A route's internal name says where the request arrives

novox/hq ADR 0151 (issues 139, 157). <label>.<node>.internal is answered
by every resolver as 'anything under that node goes to that node', so
the node in a route's internal name must be the one whose proxy answers
it; composed under the consumer's own name it sent a client to a machine
with nothing listening whenever the proxy ran elsewhere. Composed under
the serving node now — the same machine wherever the proxy runs beside
the module, so nothing changes on a mesh with one hub.

A routed public name gets no .internal alias any more: the roster
publishes it as itself, once. The alias resolved and nothing served it.

cmd/mesh-controller/acts.go

@@ -46,6 +46,13 @@ func assign(ctx context.Context, open *stores, node, module string) (string, err
 		return "", err
 	}
 	defer release()
+	// **Before the new assignment can unsettle a seat somebody holds only by being alone**
+	// (novox/hq 04-ISSUES/170): what the mesh derived so far is written down, and then the
+	// assignment resolves against a record rather than against a coincidence.
+	settled, err := recordDerivedHolders(ctx, open)
+	if err != nil {
+		return "", err
+	}
 	fresh, err := open.inventory.Assign(ctx, node, module)
 	if err != nil {
 		return "", err
@@ -57,6 +64,9 @@ func assign(ctx context.Context, open *stores, node, module string) (string, err
 			node, module), nil
 	}
 	said := fmt.Sprintf("%s is assigned %s", node, module)
+	for _, line := range settled {
+		said += "\n  " + line
+	}
 	plan, _, err := planFor(ctx, open, node)
 	if err != nil {
 		// Kept, and still refused. Both halves are the answer, and the rest of the mesh is still

cmd/mesh-controller/holdings.go

@@ -0,0 +1,92 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"sort"
+
+	"github.com/novox/mesh-controller/internal/catalogue"
+)
+
+// recordDerivedHolders writes down who holds each mesh-scoped seat that nobody was ever recorded
+// as holding.
+//
+// **A seat held by derivation is a seat held by accident of being alone** (novox/hq
+// 04-ISSUES/170). ADR 0131 lets a holder on record settle a seat, and lets any other assignment
+// whose module could hold it stand beside the holder, eligible and silent. But a seat nobody
+// ever handed over has no record, so its holder is whichever assignment happened to be the sole
+// claimant — and the day a second one is assigned, both claim, both are refused, and the first
+// one's whole machine stops resolving. That is what assigning a second postgres did to the
+// control plane's own store.
+//
+// So the mesh writes the derived answer down before it acts on an assignment: for every
+// mesh-scoped seat with exactly one resolved holder and nothing on record, that holder is
+// recorded as the standing one — the same record `seat <name> --to <node>/<module>` makes by
+// hand, made from what the mesh already resolved. A seat with two derived claimants is left
+// alone: that is the ambiguity a person settles, and recording either would be guessing.
+//
+// Node-scoped seats are untouched: a record is one holder per seat, and a node-scoped seat has
+// one holder per machine (ADR 0121), so there is nothing for a record to settle there.
+func recordDerivedHolders(ctx context.Context, open *stores) ([]string, error) {
+	inv := open.inventory
+	shelf, err := inv.Catalogue(ctx)
+	if err != nil {
+		return nil, err
+	}
+	// exclude nobody: every node's claims, resolved with the holdings on record.
+	world, err := theRestOfTheMesh(ctx, inv, shelf, "")
+	if err != nil {
+		return nil, err
+	}
+	recorded, err := inv.Holdings(ctx)
+	if err != nil {
+		return nil, err
+	}
+	// A record is a row against a seat the store knows. A seat it does not — a mesh whose seats
+	// were never seeded, a seat a module declares for itself — stays held by derivation, as it
+	// always was; a missing row is not a reason an assignment fails.
+	known, err := inv.Seats(ctx)
+	if err != nil {
+		return nil, err
+	}
+	recordable := map[string]bool{}
+	for _, s := range known {
+		recordable[s.Name] = true
+	}
+	onRecord := map[string]bool{}
+	for _, h := range recorded {
+		if s, ok := catalogue.SeatNamed(h.Claim); ok {
+			onRecord[s.Name] = true
+		}
+	}
+	holders := map[string][]catalogue.Held{}
+	for _, h := range world.Held {
+		if h.Scope != catalogue.ScopeMesh {
+			continue
+		}
+		s, ok := catalogue.SeatNamed(h.Claim)
+		if !ok || onRecord[s.Name] || !recordable[s.Name] {
+			continue
+		}
+		holders[s.Name] = append(holders[s.Name], h)
+	}
+	names := make([]string, 0, len(holders))
+	for name := range holders {
+		names = append(names, name)
+	}
+	sort.Strings(names)
+	var said []string
+	for _, name := range names {
+		if len(holders[name]) != 1 {
+			continue
+		}
+		h := holders[name][0]
+		if err := inv.HoldSeat(ctx, name, catalogue.ScopeMesh, h.Node, h.Module); err != nil {
+			return said, err
+		}
+		said = append(said, fmt.Sprintf(
+			"recorded %s on %s as the standing holder of %s, which it held only by being alone",
+			h.Module, h.Node, name))
+	}
+	return said, nil
+}

