mesh-controller/cmd/mesh-controller/conditions.go

package main

import (
	"context"
	"errors"
	"flag"
	"fmt"
	"os"
	"slices"
	"strconv"
	"strings"
	"time"

	"github.com/nats-io/nats.go"

	"github.com/novox/mesh-controller/internal/broker"
	"github.com/novox/mesh-controller/internal/conditions"
	"github.com/novox/mesh-controller/internal/link"
)

// What is wrong, kept until observation says it is not (novox/hq to-be 45 §2, ADR 0227).
//
// **`status` used to be the only place the mesh said it was wrong, and only to whoever asked.** Every
// core failure of research 031 was found by a person looking. A condition is the mesh saying it: raised
// by a watchdog when a signal is late (signals.go), by a probe when an invariant does not hold
// (doctor.go), or by an event a provider sends (standing.go); kept on the bus with since-when and
// evidence; said on the bus as it changes, for the operator's channel to carry; and cleared when an
// observation says it is resolved. Nobody resolves one by hand. A person who knows silences it, for a
// while, with a reason, and that is recorded as a hand act.

// conditionsFrom is the serving controller's keeper; nil in any other process, which opens its own.
var conditionsFrom *conditions.Keeper

// keeperOn is a keeper over the store on a connection, saying its transitions on that connection.
func keeperOn(ctx context.Context, conn *nats.Conn) (*conditions.Keeper, error) {
	store, history, err := conditions.OnTheBus(ctx, conn)
	if err != nil {
		return nil, err
	}
	js, err := conn.JetStream()
	if err != nil {
		return nil, err
	}
	return conditions.NewKeeper(ctx, conditions.Options{Store: store, History: history,
		Teller: link.OverNATS{Conn: conn, JS: js},
		Say:    func(format string, args ...any) { fmt.Fprintf(os.Stderr, format+"\n", args...) },
		// What status leads with changed: composed again soon (a nudge outside the serving controller
		// does nothing).
		Changed: statusFrom.nudge}), nil
}

// withKeeper runs f with the serving controller's keeper, or one of its own that says everything
// it was given before it returns.
func withKeeper(ctx context.Context, f func(*conditions.Keeper) error) error {
	if conditionsFrom != nil {
		return f(conditionsFrom)
	}
	return onTheBus(func(conn *nats.Conn) error {
		k, err := keeperOn(ctx, conn)
		if err != nil {
			return err
		}
		defer func() {
			flushing, cancel := context.WithTimeout(context.Background(), 15*time.Second)
			defer cancel()
			k.Close(flushing)
		}()
		return f(k)
	})
}

// openConditions is every open condition, for `status` and `node show`: from the serving keeper, or
// read from the bus. Where there is no bus to read it from, it says so — never "none open".
func openConditions(ctx context.Context) ([]conditions.Condition, error) {
	if conditionsFrom != nil {
		return conditionsFrom.Open(ctx)
	}
	if _, err := broker.BusAddress(); err != nil {
		return nil, fmt.Errorf("this process has no bus to read the conditions from: %w", err)
	}
	var out []conditions.Condition
	err := onTheBus(func(conn *nats.Conn) error {
		store, _, err := conditions.OnTheBus(ctx, conn)
		if err != nil {
			return err
		}
		reading, cancel := context.WithTimeout(ctx, 5*time.Second)
		defer cancel()
		out, err = conditions.Read(reading, store)
		return err
	})
	return out, err
}

// conditionsUsage is how the verb is typed.
const conditionsUsage = "conditions [--scope S] [--severity urgent|warning] [--machine M] [--json] | " +
	"conditions show <key> | conditions silence <key> --for <duration> --why <text> | " +
	"conditions history [--days N] [--key K] [--json]"

