Take an older bus module's allowed as held, and name only remedies that work (review 31 of PR 188, hq issue 353)

After mesh-catalog #166 merges and before the bus upgrade, the bus's
machine cannot be pushed, so any change to the composed list made the
list check read behind for good: every ask was withheld and the condition
named a push that is refused. An older module's allowed now counts as
held, the unconfirmed reload said once; the worst case is one ask refused
in the seconds before a reload, which is asked again (issue 369).

The list check stays for a module that says not allowed or cannot answer,
and its remedy is the plan's own reason when the list cannot be composed,
the bus upgrade while sends there wait on it, and a push otherwise. An
in_force false is a wait only when the module gives both times; otherwise
what is not known is named.

cmd/mesh-controller/asker.go

@@ -213,6 +213,8 @@ type asker struct {
 
 	saidNoRouter bool
 	saidNoGrant  bool
+	// saidGrantCaveat is whether a grant held with a caveat was said, so it is said once.
+	saidGrantCaveat bool
 
 	mu     sync.Mutex
 	nudged chan struct{}
@@ -317,6 +319,13 @@ func (a *asker) reconcile(ctx context.Context) error {
 			}
 			return a.sayUnasked(ctx, unasked, "the bus does not hold the controller's grant to ask yet: "+why)
 		}
+		if why != "" && !a.saidGrantCaveat {
+			// Held, with a caveat worth one line (an older bus module cannot confirm the reload).
+			a.logf("the controller asks: %s", why)
+			a.saidGrantCaveat = true
+		} else if why == "" {
+			a.saidGrantCaveat = false
+		}
 		a.saidNoGrant = false
 	}
 	channels := ""

cmd/mesh-controller/asker_test.go

@@ -12,6 +12,7 @@ import (
 
 	"git.novox.be/novox/mesh-sdk/go/asks"
 
+	"github.com/novox/mesh-controller/internal/broker"
 	"github.com/novox/mesh-controller/internal/conditions"
 	"github.com/novox/mesh-controller/internal/link"
 )
@@ -808,3 +809,207 @@ func TestARefusalIsAskedAgainAndTheUndeliveredConditionClearsOnceTaken(t *testin
 		t.Errorf("the explanation says its verdict twice: %q", e)
 	}
 }
+
+// hq issue 353, the review: the bus holds the controller's grant to ask only when both facts hold — the mesh
+// composes the controller's own grant, and the bus's module says it is in force on the running server — and
+// each fact not known is not held, said with why.
+func TestTheGrantIsHeldOnlyWhenComposedAndInForceOnTheBus(t *testing.T) {
+	yes := func(context.Context) (bool, string, error) { return true, "", nil }
+	no := func(why string) grantJudge {
+		return func(context.Context) (bool, string, error) { return false, why, nil }
+	}
+	broken := func(context.Context) (bool, string, error) { return false, "", errors.New("the store is away") }
+	for _, c := range []struct {
+		name              string
+		composed, inForce grantJudge
+		held              bool
+		says              string
+	}{
+		{"composed and in force", yes, yes, true, ""},
+		{"not composed", no("no router is assigned"), yes, false, "no router is assigned"},
+		{"composed, written, not reloaded", yes, no("the server has not reloaded"), false, "has not reloaded"},
+		{"the composition unknown", broken, yes, false, "could not be worked out: the store is away"},
+		{"the bus unknown", yes, broken, false, "could not be worked out: the store is away"},
+		{"nothing judges the bus", yes, nil, false, "not judged"},
+	} {
+		held, why, err := grantHeldBy(c.composed, c.inForce, time.Now)(context.Background())
+		if err != nil || held != c.held || !strings.Contains(why, c.says) {
+			t.Errorf("%s: held %v (%q, %v)", c.name, held, why, err)
+		}
+	}
+	// Remembered for grantLookEvery, then judged again.
+	now := time.Date(2026, 10, 9, 18, 0, 0, 0, time.UTC)
+	inForce := false
+	judge := grantHeldBy(yes, func(context.Context) (bool, string, error) { return inForce, "not yet", nil },
+		func() time.Time { return now })
+	if held, _, _ := judge(context.Background()); held {
+		t.Fatal("held before the bus enforces it")
+	}
+	inForce = true
+	if held, _, _ := judge(context.Background()); held {
+		t.Error("judged again inside grantLookEvery")
+	}
+	now = now.Add(grantLookEvery)
+	if held, _, _ := judge(context.Background()); !held {
+		t.Error("not judged again after grantLookEvery")
+	}
+}
+
+// The controller's own grant, as composed: present while a router that takes asks is assigned, absent
+// otherwise — whatever else in the user list changes.
+func TestTheControllersOwnGrantToAskIsReadFromTheComposition(t *testing.T) {
+	router := broker.Declared{Module: "messenger", Holds: []broker.Seat{{Name: broker.AsksSeat, Scope: "mesh",
+		Accepts: []string{"ask", "cancel"}, Emits: []string{"decided"}, ByCaller: []string{"ask", "cancel", "decided"}}}}
+	other := broker.Declared{Module: "dunst"}
+	with := broker.Records{Nodes: []string{"anchor"}, Assigned: map[string][]broker.Declared{"anchor": {router, other}}}
+	without := broker.Records{Nodes: []string{"anchor"}, Assigned: map[string][]broker.Declared{"anchor": {other}}}
+	if may, err := controllerMayAsk(with); err != nil || !may {
+		t.Errorf("with a router assigned: %v %v", may, err)
+	}
+	if may, err := controllerMayAsk(without); err != nil || may {
+		t.Errorf("with no router assigned: %v %v", may, err)
+	}
+}
+
+// The bus module's answer, with the record's word on the list sent as the check only where the answer does
+// not settle it (reviews 22 and 31 of PR 188); each way it is not held names its own remedy.
+func TestTheBusModulesAnswerNamesTheRemedyForEachCase(t *testing.T) {
+	const (
+		reloaded   = `{"allowed":true,"in_force":true,"file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:56:05Z"}`
+		notLoaded  = `{"allowed":true,"in_force":false,"why":"the user list on the machine allows it, and the server has not reloaded since it was written","file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:50:00Z"}`
+		noVarz     = `{"allowed":true,"in_force":false,"why":"the server's last configuration load could not be read: refused"}`
+		noStat     = `{"allowed":true,"in_force":false,"why":"when the bus's user list was written could not be read inside mesh-broker-nats: exit 1"}`
+		notAllowed = `{"allowed":false,"in_force":false,"why":"the user list on the machine does not allow it"}`
+	)
+	current := busListState{Machine: "anchor"}
+	behind := busListState{Machine: "anchor", Behind: true}
+	stepped := busListState{Machine: "anchor", Behind: true, BusStep: "sending anchor would replace the bus; `bus upgrade --why …`"}
+	uncomposed := busListState{Machine: "anchor", Behind: true, Uncomposed: errors.New("module foo requires a provision nobody provides")}
+	for _, c := range []struct {
+		name, answer string
+		askErr       error
+		list         busListState
+		listErr      error
+		held         bool
+		says, not    string
+	}{
+		{"in force", reloaded, nil, behind, nil, true, "", "push"},
+		{"written, not reloaded", notLoaded, nil, current, nil, false, "within about 5 s", "push"},
+		{"in force not known: varz", noVarz, nil, current, nil, false, "is not known: the server's last configuration load", "wait"},
+		{"in force not known: stat", noStat, nil, current, nil, false, "is not known: when the bus's user list was written", "wait"},
+		{"not allowed, list behind", notAllowed, nil, behind, nil, false, "`push anchor` carries it", "5 s"},
+		{"not allowed, bus step pending", notAllowed, nil, stepped, nil, false, "`bus upgrade", "`push anchor`"},
+		{"not allowed, list uncomposed", notAllowed, nil, uncomposed, nil, false, "`plan anchor`", "`push anchor`"},
+		{"older module, allowed, list current", `{"allowed":true}`, nil, current, nil, true, "not confirmed", "push"},
+		{"older module, allowed, list behind", `{"allowed":true}`, nil, behind, nil, true, "not confirmed", "push"},
+		{"older module, allowed, list unknown", `{"allowed":true}`, nil, current, errors.New("the store is away"), true, "`bus upgrade`", "push"},
+		{"older module, not allowed, list behind", `{"allowed":false}`, nil, behind, nil, false, "`push anchor` carries it", "5 s"},
+		{"module cannot answer, list current", "", errors.New("no responders"), current, nil, true, "could not answer", "push"},
+		{"module cannot answer, list behind", "", errors.New("no responders"), behind, nil, false, "`push anchor` carries it", ""},
+		{"module cannot answer, list unknown", "", errors.New("no responders"), current, errors.New("the store is away"), false, "could not be worked out", ""},
+		{"answer unreadable, list behind", `not json`, nil, behind, nil, false, "could not be read", ""},
+	} {
+		judge := busGrantBy(
+			func(context.Context) (string, json.RawMessage, error) {
+				return "anchor", json.RawMessage(c.answer), c.askErr
+			},
+			func(context.Context) (busListState, error) { return c.list, c.listErr })
+		held, why, _ := judgeGrantOnce(judge)
+		if held != c.held || !strings.Contains(why, c.says) || (c.not != "" && strings.Contains(why, c.not)) {
+			t.Errorf("%s: held %v (%q)", c.name, held, why)
+		}
+	}
+	none := busGrantBy(func(context.Context) (string, json.RawMessage, error) { return "", nil, nil }, nil)
+	if held, why, _ := judgeGrantOnce(none); held || !strings.Contains(why, "no module holds the bus") {
+		t.Errorf("no bus: held %v (%q)", held, why)
+	}
+}
+
+// judgeGrantOnce is the whole judgement with the composed grant held, as the asker makes it.
+func judgeGrantOnce(bus grantJudge) (bool, string, error) {
+	yes := func(context.Context) (bool, string, error) { return true, "", nil }
+	return grantHeldBy(yes, bus, time.Now)(context.Background())
+}
+
+// The orders reviews 22 and 31 of PR 188 found: this controller live before the bus module that answers
+// in_force, with the bus's machine behind on its list — and, after mesh-catalog #166 merged, unpushable until a
+// person's bus upgrade. An older module that allows the ask asks (once, with the caveat said); a new module that
+// has not reloaded names the wait, not a push; one that cannot say whether it reloaded names what is not known.
+func TestAnOlderBusModuleNeitherSilencesTheAsksNorNamesTheWrongRemedy(t *testing.T) {
+	for _, c := range []struct {
+		name, answer string
+		list         busListState
+		asks         bool
+		says, not    string
+	}{
+		{"older module, list current", `{"allowed":true}`, busListState{Machine: "anchor"}, true, "not confirmed", ""},
+		{"older module, list behind, bus step pending", `{"allowed":true}`,
+			busListState{Machine: "anchor", Behind: true, BusStep: "a planned step"}, true, "not confirmed", ""},
+		{"new module, not reloaded",
+			`{"allowed":true,"in_force":false,"why":"not reloaded","file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:50:00Z"}`,
+			busListState{Machine: "anchor"}, false, "within about 5 s", "push"},
+		{"new module, reload not known", `{"allowed":true,"in_force":false,"why":"the server's last configuration load could not be read: refused"}`,
+			busListState{Machine: "anchor"}, false, "is not known", "wait"},
+	} {
+		t.Run(c.name, func(t *testing.T) {
+			r := newAskerRig(t)
+			var said []string
+			r.a.logf = func(f string, a ...any) { said = append(said, fmt.Sprintf(f, a...)) }
+			var raised [][]conditions.Observation
+			r.a.raise = func(_ context.Context, obs []conditions.Observation) error {
+				raised = append(raised, obs)
+				return nil
+			}
+			yes := func(context.Context) (bool, string, error) { return true, "", nil }
+			r.a.grantHeld = grantHeldBy(yes, busGrantBy(
+				func(context.Context) (string, json.RawMessage, error) {
+					return "anchor", json.RawMessage(c.answer), nil
+				},
+				func(context.Context) (busListState, error) { return c.list, nil }),
+				func() time.Time { return r.now })
+			r.open = []conditions.Condition{heldCondition()}
+			_ = r.a.reconcile(context.Background())
+			_ = r.a.reconcile(context.Background())
+			sent := r.asksSent(t)
+			if c.asks {
+				if len(sent) != 1 || sent[0].About != heldCondition().Key {
+					t.Fatalf("not asked: %+v", sent)
+				}
+				n := 0
+				for _, s := range said {
+					if strings.Contains(s, c.says) {
+						n++
+					}
+				}
+				if n != 1 {
+					t.Errorf("the caveat said %d times: %q", n, said)
+				}
+				return
+			}
+			if len(sent) != 0 {
+				t.Fatalf("asked while the bus does not hold the grant: %+v", sent)
+			}
+			if len(raised) == 0 || len(raised[len(raised)-1]) != 1 ||
+				raised[len(raised)-1][0].Kind != "asks-undelivered" {
+				t.Fatalf("not said as undelivered: %+v", raised)
+			}
+			summary := raised[len(raised)-1][0].Summary
+			if !strings.Contains(summary, c.says) || (c.not != "" && strings.Contains(summary, c.not)) {
+				t.Errorf("the condition names the wrong remedy: %q", summary)
+			}
+		})
+	}
+}
+
+// The serving asker is wired to the real judgement: with records and a bus it cannot read, the grant is not
+// held, and so nothing is asked (a stub saying yes, or no judgement at all, would ask).
+func TestTheServingAskerJudgesTheGrantForReal(t *testing.T) {
+	a := servingAsker(&stores{}, nil, nil, nil)
+	if a.grantHeld == nil {
+		t.Fatal("the serving asker does not judge the bus's grant")
+	}
+	held, why, err := a.grantHeld(context.Background())
+	if err != nil || held || !strings.Contains(why, "could not be worked out") {
+		t.Errorf("held %v (%q, %v) with nothing to read", held, why, err)
+	}
+}

cmd/mesh-controller/asker_wire.go

@@ -235,12 +235,27 @@ func routerHereIn(inv *inventory.Inventory) func(ctx context.Context) (bool, err
 	}
 }
 