cmd/mesh-controller/holdings_test.go

@@ -0,0 +1,110 @@
+package main
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/novox/mesh-controller/internal/catalogue"
+)
+
+// A seat nobody ever handed over is held by whichever assignment happened to be alone — and the
+// day a second module able to hold it is assigned, both claimed, both were refused, and the first
+// one's machine stopped resolving (novox/hq 04-ISSUES/170). The mesh now writes the derived holder
+// down before it acts, so the second assignment stands beside the holder on record.
+
+func aSeatedStore() catalogue.Manifest {
+	return catalogue.Manifest{Module: "store", Version: "1",
+		Provides: []catalogue.Offer{{Name: "postgres-database", Scope: catalogue.ScopeMesh}},
+		Serves:   map[string]map[string]any{"postgres-database": {"port": 5432}},
+		Claims:   []catalogue.Claim{{Name: "mesh-store", Scope: catalogue.ScopeMesh}}}
+}
+
+func TestASecondEligibleHolderStandsBesideTheOneHeldByBeingAlone(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	// Every deploy seeds the mesh's own seats; a record is a row against one of them.
+	if _, err := open.inventory.SeedSeats(ctx, catalogue.DefaultSeats()); err != nil {
+		t.Fatal(err)
+	}
+	register(t, open, aSeatedStore())
+
+	if _, err := assign(ctx, open, "anchor", "store"); err != nil {
+		t.Fatal(err)
+	}
+	said, err := assign(ctx, open, "laptop", "store")
+	if err != nil {
+		t.Fatalf("a second store, eligible for the seat, was refused:\n%s\n%v", said, err)
+	}
+	if strings.Contains(said, "cannot be worked out") {
+		t.Fatalf("assigning a second store unsettled the first one's machine:\n%s", said)
+	}
+	if !strings.Contains(said, "recorded store on anchor as the standing holder of mesh-store") {
+		t.Fatalf("the holder by derivation was not written down:\n%s", said)
+	}
+
+	holdings, err := open.inventory.Holdings(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	var found bool
+	for _, h := range holdings {
+		if h.Claim == "mesh-store" {
+			found = true
+			if h.Node != "anchor" || h.Module != "store" {
+				t.Fatalf("mesh-store is recorded on %s/%s, not on the one that held it", h.Node, h.Module)
+			}
+		}
+	}
+	if !found {
+		t.Fatalf("mesh-store has no holder on record after assigning: %v", holdings)
+	}
+
+	// And the record decides from here: the anchor's plan holds the seat, the laptop's does not.
+	for node, holds := range map[string]bool{"anchor": true, "laptop": false} {
+		plan, _, err := planFor(ctx, open, node)
+		if err != nil {
+			t.Fatalf("%s no longer resolves: %v", node, err)
+		}
+		var claimed bool
+		for _, c := range plan.Claims {
+			if c.Claim == "mesh-store" {
+				claimed = true
+			}
+		}
+		if claimed != holds {
+			t.Fatalf("%s holds mesh-store: %v, want %v", node, claimed, holds)
+		}
+	}
+}
+
+func TestAHolderOnRecordIsNotRewrittenByDerivation(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	if _, err := open.inventory.SeedSeats(ctx, catalogue.DefaultSeats()); err != nil {
+		t.Fatal(err)
+	}
+	register(t, open, aSeatedStore())
+	for _, node := range []string{"anchor", "laptop"} {
+		if _, err := assign(ctx, open, node, "store"); err != nil {
+			t.Fatal(err)
+		}
+	}
+	// A person hands the seat to the laptop. From here the record decides, and what the mesh
+	// derives must never write over it.
+	if err := open.inventory.HoldSeat(ctx, "mesh-store", catalogue.ScopeMesh, "laptop", "store"); err != nil {
+		t.Fatal(err)
+	}
+	said, err := recordDerivedHolders(ctx, open)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(said) != 0 {
+		t.Fatalf("a seat on record was written again from derivation: %v", said)
+	}
+	holdings, _ := open.inventory.Holdings(ctx)
+	for _, h := range holdings {
+		if h.Claim == "mesh-store" && h.Node != "laptop" {
+			t.Fatalf("the record moved to %s", h.Node)
+		}
+	}
+}

