Maven/internal/loop/rules.go

package loop

import (
	"strings"
	"time"
)

// Rule — a proactive rule. Rules are CODE, not a DSL config — until ~30 rules
// and you feel the pain (per spec). A Rule has a name (ids it in nudges.outcome
// for the feedback loop), a Severity, a pure Predicate, and a cooldown.
//
// The Predicate answers "should this rule want to fire given the State?" —
// only the check against the snapshot. It is pure, no I/O. The GATE answers
// "are we allowed to fire it right now?" (quiet hours, cooldown, etc) —
// applied by the loop, never per-rule.
//
// Cooldown is the BASE duration between same-rule nudges. The feedback
// auto-tuner scales it over time (mostly ignored → lengthen; acted → leave).
// Bounds belong at the daemon-config level; here we just carry the base.
type Rule struct {
	Name      string
	Severity  Severity
	Cooldown  // base cooldown + bounded-duration envelope for the auto-tuner
	Predicate func(State) bool

	// InertWhenNoData — most rules should be silent when their substrate key is
	// missing (since(key)==null → don't fire). If the predicate already encodes
	// that check itself, leave this empty. Otherwise set to the key(s) the rule
	// needs and the gate will skip the rule when any are missing.
	InertWhenNoData []string

	// WantPrefixes — key prefixes whose whole family the gatherer must load.
	// InertWhenNoData names keys that exist at wiring time; a rule over a key
	// set that is only known at read time (one fact per kuma monitor) declares
	// the prefix here instead. Prefixes never make a rule inert: an empty
	// family is the predicate's own "no data" case.
	WantPrefixes []string

	// StillTrue — is the CONDITION still true, ignoring whether it is worth
	// saying again? Distinct from Predicate on purpose, and the distinction is
	// the whole reason this field exists (Vikunja #535).
	//
	// Predicate answers "should this fire now", which folds in edge-triggering:
	// ServiceDownRule ends in !s.NudgedSince(...), so it reads false the instant
	// a nudge goes out even though the service is still down. A repeat loop that
	// consulted Predicate would cancel every alarm one tick after raising it,
	// which is exactly backwards.
	//
	// Only a rule whose alarm repeats needs this. nil means "I cannot tell you",
	// and the caller must then fall back to a bound it can enforce without the
	// rule's help. nil must never be read as "the condition cleared": a rule
	// that says nothing about its condition is not a rule that resolved.
	StillTrue func(State) bool
}

// Cooldown — tunable bounded by the envelope so a weird week (auto-tuned) can't
// mutate maven silent or stalker. Base is what the rule ships with; Min/Max
// bound the feedback-driven adjustments persisted as `facts (source=feedback)`.
type Cooldown struct {
	Base time.Duration
	Min  time.Duration
	Max  time.Duration
}

// Canonical care/ops rules — NOT a config DSL. Code, so the predicate is
// inspectable and unit-tested. Daemon wires these up; the loop just iterates.

// WaterRule — sev1 care: if it's been ≥3h since a `water` fact, fire.
// Inert when no water fact exists at all (shuts up when uncertain).
func WaterRule() Rule {
	return Rule{
		Name:            "water",
		Severity:        Sev1,
		Cooldown:        Cooldown{Base: 30 * time.Minute, Min: 15 * time.Minute, Max: 6 * time.Hour},
		InertWhenNoData: []string{"water"},
		Predicate: func(s State) bool {
			d, ok := s.Since("water")
			if !ok {
				return false // no data → shut up
			}
			return d >= 3*time.Hour
		},
	}
}

// MealRule — sev1 care: if ≥6h since an `meal` fact, fire. Inert without data.
func MealRule() Rule {
	return Rule{
		Name:            "meal",
		Severity:        Sev1,
		Cooldown:        Cooldown{Base: 60 * time.Minute, Min: 30 * time.Minute, Max: 8 * time.Hour},
		InertWhenNoData: []string{"meal"},
		Predicate: func(s State) bool {
			d, ok := s.Since("meal")
			if !ok {
				return false
			}
			return d >= 6*time.Hour
		},
	}
}

// BreakRule — sev2 care: ≥90min of continuous desk activity without a break.
// Reads both `desk_active` (fresh input ⇒ at desk) and `break` (last taken).
// Inert unless both exist — can't claim continuous activity without both anchors.
func BreakRule() Rule {
	return Rule{
		Name:            "break",
		Severity:        Sev2,
		Cooldown:        Cooldown{Base: 45 * time.Minute, Min: 20 * time.Minute, Max: 4 * time.Hour},
		InertWhenNoData: []string{"desk_active", "break"},
		Predicate: func(s State) bool {
			dDesk, ok1 := s.Since("desk_active")
			dBreak, ok2 := s.Since("break")
			if !ok1 || !ok2 {
				return false // shut up until we have both anchors
			}
			// at desk (fresh input within 2min) AND no break for ≥90min.
			return dDesk <= 2*time.Minute && dBreak >= 90*time.Minute
		},
	}
}

// ServiceDownPrefix — mavpoll writes one fact per kuma monitor under this
// prefix, `service_down:<monitor name>`. The suffix is the name he hears.
const ServiceDownPrefix = "service_down:"

// ServiceDownSource — kuma is the source of truth for service up/down. The
// rule is provenance-scoped: a poller writing under a different source cannot
// forge the trigger.
const ServiceDownSource = "poll:uptimekuma"

