutdownDisabledByDefault(t *testing.T) {
	m := New(Config{})
	for i := 0; i < 20; i++ {
		if m.Tick(onBattery(i), nil).Shutdown {
			t.Fatal("shutdown fired with an empty Config; it must be opt-in")
		}
	}
}

func TestShutdownFiresOnSustainedDischarge(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	for i := 0; i < 3; i++ {
		if m.Tick(onBattery(i), nil).Shutdown {
			t.Fatalf("shutdown fired on qualifying tick %d, before the sample count", i+1)
		}
	}
	res := m.Tick(onBattery(3), nil)
	if !res.Shutdown {
		t.Fatal("shutdown must fire on the fourth consecutive qualifying tick")
	}
	if !contains(events(res), EventShutdownTriggered) {
		t.Error("firing must log shutdown_triggered")
	}
	if m.Tick(onBattery(4), nil).Shutdown {
		t.Error("shutdown must fire only once")
	}
}

// A wedged sensor repeats one plausible low value. Consecutive identical
// samples are one fault observed four times, not four confirmations.
func TestStuckSensorNeverTriggersShutdown(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	stuck := sensor.Reading{ACPresent: false, Volts: 3.40, SOC: 10, At: time.Unix(1754661600, 0)}
	for i := 0; i < 50; i++ {
		if m.Tick(stuck, nil).Shutdown {
			t.Fatalf("shutdown fired at tick %d on a constant voltage", i)
		}
	}
}

// "low, low, long outage, low, low" is not a sustained low battery.
func TestErrorResetsArmingWindow(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	m.Tick(onBattery(0), nil)
	m.Tick(onBattery(1), nil)

	res := m.Tick(sensor.Reading{}, errors.New("bus error"))
	if !contains(events(res), EventShutdownDisarmed) {
		t.Error("a failed tick must disarm, not pause, the shutdown window")
	}

	for i := 2; i < 5; i++ {
		if m.Tick(onBattery(i), nil).Shutdown {
			t.Fatalf("shutdown fired at tick %d; the window must restart after an error", i)
		}
	}
}

func TestACReturnDisarms(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	m.Tick(onBattery(0), nil)
	m.Tick(onBattery(1), nil)

	res := m.Tick(onMains(), nil)
	if !contains(events(res), EventShutdownDisarmed) {
		t.Error("AC returning must disarm")
	}
	for i := 2; i < 5; i++ {
		if m.Tick(onBattery(i), nil).Shutdown {
			t.Fatalf("shutdown fired at tick %d; the window must restart after AC returned", i)
		}
	}
}

// A flapping AC line must not accumulate toward a poweroff.
func TestFlappingACNeverAccumulates(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	for i := 0; i < 40; i++ {
		var res Result
		if i%2 == 0 {
			res = m.Tick(onBattery(i), nil)
		} else {
			res = m.Tick(onMains(), nil)
		}
		if res.Shutdown {
			t.Fatalf("shutdown fired at tick %d on a flapping AC line", i)
		}
	}
}

// A restart loop must not power the machine off using readings taken before
// the hardware settled.
func TestStartupInhibitionBlocksImmediateShutdown(t *testing.T) {
	m := New(shutdownConfig())
	for i := 0; i < 2; i++ {
		if m.Tick(onBattery(i), nil).Shutdown {
			t.Fatalf("shutdown fired at tick %d, inside the startup inhibition", i+1)
		}
	}
}

// The worst remaining failure: the AC line reads 0 while mains is actually
// connected. The charger then holds cell voltage flat or rising, which is what
// the discharge guard exists to catch. Without it a single stuck GPIO line
// powers the machine off during normal operation.
func TestFalseACLossWhileChargingNeverTriggersShutdown(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	for i := 0; i < 60; i++ {
		r := sensor.Reading{
			ACPresent: false,                   // the line is lying
			Volts:     3.40 + float64(i)*0.005, // but the charger is working
			SOC:       10,
		}
		if m.Tick(r, nil).Shutdown {
			t.Fatalf("shutdown fired at tick %d while voltage was RISING; "+
				"a false AC reading must not power the machine off", i)
		}
	}
}

// Guard against a future change that quietly drops the discharge requirement:
// with it disabled, the same false reading DOES power the machine off. This
// test documents the consequence rather than endorsing the setting.
func TestWithoutDischargeGuardAFalseACReadingIsEnough(t *testing.T) {
	cfg := shutdownConfig()
	cfg.RequireDischarge = false
	m := New(cfg)
	settle(t, m)

	fired := false
	for i := 0; i < 10 && !fired; i++ {
		r := sensor.Reading{ACPresent: false, Volts: 3.40, SOC: 10}
		fired = m.Tick(r, nil).Shutdown
	}
	if !fired {
		t.Error("expected the unguarded config to act on a constant low reading; " +
			"if this changed, update the RequireDischarge documentation")
	}
}

// A failed poweroff must not count as a completed one. If it latched, the
// battery would reach cell cutoff and the HAT would hard-cut the machine —
// exactly what the feature prevents.
func TestFailedActuationRetriesOnTheNextTick(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	for i := 0; i < 3; i++ {
		m.Tick(onBattery(i), nil)
	}
	if !m.Tick(onBattery(3), nil).Shutdown {
		t.Fatal("expected the first shutdown")
	}

	// systemctl poweroff failed: polkit denied it, or D-Bus was busy.
	m.ActuationFailed()

	res := m.Tick(onBattery(4), nil)
	if !res.Shutdown {
		t.Fatal("a failed poweroff must be retried on the next qualifying tick")
	}
	if m.Retries() != 1 {
		t.Errorf("Retries() = %d, want 1", m.Retries())
	}

	// Still latched while the retry is outstanding.
	if m.Tick(onBattery(5), nil).Shutdown {
		t.Error("must not fire again before the second attempt is reported failed")
	}
}

// Retrying must not defeat the safety guards: if AC returns between attempts,
// the machine must stay up.
func TestRetryStillRespectsACReturn(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	for i := 0; i < 3; i++ {
		m.Tick(onBattery(i), nil)
	}
	if !m.Tick(onBattery(3), nil).Shutdown {
		t.Fatal("expected the first shutdown")
	}
	m.ActuationFailed()

	if m.Tick(onMains(), nil).Shutdown {
		t.Fatal("AC returned; a pending retry must not power the machine off")
	}
	for i := 4; i < 7; i++ {
		if m.Tick(onBattery(i), nil).Shutdown {
			t.Fatalf("fired at tick %d; the window must restart after AC returned", i)
		}
	}
}

func TestLowSOCAloneCanArm(t *testing.T) {
	m := New(shutdownConfig())
	settle(t, m)

	// Voltage stays above the threshold; only state of charge is low.
	for i := 0; i < 3; i++ {
		r := sensor.Reading{ACPresent: false, Volts: 3.9 - float64(i)*0.01, SOC: 5}
		if m.Tick(r, nil).Shutdown {
			t.Fatalf("fired early at tick %d", i)
		}
	}
	r := sensor.Reading{ACPresent: false, Volts: 3.87, SOC: 5}
	if !m.Tick(r, nil).Shutdown {
		t.Error("a sustained low state of charge must trigger shutdown")
	}
}