internal/catalogue/declaration.go

@@ -618,17 +618,15 @@ func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[stri
 		// merging earlier would throw away the files it still needs.
 		resources = append(append([]map[string]any{}, first...), resources...)
 
-		// Every container is given the mesh's names. Not a choice a module makes: a module that
-		// listed them would go stale the day a machine joins, and one that did not would be a
-		// module whose containers cannot reach anything by name.
-		//
-		// A container that was given names of its own keeps them and gets the mesh's beside them:
-		// the mesh does not know what else a workload needs to reach, and taking something away
-		// to add something is not what "also" means.
-		if len(with.Names) > 0 {
-			resources = withMeshNames(resources, with.Names)
-		}
-
+		// No container is given the mesh's names (novox/hq ADR 0148). It used to be: every
+		// container got the whole roster as `--add-host` entries at creation, and a name that
+		// moved afterwards was wrong inside it for as long as it ran (issues 109, 135) — and once
+		// the roster was made part of a container's identity so that could be caught, one name
+		// moving anywhere replaced every container in the mesh (issue 151). A container resolves a
+		// mesh name through its machine's resolver at the moment it asks, which the runtime is
+		// told once per machine, as a file, by the resolver's own module. The names a module
+		// declares for itself are its own and stay exactly as written: they are part of what the
+		// module is, and the mesh does not know what they mean.
 		// What this module may name from inside one of its own files. Gathered once per module
 		// rather than per file, because it is a fact about the module.
 		sealed, err := sealedFor(m, r.Needs, with)
@@ -1103,7 +1101,7 @@ func (r Resolution) contributions(settings SettingsBy, grants []Grant,
 				return nil, fmt.Errorf("%s contributing to %s: %w", m.Module, to, err)
 			}
 			portOfEndpoint(values, endpointPorts(m))
-			composeName(values, r.PublicDomain, r.At, reaches, endpointPorts(m), blocks)
+			composeName(values, r.PublicDomain, servingAt(r, to), reaches, endpointPorts(m), blocks)
 			out[to] = append(out[to], Contribution{From: m.Module, Values: values})
 		}
 		// Several contributions to one requirement (ADR 0094's sibling for `contributes`): an
@@ -1126,7 +1124,7 @@ func (r Resolution) contributions(settings SettingsBy, grants []Grant,
 					return nil, fmt.Errorf("%s contributing %s to %s: %w", m.Module, local, to, err)
 				}
 				portOfEndpoint(values, endpointPorts(m))
-				composeName(values, r.PublicDomain, r.At, reaches, endpointPorts(m), blocks)
+				composeName(values, r.PublicDomain, servingAt(r, to), reaches, endpointPorts(m), blocks)
 				out[to] = append(out[to], Contribution{From: m.Module, Values: values})
 			}
 		}
@@ -1226,6 +1224,24 @@ func composeName(values map[string]any, publicDomain, internalDomain string, rea
 	}
 }
 
+// servingAt is the private-network name of the node a contribution to `to` arrives at: the
+// provider's, when the provision is answered elsewhere, and this machine's own when it is answered
+// here or not yet settled.
+//
+// A route's internal name is composed under it (novox/hq ADR 0151, issue 139). `<label>.<node>.internal`
+// is answered by every machine's resolver as *anything under that node's name goes to that node* —
+// so the node in the name has to be the one whose proxy answers, or the name sends a client to a
+// machine with nothing listening while the public name, published at the serving node's address,
+// works. Where the proxy runs beside the module the two are the same machine and nothing changes.
+func servingAt(r Resolution, to string) string {
+	for _, n := range r.Needs {
+		if n.Name == to && n.At != "" {
+			return n.At
+		}
+	}
+	return r.At
+}
+
 // receivedFile is the file a provider is given its consumers' contributions in.
 func receivedFile(requirement, path string, given []Contribution) (map[string]any, error) {
 	if given == nil {
@@ -1482,43 +1498,6 @@ func (r Resolution) servedOnThisMachine(provision string, with Rendering) (map[s
 	return nil, false, nil
 }
 