-// grantHeldIn says whether the bus holds the controller's grant to ask (novox/hq issue 353): the user list the
-// machine holding the bus was last sent is the one the mesh composes now (brokerBehind, the same judgement a
-// push makes to send that machine first). While it is behind, the controller's ask is refused by the bus,
-// whatever the record says of the router, so nothing is asked and the operator is told to push that machine.
-// Judged at most every grantLookEvery: composing the list resolves the bus's machine whole.
-func grantHeldIn(open *stores) func(ctx context.Context) (bool, string, error) {
+// grantHeldIn says whether the bus holds the controller's grant to ask (novox/hq issue 353), judged on the two
+// facts that make it so, and failing closed on each:
+//
+//  1. **composed**: the user list the mesh composes now grants the controller itself to publish its ask
+//     (controllerMayAsk) — the controller's own grant, not whether any user of the list changed;
+//  2. **in force**: the bus's own module, on the machine holding the bus, says the user list there allows it
+//     and the server reloaded after that list was written (the nats module's `nats_user_can`, `in_force`) — a
+//     list sent is not a list the bus enforces until it reloads.
+//
+// Anything that cannot be worked out is not held, with why, so the conditions that need the operator are said
+// as undelivered rather than asked into a refusal.
+func grantHeldIn(open *stores, conn *nats.Conn) func(ctx context.Context) (bool, string, error) {
+	return grantHeldBy(composedGrantIn(open), busGrantIn(open, conn), time.Now)
+}
+
+// grantJudge is one of the two facts: whether it holds, and why not.
+type grantJudge func(ctx context.Context) (bool, string, error)
+
+// grantHeldBy is the judgement over the two facts, remembered for grantLookEvery: composing the list resolves
+// the bus's machine whole, and asking the bus's module is a call.
+func grantHeldBy(composed, inForce grantJudge, now func() time.Time) func(ctx context.Context) (bool, string, error) {
 	var mu sync.Mutex
 	var at time.Time
 	var held bool
@@ -248,22 +263,251 @@ func grantHeldIn(open *stores) func(ctx context.Context) (bool, string, error) {
 	return func(ctx context.Context) (bool, string, error) {
 		mu.Lock()
 		defer mu.Unlock()
-		if !at.IsZero() && time.Since(at) < grantLookEvery {
+		if !at.IsZero() && now().Sub(at) < grantLookEvery {
 			return held, why, nil
 		}
-		machine, behind, err := brokerBehind(ctx, open, nil)
+		held, why = judgeGrant(ctx, composed, inForce)
+		at = now()
+		return held, why, nil
+	}
+}
+
+// judgeGrant is held only when both facts hold; an error is a fact not known, never a yes. A fact that holds
+// with a caveat (a reload not confirmed) gives that caveat as the why of a yes.
+func judgeGrant(ctx context.Context, composed, inForce grantJudge) (bool, string) {
+	var caveat []string
+	for _, fact := range []struct {
+		judge grantJudge
+		what  string
+	}{{composed, "whether the mesh composes the controller a grant to ask"}, {inForce, "whether the bus enforces it"}} {
+		if fact.judge == nil {
+			return false, fact.what + " is not judged here"
+		}
+		ok, why, err := fact.judge(ctx)
+		if err != nil {
+			return false, fact.what + " could not be worked out: " + err.Error()
+		}
+		if !ok {
+			return false, why
+		}
+		if why != "" {
+			caveat = append(caveat, why)
+		}
+	}
+	return true, strings.Join(caveat, "; ")
+}
+
+// controllerMayAsk says whether the controller's own grant, as composed from these records, lets it publish its
+// ask (ADR 0259 §3: composed while a router that takes asks under its asker's name is assigned).
+func controllerMayAsk(records broker.Records) (bool, error) {
+	users, err := broker.Users(records)
+	if err != nil {
+		return false, err
+	}
+	for _, u := range users {
+		if u.Kind != broker.KindController {
+			continue
+		}
+		perms, err := broker.PermissionsFor(u)
+		if err != nil {
+			return false, err
+		}
+		return broker.MayPublish(perms, asks.AskSubject(askerName)), nil
+	}
+	return false, errors.New("the composition holds no controller")
+}
+
+// composedGrantIn is the first fact, from the mesh's records.
+func composedGrantIn(open *stores) grantJudge {
+	return func(ctx context.Context) (bool, string, error) {
+		if open == nil || open.inventory == nil {
+			return false, "", errors.New("the mesh's records are not open")
+		}
+		records, err := open.inventory.BusRecords(ctx)
 		if err != nil {
 			return false, "", err
 		}
-		at, held, why = time.Now(), !behind, ""
-		if behind {
-			why = fmt.Sprintf("the bus's user list on %s is behind what the mesh composes, so the bus has not been "+
-				"given the controller's grant to ask; `push %s` carries it", machine, machine)
+		may, err := controllerMayAsk(records)
+		if err != nil || may {
+			return may, "", err
 		}
-		return held, why, nil
+		return false, "the mesh composes the controller no grant to ask: no router that takes asks under its " +
+			"asker's name is assigned", nil
 	}
 }
 
+// busGrantIn is the second fact, asked of the bus's own module on the machine holding the bus, with the check
+// main made before it (novox/hq issue 353, PR 186: is the user list sent to the bus's machine the one composed
+// now) kept for the cases the module's word does not settle.
+func busGrantIn(open *stores, conn *nats.Conn) grantJudge {
+	ask := func(ctx context.Context) (string, json.RawMessage, error) {
+		if open == nil || open.inventory == nil || conn == nil {
+			return "", nil, errors.New("the mesh's records or the bus are not open")
+		}
+		holders, err := seatHolders(ctx, open.inventory)
+		if err != nil {
+			return "", nil, err
+		}
+		h, held := holders[theBrokerSeat]
+		if !held || h.Node == "" || h.Module == "" {
+			return "", nil, nil
+		}
+		a, err := link.AskModuleToolOn(ctx, conn, h.Module, busUserCanTool, h.Node, map[string]any{
+			"user": broker.ControllerName, "action": "publish", "subject": asks.AskSubject(askerName)}, 15*time.Second)
+		if err != nil {
+			return h.Node, nil, err
+		}
+		if a.Error != "" {
+			return h.Node, nil, errors.New(a.Error)
+		}
+		return h.Node, a.Result, nil
+	}
+	list := func(ctx context.Context) (busListState, error) {
+		if open == nil || open.inventory == nil {
+			return busListState{}, errors.New("the mesh's records are not open")
+		}
+		s, err := brokerListState(ctx, open, nil)
+		if err != nil || s.Machine == "" || !s.Behind {
+			return s, err
+		}
+		step, err := busHeld(ctx, open.inventory, []string{s.Machine})
+		if err != nil {
+			return busListState{}, err
+		}
+		s.BusStep = step[s.Machine]
+		return s, nil
+	}
+	return busGrantBy(ask, list)
+}
+
+// busListState is the user list on the bus's machine as the controller's record knows it: whether the list
+// sent there is behind the one composed now, why it could not be composed, and the bus step a send there waits
+// on (that machine cannot be pushed until a person's `bus upgrade`).
+type busListState struct {
+	Machine    string
+	Behind     bool
+	Uncomposed error
+	BusStep    string
+}
+
+// remedy is the one thing that sends the bus's machine the list composed now: the plan's own reason when it
+// cannot be composed, the bus upgrade while sends there wait on it, and otherwise a push of that machine.
+func (s busListState) remedy(node string) string {
+	if s.Machine != "" {
+		node = s.Machine
+	}
+	switch {
+	case s.Uncomposed != nil:
+		return fmt.Sprintf("the user list for %s cannot be composed (%v); `plan %s` says what to fix first",
+			node, s.Uncomposed, node)
+	case s.BusStep != "":
+		return fmt.Sprintf("sends to %s wait on the bus's planned step, so a push will not carry it: %s", node, s.BusStep)
+	}
+	return fmt.Sprintf("`push %s` carries it", node)
+}
+
+// busGrantBy judges the bus's word, and names for each way it is not held the one thing that makes it held:
+//
+//   - **in force**: held;
+//   - **allowed, from a module older than `in_force`**: held, with the caveat that the reload is not confirmed.
+//     The file allows the publish, and the bus reloads within about 5 s of a change to it, so the worst case is
+//     one ask refused in those seconds, which is asked again (issue 369). The list check is not consulted:
+//     while a bus step is pending the bus's machine cannot be pushed, so any change to the composed list would
+//     read as behind for good and silence every ask until a person's bus upgrade (the review of PR 188);
+//   - **allowed, written, not reloaded** (the module gives both times): wait about 5 s;
+//   - **allowed, in force not known** (the module could not read a time): what is not known, said;
+//   - **not allowed, or the module cannot answer**: the list check decides — the remedy that sends the list
+//     when it is behind (busListState.remedy), and, for a module that cannot answer, held while the list sent
+//     is current, as main judged it.
+//
+// ask answers the machine holding the bus and its module's answer ("" when nothing holds the bus); list is the
+// record's word on the list sent to that machine.
+func busGrantBy(ask func(ctx context.Context) (string, json.RawMessage, error),
+	list func(ctx context.Context) (busListState, error)) grantJudge {
+	return func(ctx context.Context) (bool, string, error) {
+		node, raw, askErr := ask(ctx)
+		if askErr == nil && node == "" {
+			return false, "no module holds the bus, so nothing says what it enforces", nil
+		}
+		var answer busAnswer
+		if askErr == nil {
+			if answer, askErr = readBusAnswer(raw); askErr != nil {
+				askErr = fmt.Errorf("its answer could not be read: %w", askErr)
+			}
+		}
+		if askErr != nil {
+			if node == "" {
+				node = "the bus's machine"
+			}
+			s, err := list(ctx)
+			if err != nil {
+				return false, "", fmt.Errorf("the bus module on %s could not answer (%v), and whether the list sent "+
+					"there is the one composed now could not be worked out: %w", node, askErr, err)
+			}
+			if s.Behind {
+				return false, fmt.Sprintf("the bus module on %s could not answer (%v), and the user list sent there is "+
+					"behind what the mesh composes; %s", node, askErr, s.remedy(node)), nil
+			}
+			return true, fmt.Sprintf("the bus module on %s could not answer (%v); judged by the user list sent there, "+
+				"which is the one composed now", node, askErr), nil
+		}
+		notAllowed := func(older string) (bool, string, error) {
+			s, err := list(ctx)
+			if err != nil {
+				return false, "", fmt.Errorf("the user list on %s does not allow the controller to ask%s, and whether "+
+					"the list sent there is the one composed now could not be worked out: %w", node, older, err)
+			}
+			if s.Behind {
+				return false, fmt.Sprintf("the user list on %s does not allow the controller to ask%s: it is behind "+
+					"what the mesh composes; %s", node, older, s.remedy(node)), nil
+			}
+			return false, fmt.Sprintf("the user list on %s does not allow the controller to ask%s, though the list "+
+				"sent there is the one composed now; %s again", node, older, s.remedy(node)), nil
+		}
+		switch {
+		case answer.InForce == nil && answer.Allowed:
+			return true, fmt.Sprintf("the user list on %s allows the controller to ask, but its reload is not "+
+				"confirmed: the bus module there is older than the answer whether a grant is in force, and the bus "+
+				"upgrade (`bus upgrade`) carries one that confirms it", node), nil
+		case answer.InForce == nil:
+			return notAllowed(" (the bus module there is older than the answer whether a grant is in force)")
+		case !answer.Allowed:
+			return notAllowed("")
+		case *answer.InForce:
+			return true, "", nil
+		case answer.FileWritten != "" && answer.ServerLoaded != "":
+			return false, fmt.Sprintf("the bus on %s has the controller's grant to ask written (%s) but has not "+
+				"reloaded since (last load %s); it reloads in place within about 5 s, so nothing is to be done but wait",
+				node, answer.FileWritten, answer.ServerLoaded), nil
+		}
+		why := answer.Why
+		if why == "" {
+			why = "it gives no reason"
+		}
+		return false, fmt.Sprintf("the user list on %s allows the controller to ask, but whether the bus enforces it "+
+			"is not known: %s", node, why), nil
+	}
+}
+
+// busUserCanTool is the bus module's answer to whether a user may do something, and whether it is in force.
+const busUserCanTool = "nats_user_can"
+
+// busAnswer is the bus module's answer to busUserCanTool; InForce is nil from a module older than that field,
+// and FileWritten and ServerLoaded are given only when it could read both times (mesh-catalog's nats InForce).
+type busAnswer struct {
+	Allowed      bool   `json:"allowed"`
+	InForce      *bool  `json:"in_force"`
+	Why          string `json:"why"`
+	FileWritten  string `json:"file_written"`
+	ServerLoaded string `json:"server_loaded"`
+}
+
+func readBusAnswer(raw json.RawMessage) (busAnswer, error) {
+	var answer busAnswer
+	err := json.Unmarshal(raw, &answer)
+	return answer, err
+}
+
 // grantLookEvery is how often the bus's user list is judged against the one its machine was last sent.
 const grantLookEvery = 30 * time.Second
 
@@ -302,7 +546,19 @@ func startAsking(ctx context.Context, open *stores, server *link.Server, conn *n
 		fmt.Printf("the operator cannot be asked: %v\n", err)
 		return
 	}
-	a := &asker{
+	a := servingAsker(open, conn, js, keeper)
+	if err := server.Decides(a); err != nil {
+		fmt.Printf("the operator's answers cannot be heard, so nothing is asked: %v\n", err)
+		return
+	}
+	askerFrom = a
+	go a.keep(ctx)
+}
+
+// servingAsker is the serving controller's asker, wired to the mesh: what it reads, publishes, performs and
+// records, and the judgements it asks by — the bus's grant to ask among them (novox/hq issue 353).
+func servingAsker(open *stores, conn *nats.Conn, js jetstream.JetStream, keeper *conditions.Keeper) *asker {
+	return &asker{
 		open: keeper.Open,
 		silence: func(ctx context.Context, key string, d time.Duration, by, why string) error {
 			_, err := keeper.Silence(ctx, key, d, by, why)
@@ -322,7 +578,7 @@ func startAsking(ctx context.Context, open *stores, server *link.Server, conn *n
 		},
 		routerRecord: routerRecordOf(conn, open.inventory),
 		routerHere:   routerHereIn(open.inventory),
-		grantHeld:    grantHeldIn(open),
+		grantHeld:    grantHeldIn(open, conn),
 		channels:     channelsIn(open.inventory),
 		raise: func(ctx context.Context, obs []conditions.Observation) error {
 			return keeper.Reconcile(ctx, sourceAsker, obs)
@@ -330,10 +586,4 @@ func startAsking(ctx context.Context, open *stores, server *link.Server, conn *n
 		now:  time.Now,
 		logf: func(format string, args ...any) { fmt.Printf(format+"\n", args...) },
 	}
-	if err := server.Decides(a); err != nil {
-		fmt.Printf("the operator's answers cannot be heard, so nothing is asked: %v\n", err)
-		return
-	}
-	askerFrom = a
-	go a.keep(ctx)
 }

cmd/mesh-controller/batches_test.go

@@ -226,7 +226,7 @@ func TestTheAssemblingBatchIsShown(t *testing.T) {
 	asksWithPaths(t)
 	var said []inventory.Plan
 	was := inventory.PlanSaved
-	inventory.PlanSaved = func(p inventory.Plan) { said = append(said, p) }
+	inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { said = append(said, p) }
 	t.Cleanup(func() { inventory.PlanSaved = was })
 	now := time.Now().UTC()
 	claude := catalogueMerge("553b7191claude", "app", now.Add(-20*time.Second))