// conditionsCommand is `conditions`, `conditions show`, `conditions silence` and `conditions history`.
func conditionsCommand(ctx context.Context, args []string) error {
	sub := "list"
	if len(args) > 0 && !strings.HasPrefix(args[0], "-") {
		sub, args = args[0], args[1:]
	}
	switch sub {
	case "list":
		return listConditions(ctx, args)
	case "show":
		return showCondition(ctx, args)
	case "silence":
		return silenceCondition(ctx, args)
	case "history":
		return conditionHistory(ctx, args)
	}
	return errors.New(conditionsUsage)
}

func listConditions(ctx context.Context, args []string) error {
	set := flag.NewFlagSet("conditions", flag.ContinueOnError)
	scope := set.String("scope", "", "only this scope: "+strings.Join(conditions.Scopes, ", "))
	severity := set.String("severity", "", "only urgent, or only warning")
	machine := set.String("machine", "", "only those about this machine")
	asJSON := set.Bool("json", false, "as data")
	if rest, err := parseAround(set, args); err != nil {
		return err
	} else if len(rest) > 0 {
		return errors.New(conditionsUsage)
	}
	if *severity != "" && *severity != string(conditions.Urgent) && *severity != string(conditions.Warning) {
		return fmt.Errorf("a severity is urgent or warning, not %q", *severity)
	}
	open, err := openConditions(ctx)
	if err != nil {
		return err
	}
	var out []conditions.Condition
	for _, c := range open {
		if (*scope == "" || c.Subject.Scope == *scope) && (*severity == "" || string(c.Severity) == *severity) &&
			(*machine == "" || concerns(c, *machine)) {
			out = append(out, c)
		}
	}
	if *asJSON {
		if out == nil {
			out = []conditions.Condition{}
		}
		return printJSON(map[string]any{"conditions": out, "open": len(open),
			"note": "urgent first, then oldest first; a condition clears when observation says so, never by hand"})
	}
	if len(out) == 0 {
		if len(open) == 0 {
			fmt.Println("no open conditions")
		} else {
			fmt.Printf("none of the %d open condition(s) is about that\n", len(open))
		}
		return nil
	}
	for _, line := range conditionLines(out, time.Now()) {
		fmt.Println(line)
	}
	return nil
}

// concerns says whether a condition is about a machine: it names it, or its key does.
func concerns(c conditions.Condition, machine string) bool {
	if c.Subject.Machine == machine || slices.Contains(c.Subject.Also, machine) {
		return true
	}
	for _, part := range strings.Split(c.Key, ".") {
		if part == machine {
			return true
		}
	}
	return false
}

// conditionLines is how a list of conditions reads: one line each, its silence under it.
func conditionLines(list []conditions.Condition, now time.Time) []string {
	var out []string
	for _, c := range list {
		times := ""
		if c.Count > 1 {
			times = fmt.Sprintf(", raised %d times", c.Count)
		}
		out = append(out, fmt.Sprintf("  %-7s %s — %s (since %s%s)", strings.ToUpper(string(c.Severity)),
			c.Key, c.Summary, c.Raised.Local().Format("2006-01-02 15:04"), times))
		if c.SilencedAt(now) {
			out = append(out, fmt.Sprintf("          silenced until %s by %s: %s",
				c.Silenced.Until.Local().Format("2006-01-02 15:04"), c.Silenced.By, c.Silenced.Why))
		}
	}
	return out
}