-// withMeshNames gives every container in a set the mesh's names.
-//
-// Copied rather than edited in place: these maps come from a module's manifest, and mutating one
-// would change what the catalogue holds for every other machine running that module.
-//
-// A host-network container gets the names too. It was once skipped, on the belief that it "shares
-// the machine's hosts file already" — but it does not: `docker run --network host` still gives the
-// container its own /etc/hosts (localhost and its own id only), so every `<node>.internal` name the
-// mesh wrote for the machine is invisible inside it, and a client that dials one gets EAI_AGAIN. The
-// remedy is the same `--add-host` every other container gets — the runtime accepts it with
-// `--network host` (verified), and without it a host-network consumer cannot reach a provider by the
-// `.internal` address the mesh hands it as `${bound:...:at}`.
-func withMeshNames(resources []map[string]any, names map[string]string) []map[string]any {
-	out := make([]map[string]any, 0, len(resources))
-	for _, r := range resources {
-		if r["type"] != "container" {
-			out = append(out, r)
-			continue
-		}
-
-		copied := map[string]any{}
-		for k, v := range r {
-			copied[k] = v
-		}
-		var given []any
-		if already, ok := copied["hosts"].([]any); ok {
-			given = append(given, already...)
-		}
-		for _, name := range sortedKeys(names) {
-			given = append(given, name+":"+names[name])
-		}
-		copied["hosts"] = given
-		out = append(out, copied)
-	}
-	return out
-}
-
 // pinned refuses an image that is not really pinned, on its way to a machine.
 //
 // **Here and not at parse** (novox/hq 04-ISSUES/025). A manifest in a repository names artifacts

internal/catalogue/holdings_test.go

@@ -158,3 +158,16 @@ func TestAStoreRowWithoutAProtocolKeepsTheCompiledOne(t *testing.T) {
 		t.Fatalf("the store's own columns were not kept: %+v", got)
 	}
 }
+
+func TestARefusalWithNothingOnRecordNamesTheHandover(t *testing.T) {
+	busSeatDelivering(t, "mesh-bus")
+	elsewhere := []Held{{Claim: "mesh-broker", Scope: ScopeMesh, Node: "anchor", Module: "old-broker"}}
+
+	_, problems := checkClaims([]Manifest{newBroker()}, Node{Name: "laptop"}, elsewhere, nil)
+	if len(problems) != 1 {
+		t.Fatalf("two derived claimants across machines were not refused: %v", problems)
+	}
+	if !strings.Contains(problems[0], "`seat mesh-broker --to anchor/old-broker`") {
+		t.Fatalf("the refusal does not name the handover that records the holder: %s", problems[0])
+	}
+}

internal/catalogue/names_test.go

@@ -1,6 +1,7 @@
 package catalogue
 
 import (
+	"reflect"
 	"strings"
 	"testing"
 )
@@ -30,36 +31,38 @@ func namesOf(r map[string]any) []string {
 	return out
 }
 