cmd/mesh-controller/delivery.go

@@ -10,6 +10,7 @@ import (
 	"slices"
 	"sort"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/nats-io/nats.go"
@@ -940,7 +941,7 @@ func deliveryCommand(ctx context.Context, args []string) error {
 		if *group == "" && len(members) == 1 {
 			// One head, checked again as the forge's announcement would have it (a recheck): the controller's
 			// own path for a pull request, run because the delivery's owner asked.
-			if err := sayingOnTheBus(ctx, func() error { return (following{open}).PullUpdated(ctx, members[0].pull()) }); err != nil {
+			if err := sayingOnTheBus(ctx, inv, func() error { return (following{open}).PullUpdated(ctx, members[0].pull()) }); err != nil {
 				return err
 			}
 			return answer(map[string]any{"rechecked": members[0].ID})
@@ -958,7 +959,7 @@ func deliveryCommand(ctx context.Context, args []string) error {
 			return errors.New("delivery go <plan> [--by <who>] [--why <text>]")
 		}
 		var p inventory.Plan
-		if err := sayingOnTheBus(ctx, func() (err error) {
+		if err := sayingOnTheBus(ctx, inv, func() (err error) {
 			p, err = letGo(ctx, inv, positionals[0], *by, strings.TrimSpace(*why))
 			return err
 		}); err != nil {
@@ -973,7 +974,7 @@ func deliveryCommand(ctx context.Context, args []string) error {
 		}
 		var p inventory.Plan
 		var said stopAnswer
-		if err := sayingOnTheBus(ctx, func() (err error) {
+		if err := sayingOnTheBus(ctx, inv, func() (err error) {
 			p, said, err = stopWalkWithout(ctx, inv, positionals[0], *by, strings.TrimSpace(*why), splitList(*without),
 				time.Now().UTC())
 			return err
@@ -1215,15 +1216,19 @@ func shelfOf(entries []inventory.Entry) map[string]catalogue.Manifest {
 // delivery it walks reads its steps from. Never in the way of the walk: said beside it, and a save that could
 // not be said is logged — the delivery's owner, which also asks for the walks it follows, finds it by
 // comparison. Records arriving out of order are told apart by the plan's revision.
-func sayPlanMoved(ctx context.Context, bus link.Bus, p inventory.Plan) {
-	go publishPlanMoved(ctx, bus, p)
+//
+// On the save that starts the walk and the one that ends it, the walk also says what it touches, its bound and,
+// at the end, its outcome (novox/hq ADR 0308 decision 1, walk_said.go), read from facts; nil facts say only what
+// the walk recorded.
+func sayPlanMoved(ctx context.Context, bus link.Bus, facts walkFacts, p inventory.Plan) {
+	go publishPlanMoved(ctx, bus, facts, p)
 }
 
-func publishPlanMoved(ctx context.Context, bus link.Bus, p inventory.Plan) {
+func publishPlanMoved(ctx context.Context, bus link.Bus, facts walkFacts, p inventory.Plan) {
 	// Its phases so far (novox/hq ADR 0282 decision 6): the rest's reports come after the walk ends, and are
 	// read by whoever asks for the walk (`delivery walks`).
 	p.Phases = p.WalkPhases(time.Now(), nil)
-	body, err := json.Marshal(p)
+	body, err := json.Marshal(planMovedBody{Plan: p, walkSaid: sayWalk(ctx, facts, p)})
 	if err != nil {
 		return
 	}
@@ -1238,7 +1243,7 @@ func publishPlanMoved(ctx context.Context, bus link.Bus, p inventory.Plan) {
 // controller's, or a connection of the command's own — a verb runs as a command of its own, and what it kept
 // would otherwise be said by nobody until the delivery's owner read the walks back. Without a bus the command
 // still runs; what it did is found by comparison.
-func sayingOnTheBus(ctx context.Context, f func() error) error {
+func sayingOnTheBus(ctx context.Context, facts walkFacts, f func() error) error {
 	if checkEvents != nil {
 		return f()
 	}
@@ -1249,9 +1254,10 @@ func sayingOnTheBus(ctx context.Context, f func() error) error {
 			return err
 		}
 		bus := link.OverNATS{Conn: conn, JS: js}
+		was := inventory.PlanSaved
 		checkEvents = bus
-		inventory.PlanSaved = func(p inventory.Plan) { publishPlanMoved(ctx, bus, p) }
-		defer func() { checkEvents, inventory.PlanSaved = nil, nil }()
+		inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { publishPlanMoved(ctx, bus, facts, p) }
+		defer func() { checkEvents, inventory.PlanSaved = nil, was }()
 		ran = true
 		return f()
 	})
@@ -1261,3 +1267,65 @@ func sayingOnTheBus(ctx context.Context, f func() error) error {
 	}
 	return err
 }
+
+// sayingWhatAVerbKept is PlanSaved for a process that is not the serving controller: each walk the verb keeps is
+// said as `plan-moved` before the save returns, with the facts of the inventory that kept it, on the bus the verb
+// reaches. It reaches the bus on the first save and never for a verb that keeps no walk. When the bus cannot be
+// reached, a save that started or ended a walk says so on the verb's error output: its mark is kept and no later
+// save says it, so the router holds what the walk touched until its bound, or not at all for a start. done lets
+// the bus go and takes the hook back.
+func sayingWhatAVerbKept(ctx context.Context) (said func(*inventory.Inventory, inventory.Plan), done func()) {
+	var (
+		mu      sync.Mutex
+		reached bool
+		bus     link.Bus
+		closing func()
+		failed  error
+	)
+	said = func(inv *inventory.Inventory, p inventory.Plan) {
+		mu.Lock()
+		defer mu.Unlock()
+		if !reached {
+			reached = true
+			if handActConn != nil {
+				bus, failed = overNATS(handActConn)
+			} else if js, err := aBus(); err != nil {
+				failed = err
+			} else if bus, failed = overNATS(js.Conn()); failed == nil {
+				closing = js.Close
+			} else {
+				js.Close()
+			}
+		}
+		if bus == nil {
+			switch p.WalkSaid {
+			case inventory.WalkStarted:
+				fmt.Fprintf(os.Stderr, "%s: its start is kept and could NOT be said as plan-moved (%v): the router "+
+					"does not hold what it touches\n", p.ID, failed)
+			case inventory.WalkEnded:
+				fmt.Fprintf(os.Stderr, "%s: its end is kept and could NOT be said as plan-moved (%v): the router holds "+
+					"what it touched until its bound\n", p.ID, failed)
+			}
+			return
+		}
+		publishPlanMoved(ctx, bus, inv, p)
+	}
+	done = func() {
+		mu.Lock()
+		defer mu.Unlock()
+		inventory.PlanSaved = nil
+		if closing != nil {
+			closing()
+		}
+	}
+	return said, done
+}
+
+// overNATS is the bus a connection carries, with its JetStream.
+func overNATS(conn *nats.Conn) (link.Bus, error) {
+	js, err := conn.JetStream()
+	if err != nil {
+		return nil, err
+	}
+	return link.OverNATS{Conn: conn, JS: js}, nil
+}

cmd/mesh-controller/delivery_order_test.go

@@ -119,6 +119,13 @@ func TestTheBusMachineIsBehindByItsUserListAlone(t *testing.T) {
 	if userListBehind("", "") {
 		t.Fatal("a machine sent no list reads as behind")
 	}
+	// A list that could not be composed is behind: not known is never "not behind" (the review of hq issue 353).
+	if !listBehind("", errors.New("the plan cannot be worked out"), digestOf([]byte(list))) {
+		t.Fatal("a list nobody could compose reads as current")
+	}
+	if listBehind(list, nil, digestOf([]byte(list))) || !listBehind(list, nil, "") {
+		t.Fatal("listBehind does not read the digest as userListBehind does")
+	}
 }
 
 // The machine holding the bus goes first: its declaration carries the user list the new grants are

cmd/mesh-controller/main.go

@@ -63,6 +63,15 @@ func run() error {
 	// 45 §6), so the next controller takes it at once rather than after its age.
 	defer theLease.release()
 
+	// Every walk a verb keeps is said on the bus, whichever verb kept it (novox/hq ADR 0308 decision 1): the save
+	// that starts or ends a walk keeps its mark, and no later save says it again. The serving controller says its
+	// own saves.
+	if args[0] != "serve" {
+		said, done := sayingWhatAVerbKept(ctx)
+		inventory.PlanSaved = said
+		defer done()
+	}
+
 	switch args[0] {
 	case "build":
 		return buildCommand(ctx, args[1:])

cmd/mesh-controller/plan_retry.go

@@ -251,6 +251,16 @@ func resumed(p *inventory.Plan, why string) {
 	if p.State == inventory.PlanFailed && len(failedIn(*p)) == 0 {
 		p.State = inventory.PlanBuilding
 		p.Note = why
+		goesOnAgain(p)
+	}
+}
+
+// goesOnAgain clears a stop from a walk that walks again: a stop said why the walk ended, and a walk resumed has
+// not ended. Kept, it would end a retried walk that fails again as stopped, not failed (novox/hq ADR 0308
+// decision 1), and keep the search for the merge that brought the failure from running (searchAfterFailures).
+func goesOnAgain(p *inventory.Plan) {
+	if p.Delivery != nil {
+		p.Delivery.Stopped, p.Delivery.StoppedWhy = "", ""
 	}
 }
 
@@ -460,6 +470,7 @@ func retryRollouts(ctx context.Context, open *stores, p *inventory.Plan) (string
 		said = append(said, m+" to "+strings.Join(again, ", "))
 	}
 	p.State = inventory.PlanRolling
+	goesOnAgain(p)
 	p.Note = fmt.Sprintf("tier %d retried by hand; sent %s first again", p.Tier, strings.Join(said, "; "))
 	if err := open.inventory.SavePlan(ctx, p); err != nil {
 		return "", err
@@ -525,6 +536,7 @@ func retryTierWhole(ctx context.Context, open *stores, p *inventory.Plan, again
 	}
 	if p.State == inventory.PlanFailed && len(failedIn(*p)) == 0 {
 		p.State = inventory.PlanBuilding
+		goesOnAgain(p)
 		p.Note = fmt.Sprintf("tier %d retried by hand: %s asked again; %s sent again with the tier", p.Tier,
 			strings.Join(again, ", "), orNone(strings.Join(resent, ", ")))
 	}

cmd/mesh-controller/proposals.go

@@ -591,7 +591,7 @@ func proposeCommand(ctx context.Context, module, node, valuesArg string, clear,
 			return err
 		},
 		routerHere: routerHereIn(open.inventory),
-		grantHeld:  grantHeldIn(open),
+		grantHeld:  grantHeldIn(open, conn),
 		routerRecord: func(ctx context.Context, id string) (string, error) {
 			bucket, err := asksRecords(ctx, open.inventory)
 			if err != nil || bucket == "" {

cmd/mesh-controller/push.go

@@ -249,7 +249,7 @@ func serve(ctx context.Context) (err error) {
 	// (novox/hq to-be 45 §9).
 	checkEvents = bus
 	// And every walk this controller keeps in a new state, for the delivery it walks (novox/hq ADR 0239).
-	inventory.PlanSaved = func(p inventory.Plan) { sayPlanMoved(ctx, bus, p) }
+	inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { sayPlanMoved(ctx, bus, open.inventory, p) }
 	if err := server.Checks(following{open}); err != nil {
 		return err
 	}
@@ -1084,42 +1084,58 @@ func brokerFirst(names []string, holder string, behind bool) []string {
 // send anywhere, and a module running there always put it in its first wave. A digest of the list
 // last sent is kept for this (ADR 0043: the list is composed on each push, never kept itself).
 func brokerBehind(ctx context.Context, open *stores, names []string) (string, bool, error) {
+	s, err := brokerListState(ctx, open, names)
+	return s.Machine, s.Behind, err
+}
+
+// brokerListState is brokerBehind with why the list could not be composed, when it could not: the plan's own
+// reason, which a remedy names rather than a push that would fail on it (the review of hq issue 353).
+func brokerListState(ctx context.Context, open *stores, names []string) (busListState, error) {
 	inv := open.inventory
 	holders, err := seatHolders(ctx, inv)
 	if err != nil {
-		return "", false, err
+		return busListState{}, err
 	}
 	h, held := holders[theBrokerSeat]
 	if !held || h.Node == "" {
-		return "", false, nil
+		return busListState{}, nil
 	}
 	shelf, err := inv.Catalogue(ctx)
 	if err != nil {
-		return "", false, err
+		return busListState{}, err
 	}
 	if m, known := shelf[h.Module]; !known || m.BusUsers == "" {
 		// A holder that is sent no user list carries no grant: nothing to send first.
-		return "", false, nil
+		return busListState{}, nil
 	}
 	for _, n := range names {
 		if n == h.Node {
-			return h.Node, false, nil
+			return busListState{Machine: h.Node}, nil
 		}
 	}
+	// **What cannot be worked out is behind** (the review of hq issue 353). The list it would be sent cannot be
+	// composed, so whether it carries the grants a send relies on is not known; it is taken as behind, so a push
+	// sends that machine first and says why it cannot (`plan` says it too), and a rollout that needs the list
+	// refuses rather than sending code whose grants the bus may not hold. It said "not behind" until then: a
+	// send went ahead as if the bus held a list nobody could compose.
+	list, composeErr := "", error(nil)
 	plan, _, err := planFor(ctx, open, h.Node)
 	if err != nil {
-		// It cannot be worked out: sending it would refuse the whole send, and `plan` says why.
-		return h.Node, false, nil
-	}
-	list, _, err := busUserList(ctx, inv, plan.Modules)
-	if err != nil {
-		return h.Node, false, nil
+		composeErr = err
+	} else if list, _, err = busUserList(ctx, inv, plan.Modules); err != nil {
+		composeErr = err
 	}
 	sent, err := inv.SentBusUsers(ctx, h.Node)
 	if err != nil {
-		return "", false, err
+		return busListState{}, err
 	}
-	return h.Node, userListBehind(list, sent), nil
+	return busListState{Machine: h.Node, Behind: listBehind(list, composeErr, sent), Uncomposed: composeErr}, nil
+}
+
+// listBehind is whether the bus's machine is behind: the list composed now is not the one last sent, or it
+// could not be composed at all — not known is behind, never "not behind".
+func listBehind(list string, composeErr error, sentDigest string) bool {
+	return composeErr != nil || userListBehind(list, sentDigest)
 }
 