// DownServices — the monitors currently reading "down", by name, in key order.
//
// Pure, and the rule and the phraser both call it, so the message can never
// name a service the predicate did not fire on.
func DownServices(s State) []string {
	var out []string
	for _, f := range s.FactsUnder(ServiceDownPrefix) {
		if f.Source == ServiceDownSource && f.Value == `"down"` {
			out = append(out, strings.TrimPrefix(f.Key, ServiceDownPrefix))
		}
	}
	return out
}

// MinDownAge — how long a monitor must have read "down" before it is worth
// waking him (Vikunja #536).
//
// Technitium read down on one kuma poll and up on the next, sixty seconds
// apart, and the alarm arrived after the service was already back. mavpoll
// writes a service_down fact only when the state CHANGES, so the fact's
// timestamp is the instant the monitor went down and its age is how long it
// has stayed there. That is the whole debounce: no history to keep, no counter
// to persist.
//
// Ninety seconds is one poll interval plus room for jitter, so a monitor must
// survive at least one further poll as down. The cost is up to ninety seconds
// of alarm latency on a real outage, against never being paged for a blip.
//
// It bounds the alarm, not the truth: DownServices still reports a monitor the
// instant it goes down, because /dash showing a fresh outage is right even
// when phoning him about it is not.
const MinDownAge = 90 * time.Second

// downLongEnough — the newest down fact that has aged past MinDownAge, or the
// zero time when no monitor has. The rule fires off this and not off the
// newest down fact outright.
func downLongEnough(s State, now time.Time) time.Time {
	var newest time.Time
	for _, f := range s.FactsUnder(ServiceDownPrefix) {
		if f.Source != ServiceDownSource || f.Value != `"down"` {
			continue
		}
		if now.Sub(f.Ts) < MinDownAge {
			continue
		}
		if f.Ts.After(newest) {
			newest = f.Ts
		}
	}
	return newest
}

// ServiceDownRule — sev4 ops hard: at least one kuma monitor reads "down".
//
// It used to read one aggregate `service_down` fact, which is why it was
// disabled in deploy: the nudge could say that something on homesrv was down
// but never which thing. Per-monitor facts fix that, and pausing a monitor in
// kuma now silences that monitor rather than nothing.
//
// Edge-triggered — see State.NudgedSince. Without it a service that stays down
// for a day qualifies on every tick and cooldown alone is the only brake.
func ServiceDownRule() Rule {
	return Rule{
		Name:         "service_down",
		Severity:     Sev4,
		Cooldown:     Cooldown{Base: 15 * time.Minute, Min: 5 * time.Minute, Max: 1 * time.Hour},
		WantPrefixes: []string{ServiceDownPrefix},
		Predicate: func(s State) bool {
			newest := downLongEnough(s, s.Now)
			if newest.IsZero() {
				// Nothing down, no data at all, or nothing down long enough
				// to be more than a flap → shut up. See MinDownAge.
				return false
			}
			return !s.NudgedSince("service_down", newest)
		},
		// The condition without the edge trigger. DownServices is the same
		// helper the predicate and the phraser read, so the repeat stops on
		// exactly the monitors he was told about.
		StillTrue: func(s State) bool { return len(DownServices(s)) > 0 },
	}
}

// NetdataCriticalRule — sev3 ops soft: netdata has a CRITICAL alarm active
// (disk/mem/cert/temp). The `netdata_alarm` aggregate fact (mavpoll, source
// poll:netdata) reads "critical". Sev3 not sev4: netdata resource alarms are
// "look soon", not "wake me" — a full disk matters, but kuma's service_down is
// the hard page. Provenance-scoped to poll:netdata.
func NetdataCriticalRule() Rule {
	return Rule{
		Name:            "netdata_critical",
		Severity:        Sev3,
		Cooldown:        Cooldown{Base: 20 * time.Minute, Min: 10 * time.Minute, Max: 2 * time.Hour},
		InertWhenNoData: []string{"netdata_alarm"},
		Predicate: func(s State) bool {
			f, ok := s.Fact("netdata_alarm")
			if !ok || f.Ts.IsZero() {
				return false
			}
			return f.Source == "poll:netdata" && f.Value == `"critical"`
		},
	}
}

// RulesExcept returns DefaultRules minus the named ones (config's
// `disabled_rules`). Config subtracts from the canonical set; it never adds to
// it and never reorders it, so the "rules are code" line above still holds.
//
// Names are matched exactly and an unknown one is ignored, on purpose: a
// config that still lists a rule someone deleted must not stop the daemon from
// booting. The logging of what was actually dropped belongs to the caller,
// which knows whether anyone is listening.
func RulesExcept(disabled []string) ([]Rule, []string) {
	all := DefaultRules()
	if len(disabled) == 0 {
		return all, nil
	}
	off := make(map[string]bool, len(disabled))
	for _, n := range disabled {
		if n = strings.TrimSpace(n); n != "" {
			off[n] = true
		}
	}
	out := make([]Rule, 0, len(all))
	var dropped []string
	for _, r := range all {
		if off[r.Name] {
			dropped = append(dropped, r.Name)
			continue
		}
		out = append(out, r)
	}
	return out, dropped
}

// DefaultRules — the canonical set the daemon wires. Add more as code, not config.
// Order here is NOT load-bearing — the loop picks max severity, ties broken by
// (severity desc, name asc) for deterministic output.
func DefaultRules() []Rule {
	return []Rule{
		WaterRule(),
		MealRule(),
		BreakRule(),
		ServiceDownRule(),
		NetdataCriticalRule(),
	}
}