-// A container does not inherit the machine's names, so the mesh gives them to it.
+// No mesh name is written into a container (novox/hq ADR 0148). It resolves them through its
+// machine's resolver at the moment it asks, so a name that moves is answered differently by the
+// next lookup, in every container, with nothing recreated.
 //
-// It gets its own hosts file holding only its own hostname — every internal name the mesh wrote
-// for the machine is invisible to what the machine runs. A database client on one node could not
-// resolve another node, on a mesh where both names were correct and present on both machines.
-func TestEveryContainerIsGivenTheMeshsNames(t *testing.T) {
-	got := containersOf(t, Resolution{Node: "laptop", Modules: []Manifest{{
-		Module: "app",
-		Resources: []map[string]any{{"id": "web", "type": "container", "name": "web",
-			"image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}},
-	}}}, Rendering{Names: map[string]string{
-		"anchor.internal": "10.42.0.1", "laptop.internal": "10.42.0.2",
-	}})
-	if len(got) != 1 {
-		t.Fatalf("expected one container, got %d", len(got))
+// Checked the way the record says: the declaration a container gets does not move when the mesh's
+// roster does. A roster with one machine and a roster with three produce the same container, byte
+// for byte, so the digest a host computes from it cannot move either — which is what stopped one
+// name moving from replacing every container in the mesh (issue 151).
+func TestAContainerIsTheSameWhateverTheMeshsRosterSays(t *testing.T) {
+	module := Manifest{Module: "app", Resources: []map[string]any{{"id": "web", "type": "container",
+		"name": "web", "image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}}}
+	one := containersOf(t, Resolution{Node: "laptop", Modules: []Manifest{module}},
+		Rendering{Names: map[string]string{"laptop.internal": "10.42.0.2"}})
+	three := containersOf(t, Resolution{Node: "laptop", Modules: []Manifest{module}},
+		Rendering{Names: map[string]string{
+			"anchor.internal": "10.42.0.1", "laptop.internal": "10.42.0.2", "git.example.tld": "10.42.0.1",
+		}})
+	if len(one) != 1 || len(three) != 1 {
+		t.Fatalf("expected one container each, got %d and %d", len(one), len(three))
 	}
-	given := namesOf(got[0])
-	if len(given) != 2 {
-		t.Fatalf("the container was given %d name(s): %v", len(given), given)
+	if given := namesOf(three[0]); len(given) != 0 {
+		t.Fatalf("the mesh's names were copied into the container: %v", given)
 	}
-	if given[0] != "anchor.internal:10.42.0.1" {
-		t.Fatalf("the name is not in the form a runtime writes: %v", given)
+	if !reflect.DeepEqual(one[0], three[0]) {
+		t.Fatalf("the container moved with the roster:\n%v\n%v", one[0], three[0])
 	}
 }
 
-// A container that named its own keeps them and gets the mesh's beside them.
-//
-// The mesh does not know what else a workload needs to reach, and taking something away in order
-// to add something is not what "also" means.
-func TestAContainersOwnNamesAreKept(t *testing.T) {
+// The names a module declares for itself are its own: part of what the module is, kept exactly as
+// written, and the mesh does not know what they mean. They are the one thing in a container's
+// hosts that does move its identity, because they do not move when the mesh's roster does.
+func TestAContainersOwnNamesAreKeptAsWritten(t *testing.T) {
 	got := containersOf(t, Resolution{Node: "laptop", Modules: []Manifest{{
 		Module: "app",
 		Resources: []map[string]any{{"id": "web", "type": "container", "name": "web",
@@ -68,62 +71,15 @@ func TestAContainersOwnNamesAreKept(t *testing.T) {
 	}}}, Rendering{Names: map[string]string{"anchor.internal": "10.42.0.1"}})
 
 	given := namesOf(got[0])
-	if len(given) != 2 || given[0] != "something.else:203.0.113.9" {
-		t.Fatalf("the container's own names were lost: %v", given)
+	if len(given) != 1 || given[0] != "something.else:203.0.113.9" {
+		t.Fatalf("the container's own names were not kept as written: %v", given)
 	}
 }
 