 // userListBehind is whether the user list composed now is not the one last sent, by its digest. An

cmd/mesh-controller/reconnects_test.go

@@ -80,7 +80,7 @@ func TestAVerbsOwnProcessNamesItsConnection(t *testing.T) {
 	// A silence acts, so it is still its own process; it dials, and finds no such condition.
 	_, _ = handlers["conditions"](context.Background(),
 		json.RawMessage(`{"silence":"bus.nothing.here","for":"1h","why":"a test"}`))
-	names := closedNames(t, bus)
+	names := closedNames(t, bus, "mesh-controller verb conditions")
 	found := false
 	for _, n := range names {
 		found = found || n == "mesh-controller verb conditions"

cmd/mesh-controller/release.go

@@ -812,14 +812,19 @@ func backlogCommand(ctx context.Context, sub string, args []string) error {
 	}
 	defer open.Close()
 	if sub == "release-backlog" {
-		release, err := open.inventory.HoldPlans(ctx, true)
-		if err != nil {
+		// Said on the bus (novox/hq ADR 0308 decision 1): the release plan starts walking here, and its start is
+		// said by the verb that opens it.
+		var p *inventory.Plan
+		if err := sayingOnTheBus(ctx, open.inventory, func() error {
+			release, err := open.inventory.HoldPlans(ctx, true)
+			if err != nil {
+				return err
+			}
+			defer release()
+			why.record(ctx, "upgrade release-backlog", nil)
+			p, err = releaseBacklog(ctx, open, link.Caller())
 			return err
-		}
-		defer release()
-		why.record(ctx, "upgrade release-backlog", nil)
-		p, err := releaseBacklog(ctx, open, link.Caller())
-		if err != nil {
+		}); err != nil {
 			return err
 		}
 		if p == nil {

cmd/mesh-controller/release_plan.go

@@ -1559,7 +1559,7 @@ func plansCommand(ctx context.Context, args []string) error {
 	if len(positionals) == 2 && positionals[0] == "go" {
 		why.record(ctx, "plans go", positionals[1:])
 		var p inventory.Plan
-		if err := sayingOnTheBus(ctx, func() (err error) {
+		if err := sayingOnTheBus(ctx, inv, func() (err error) {
 			p, err = letGo(ctx, inv, positionals[1], "a person ("+whoAsked()+")", strings.TrimSpace(*why.why))
 			return err
 		}); err != nil {
@@ -1571,8 +1571,13 @@ func plansCommand(ctx context.Context, args []string) error {
 	}
 	// `retry` (novox/hq ADR 0219): a failed plan's failed builds asked again, and the plan goes on.
 	if len(positionals) == 2 && positionals[0] == "retry" {
-		said, err := retryPlan(ctx, open, positionals[1])
-		if err != nil {
+		// Said on the bus (novox/hq ADR 0308 decision 1): a retried walk starts again, and its start is said
+		// by the verb that starts it.
+		var said string
+		if err := sayingOnTheBus(ctx, inv, func() (err error) {
+			said, err = retryPlan(ctx, open, positionals[1])
+			return err
+		}); err != nil {
 			return err
 		}
 		fmt.Println(said)
@@ -1586,26 +1591,29 @@ func plansCommand(ctx context.Context, args []string) error {
 		if positionals[0] == "close" {
 			how = "closed"
 		}
-		release, err := inv.HoldPlans(ctx, true)
-		if err != nil {
-			return err
-		}
-		defer release()
-		p, err := inv.PlanByID(ctx, positionals[1])
-		if err != nil {
-			return err
-		}
-		if !p.Open() {
-			return fmt.Errorf("%s is already %s", p.ID, p.State)
-		}
-		why.record(ctx, "plans "+positionals[0], positionals[1:])
-		p.State = inventory.PlanFailed
-		p.Note = how + " by hand at tier " + fmt.Sprint(p.Tier) + ": " + strings.TrimSpace(*why.why)
-		sayUnsent(&p, func(m string) bool {
-			u, err := inv.UpgradeOf(ctx, m)
-			return err == nil && u.RollOut
-		})
-		if err := inv.SavePlan(ctx, &p); err != nil {
+		// Said on the bus (novox/hq ADR 0308 decision 1): the walk's end, outcome stopped, is said by the verb
+		// that ends it, so what it touched is not held until its bound.
+		var p inventory.Plan
+		if err := sayingOnTheBus(ctx, inv, func() error {
+			release, err := inv.HoldPlans(ctx, true)
+			if err != nil {
+				return err
+			}
+			defer release()
+			if p, err = inv.PlanByID(ctx, positionals[1]); err != nil {
+				return err
+			}
+			if !p.Open() {
+				return fmt.Errorf("%s is already %s", p.ID, p.State)
+			}
+			why.record(ctx, "plans "+positionals[0], positionals[1:])
+			stopByHand(&p, how, "a person ("+whoAsked()+")", strings.TrimSpace(*why.why))
+			sayUnsent(&p, func(m string) bool {
+				u, err := inv.UpgradeOf(ctx, m)
+				return err == nil && u.RollOut
+			})
+			return inv.SavePlan(ctx, &p)
+		}); err != nil {
 			return err
 		}
 		fmt.Printf("%s %s at tier %d of %d; what was asked still builds and registers, nothing further is asked\n",
@@ -1924,3 +1932,15 @@ func forgetDeleted(ctx context.Context, inv *inventory.Inventory, module string,
 			"`module forget %s`: %v\n", p.ID, module, module, firstLine(err.Error()))
 	}
 }
+
+// stopByHand ends a walk a person stopped or closed (`plans stop|close`): failed, with who stopped it and why
+// kept as the delivery's owner keeps its own stop, so the walk ends with outcome stopped, not failed (novox/hq
+// ADR 0308 decision 1).
+func stopByHand(p *inventory.Plan, how, by, why string) {
+	p.State = inventory.PlanFailed
+	p.Note = how + " by hand at tier " + fmt.Sprint(p.Tier) + ": " + why
+	if p.Delivery == nil {
+		p.Delivery = &inventory.PlanDelivery{}
+	}
+	p.Delivery.Stopped, p.Delivery.StoppedWhy = by, why
+}

cmd/mesh-controller/replay327_test.go

@@ -84,8 +84,12 @@ func asAProcess(t *testing.T, url string) {
 	t.Setenv(broker.CertificateVar, "")
 }
 
-// closedNames are the names of the connections the bus saw closed.
-func closedNames(t *testing.T, bus *server.Server) []string {
+// closedNames are the names of the connections the bus saw closed, waited for by want's own name: the
+// bus can register another connection's close first (the test's own setup connection, say), so returning
+// on the first non-empty list names whichever closed first, not necessarily the one being waited for
+// (novox/hq issue 543). closedNames instead waits until want itself appears among the closed connections,
+// or the deadline passes, and returns whatever names it last saw either way.
+func closedNames(t *testing.T, bus *server.Server, want string) []string {
 	t.Helper()
 	deadline := time.Now().Add(5 * time.Second)
 	var names []string
@@ -95,10 +99,14 @@ func closedNames(t *testing.T, bus *server.Server) []string {
 			t.Fatal(err)
 		}
 		names = names[:0]
+		found := false
 		for _, c := range connz.Conns {
 			names = append(names, c.Name)
+			if c.Name == want {
+				found = true
+			}
 		}
-		if len(names) > 0 {
+		if found {
 			return names
 		}
 		time.Sleep(50 * time.Millisecond)

cmd/mesh-controller/seat_dependencies_test.go

@@ -15,7 +15,8 @@ import (
 func serviceManagerHolder() catalogue.Manifest {
 	return catalogue.Manifest{Module: "systemd", Version: "1",
 		Claims: []catalogue.Claim{{Name: catalogue.ServiceManagerSeat, Scope: catalogue.ScopeNode,
-			Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal"}}},
+			Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal",
+				"reset-failed", "wanted-by", "unlink-dangling"}}},
 		Resources: []map[string]any{{"id": "systemd", "type": "package", "package": "systemd"}}}
 }
 

cmd/mesh-controller/walk_said.go

@@ -0,0 +1,334 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"slices"
+	"sort"
+	"time"
+
+	"github.com/novox/mesh-controller/internal/broker"
+	"github.com/novox/mesh-controller/internal/catalogue"
+	"github.com/novox/mesh-controller/internal/inventory"
+)
+
+// What a walk touches, its bound and its outcome (novox/hq ADR 0308 decision 1, decision 5): said in
+// `plan-moved` on the save that starts the walk and the save that ends it, beside the walk whole, for the holder
+// of the operator's channel to hold what the walk touches while it runs and tell its result once.
+//
+// **What a walk touches** is every module it moves on every machine it sends it to, and every module a moved
+// tool runner (node-tools) or node-engine (mesh-host) carries on that machine: what restarts there. At the start
+// that is what the walk will send — each module of its tiers whose policy rolls it out, on every machine running
+// it; at the end it is what it reached — the machines each module was sent to, first and rest, and what a gated
+// send carried with it.
+//
+// **Its bound** is twice the largest delivery budget among the walk's deliveries (deliveryBudgets: a core
+// module's ten minutes, a leaf module's budget in force), and fifteen minutes, not doubled, for a walk none of
+// whose deliveries has a budget: a release plan (builds waiting for a person's gate), a walk whose every module's
+// policy records rather than rolls out (held for a person, ADR 0282 decision 1), or a walk kept without a class.
+
+// walkNoBudgetBound is the bound of a walk with no budget (ADR 0308 decision 5): not doubled.
+const walkNoBudgetBound = 15 * time.Minute
+
+// budgetNone is the budget class of a walk none of whose deliveries has a budget.
+const budgetNone = "none"
+
+// walkSaid is what `plan-moved` adds on a walk's start and end, beside the walk whole.
+type walkSaid struct {
+	Walk  string `json:"walk"`
+	Phase string `json:"phase"`
+	// Touches is, per machine, the modules the walk moves or reaches there and what a moved tool runner or
+	// node-engine carries there; never null.
+	Touches []walkTouch `json:"touches"`
+	// Outcome is on the end only: delivered, failed or stopped.
+	Outcome string `json:"outcome,omitempty"`
+	// BoundSeconds and BudgetClass are said on both, read from the walk's class at the start.
+	BoundSeconds int    `json:"bound_seconds"`
+	BudgetClass  string `json:"budget_class"`
+	// StartedAt is when the walk was said started, on both; EndedAt when it was said ended, on the end: the
+	// bound runs from StartedAt, whenever the event is heard.
+	StartedAt *time.Time `json:"started_at,omitempty"`
+	EndedAt   *time.Time `json:"ended_at,omitempty"`
+}
+
+// walkTouch is what a walk touches on one machine.
+type walkTouch struct {
+	Machine string   `json:"machine"`
+	Modules []string `json:"modules"`
+	// Carried names those of Modules that are there only because a moved tool runner or node-engine carries
+	// them: what restarts with it, not what the walk builds.
+	Carried []string `json:"carried,omitempty"`
+}
+
+// planMovedBody is `plan-moved`'s body: the walk whole, as before, and on its start and end what it touches.
+type planMovedBody struct {
+	inventory.Plan
+	*walkSaid
+}
+
+// walkFacts is what the touches are read from: the controller's inventory.
+type walkFacts interface {
+	Running(ctx context.Context, module string) ([]string, error)
+	UpgradeOf(ctx context.Context, module string) (inventory.Upgrade, error)
+	Assigned(ctx context.Context, node string) ([]string, error)
+	SentBuilds(ctx context.Context, node string) (map[string]string, bool, error)
+	Catalogue(ctx context.Context) (map[string]catalogue.Manifest, error)
+}
+
+// sayWalk is what `plan-moved` adds to the save that started or ended the walk; nil on every other save. A fact
+// that cannot be read is said on the controller's log and left out, never in the way of the event: a walk said
+// with fewer touches is held less, never longer.
+func sayWalk(ctx context.Context, facts walkFacts, p inventory.Plan) *walkSaid {
+	if p.WalkSaid == "" {
+		return nil
+	}
+	w := &walkSaid{Walk: p.ID, Phase: p.WalkSaid}
+	if p.Times != nil {
+		w.StartedAt = p.Times.Started
+		if p.WalkSaid == inventory.WalkEnded {
+			w.EndedAt, w.Outcome = p.Times.Ended, p.Outcome()
+		}
+	}
+	read := readWalkFacts(ctx, facts, p)
+	w.BudgetClass = walkBudgetClass(p, read.rollsOut)
+	w.BoundSeconds = int(walkBound(w.BudgetClass) / time.Second)
+	var moved map[string][]string
+	if p.WalkSaid == inventory.WalkStarted {
+		moved = walkSends(p, read.running, read.rollsOut)
+	} else {
+		moved = walkReached(p, read.running)
+	}
+	var shelf map[string]catalogue.Manifest
+	if len(moved[broker.RuntimeModule]) > 0 {
+		// Which modules the tool runner serves is the catalogue's: read only when the walk moves it.
+		shelf = read.shelf()
+	}
+	w.Touches = touchesOf(moved, read.onMachine(moved), shelf)
+	return w
+}
+
+// walkBudgetClass is the largest budget class among the walk's deliveries: its class read at the cut when one of
+// its modules rolls out, and none when it has no budget.
+func walkBudgetClass(p inventory.Plan, rollsOut func(string) bool) string {
+	if p.Release != nil || p.Times == nil {
+		return budgetNone
+	}
+	if _, budgeted := deliveryBudgets[p.Times.Class]; !budgeted {
+		return budgetNone
+	}
+	for _, tier := range p.Tiers {
+		for _, m := range tier {
+			if rollsOut(m) {
+				return p.Times.Class
+			}
+		}
+	}
+	return budgetNone
+}
+
+// walkBound is a walk's bound by its budget class: twice its budget, or fifteen minutes with none.
+func walkBound(class string) time.Duration {
+	if b, ok := deliveryBudgets[class]; ok {
+		return 2 * b
+	}
+	return walkNoBudgetBound
+}
+
+// walkSends is what a walk will send at its start, per module the machines it goes to: each module of its tiers
+// whose policy rolls it out, on every machine running it (for a release plan, those of its order).
+func walkSends(p inventory.Plan, running func(string) []string, rollsOut func(string) bool) map[string][]string {
+	out := map[string][]string{}
+	for _, tier := range p.Tiers {
+		for _, m := range tier {
+			if s := p.Modules[m]; s != nil && s.State == planDeleted {
+				continue
+			}
+			if p.Release == nil && !rollsOut(m) {
+				continue
+			}
+			for _, n := range running(m) {
+				if p.Release != nil && !slices.Contains(p.Release.Order, n) {
+					continue
+				}
+				out[m] = appendNew(out[m], n)
+			}
+		}
+	}
+	return out
+}
+
+// walkReached is what a walk sent by its end, per module the machines it reached: its first machines, its rest,
+// and every module a gated send carried with it. A release plan reached the machines it walked: those done and
+// the one being judged.
+func walkReached(p inventory.Plan, running func(string) []string) map[string][]string {
+	out := map[string][]string{}
+	carried := func(g *inventory.PlanGate) {
+		if g == nil {
+			return
+		}
+		for _, c := range g.Carried {
+			out[c.Module] = appendNew(out[c.Module], c.Node)
+		}
+	}
+	if r := p.Release; r != nil {
+		reached := append([]string{}, r.Done...)
+		if r.Gate != nil {
+			reached = appendNew(reached, r.Gate.Machines...)
+			carried(r.Gate)
+		}
+		for _, tier := range p.Tiers {
+			for _, m := range tier {
+				for _, n := range running(m) {
+					if slices.Contains(reached, n) {
+						out[m] = appendNew(out[m], n)
+					}
+				}
+			}
+		}
+		return out
+	}
+	for m, s := range p.Modules {
+		if s == nil {
+			continue
+		}
+		out[m] = appendNew(out[m], s.First...)
+		for n := range s.Rest {
+			out[m] = appendNew(out[m], n)
+		}
+		carried(s.Gate)
+		if len(out[m]) == 0 {
+			delete(out, m)
+		}
+	}
+	return out
+}
+
+// touchesOf turns what a walk moves, per module, into what it touches, per machine: the modules it moves there,
+// and, where it moves the tool runner, every module there whose tools it serves, and where it moves the
+// node-engine, every module there. Sorted by machine and module.
+func touchesOf(moved map[string][]string, on map[string][]string, shelf map[string]catalogue.Manifest) []walkTouch {
+	byMachine := map[string][]string{}
+	for m, machines := range moved {
+		for _, n := range machines {
+			byMachine[n] = appendNew(byMachine[n], m)
+		}
+	}
+	out := make([]walkTouch, 0, len(byMachine))
+	for n, modules := range byMachine {
+		t := walkTouch{Machine: n, Modules: modules}
+		engine, runner := slices.Contains(modules, hostModule), slices.Contains(modules, broker.RuntimeModule)
+		if engine || runner {
+			for _, m := range on[n] {
+				if slices.Contains(t.Modules, m) || (!engine && !servesTools(shelf[m])) {
+					continue
+				}
+				t.Modules = append(t.Modules, m)
+				t.Carried = append(t.Carried, m)
+			}
+		}
+		sort.Strings(t.Modules)
+		sort.Strings(t.Carried)
+		out = append(out, t)
+	}
+	sort.Slice(out, func(i, j int) bool { return out[i].Machine < out[j].Machine })
+	return out
+}
+
+// servesTools says the tool runner serves something of this module: a bundle it loads entrypoints from, or the
+// module's own tools.
+func servesTools(m catalogue.Manifest) bool {
+	if len(m.Tools) > 0 {
+		return true
+	}
+	for _, b := range m.Bundles {
+		if len(b.Loads) > 0 {
+			return true
+		}
+	}
+	return false
+}
+
+// walkRead is the facts a walk's touches are worked out from, read once per event.
+type walkRead struct {
+	running   func(string) []string
+	rollsOut  func(string) bool
+	onMachine func(moved map[string][]string) map[string][]string
+	shelf     func() map[string]catalogue.Manifest
+}
+
+// readWalkFacts reads what the walk's touches need. Without facts (a test, a command with no store), nothing runs
+// anywhere and every module rolls out: the touches are then what the walk itself recorded.
+func readWalkFacts(ctx context.Context, facts walkFacts, p inventory.Plan) walkRead {
+	cantRead := func(what string, err error) {
+		fmt.Fprintf(os.Stderr, "%s: %s cannot be read for what the walk touches: %v\n", p.ID, what, err)
+	}
+	r := walkRead{
+		running:   func(string) []string { return nil },
+		rollsOut:  func(string) bool { return true },
+		onMachine: func(map[string][]string) map[string][]string { return nil },
+		shelf:     func() map[string]catalogue.Manifest { return nil },
+	}
+	if facts == nil {
+		return r
+	}
+	running := map[string][]string{}
+	r.running = func(m string) []string {
+		if on, read := running[m]; read {
+			return on
+		}
+		on, err := facts.Running(ctx, m)
+		if err != nil {
+			cantRead("where "+m+" runs", err)
+		}
+		running[m] = on
+		return on
+	}
+	rolls := map[string]bool{}
+	r.rollsOut = func(m string) bool {
+		if yes, read := rolls[m]; read {
+			return yes
+		}
+		u, err := facts.UpgradeOf(ctx, m)
+		if err != nil {
+			cantRead(m+"'s policy", err)
+		}
+		// A policy that cannot be read is taken to roll out: the walk is then held more, never less.
+		rolls[m] = err != nil || u.RollOut
+		return rolls[m]
+	}
+	r.onMachine = func(moved map[string][]string) map[string][]string {
+		out := map[string][]string{}
+		for _, core := range []string{hostModule, broker.RuntimeModule} {
+			for _, n := range moved[core] {
+				if _, read := out[n]; read {
+					continue
+				}
+				var there []string
+				if sent, known, err := facts.SentBuilds(ctx, n); err != nil {
+					cantRead("what "+n+" was sent", err)
+				} else if known {
+					for m := range sent {
+						there = append(there, m)
+					}
+				}
+				if assigned, err := facts.Assigned(ctx, n); err != nil {
+					cantRead("what "+n+" is assigned", err)
+				} else {
+					there = appendNew(there, assigned...)
+				}
+				sort.Strings(there)
+				out[n] = there
+			}
+		}
+		return out
+	}
+	r.shelf = func() map[string]catalogue.Manifest {
+		shelf, err := facts.Catalogue(ctx)
+		if err != nil {
+			cantRead("the catalogue", err)
+		}
+		return shelf
+	}
+	return r
+}