func showCondition(ctx context.Context, args []string) error {
	set := flag.NewFlagSet("conditions show", flag.ContinueOnError)
	asJSON := set.Bool("json", false, "as data")
	rest, err := parseAround(set, args)
	if err != nil {
		return err
	}
	if len(rest) != 1 {
		return errors.New("conditions show <key>")
	}
	key := rest[0]
	var c conditions.Condition
	var found bool
	if conditionsFrom != nil {
		c, found, err = conditionsFrom.Get(ctx, key)
	} else {
		err = onTheBus(func(conn *nats.Conn) error {
			store, _, err := conditions.OnTheBus(ctx, conn)
			if err != nil {
				return err
			}
			c, found, err = conditions.ReadOne(ctx, store, key)
			return err
		})
	}
	if err != nil {
		return err
	}
	if !found {
		return fmt.Errorf("no condition %s is open — `conditions` lists those that are, and `conditions "+
			"history --key %s` what became of it", key, key)
	}
	if *asJSON {
		return printJSON(c)
	}
	now := time.Now()
	fmt.Printf("%s  %s\n  %s\n\n", strings.ToUpper(string(c.Severity)), c.Key, c.Summary)
	fmt.Printf("  kind       %s\n  about      %s %s", c.Kind, c.Subject.Scope, c.Subject.ID)
	if c.Subject.Machine != "" {
		fmt.Printf(", on %s", c.Subject.Machine)
	}
	fmt.Printf("\n  raised by  %s\n  since      %s (%s ago), observed %d time(s), last %s ago\n",
		c.Source, c.Raised.Local().Format("2006-01-02 15:04:05"), roughly(now.Sub(c.Raised)), c.Observations,
		now.Sub(c.LastObserved).Round(time.Second))
	if c.Count > 1 {
		fmt.Printf("  raised     %d times, each within ten minutes of clearing\n", c.Count)
	}
	fmt.Printf("  resolved   by %s\n", resolverWords(c.Resolver))
	if c.Silenced != nil {
		fmt.Printf("  silenced   until %s by %s: %s\n", c.Silenced.Until.Local().Format("2006-01-02 15:04"),
			c.Silenced.By, c.Silenced.Why)
	}
	if len(c.Tried) > 0 {
		fmt.Println("\n  tried:")
		for _, t := range c.Tried {
			fmt.Printf("    %s  %s: %s\n", t.At.Local().Format("2006-01-02 15:04"), t.What, t.Outcome)
		}
	}
	fmt.Println("\n  evidence, newest first:")
	for _, e := range c.Evidence {
		fmt.Printf("    %s  %s\n", e.At.Local().Format("2006-01-02 15:04:05"), e.Said)
	}
	return nil
}

func resolverWords(r string) string {
	switch r {
	case conditions.ResolverSelf:
		return "itself: it clears when observation says it is resolved"
	case conditions.ResolverOperator:
		return "the operator: nothing in the mesh will repair it"
	case conditions.ResolverAgent:
		return "an agent"
	}
	return r
}

// silenceCondition stops a condition's messages for a while (to-be 45 §2). A hand act: recorded with
// who and why before it is done, its cause the condition's kind unless one is given.
func silenceCondition(ctx context.Context, args []string) error {
	set := flag.NewFlagSet("conditions silence", flag.ContinueOnError)
	forFlag := set.String("for", "", "how long: 30m, 4h, 2d — at most 7d")
	acts := addHandActFlags(set)
	rest, err := parseAround(set, args)
	if err != nil {
		return err
	}
	if len(rest) != 1 {
		return errors.New("conditions silence <key> --for <duration> --why <text>")
	}
	key := rest[0]
	if err := acts.require("conditions silence"); err != nil {
		return err
	}
	d, err := parseFor(*forFlag)
	if err != nil {
		return err
	}
	if d > conditions.MaxSilence {
		return fmt.Errorf("a condition is silenced for at most %s at once; past it, say so again", conditions.MaxSilence)
	}
	return withKeeper(ctx, func(k *conditions.Keeper) error {
		c, found, err := k.Get(ctx, key)
		if err != nil {
			return err
		}
		if !found {
			return fmt.Errorf("no condition %s is open — `conditions` lists them. Nothing was silenced", key)
		}
		if strings.TrimSpace(*acts.cause) == "" {
			*acts.cause = c.Kind
		}
		*acts.condition = key
		acts.record(ctx, "conditions silence", []string{key, "--for", *forFlag})
		held, err := k.Silence(ctx, key, d, link.Caller(), *acts.why)
		if err != nil {
			return err
		}
		fmt.Printf("%s is silenced until %s: no message is sent for it until then. It is still open, and "+
			"`status` still says it; it clears when observation says it is resolved\n",
			held.Key, held.Silenced.Until.Local().Format("2006-01-02 15:04"))
		return nil
	})
}