-// A container on the machine's own network gets the names too — it does NOT share the machine's
-// hosts file. `docker run --network host` still gives the container its own /etc/hosts (localhost
-// and its own id only), so every `<node>.internal` name the mesh wrote is invisible inside it, and a
-// client that dials one gets EAI_AGAIN. It gets the same `--add-host` entries every other container
-// gets (the runtime accepts them with `--network host`), so a host-network consumer can reach a
-// provider by the `.internal` address the mesh hands it.
-func TestAContainerOnTheMachinesNetworkIsGivenTheNamesToo(t *testing.T) {
-	got := containersOf(t, Resolution{Node: "anchor", Modules: []Manifest{{
-		Module: "control",
-		Resources: []map[string]any{{"id": "c", "type": "container", "name": "c",
-			"image": "registry.example/c@sha256:" + strings.Repeat("a", 64), "network": "host"}},
-	}}}, Rendering{Names: map[string]string{"anchor.internal": "10.42.0.1"}})
-
-	given := namesOf(got[0])
-	if len(given) != 1 || given[0] != "anchor.internal:10.42.0.1" {
-		t.Fatalf("a host-networked container was not given the mesh's names: %v", got[0])
-	}
-}
-
-// A mesh with no private network gives nothing, rather than a name with no address behind it.
-func TestAMeshWithNoNamesGivesNone(t *testing.T) {
-	got := containersOf(t, Resolution{Node: "alone", Modules: []Manifest{{
-		Module: "app",
-		Resources: []map[string]any{{"id": "web", "type": "container", "name": "web",
-			"image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}},
-	}}}, Rendering{})
-	if len(namesOf(got[0])) != 0 {
-		t.Fatalf("names were invented for a mesh that has none: %v", got[0])
-	}
-}
-
-// The catalogue's copy is not edited: these maps come from a manifest, and mutating one would
-// change what every other machine running that module is given.
-func TestGivingNamesDoesNotChangeTheCatalogue(t *testing.T) {
-	held := map[string]any{"id": "web", "type": "container", "name": "web",
-		"image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}
-	module := Manifest{Module: "app", Resources: []map[string]any{held}}
-
-	for _, node := range []string{"one", "two"} {
-		containersOf(t, Resolution{Node: node, Modules: []Manifest{module}},
-			Rendering{Names: map[string]string{"anchor.internal": "10.42.0.1"}})
-	}
-	if _, changed := held["hosts"]; changed {
-		t.Fatal("the manifest the catalogue holds was edited, so every machine now carries this")
-	}
-}
-
-// Only containers. A file or a service given a `hosts` key is a declaration the host refuses
-// outright — it takes no unknown field — so getting this wrong breaks the whole machine rather
-// than one resource, and breaks it for something that was never about names.
-func TestNothingButAContainerIsGivenNames(t *testing.T) {
+// No resource is given a `hosts` key it did not declare. A file or a service carrying one is a
+// declaration the host refuses outright — it takes no unknown field — so an invented key breaks
+// the whole machine rather than one resource.
+func TestNothingIsGivenNamesItDidNotDeclare(t *testing.T) {
 	out, err := Resolution{Node: "laptop", Modules: []Manifest{{
 		Module: "app",
 		Resources: []map[string]any{
@@ -137,11 +93,8 @@ func TestNothingButAContainerIsGivenNames(t *testing.T) {
 		t.Fatal(err)
 	}
 	for _, r := range out {
-		if r["type"] == "container" {
-			continue
-		}
 		if _, given := r["hosts"]; given {
-			t.Fatalf("a %v was given names, which the host will refuse: %v", r["type"], r)
+			t.Fatalf("a %v was given names it never declared: %v", r["type"], r)
 		}
 	}
 }

internal/catalogue/port_into.go

@@ -98,8 +98,7 @@ func portInto(resource map[string]any, module string, listens []Listening, with
 
 		// **A fresh map, and only when something changes.** This map came out of the module's
 		// manifest and the resource around it is a shallow copy, so filling a value in place would
-		// change what the catalogue holds for every other machine running the module — the trap
-		// withMeshNames is written to avoid, one field along.
+		// change what the catalogue holds for every other machine running the module.
 		var filled map[string]any
 		for _, key := range named {
 			written, ok := env[key].(string)

internal/catalogue/resolve.go

@@ -707,9 +707,14 @@ func checkClaims(modules []Manifest, node Node, elsewhere []Held, holdings []Hel
 			}
 			switch h.Scope {
 			case ScopeMesh:
+				// Both claim and nobody is on record, or this refusal could not have happened.
+				// The remedy is the handover that records the holder (novox/hq ADR 0131,
+				// 04-ISSUES/170), so it is named here rather than left to be found.
 				problems = append(problems, fmt.Sprintf(
-					"%s on %s claims %q, which %s on %s already holds — one per mesh",
-					h.Module, node.Name, h.Claim, e.Module, e.Node))
+					"%s on %s claims %q, which %s on %s already holds — one per mesh. Nothing is "+
+						"on record for it; `seat %s --to %s/%s` records the holder, and the other "+
+						"assignment then stands beside it, eligible and silent",
+					h.Module, node.Name, h.Claim, e.Module, e.Node, h.Claim, e.Node, e.Module))
 			case ScopeSite:
 				if node.Site != "" && node.Site == e.Site {
 					problems = append(problems, fmt.Sprintf(