cmd/mesh-controller/walk_said_test.go

@@ -0,0 +1,514 @@
+package main
+
+import (
+	"context"
+	"encoding/json"
+	"os"
+	"reflect"
+	"testing"
+	"time"
+
+	"github.com/nats-io/nats.go"
+
+	"github.com/novox/mesh-controller/internal/broker"
+	"github.com/novox/mesh-controller/internal/catalogue"
+	"github.com/novox/mesh-controller/internal/inventory"
+	"github.com/novox/mesh-controller/internal/link"
+	"github.com/novox/mesh-controller/internal/testbus"
+)
+
+// fakeWalkFacts is the inventory as far as a walk's touches read it.
+type fakeWalkFacts struct {
+	running  map[string][]string
+	records  map[string]bool // modules whose policy records rather than rolls out
+	sent     map[string]map[string]string
+	assigned map[string][]string
+	shelf    map[string]catalogue.Manifest
+}
+
+func (f fakeWalkFacts) Running(_ context.Context, m string) ([]string, error) {
+	return f.running[m], nil
+}
+func (f fakeWalkFacts) UpgradeOf(_ context.Context, m string) (inventory.Upgrade, error) {
+	return inventory.Upgrade{RollOut: !f.records[m]}, nil
+}
+func (f fakeWalkFacts) Assigned(_ context.Context, n string) ([]string, error) {
+	return f.assigned[n], nil
+}
+func (f fakeWalkFacts) SentBuilds(_ context.Context, n string) (map[string]string, bool, error) {
+	s, ok := f.sent[n]
+	return s, ok, nil
+}
+func (f fakeWalkFacts) Catalogue(context.Context) (map[string]catalogue.Manifest, error) {
+	return f.shelf, nil
+}
+
+// theMesh is four machines: the tool runner on each, messenger and mesh-issues on novox, gitea on ace.
+func theMesh() fakeWalkFacts {
+	return fakeWalkFacts{
+		running: map[string][]string{
+			broker.RuntimeModule: {"ace", "g14", "novox", "shanks"},
+			"messenger":          {"novox"},
+			"gitea":              {"ace"},
+			"plex":               {"ace"},
+		},
+		sent: map[string]map[string]string{
+			"novox": {broker.RuntimeModule: "c0", "messenger": "c1", "mesh-issues": "c2", "postgres": "c3"},
+			"ace":   {broker.RuntimeModule: "c0", "gitea": "c4"},
+		},
+		assigned: map[string][]string{"g14": {broker.RuntimeModule, "desktop"}, "shanks": {broker.RuntimeModule}},
+		shelf: map[string]catalogue.Manifest{
+			"messenger":   {Module: "messenger", Tools: []string{"notify"}},
+			"mesh-issues": {Module: "mesh-issues", Bundles: []catalogue.Bundle{{Name: "tools", Loads: []string{"main"}}}},
+			"postgres":    {Module: "postgres"},
+			"gitea":       {Module: "gitea", Tools: []string{"gitea_api"}},
+			"desktop":     {Module: "desktop", Tools: []string{"notify_send"}},
+		},
+	}
+}
+
+func walkOfTiers(class string, tiers ...[]string) inventory.Plan {
+	cut := time.Date(2026, 10, 12, 11, 0, 0, 0, time.UTC)
+	started := cut.Add(time.Second)
+	p := inventory.Plan{ID: "plan-308", State: inventory.PlanBuilding, Tiers: tiers,
+		Modules: map[string]*inventory.PlanModule{}, Times: &inventory.PlanTimes{Cut: &cut, Class: class, Started: &started}}
+	for _, tier := range tiers {
+		for _, m := range tier {
+			p.Modules[m] = &inventory.PlanModule{}
+		}
+	}
+	p.WalkSaid = inventory.WalkStarted
+	return p
+}
+
+// novox/hq ADR 0308 How it is checked §1: the start names the modules the walk moves and the machines it sends
+// them to, and every module a moved tool runner carries there.
+func TestAWalksStartNamesWhatItTouchesWithWhatTheToolRunnerCarries(t *testing.T) {
+	p := walkOfTiers(inventory.ClassCore, []string{broker.RuntimeModule}, []string{"messenger"})
+	w := sayWalk(t.Context(), theMesh(), p)
+	if w == nil || w.Walk != "plan-308" || w.Phase != inventory.WalkStarted || w.Outcome != "" {
+		t.Fatalf("the start is said: %+v", w)
+	}
+	want := []walkTouch{
+		{Machine: "ace", Modules: []string{"gitea", broker.RuntimeModule}, Carried: []string{"gitea"}},
+		{Machine: "g14", Modules: []string{"desktop", broker.RuntimeModule}, Carried: []string{"desktop"}},
+		// postgres serves no tools: the tool runner does not carry it.
+		{Machine: "novox", Modules: []string{"mesh-issues", "messenger", broker.RuntimeModule}, Carried: []string{"mesh-issues"}},
+		{Machine: "shanks", Modules: []string{broker.RuntimeModule}},
+	}
+	if !reflect.DeepEqual(w.Touches, want) {
+		t.Fatalf("touches:\n got %+v\nwant %+v", w.Touches, want)
+	}
+	if w.BudgetClass != inventory.ClassCore || w.BoundSeconds != 1200 || w.StartedAt == nil {
+		t.Fatalf("a core walk is bound at 20 minutes: %+v", w)
+	}
+}
+
+// A moved node-engine carries every module on its machine; a module whose policy records is not sent, and not
+// touched.
+func TestAMovedNodeEngineCarriesEverythingOnItsMachine(t *testing.T) {
+	f := theMesh()
+	f.running[hostModule] = []string{"novox"}
+	f.records = map[string]bool{"plex": true}
+	p := walkOfTiers(inventory.ClassCore, []string{hostModule, "plex"})
+	w := sayWalk(t.Context(), f, p)
+	want := []walkTouch{{Machine: "novox",
+		Modules: []string{"mesh-host", "mesh-issues", "messenger", "node-tools", "postgres"},
+		Carried: []string{"mesh-issues", "messenger", "node-tools", "postgres"}}}
+	if !reflect.DeepEqual(w.Touches, want) {
+		t.Fatalf("touches:\n got %+v\nwant %+v", w.Touches, want)
+	}
+}
+
+// The end names what the walk reached — its first machines, its rest, what a gated send carried — and its
+// outcome; the modules a reached tool runner carries are touched there too.
+func TestAWalksEndNamesWhatItReachedAndItsOutcome(t *testing.T) {
+	p := walkOfTiers(inventory.ClassCore, []string{broker.RuntimeModule}, []string{"messenger"})
+	ended := p.Times.Started.Add(4 * time.Minute)
+	p.Times.Ended = &ended
+	p.State, p.WalkSaid = inventory.PlanDone, inventory.WalkEnded
+	p.Modules[broker.RuntimeModule] = &inventory.PlanModule{First: []string{"shanks"},
+		Rest: map[string]inventory.SentDeclaration{"novox": {}},
+		Gate: &inventory.PlanGate{Carried: []inventory.CarriedMove{{Module: "gitea", Node: "shanks"}}}}
+	// messenger was built and found unchanged: no move, not reached.
+	p.Modules["messenger"] = &inventory.PlanModule{Why: "no move"}
+	w := sayWalk(t.Context(), theMesh(), p)
+	if w.Phase != inventory.WalkEnded || w.Outcome != inventory.WalkDelivered || w.EndedAt == nil {
+		t.Fatalf("the end is said with its outcome: %+v", w)
+	}
+	want := []walkTouch{
+		{Machine: "novox", Modules: []string{"mesh-issues", "messenger", broker.RuntimeModule},
+			Carried: []string{"mesh-issues", "messenger"}},
+		{Machine: "shanks", Modules: []string{"gitea", broker.RuntimeModule}},
+	}
+	if !reflect.DeepEqual(w.Touches, want) {
+		t.Fatalf("touches:\n got %+v\nwant %+v", w.Touches, want)
+	}
+	for outcome, end := range map[string]func(*inventory.Plan){
+		inventory.WalkFailed: func(p *inventory.Plan) { p.State = inventory.PlanFailed },
+		inventory.WalkStopped: func(p *inventory.Plan) {
+			p.State, p.Delivery = inventory.PlanFailed, &inventory.PlanDelivery{Stopped: "a person"}
+		},
+	} {
+		q := p
+		end(&q)
+		if got := sayWalk(t.Context(), theMesh(), q).Outcome; got != outcome {
+			t.Errorf("outcome %q, want %q", got, outcome)
+		}
+	}
+}
+
+// novox/hq ADR 0308 How it is checked §1 and decision 5: the bound is twice the largest budget in force among
+// the walk's deliveries — 20 minutes for a core walk, twice the leaf budget for a leaf walk — and 15 minutes, not
+// doubled, for a walk none of whose deliveries has a budget.
+func TestAWalksBoundIsTwiceItsBudgetOrFifteenMinutesWithNone(t *testing.T) {
+	f := theMesh()
+	f.records = map[string]bool{"plex": true}
+	release := walkOfTiers("", []string{"gitea"})
+	release.Times, release.Release = &inventory.PlanTimes{}, &inventory.PlanRelease{Order: []string{"ace"}}
+	for name, c := range map[string]struct {
+		p     inventory.Plan
+		class string
+		bound int
+	}{
+		"core":                 {walkOfTiers(inventory.ClassCore, []string{"messenger"}), inventory.ClassCore, 1200},
+		"leaf":                 {walkOfTiers(inventory.ClassLeaf, []string{"messenger"}), inventory.ClassLeaf, int(2 * deliveryBudgets[inventory.ClassLeaf] / time.Second)},
+		"held for a person":    {walkOfTiers(inventory.ClassLeaf, []string{"plex"}), budgetNone, 900},
+		"a release":            {release, budgetNone, 900},
+		"kept without a class": {walkOfTiers("", []string{"messenger"}), budgetNone, 900},
+	} {
+		w := sayWalk(t.Context(), f, c.p)
+		if w.BudgetClass != c.class || w.BoundSeconds != c.bound {
+			t.Errorf("%s: %s bound %ds, want %s %ds", name, w.BudgetClass, w.BoundSeconds, c.class, c.bound)
+		}
+	}
+	// The leaf budget in force is three minutes (ADR 0304 decision 4): a leaf walk is bound at six.
+	if deliveryBudgets[inventory.ClassLeaf] == 3*time.Minute {
+		if w := sayWalk(t.Context(), f, walkOfTiers(inventory.ClassLeaf, []string{"messenger"})); w.BoundSeconds != 360 {
+			t.Errorf("a leaf walk at a three-minute budget is bound at 360 s: %d", w.BoundSeconds)
+		}
+	}
+}
+
+// plan-moved's body: the walk whole as before, and on its start the walk's fields beside it; on any other save
+// none of them.
+func TestPlanMovedCarriesTheWalkWholeAndOnItsStartWhatItTouches(t *testing.T) {
+	p := walkOfTiers(inventory.ClassLeaf, []string{"messenger"})
+	body, err := json.Marshal(planMovedBody{Plan: p, walkSaid: sayWalk(t.Context(), theMesh(), p)})
+	if err != nil {
+		t.Fatal(err)
+	}
+	var said map[string]any
+	if err := json.Unmarshal(body, &said); err != nil {
+		t.Fatal(err)
+	}
+	for _, k := range []string{"id", "state", "tiers", "modules", "times", "walk", "phase", "touches", "bound_seconds", "budget_class", "started_at"} {
+		if _, ok := said[k]; !ok {
+			t.Errorf("plan-moved lacks %q: %s", k, body)
+		}
+	}
+	if _, ok := said["outcome"]; ok {
+		t.Errorf("a start says no outcome: %s", body)
+	}
+	if said["walk"] != "plan-308" || said["phase"] != "started" || said["budget_class"] != "leaf" {
+		t.Errorf("the walk's fields: %s", body)
+	}
+	p.WalkSaid = ""
+	body, _ = json.Marshal(planMovedBody{Plan: p, walkSaid: sayWalk(t.Context(), theMesh(), p)})
+	said = map[string]any{}
+	_ = json.Unmarshal(body, &said)
+	for _, k := range []string{"walk", "phase", "touches", "bound_seconds"} {
+		if _, ok := said[k]; ok {
+			t.Errorf("a save neither starting nor ending the walk says %q: %s", k, body)
+		}
+	}
+	// A walk that touches nothing says an empty list, never null.
+	q := walkOfTiers(inventory.ClassLeaf, []string{"nobody-runs-this"})
+	body, _ = json.Marshal(planMovedBody{Plan: q, walkSaid: sayWalk(t.Context(), theMesh(), q)})
+	said = map[string]any{}
+	_ = json.Unmarshal(body, &said)
+	if touches, ok := said["touches"].([]any); !ok || len(touches) != 0 {
+		t.Errorf("touches nothing: %s", body)
+	}
+}
+
+// Live, with the store and a bus: a walk let go by the delivery's verb is said started with what it touches and
+// its bound, and stopped by the verb is said ended, stopped (novox/hq ADR 0308 How it is checked §1).
+func TestAWalkLetGoAndStoppedByVerbsIsSaidStartedAndEnded(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	next := planMovedHeard(t)
+	register(t, open, catalogue.Manifest{Module: "app", Version: "1"})
+	if _, err := assign(ctx, open, "anchor", "app"); err != nil {
+		t.Fatal(err)
+	}
+	cut := time.Now().UTC()
+	waiting := inventory.Plan{ID: "plan-308-live", Repository: "novox/mesh-catalog", Branch: "main", Commit: "c8c8c8c8",
+		Created: cut, State: inventory.PlanBuilding, Tiers: [][]string{{"app"}},
