Keep calls and hand acts on the bus, answer status at once, record durations (hq to-be 45 Phase 0)

A controller restart lost every call's outcome, `status` composed the mesh while its caller waited (18.6s live on 2026-10-06, past the 10s window), a repair by hand left no trace, and the core's bounds had nothing measured to be set from. - calls: kept in the controller's bucket mesh-controller_calls (last 1000 or 14 days, answers bounded to 64 KiB), read by id across a restart; a controller starting marks a stopped one's running calls abandoned; each call names its caller from the inbox its answer goes to. - status: the serving controller composes it at start, after news from a machine, a build or an acting verb, and every minute; the verb answers the last composition at once with when and how long it took. Composing resolves each machine once instead of twice. - hand-act log in mesh-controller_hand-acts: push (required through the seat), plans stop/close, broker consumer-reset and the new hand-act record take --why/--cause/--condition; `hand-acts` lists them and repeated causes; status counts the week's. - durations (migration 0066): apply (send to first report), heartbeat gap, plan tier and build, recorded as heard; `durations` summarises them. - the controller's seat row takes this binary's definition of its own verbs, so the console no longer judges calls against an older build's schema. - the controller is granted its two buckets' subjects.
2026-10-06 02:59:36 +02:00
parent 146c48fd96
commit e74c32ed50
35 changed files with 2313 additions and 75 deletions
@@ -0,0 +1,197 @@
+package main
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"flag"
+	"fmt"
+	"os"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/nats-io/nats.go"
+
+	"github.com/novox/mesh-controller/internal/broker"
+	"github.com/novox/mesh-controller/internal/link"
+)
+
+// Acts done by hand, and why (novox/hq to-be 45 §7).
+//
+// **Which verbs ask why.** `plans close` and `plans stop`, `broker consumer-reset` and `hand-act
+// record` refuse without it everywhere: nothing automated runs them, so a call without a reason is a
+// person who has not given one. A named `push` asks for it through the mesh-controller seat, which is
+// how a person or an agent acts by hand on the mesh; at a shell `--why` is recorded when given and not
+// required, because the installer and the lab push by command line as a step of what they do, and a
+// step of a procedure is not a repair. `conditions silence` joins them when the condition store does
+// (Phase 1).
+
+// handActFlags are the flags every repairing verb takes.
+type handActFlags struct {
+	why, cause, condition *string
+}
+
+func addHandActFlags(set *flag.FlagSet) handActFlags {
+	return handActFlags{
+		why:       set.String("why", "", "why this is done by hand — recorded in the hand-act log (novox/hq to-be 45 §7)"),
+		cause:     set.String("cause", "", "the cause, in a word or a condition's kind; the verb's own name when not given"),
+		condition: set.String("condition", "", "the key of the condition this act addresses, if any"),
+	}
+}
+
+// given is whether a reason was given.
+func (f handActFlags) given() bool { return strings.TrimSpace(*f.why) != "" }
+
+// require refuses an act without a reason, before anything is done.
+func (f handActFlags) require(verb string) error {
+	if f.given() {
+		return nil
+	}
+	return fmt.Errorf("%s is a repair done by hand, and says why: --why <text> (recorded in the hand-act "+
+		"log, novox/hq to-be 45 §7). Nothing was done", verb)
+}
+
+// handActConn is the serving controller's connection, for what it reads of the log itself; a
+// command dials its own.
+var handActConn *nats.Conn
+
+// onTheBus runs f with a connection to the bus: the serving controller's, or one of its own.
+func onTheBus(f func(*nats.Conn) error) error {
+	if handActConn != nil {
+		return f(handActConn)
+	}
+	address, err := broker.BusAddress()
+	if err != nil {
+		return err
+	}
+	js, err := broker.Dial(address)
+	if err != nil {
+		return fmt.Errorf("cannot reach the bus: %w", err)
+	}
+	defer js.Close()
+	return f(js.Conn())
+}
+
+// record writes the entry for an act about to be done. **Before the act, and never instead of it**:
+// a log that cannot be written is said loudly, and the repair it was about still happens — a mesh
+// whose bus is down is exactly the mesh somebody is repairing by hand.
+func (f handActFlags) record(ctx context.Context, verb string, args []string) {
+	if !f.given() {
+		return
+	}
+	act := link.HandAct{Verb: verb, Args: args, Why: strings.TrimSpace(*f.why),
+		Cause: strings.TrimSpace(*f.cause), Condition: strings.TrimSpace(*f.condition)}
+	err := onTheBus(func(conn *nats.Conn) error {
+		written, err := link.RecordHandAct(ctx, conn, act)
+		act = written
+		return err
+	})
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "this act by hand could NOT be recorded in the hand-act log, and is done anyway: %v\n", err)
+		return
+	}
+	fmt.Printf("recorded as %s in the hand-act log: %s, because %q (cause: %s)\n", act.ID, act.By, act.Why, act.Cause)
+}
+
+// handActCommand is `hand-act record` and `hand-acts`.