// parseFor reads a duration, days included.
func parseFor(s string) (time.Duration, error) {
	s = strings.TrimSpace(s)
	if s == "" {
		return 0, errors.New("say for how long: --for 30m, 4h or 2d")
	}
	if days, ok := strings.CutSuffix(s, "d"); ok {
		n, err := strconv.Atoi(days)
		if err != nil || n <= 0 {
			return 0, fmt.Errorf("%q is not a number of days", s)
		}
		return time.Duration(n) * 24 * time.Hour, nil
	}
	d, err := time.ParseDuration(s)
	if err != nil || d <= 0 {
		return 0, fmt.Errorf("%q is not a duration: 30m, 4h or 2d", s)
	}
	return d, nil
}

func conditionHistory(ctx context.Context, args []string) error {
	set := flag.NewFlagSet("conditions history", flag.ContinueOnError)
	days := set.Int("days", 7, "how many days back, at most 90")
	key := set.String("key", "", "only this condition")
	asJSON := set.Bool("json", false, "as data")
	if rest, err := parseAround(set, args); err != nil {
		return err
	} else if len(rest) > 0 {
		return errors.New("conditions history [--days N] [--key K] [--json]")
	}
	since := time.Now().Add(-time.Duration(*days) * 24 * time.Hour)
	var events []conditions.Event
	read := func(h conditions.History) error {
		var err error
		events, err = h.Since(ctx, since)
		return err
	}
	var err error
	if conditionsFrom != nil {
		events, err = conditionsFrom.HistorySince(ctx, since)
	} else {
		err = onTheBus(func(conn *nats.Conn) error {
			_, history, err := conditions.OnTheBus(ctx, conn)
			if err != nil {
				return err
			}
			return read(history)
		})
	}
	if err != nil {
		return err
	}
	var out []conditions.Event
	for _, e := range events {
		if *key == "" || e.Key == *key {
			out = append(out, e)
		}
	}
	if *asJSON {
		if out == nil {
			out = []conditions.Event{}
		}
		return printJSON(map[string]any{"history": out, "days": *days})
	}
	if len(out) == 0 {
		fmt.Printf("nothing was raised, changed or cleared in the last %d day(s)\n", *days)
		return nil
	}
	for _, e := range out {
		line := fmt.Sprintf("%s  %-13s %s", e.At.Local().Format("2006-01-02 15:04:05"), e.Change, e.Key)
		switch e.Change {
		case conditions.ChangeRaised, conditions.ChangeReopened:
			line += " — " + e.Summary
		case conditions.ChangeSeverity:
			line += fmt.Sprintf(" — %s, was %s", e.Severity, e.Was)
		case conditions.ChangeResolver:
			line += fmt.Sprintf(" — %s, was %s", e.Resolver, e.Was)
		default:
			if e.Why != "" {
				line += " — " + e.Why
			}
		}
		fmt.Println(line)
	}
	return nil
}

// printConditions is the status section that leads it: every open condition, urgent first, oldest
// first, silenced ones with their expiry (to-be 45 §2). A store that could not be read is said, and
// is not "none open".
func printConditions(list []conditions.Condition, unread string, now time.Time) {
	if unread != "" {
		fmt.Printf("the open conditions could NOT be read, so whether anything is wrong is not known: %s\n\n", unread)
		return
	}
	if len(list) == 0 {
		return
	}
	urgent := 0
	for _, c := range list {
		if c.Severity == conditions.Urgent {
			urgent++
		}
	}
	fmt.Printf("%d open condition(s), %d urgent:\n\n", len(list), urgent)
	for _, line := range conditionLines(list, now) {
		fmt.Println(line)
	}
	fmt.Printf("\n  `conditions show <key>` says more; each clears when observation says it is resolved, " +
		"never by hand — `conditions silence <key> --for <d> --why <text>` stops its messages\n\n")
}