+		Modules:  map[string]*inventory.PlanModule{"app": {}},
+		Delivery: &inventory.PlanDelivery{Awaits: catalogue.DeliverySeat},
+		Times:    &inventory.PlanTimes{Cut: &cut, Class: inventory.ClassLeaf}}
+	if err := open.inventory.SavePlan(ctx, &waiting); err != nil {
+		t.Fatal(err)
+	}
+	if err := deliveryCommand(ctx, []string{"go", waiting.ID, "--why", "its turn"}); err != nil {
+		t.Fatal(err)
+	}
+	started := next(inventory.WalkStarted)
+	touches, _ := json.Marshal(started["touches"])
+	if started["walk"] != waiting.ID || string(touches) != `[{"machine":"anchor","modules":["app"]}]` ||
+		started["budget_class"] != inventory.ClassLeaf ||
+		started["bound_seconds"] != float64(2*deliveryBudgets[inventory.ClassLeaf]/time.Second) {
+		t.Fatalf("the start: %v", started)
+	}
+	if err := deliveryCommand(ctx, []string{"stop", waiting.ID, "--why", "a test", "--by", "a person"}); err != nil {
+		t.Fatal(err)
+	}
+	ended := next(inventory.WalkEnded)
+	touches, _ = json.Marshal(ended["touches"])
+	if ended["walk"] != waiting.ID || ended["outcome"] != inventory.WalkStopped || string(touches) != `[]` {
+		t.Fatalf("the end, which sent nothing: %v", ended)
+	}
+}
+
+// planMovedHeard raises a bus of the test's own, points the verbs' hand-act connection at it, and returns what
+// waits for the next plan-moved said with the given phase, failing the test when none comes within 5 s.
+func planMovedHeard(t *testing.T) func(phase string) map[string]any {
+	t.Helper()
+	js, err := broker.Dial(testbus.URL(t))
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(js.Close)
+	if err := broker.AssertMeshStreams(js); err != nil {
+		t.Fatal(err)
+	}
+	before := handActConn
+	handActConn = js.Conn()
+	t.Cleanup(func() { handActConn = before })
+	heard := make(chan *nats.Msg, 64)
+	sub, err := js.Conn().ChanSubscribe(link.SeatEventSubject(link.MeshControllerSeat, link.KeyPlanMoved), heard)
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(func() { _ = sub.Unsubscribe() })
+	return func(phase string) map[string]any {
+		t.Helper()
+		deadline := time.After(5 * time.Second)
+		for {
+			select {
+			case m := <-heard:
+				var said map[string]any
+				if err := json.Unmarshal(m.Data, &said); err != nil {
+					t.Fatal(err)
+				}
+				if said["phase"] == phase {
+					return said
+				}
+			case <-deadline:
+				t.Fatalf("no walk was said %s", phase)
+			}
+		}
+	}
+}
+
+// Live, with the store and a bus: a walk a person stops with `plans stop` is said ended, outcome stopped, by the
+// verb itself, and is kept stopped by that person; `plans close` ends one the same way (novox/hq ADR 0308
+// decision 1, review 15 on mesh-controller#247).
+func TestAWalkStoppedOrClosedByAPersonIsSaidEndedStopped(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	next := planMovedHeard(t)
+	register(t, open, catalogue.Manifest{Module: "app", Version: "1"})
+	if _, err := assign(ctx, open, "anchor", "app"); err != nil {
+		t.Fatal(err)
+	}
+	for _, verb := range []string{"stop", "close"} {
+		cut := time.Now().UTC()
+		walk := inventory.Plan{ID: "plan-308-" + verb, Repository: "novox/mesh-catalog", Branch: "main",
+			Commit: "c8c8c8c8", Created: cut, State: inventory.PlanBuilding, Tiers: [][]string{{"app"}},
+			Modules: map[string]*inventory.PlanModule{"app": {}},
+			Times:   &inventory.PlanTimes{Cut: &cut, Started: &cut, Class: inventory.ClassLeaf}}
+		if err := open.inventory.SavePlan(ctx, &walk); err != nil {
+			t.Fatal(err)
+		}
+		if err := plansCommand(ctx, []string{verb, walk.ID, "--why", "a test"}); err != nil {
+			t.Fatal(err)
+		}
+		ended := next(inventory.WalkEnded)
+		if ended["walk"] != walk.ID || ended["outcome"] != inventory.WalkStopped {
+			t.Fatalf("plans %s: the end is %v", verb, ended)
+		}
+		p, err := open.inventory.PlanByID(ctx, walk.ID)
+		if err != nil {
+			t.Fatal(err)
+		}
+		if p.Outcome() != inventory.WalkStopped || p.Delivery == nil || p.Delivery.StoppedWhy != "a test" {
+			t.Fatalf("plans %s kept the walk %s, %+v", verb, p.Outcome(), p.Delivery)
+		}
+	}
+}
+
+// Live, with the store and a bus: a failed walk retried with `plans retry` starts again, and the verb says its
+// start (novox/hq ADR 0308 decision 1, review 15 on mesh-controller#247).
+func TestAWalkRetriedByAPersonIsSaidStartedAgain(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	asksRecorded(t)
+	next := planMovedHeard(t)
+	twoTiers(t, open)
+	before := time.Now().UTC().Add(-time.Hour)
+	ended := before.Add(time.Minute)
+	failed := inventory.Plan{ID: "plan-308-retry", Repository: "novox/a", Branch: "main", Commit: "c0ffee",
+		Created: before, State: inventory.PlanFailed, Tier: 0, Tiers: [][]string{{"a"}, {"b"}},
+		Note: "a failed to build in tier 0",
+		Modules: map[string]*inventory.PlanModule{"a": {State: "failed", AskedAt: &before, Build: "build-1",
+			Why: link.KilledByHand}},
+		Times: &inventory.PlanTimes{Cut: &before, Started: &before, Ended: &ended, Class: inventory.ClassLeaf}}
+	if err := open.inventory.SavePlan(ctx, &failed); err != nil {
+		t.Fatal(err)
+	}
+	if err := plansCommand(ctx, []string{"retry", failed.ID}); err != nil {
+		t.Fatal(err)
+	}
+	started := next(inventory.WalkStarted)
+	if started["walk"] != failed.ID || started["budget_class"] != inventory.ClassLeaf {
+		t.Fatalf("the retried start: %v", started)
+	}
+}
+
+// Live, with the store and a bus: the release plan `upgrade release-backlog` opens is said started by the verb
+// (novox/hq ADR 0308 decision 1, review 15 on mesh-controller#247).
+func TestABacklogReleasedByAPersonIsSaidStarted(t *testing.T) {
+	b := aBacklog(t)
+	next := planMovedHeard(t)
+	if err := backlogCommand(t.Context(), "release-backlog", []string{"--why", "a test"}); err != nil {
+		t.Fatal(err)
+	}
+	started := next(inventory.WalkStarted)
+	if p := b.release(t); started["walk"] != p.ID {
+		t.Fatalf("the release's start: %v", started)
+	}
+}
+
+// asTyped runs a verb as the controller's command line runs it, through run, as a person's terminal would.
+func asTyped(t *testing.T, args ...string) error {
+	t.Helper()
+	was := os.Args
+	os.Args = append([]string{"mesh-controller"}, args...)
+	t.Cleanup(func() { os.Args = was })
+	err := run()
+	// run gives back the lease as the process would end; the test's process goes on, and takes it again.
+	theLease.mu.Lock()
+	theLease.held, theLease.kv, theLease.noBus = nil, nil, false
+	theLease.mu.Unlock()
+	return err
+}
+
+// aStartedWalkAsking keeps a live walk, said started, whose first tier asked a as build.
+func aStartedWalkAsking(t *testing.T, open *stores, id, build string, asked time.Time) inventory.Plan {
+	t.Helper()
+	walk := inventory.Plan{ID: id, Repository: "novox/a", Branch: "main", Commit: "c0ffee", Created: asked,
+		State: inventory.PlanBuilding, Tiers: [][]string{{"a"}, {"b"}},
+		Modules: map[string]*inventory.PlanModule{"a": {State: "asked", AskedAt: &asked, Build: build}},
+		Times:   &inventory.PlanTimes{Cut: &asked, Started: &asked, Class: inventory.ClassLeaf}}
+	if err := open.inventory.SavePlan(t.Context(), &walk); err != nil {
+		t.Fatal(err)
+	}
+	return walk
+}
+
+// Live, with the store and a bus: `cancel <build>` and `clear` fail the walk that asked the build, and the verb
+// says its end, failed (novox/hq ADR 0308 decision 1, review 21 on mesh-controller#247).
+func TestAWalkEndedByCancelOrClearIsSaidEnded(t *testing.T) {
+	_, ask := aBuildQueue(t)
+	open := aMesh(t)
+	next := planMovedHeard(t)
+	twoTiers(t, open)
+	for _, verb := range [][]string{{"cancel"}, {"clear"}} {
+		id := link.NewBuildID(time.Now())
+		ask(id, "https://forge.example/novox/a.git")
+		asked, _ := link.BuildAskedAt(id)
+		walk := aStartedWalkAsking(t, open, "plan-308-"+verb[0], id, asked)
+		args := verb
+		if verb[0] == "cancel" {
+			args = append(args, id)
+		}
+		if err := asTyped(t, args...); err != nil {
+			t.Fatal(err)
+		}
+		ended := next(inventory.WalkEnded)
+		if ended["walk"] != walk.ID || ended["outcome"] != inventory.WalkFailed {
+			t.Fatalf("%s: the end is %v", verb[0], ended)
+		}
+		// Ended, and so the next walk may be cut on the same repository.
+		p, _ := open.inventory.PlanByID(t.Context(), walk.ID)
+		if p.State != inventory.PlanFailed {
+			t.Fatalf("%s left the walk %s", verb[0], p.State)
+		}
+	}
+}
+
+// Live, with the store and a bus: `rebuild <module>` joining a failed walk sets it building again, and the verb
+// says its start (novox/hq ADR 0308 decision 1, review 21 on mesh-controller#247).
+func TestAWalkRestartedByARebuildIsSaidStarted(t *testing.T) {
+	open := aMesh(t)
+	asksRecorded(t)
+	next := planMovedHeard(t)
+	twoTiers(t, open)
+	before := time.Now().UTC().Add(-time.Hour)
+	ended := before.Add(time.Minute)
+	failed := inventory.Plan{ID: "plan-308-rebuild", Repository: "novox/a", Branch: "main", Commit: "c0ffee",
+		Created: before, State: inventory.PlanFailed, Tiers: [][]string{{"a"}, {"b"}},
+		Modules: map[string]*inventory.PlanModule{"a": {State: "failed", AskedAt: &before, Build: "build-1",
+			Why: link.CancelledByHand}},
+		Times: &inventory.PlanTimes{Cut: &before, Started: &before, Ended: &ended, Class: inventory.ClassLeaf}}
+	if err := open.inventory.SavePlan(t.Context(), &failed); err != nil {
+		t.Fatal(err)
+	}
+	if err := asTyped(t, "rebuild", "a"); err != nil {
+		t.Fatal(err)
+	}
+	if started := next(inventory.WalkStarted); started["walk"] != failed.ID {
+		t.Fatalf("the rebuilt walk's start: %v", started)
+	}
+}
+
+// Live, with the store: a walk a person stopped and then retried, by `plans retry` or by `rebuild`, walks again
+// without the stop, so when it fails again it ends failed, not stopped, and the search for the merge that
+// brought the failure is not kept from it (novox/hq ADR 0308 decision 1, review 21 on mesh-controller#247).
+func TestAWalkStoppedByHandAndRetriedEndsFailedWhenItFailsAgain(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	asksRecorded(t)
+	twoTiers(t, open)
+	for _, again := range [][]string{{"plans", "retry"}, {"rebuild", "a"}} {
+		before := time.Now().UTC().Add(-time.Hour)
+		walk := aStartedWalkAsking(t, open, "plan-308-again-"+again[0], "build-1", before)
+		if err := asTyped(t, "plans", "stop", walk.ID, "--why", "a test"); err != nil {
+			t.Fatal(err)
+		}
+		// The build asked before the stop fails after it.
+		p, _ := open.inventory.PlanByID(ctx, walk.ID)
+		p.Modules["a"].State, p.Modules["a"].Why = "failed", "it broke"
+		if err := open.inventory.SavePlan(ctx, &p); err != nil {
+			t.Fatal(err)
+		}
+		args := again
+		if again[0] == "plans" {
+			args = append(append([]string(nil), again...), walk.ID)
+		}
+		if err := asTyped(t, args...); err != nil {
+			t.Fatal(err)
+		}
+		p, _ = open.inventory.PlanByID(ctx, walk.ID)
+		if p.State != inventory.PlanBuilding || (p.Delivery != nil && p.Delivery.Stopped != "") {
+			t.Fatalf("%s: the walk is %s and keeps its stop: %+v", again[0], p.State, p.Delivery)
+		}
+		asking, _ := link.BuildAskedAt(p.Modules["a"].Build)
+		planBuilt(ctx, open, "a", "c0ffee", "it broke again", asking, p.Modules["a"].Build)
+		if p, _ = open.inventory.PlanByID(ctx, walk.ID); p.State != inventory.PlanFailed || p.Outcome() != inventory.WalkFailed {
+			t.Fatalf("%s: failing again, the walk is %s and ends %s", again[0], p.State, p.Outcome())
+		}
+	}
+}