internal/catalogue/resolver_manifests_test.go

@@ -48,7 +48,7 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
 	}
 	for _, want := range []string{
 		"\nno-resolv\n", "\nserver=1.1.1.1\n", "\nserver=8.8.8.8\n",
-		"\nlisten-address=127.0.0.1\n", "\ninterface=mesh0\n", "\nbind-dynamic\n",
+		"\nlisten-address=127.0.0.1\n", "\nlisten-address=${machine:address}\n", "\nbind-dynamic\n",
 		"\ndomain-needed\n", "\nbogus-priv\n",
 		"\nconf-file=" + m.Facts["node-zones"].Path + "\n",
 	} {
@@ -56,6 +56,14 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
 			t.Errorf("the resolver's configuration lacks %q:\n%s", strings.TrimSpace(want), config)
 		}
 	}
+	// By address and never by interface: dnsmasq admits a query by the interface it arrives on
+	// when told one, and a container's query to the private address arrives on the runtime's
+	// bridge — `interface=mesh0` dropped every such query, silently (novox/hq issue 110).
+	for _, line := range strings.Split(config, "\n") {
+		if strings.HasPrefix(line, "interface=") {
+			t.Errorf("the resolver answers by interface, so a container's query on a bridge is dropped: %s", line)
+		}
+	}
 	// Not .53 or .54, which systemd-resolved holds; and not .55 any more, which was a convention
 	// beside the one every machine already followed — the predecessor's resolv.conf says .1.
 	for _, taken := range []string{"127.0.0.53", "127.0.0.54", "127.0.0.55"} {
@@ -137,23 +145,39 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
 		t.Errorf("the daemon does not restart on its configuration and the machines file both: %v", service["restart-on"])
 	}
 
-	// The runtime's own file, written into (novox/hq ADR 0102) with the one key this module states.
+	// The runtime's own file, written into (novox/hq ADR 0102) with the keys this module states:
+	// where containers resolve, and that a restart keeps them running — because the runtime reads
+	// `dns` only when it starts, and the one restart that needs is the operator's (issue 110).
 	runtime := ids["dnsmasq.runtime-dns"]
 	if runtime == nil || runtime["path"] != "/etc/docker/daemon.json" || runtime["into"] != "json" {
 		t.Fatalf("the runtime's dns is not written into its file: %v", runtime)
 	}
-	var keys map[string][]string
+	var keys map[string]any
 	if err := json.Unmarshal([]byte(runtime["content"].(string)), &keys); err != nil {
 		t.Fatalf("the runtime's keys are not JSON: %v", err)
 	}
-	if len(keys) != 1 || len(keys["dns"]) != 1 || keys["dns"][0] != "10.42.0.1" {
-		t.Errorf("the runtime is pointed at %v; containers resolve at this machine's own private-network address, and nothing else is written", keys)
+	dns, _ := keys["dns"].([]any)
+	if len(keys) != 2 || len(dns) != 1 || dns[0] != "10.42.0.1" || keys["live-restore"] != true {
+		t.Errorf("the runtime is given %v; containers resolve at this machine's own private-network address, a restart keeps them, and nothing else is written", keys)
 	}
+	// The runtime is reloaded when that file changes, and never restarted: a restart stops every
+	// container on the machine (ADR 0102), and a reload is what turns live-restore on.
+	var reloaded bool
 	for _, r := range out {
-		if r["type"] == "service" && r["unit"] == "docker.service" && r["id"] != "" &&
-			strings.HasPrefix(r["id"].(string), "dnsmasq.") {
-			t.Errorf("the resolver orders the runtime restarted or reloaded, which stops every container (ADR 0102) or does nothing for dns: %v", r)
+		if r["type"] != "service" || r["unit"] != "docker.service" {
+			continue
 		}
+		if _, restarts := r["restart-on"]; restarts {
+			t.Errorf("the resolver orders the runtime restarted, which stops every container (ADR 0102): %v", r)
+		}
+		for _, on := range asStrings(r["reload-on"]) {
+			if on == "dnsmasq.runtime-dns" {
+				reloaded = true
+			}
+		}
+	}
+	if !reloaded {
+		t.Errorf("the runtime is not reloaded when its file changes, so live-restore never takes effect")
 	}
 
 	resolv := ids["resolv-conf.resolv"]