+func handActCommand(ctx context.Context, args []string) error {
+	if len(args) > 0 && args[0] == "record" {
+		set := flag.NewFlagSet("hand-act record", flag.ContinueOnError)
+		f := addHandActFlags(set)
+		positionals, err := parseAround(set, args[1:])
+		if err != nil {
+			return err
+		}
+		what := strings.TrimSpace(strings.Join(positionals, " "))
+		if what == "" {
+			return errors.New("hand-act record <what was done> --why <text> [--cause <word>] [--condition <key>]")
+		}
+		if err := f.require("hand-act record"); err != nil {
+			return err
+		}
+		if strings.TrimSpace(*f.cause) == "" {
+			return errors.New("hand-act record says the cause too: --cause <word>, the word a second " +
+				"act for the same reason will use — it is how a repair done twice is found")
+		}
+		act := link.HandAct{Verb: "hand-act record", Args: []string{what}, Why: strings.TrimSpace(*f.why),
+			Cause: strings.TrimSpace(*f.cause), Condition: strings.TrimSpace(*f.condition)}
+		return onTheBus(func(conn *nats.Conn) error {
+			written, err := link.RecordHandAct(ctx, conn, act)
+			if err != nil {
+				return fmt.Errorf("the act could not be recorded: %w", err)
+			}
+			fmt.Printf("recorded as %s: %s did %q, because %q (cause: %s)\n", written.ID, written.By, what,
+				written.Why, written.Cause)
+			return nil
+		})
+	}
+	if len(args) > 0 && args[0] != "list" && !strings.HasPrefix(args[0], "-") {
+		return errors.New("hand-act record <what> --why <text> --cause <word> | hand-acts [--days N] [--json]")
+	}
+	if len(args) > 0 && args[0] == "list" {
+		args = args[1:]
+	}
+	set := flag.NewFlagSet("hand-acts", flag.ContinueOnError)
+	days := set.Int("days", 14, "how many days back")
+	asJSON := set.Bool("json", false, "as data")
+	if _, err := parseAround(set, args); err != nil {
+		return err
+	}
+	return onTheBus(func(conn *nats.Conn) error {
+		now := time.Now()
+		acts, err := link.HandActs(ctx, conn, now.Add(-time.Duration(*days)*24*time.Hour))
+		if err != nil {
+			return err
+		}
+		repeated := link.RepeatedCauses(acts, now)
+		if *asJSON {
+			body, err := json.MarshalIndent(map[string]any{"acts": acts, "repeated": repeated}, "", "  ")
+			if err != nil {
+				return err
+			}
+			fmt.Println(string(body))
+			return nil
+		}
+		if len(acts) == 0 {
+			fmt.Printf("nothing was done by hand in the last %d day(s)\n", *days)
+			return nil
+		}
+		for i := len(acts) - 1; i >= 0; i-- {
+			a := acts[i]
+			fmt.Printf("%s  %s  %s %s\n    by %s — %s (cause: %s", a.At.Local().Format("2006-01-02 15:04"), a.ID,
+				a.Verb, strings.Join(a.Args, " "), a.By, a.Why, a.Cause)
+			if a.Condition != "" {
+				fmt.Printf(", condition %s", a.Condition)
+			}
+			fmt.Println(")")
+		}
+		if len(repeated) > 0 {
+			causes := make([]string, 0, len(repeated))
+			for c, n := range repeated {
+				causes = append(causes, fmt.Sprintf("%s ×%d", c, n))
+			}
+			sort.Strings(causes)
+			fmt.Printf("\ndone by hand more than once in a fortnight — a healer is wanted (to-be 45 S15): %s\n",
+				strings.Join(causes, ", "))
+		}
+		return nil
+	})
+}
+
+// handActsThisWeek is how many acts were done by hand in the last seven days, for `status`; -1 when
+// the log could not be read, which status says rather than reading as none.
+func handActsThisWeek(ctx context.Context) (int, string) {
+	n := -1
+	err := onTheBus(func(conn *nats.Conn) error {
+		reading, cancel := context.WithTimeout(ctx, 5*time.Second)
+		defer cancel()
+		acts, err := link.HandActs(reading, conn, time.Now().Add(-7*24*time.Hour))
+		n = len(acts)
+		return err
+	})
+	if err != nil {
+		return -1, err.Error()
+	}
+	return n, ""
+}