internal/catalogue/operators_machine_test.go

@@ -68,9 +68,10 @@ func TestFailedIsAnOptionalVerbOfTheServiceManager(t *testing.T) {
 	holder := func(serves ...string) Manifest {
 		return Manifest{Module: "systemd", Version: "1", Claims: []Claim{{Name: ServiceManagerSeat, Scope: ScopeNode, Serves: serves}}}
 	}
-	eight := []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal"}
+	eight := []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal",
+		"reset-failed", "wanted-by", "unlink-dangling"}
 	if err := CanHold(holder(eight...), seat); err != nil {
-		t.Fatalf("today's holder, without failed, is refused: %v", err)
+		t.Fatalf("a holder without failed is refused: %v", err)
 	}
 	if err := CanHold(holder(append(eight, "failed")...), seat); err != nil {
 		t.Fatalf("a holder serving failed is refused: %v", err)
@@ -81,7 +82,7 @@ func TestFailedIsAnOptionalVerbOfTheServiceManager(t *testing.T) {
 	if err := CanHold(holder(eight[1:]...), seat); err == nil || !strings.Contains(err.Error(), "does not serve units") {
 		t.Fatalf("a holder missing a required verb was accepted: %v", err)
 	}
-	optional := map[string]bool{"failed": true, "reset-failed": true, "wanted-by": true, "unlink-dangling": true}
+	optional := map[string]bool{"failed": true}
 	for _, v := range seat.Serves {
 		if v.Optional != optional[v.Name] {
 			t.Errorf("%s optional: %v", v.Name, v.Optional)
@@ -89,26 +90,35 @@ func TestFailedIsAnOptionalVerbOfTheServiceManager(t *testing.T) {
 	}
 }
 
-// **`reset-failed` and `wanted-by` join the seat optional** (novox/hq issue 332, ADR 0246 step 1): the
-// holder running today, serving the nine verbs, still holds the seat; a holder serving all eleven is not
-// refused; each replaces the shell command it names; and read back from the store's row they stay optional.
-func TestResetFailedAndWantedByAreOptionalVerbsOfTheServiceManager(t *testing.T) {
+// **`reset-failed`, `wanted-by` and `unlink-dangling` are required** (novox/hq issue 332, ADR 0246 step 3):
+// every holder serves them, so a holder serving only the nine verbs before them is refused by the verb it
+// lacks; a holder serving all twelve holds the seat; each replaces the shell command it names; and read
+// back from the store's row they stay required.
+func TestResetFailedWantedByAndUnlinkDanglingAreRequiredVerbsOfTheServiceManager(t *testing.T) {
 	defer UseSeats(DefaultSeats())
 	nine := []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal", "failed"}
+	all := append(slices.Clone(nine), "reset-failed", "wanted-by", "unlink-dangling")
 	holder := func(serves ...string) Manifest {
 		return Manifest{Module: "systemd", Version: "1", Claims: []Claim{{Name: ServiceManagerSeat, Scope: ScopeNode, Serves: serves}}}
 	}
+	refusedWithout := func(seat Seat) {
+		t.Helper()
+		for _, verb := range []string{"reset-failed", "wanted-by", "unlink-dangling"} {
+			serves := slices.DeleteFunc(slices.Clone(all), func(v string) bool { return v == verb })
+			if err := CanHold(holder(serves...), seat); err == nil || !strings.Contains(err.Error(), "does not serve "+verb) {
+				t.Errorf("a holder not serving %s holds the seat: %v", verb, err)
+			}
+		}
+	}
 	seat, _ := SeatNamed(ServiceManagerSeat)
-	if err := CanHold(holder(nine...), seat); err != nil {
-		t.Fatalf("today's holder, without the two verbs, is refused: %v", err)
+	if err := CanHold(holder(nine...), seat); err == nil {
+		t.Fatal("a holder serving only the nine verbs before issue 332 holds the seat")
 	}
-	if err := CanHold(holder(append(nine, "reset-failed", "wanted-by")...), seat); err != nil {
-		t.Fatalf("a holder serving both is refused: %v", err)
+	refusedWithout(seat)
+	if err := CanHold(holder(all...), seat); err != nil {
+		t.Fatalf("a holder serving all twelve is refused: %v", err)
 	}
-	if err := CanHold(holder(append(nine, "reset-failed", "wanted-by", "unlink-dangling")...), seat); err != nil {
-		t.Fatalf("a holder serving unlink-dangling too is refused: %v", err)
-	}
-	if err := CanHold(holder(append(nine, "why-started")...), seat); err == nil || !strings.Contains(err.Error(), "does not promise") {
+	if err := CanHold(holder(append(slices.Clone(all), "why-started")...), seat); err == nil || !strings.Contains(err.Error(), "does not promise") {
 		t.Fatalf("a verb the seat does not promise was accepted: %v", err)
 	}
 	replaces := map[string]string{"reset-failed": "systemctl reset-failed", "wanted-by": "systemctl list-dependencies --reverse",
@@ -118,6 +128,9 @@ func TestResetFailedAndWantedByAreOptionalVerbsOfTheServiceManager(t *testing.T)
 		if !ok {
 			continue
 		}
+		if v.Optional {
+			t.Errorf("%s is still optional", v.Name)
+		}
 		if !slices.Contains(v.Replaces, want) {
 			t.Errorf("%s does not say it replaces %q: %v", v.Name, want, v.Replaces)
 		}
@@ -148,8 +161,9 @@ func TestResetFailedAndWantedByAreOptionalVerbsOfTheServiceManager(t *testing.T)
 	}
 	UseSeats(rows)
 	seat, _ = SeatNamed(ServiceManagerSeat)
-	if err := CanHold(holder(nine...), seat); err != nil {
-		t.Fatalf("read back from the row, the two verbs are required: %v", err)
+	refusedWithout(seat)
+	if err := CanHold(holder(all...), seat); err != nil {
+		t.Fatalf("read back from the row, a holder serving all twelve is refused: %v", err)
 	}
 }
 
@@ -169,8 +183,9 @@ func TestAnOptionalVerbStaysOptionalInASetReadFromTheStore(t *testing.T) {
 	UseSeats(rows)
 	seat, _ := SeatNamed(ServiceManagerSeat)
 	holder := Manifest{Module: "systemd", Version: "1", Claims: []Claim{{Name: ServiceManagerSeat, Scope: ScopeNode,
-		Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal"}}}}
+		Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal",
+			"reset-failed", "wanted-by", "unlink-dangling"}}}}
 	if err := CanHold(holder, seat); err != nil {
-		t.Fatalf("a set read from rows refuses today's holder: %v", err)
+		t.Fatalf("a set read from rows refuses a holder without the optional failed: %v", err)
 	}
 }

internal/catalogue/seats.go

@@ -678,13 +678,13 @@ func serviceManagerVerbs() []Verb {
 			Replaces: []string{"systemctl --failed"}},
 		// **Clearing a failed record, and finding what starts a unit** (novox/hq issue 332): a unit whose
 		// file is gone stays failed in its manager until the record is reset, and what keeps asking for it
-		// is a dependency or an enable link no verb could show. Both optional while their holders catch up
-		// (ADR 0246 step 1); a later change requires them.
-		{Name: "reset-failed", Optional: true, Description: "Clear one unit's failed record in its manager — " +
+		// is a dependency or an enable link no verb could show. Required since every holder serves them
+		// (ADR 0246 step 3).
+		{Name: "reset-failed", Description: "Clear one unit's failed record in its manager — " +
 			"its failed state and its start-limit count — and answer its state after. It removes no file and " +
 			"starts nothing.",
 			Input: scoped(unit, []string{"unit"}), Replaces: []string{"systemctl reset-failed"}},
-		{Name: "wanted-by", Optional: true, Description: "What wants, requires or triggers one unit, read-only: the " +
+		{Name: "wanted-by", Description: "What wants, requires or triggers one unit, read-only: the " +
 			"manager's reverse dependencies (WantedBy, RequiredBy, UpheldBy, BoundBy, TriggeredBy and the rest) and " +
 			"every enable link naming it in the scope's configuration directories (*.wants, *.requires, *.upholds), " +
 			"each with where it points and whether it dangles — the account's own directory included in user scope.",
@@ -692,9 +692,9 @@ func serviceManagerVerbs() []Verb {
 			Replaces: []string{"systemctl list-dependencies --reverse", "systemctl show -p WantedBy",
 				"ls ~/.config/systemd/user/*.wants"}},
 		// **A dangling enable link removed on the person's word** (novox/hq issue 332): `systemctl disable`
-		// leaves a link whose unit file is gone, so the manager keeps asking for the unit. Optional until its
-		// holders serve it (ADR 0246 step 1).
-		{Name: "unlink-dangling", Optional: true, Description: "Remove the dangling enable links named for one " +
+		// leaves a link whose unit file is gone, so the manager keeps asking for the unit. Required since
+		// every holder serves it (ADR 0246 step 3).
+		{Name: "unlink-dangling", Description: "Remove the dangling enable links named for one " +
 			"unit — links in a *.wants, *.requires or *.upholds directory of the account's or the machine's own " +
 			"configuration whose target does not exist, which `disable` leaves once the unit's file is gone — on " +
 			"the person's word: `why` is required. Each is recorded (its path, its target, the reason) before it is " +

internal/inventory/plans.go

@@ -61,6 +61,10 @@ type Plan struct {
 	// Phases is the walk's time from its merge, phase by phase (ADR 0282 decision 6): never kept, worked out
 	// from the walk's own moments by whoever says the walk (`delivery walks`, `plan-moved`).
 	Phases *WalkPhases `json:"phases,omitempty"`
+	// WalkSaid is, on the save that started or ended the walk, which of the two it was (novox/hq ADR 0308
+	// decision 1): set by the save, never kept, read by whoever says the save (`plan-moved`). Empty on every
+	// other save.
+	WalkSaid string `json:"-"`
 }
 
 // PlanTimes are a walk's own moments beside its modules' (novox/hq ADR 0282 decision 6).
@@ -73,6 +77,10 @@ type PlanTimes struct {
 	// Class is the walk's module class, read at its cut: core when it moves a module on the controller's own
 	// path or the mesh's resolver, leaf otherwise (ADR 0282 decision 1).
 	Class string `json:"class,omitempty"`
+	// Started is when the walk was said started, and Ended when it was said ended (novox/hq ADR 0308 decision
+	// 1): each said once, on the save that marked it.
+	Started *time.Time `json:"started,omitempty"`
+	Ended   *time.Time `json:"ended,omitempty"`
 }
 
 // PlanCommit is one repository's commit a walk carries: the latest merge of its branch in the batch.
@@ -183,8 +191,8 @@ type PlanDelivery struct {
 	Go  *time.Time `json:"go,omitempty"`
 	By  string     `json:"by,omitempty"`
 	Why string     `json:"why,omitempty"`
-	// Stopped is who ended the walk through the delivery's owner, and StoppedWhy why: the walk is failed,
-	// and the delivery reads it as stopped, not as a build that failed.
+	// Stopped is who ended the walk, through the delivery's owner or by hand (`plans stop|close`), and StoppedWhy
+	// why: the walk is failed, and the delivery reads it as stopped, not as a build that failed.
 	Stopped    string `json:"stopped,omitempty"`
 	StoppedWhy string `json:"stopped_why,omitempty"`
 	// Merges is every merge the walk or batch answers (novox/hq ADR 0276): its own commits, and the earlier
@@ -236,10 +244,12 @@ func (p Plan) Waiting() bool {
 	return p.Delivery != nil && p.Delivery.Awaits != "" && p.Delivery.Go == nil
 }
 
-// PlanSaved is told every plan this process kept, after it is kept (novox/hq ADR 0239): the serving
-// controller says it on the bus as `plan-moved`. Nil in a command, which says nothing; whoever follows a
-// walk also asks for it, so a save made by a command is found by comparison.
-var PlanSaved func(Plan)
+// PlanSaved is told every plan this process kept, after it is kept, with the inventory that kept it (novox/hq
+// ADR 0239): the serving controller says it on the bus as `plan-moved`, and so does a command (the controller's
+// run installs it for every verb, novox/hq ADR 0308 decision 1), so the save that starts or ends a walk is said
+// whichever process made it. Nil says nothing; whoever follows a walk also asks for it, and finds an unsaid save
+// by comparison.
+var PlanSaved func(*Inventory, Plan)
 
 // ErrPlanMoved is a save against a plan written by somebody else since it was read.
 var ErrPlanMoved = errors.New("the plan was written by somebody else since it was read")
@@ -451,7 +461,7 @@ type MergeMove struct {
 // leaves a merge answered by two plans, nor a walk stopped whose merges were not moved). A plan written by
 // somebody else since it was read refuses the whole act with ErrPlanMoved. Each plan is said (PlanSaved) once
 // the transaction is committed, in order.
-func (i *Inventory) SavePlansMoving(ctx context.Context, plans []*Plan, moves []MergeMove) error {
+func (i *Inventory) SavePlansMoving(ctx context.Context, plans []*Plan, moves []MergeMove) (err error) {
 	epoch, err := i.actingEpoch(ctx)
 	if err != nil {
 		if len(plans) > 0 {
@@ -472,6 +482,20 @@ func (i *Inventory) SavePlansMoving(ctx context.Context, plans []*Plan, moves []
 		entered  time.Time
 	}
 	done := make([]written, len(plans))
+	// **The save that starts or ends a walk is marked** (novox/hq ADR 0308 decision 1), in the same write, and
+	// unmarked should the write not be made, so the next save marks it again.
+	marked := time.Now()
+	undo := make([]func(), 0, len(plans))
+	defer func() {
+		if err != nil {
+			for _, u := range undo {
+				u()
+			}
+		}
+	}()
+	for _, p := range plans {
+		undo = append(undo, p.markWalk(marked))
+	}
 	for n, p := range plans {
 		revision, entered, err := writePlan(ctx, tx, p, epoch)
 		if err != nil {
@@ -497,7 +521,7 @@ func (i *Inventory) SavePlansMoving(ctx context.Context, plans []*Plan, moves []
 			p.Epoch = 0
 		}
 		if PlanSaved != nil {
-			PlanSaved(*p)
+			PlanSaved(i, *p)
 		}
 	}
 	return nil

internal/inventory/seats_test.go

@@ -202,14 +202,15 @@ func TestASeatsVerbGainsTheArgumentsTheBinaryNames(t *testing.T) {
 		t.Fatal("failed was not added to the row")
 	}
 	// The optional mark is not stored; the working set read from the rows takes it from the compiled seat,
-	// so today's holder, which does not serve failed, still holds the seat.
+	// so a holder that does not serve the optional failed still holds the seat.
 	catalogue.UseSeats(seats)
 	defer catalogue.UseSeats(catalogue.DefaultSeats())
 	live, _ := catalogue.SeatNamed(catalogue.ServiceManagerSeat)
 	holder := catalogue.Manifest{Module: "systemd", Version: "1", Claims: []catalogue.Claim{{Name: catalogue.ServiceManagerSeat,
-		Scope: catalogue.ScopeNode, Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal"}}}}
+		Scope: catalogue.ScopeNode, Serves: []string{"units", "status", "start", "stop", "restart", "enable", "disable", "journal",
+			"reset-failed", "wanted-by", "unlink-dangling"}}}}
 	if err := catalogue.CanHold(holder, live); err != nil {
-		t.Fatalf("the seat read from the store refuses today's holder: %v", err)
+		t.Fatalf("the seat read from the store refuses a holder without the optional failed: %v", err)
 	}
 	// Seeding again changes nothing more.
 	before := verbs["journal"]

internal/inventory/walksaid.go

@@ -0,0 +1,81 @@
+package inventory
+
+import "time"
+
+// A walk says when it starts and when it ends (novox/hq ADR 0308 decision 1): the save that starts it and the
+// save that ends it are marked, so `plan-moved` names what the walk touches, its bound and its outcome on those
+// two saves, and on no other. The marks are kept in the walk's times, so a controller replaced mid-walk (a core
+// walk replaces it) neither says a start again nor misses the end.
+
+// The moments of a walk `plan-moved` names.
+const (
+	WalkStarted = "started"
+	WalkEnded   = "ended"
+)
+
+// The outcomes of an ended walk (ADR 0308 decision 1).
+const (
+	WalkDelivered = "delivered"
+	WalkFailed    = "failed"
+	WalkStopped   = "stopped"
+)
+
+// Live says the walk is walking: cut, not waiting for its delivery's word, and not ended.
+func (p Plan) Live() bool { return p.Open() && !p.Batch() && !p.Waiting() }
+
+// Ended says the walk is in a state it does not leave by itself: done, failed or superseded.
+func (p Plan) Ended() bool {
+	return p.State == PlanDone || p.State == PlanFailed || p.State == PlanSuperseded
+}
+
+// Outcome is how an ended walk ended: delivered when done; stopped when a person or the delivery's owner stopped
+// it, or a newer walk took it over; failed otherwise. Empty for a walk not ended.
+func (p Plan) Outcome() string {
+	switch {
+	case p.State == PlanDone:
+		return WalkDelivered
+	case p.State == PlanSuperseded:
+		return WalkStopped
+	case p.State == PlanFailed && p.Delivery != nil && p.Delivery.Stopped != "":
+		return WalkStopped
+	case p.State == PlanFailed:
+		return WalkFailed
+	}
+	return ""
+}
+
+// markWalk marks the save that starts or ends the walk, in its times and in WalkSaid, and returns what undoes
+// the mark should the save not be written. A walk starts on the first save that finds it live — when it is cut
+// and needs no word, or when it is let go — which is before its first tier is asked, and so before anything is
+// sent: what it restarts is held from its first send on. It starts again when a failed walk is retried. It ends
+// on the first save that finds it ended after it started; one that ends without ever starting (a batch that
+// moved nothing, a walk stopped while it waited for its word) touched nothing and says neither. A walk kept
+// before its times were (ADR 0282 decision 6) is not marked; a release plan is, its times holding only these.
+func (p *Plan) markWalk(now time.Time) (undo func()) {
+	p.WalkSaid = ""
+	if p.Batch() || (p.Times == nil && p.Release == nil) {
+		return func() {}
+	}
+	var was *PlanTimes
+	if p.Times != nil {
+		kept := *p.Times
+		was = &kept
+	}
+	times := PlanTimes{}
+	if p.Times != nil {
+		times = *p.Times
+	}
+	at := now.UTC()
+	switch {
+	case p.Live() && (times.Started == nil || times.Ended != nil):
+		times.Started, times.Ended = &at, nil
+		p.WalkSaid = WalkStarted
+	case p.Ended() && times.Started != nil && times.Ended == nil:
+		times.Ended = &at
+		p.WalkSaid = WalkEnded
+	default:
+		return func() {}
+	}
+	p.Times = &times
+	return func() { p.Times, p.WalkSaid = was, "" }
+}

internal/inventory/walksaid_test.go

@@ -0,0 +1,130 @@
+package inventory
+
+import (
+	"testing"
+	"time"
+)
+
+// A walk is said started on the save that finds it live, ended on the save that finds it ended after it started,
+// and neither on any other save (novox/hq ADR 0308 decision 1).
+func TestAWalkIsSaidStartedOnceAndEndedOnce(t *testing.T) {
+	now := time.Date(2026, 10, 12, 11, 0, 0, 0, time.UTC)
+	cut := now.Add(-time.Second)
+	p := Plan{ID: "plan-1", State: PlanBuilding, Tiers: [][]string{{"messenger"}},
+		Modules: map[string]*PlanModule{"messenger": {}}, Times: &PlanTimes{Cut: &cut, Class: ClassLeaf}}
+	p.markWalk(now)
+	if p.WalkSaid != WalkStarted || p.Times.Started == nil || !p.Times.Started.Equal(now) {
+		t.Fatalf("a live walk's first save starts it: %q %+v", p.WalkSaid, p.Times)
+	}
+	p.State = PlanRolling
+	p.markWalk(now.Add(time.Minute))
+	if p.WalkSaid != "" || !p.Times.Started.Equal(now) {
+		t.Fatalf("a later save says nothing and keeps the start: %q %+v", p.WalkSaid, p.Times)
+	}
+	p.State = PlanDone
+	p.markWalk(now.Add(2 * time.Minute))
+	if p.WalkSaid != WalkEnded || p.Times.Ended == nil || p.Outcome() != WalkDelivered {
+		t.Fatalf("the save that finds it done ends it, delivered: %q %+v %q", p.WalkSaid, p.Times, p.Outcome())
+	}
+	p.markWalk(now.Add(3 * time.Minute))
+	if p.WalkSaid != "" {
+		t.Fatalf("an ended walk saved again says nothing: %q", p.WalkSaid)
+	}
+	// Retried, it walks again: a new start.
+	p.State = PlanBuilding
+	p.markWalk(now.Add(4 * time.Minute))
+	if p.WalkSaid != WalkStarted || p.Times.Ended != nil || !p.Times.Started.Equal(now.Add(4*time.Minute)) {
+		t.Fatalf("a retried walk starts again: %q %+v", p.WalkSaid, p.Times)
+	}
+}
+
+// What is never said: a batch, a walk waiting for its word, a walk that ends without having started, and a walk
+// kept before its times were. A release plan is said.
+func TestWhatIsNotAWalkStartIsNotSaid(t *testing.T) {
+	now := time.Now()
+	for name, p := range map[string]Plan{
+		"a batch":             {State: PlanAssembling, Times: &PlanTimes{}},
+		"waiting for a word":  {State: PlanBuilding, Times: &PlanTimes{}, Delivery: &PlanDelivery{Awaits: "mesh-delivery"}},
+		"ended, never begun":  {State: PlanDone, Times: &PlanTimes{}},
+		"kept before times":   {State: PlanBuilding},
+		"stopped while waits": {State: PlanFailed, Times: &PlanTimes{}, Delivery: &PlanDelivery{Awaits: "mesh-delivery", Stopped: "x"}},
+	} {
+		p.markWalk(now)
+		if p.WalkSaid != "" {
+			t.Errorf("%s: said %q", name, p.WalkSaid)
+		}
+	}
+	r := Plan{State: PlanRolling, Release: &PlanRelease{Order: []string{"ace"}}}
+	r.markWalk(now)
+	if r.WalkSaid != WalkStarted || r.Times == nil || r.Times.Started == nil || r.Times.Class != "" {
+		t.Fatalf("a release plan is said started, its times holding only that: %q %+v", r.WalkSaid, r.Times)
+	}
+	// Let go, the walk starts.
+	go1 := now
+	w := Plan{State: PlanBuilding, Times: &PlanTimes{}, Delivery: &PlanDelivery{Awaits: "mesh-delivery", Go: &go1}}
+	w.markWalk(now)
+	if w.WalkSaid != WalkStarted {
+		t.Fatalf("a walk let go starts: %q", w.WalkSaid)
+	}
+}
+
+// An ended walk's outcome: delivered, failed, or stopped by a person or the delivery's owner, or by a newer walk.
+func TestAWalksOutcome(t *testing.T) {
+	for want, p := range map[string]Plan{
+		WalkDelivered: {State: PlanDone},
+		WalkFailed:    {State: PlanFailed},
+		WalkStopped:   {State: PlanFailed, Delivery: &PlanDelivery{Stopped: "mesh-delivery"}},
+		"":            {State: PlanRolling},
+	} {
+		if got := p.Outcome(); got != want {
+			t.Errorf("%s: outcome %q, want %q", p.State, got, want)
+		}
+	}
+	if (Plan{State: PlanSuperseded}).Outcome() != WalkStopped {
+		t.Error("a superseded walk is stopped")
+	}
+}
+
+// The marks are kept with the walk, so a controller replaced mid-walk neither says its start again nor misses
+// its end; and a save refused leaves the walk unmarked, so the save that is made says it.
+func TestAWalksStartIsKeptAndARefusedSaveLeavesItUnsaid(t *testing.T) {
+	inv := ForTest(t)
+	ctx := t.Context()
+	cut := time.Now().UTC().Add(-time.Minute)
+	p := Plan{ID: "plan-308", Repository: "novox/mesh-catalog", Commit: "abc", Created: cut, State: PlanBuilding,
+		Tiers: [][]string{{"messenger"}}, Modules: map[string]*PlanModule{"messenger": {}},
+		Times: &PlanTimes{Cut: &cut, Class: ClassLeaf}}
+	var said []string
+	was := PlanSaved
+	PlanSaved = func(_ *Inventory, p Plan) { said = append(said, p.WalkSaid) }
+	t.Cleanup(func() { PlanSaved = was })
+	if err := inv.SavePlan(ctx, &p); err != nil {
+		t.Fatal(err)
+	}
+	back, err := inv.PlanByID(ctx, p.ID)
+	if err != nil || back.Times == nil || back.Times.Started == nil || back.Times.Class != ClassLeaf {
+		t.Fatalf("the start is kept with the walk: %v %+v", err, back.Times)
+	}
+	// Read back by another controller and saved: not said again.
+	back.State = PlanRolling
+	if err := inv.SavePlan(ctx, &back); err != nil {
+		t.Fatal(err)
+	}
+	// A stale copy ending it is refused, and unmarked.
+	stale := p
+	stale.Revision = 1
+	stale.State = PlanDone
+	if err := inv.SavePlan(ctx, &stale); err == nil {
+		t.Fatal("a stale save is refused")
+	}
+	if stale.WalkSaid != "" || stale.Times.Ended != nil {
+		t.Fatalf("a refused save is unmarked: %q %+v", stale.WalkSaid, stale.Times)
+	}
+	back.State = PlanDone
+	if err := inv.SavePlan(ctx, &back); err != nil {
+		t.Fatal(err)
+	}
+	if len(said) != 3 || said[0] != WalkStarted || said[1] != "" || said[2] != WalkEnded {
+		t.Fatalf("said: %q, want started, nothing, ended", said)
+	}
+}

testdata/store-tests

@@ -14,3 +14,11 @@
 ./internal/inventory TestAnIssuedValueIsSealedAgainAfterAKeyChangeOrAnAcceptance
 ./internal/inventory TestAConditionsLooksAreKeptBesideTheBucket
 ./cmd/mesh-controller TestTheConditionsVerbReadsTheLooksTheBucketNoLongerHolds
+./internal/inventory TestAWalksStartIsKeptAndARefusedSaveLeavesItUnsaid
+./cmd/mesh-controller TestAWalkLetGoAndStoppedByVerbsIsSaidStartedAndEnded
+./cmd/mesh-controller TestAWalkStoppedOrClosedByAPersonIsSaidEndedStopped
+./cmd/mesh-controller TestAWalkRetriedByAPersonIsSaidStartedAgain
+./cmd/mesh-controller TestABacklogReleasedByAPersonIsSaidStarted
+./cmd/mesh-controller TestAWalkEndedByCancelOrClearIsSaidEnded
+./cmd/mesh-controller TestAWalkRestartedByARebuildIsSaidStarted
+./cmd/mesh-controller TestAWalkStoppedByHandAndRetriedEndsFailedWhenItFailsAgain