internal/catalogue/roster.go

@@ -162,6 +162,13 @@ func renderRoster(tmpl string, view rosterView) (string, error) {
 func entriesFrom(addresses, accounts map[string]string, suffix string) []rosterEntry {
 	out := make([]rosterEntry, 0, len(addresses))
 	for _, name := range sortedNames(addresses) {
+		if routed(name, suffix) {
+			// A routed name is already a full name under a public domain, and it has no mesh
+			// form: appending the suffix made `<name>.<suffix>`, which every machine's hosts file
+			// carried and nothing served (novox/hq issue 157). It is published as itself, once.
+			out = append(out, rosterEntry{Name: name, FQDN: name, Address: addresses[name], Account: accounts[name]})
+			continue
+		}
 		internal, bare := meshName(name, suffix)
 		// The account is looked up by whichever key the caller keys accounts on — the internal name
 		// or the bare one — so a template gets the right login however the maps were built.
@@ -187,6 +194,14 @@ func meshName(name, suffix string) (internal, bare string) {
 	return name + dotted, name
 }
 
+// routed says whether a name the mesh serves is a routed public name rather than a machine's: it
+// carries a domain of its own and not the mesh's suffix. A machine's name is bare (`homer`) or
+// internal (`homer.internal`); anything else with a dot in it was composed under a public domain.
+func routed(name, suffix string) bool {
+	dotted := "." + strings.TrimPrefix(suffixOr(suffix), ".")
+	return strings.Contains(name, ".") && !strings.HasSuffix(name, dotted)
+}
+
 // suffixOr is the suffix given, or the one the mesh composes names with when none was handed down.
 // The one place the default is written, so a fact and a name cannot disagree about it.
 func suffixOr(suffix string) string {

internal/catalogue/roster_test.go

@@ -258,3 +258,24 @@ func TestAHomeFactIsSkippedWhereThereIsNoAccount(t *testing.T) {
 		t.Fatalf("a home fact was placed on a machine with no operator account: %v", given)
 	}
 }
+
+// A routed name is already a full name under a public domain and has no mesh form. Appending the
+// suffix to it made `git.example.tld.internal` — carried by every machine's hosts file, served by
+// nothing, and refused by the proxy at the handshake (novox/hq issue 157). It is published as
+// itself, and only a machine has a bare name beside its full one.
+func TestARoutedNameIsPublishedAsItselfAndNotSuffixed(t *testing.T) {
+	names := map[string]string{"homer.internal": "10.42.0.1", "git.example.tld": "10.42.0.1"}
+	tmpl := RosterFile{Path: "/f", Template: "{{range .Names}}{{.FQDN}} {{.Name}}\n{{end}}"}
+	out, err := FactsInto(Manifest{Module: "a", Facts: map[string]RosterFile{"f": tmpl}},
+		Resolution{Node: "homer"}, names, map[string]string{"homer.internal": "10.42.0.1"}, nil, "internal")
+	if err != nil {
+		t.Fatal(err)
+	}
+	got := out[0]["content"].(string)
+	if strings.Contains(got, "tld.internal") {
+		t.Fatalf("the routed name was given a suffixed alias that nothing serves:\n%s", got)
+	}
+	if !strings.Contains(got, "git.example.tld git.example.tld\n") || !strings.Contains(got, "homer.internal homer\n") {
+		t.Fatalf("the roster does not carry the routed name as itself beside the machine's two forms:\n%s", got)
+	}
+}

internal/catalogue/routing_test.go

@@ -198,37 +198,59 @@ func TestTheApexLabelComposesToTheBarePrivateAddress(t *testing.T) {
 	}
 }
 
+// novox/hq ADR 0066 propagate, by ADR 0148's means: a granted route name is published into the
+// machine's roster mapped to the node that serves it, beside the `<node>.internal` names, and the
+// machine's resolver answers it to every container. Nothing is written into the container itself —
+// a routed name that moved would otherwise be wrong inside every container until each was recreated.
 func TestARoutedNameResolvesToTheServingNode(t *testing.T) {
-	// novox/hq ADR 0066 propagate: a granted route name is published into internal resolution,
-	// mapped to the node that serves it, alongside the `<node>.internal` names — so every
-	// container, and an in-mesh ACME validator, resolves a routed name to the proxy that serves it.
-	// The names map is what withMeshNames writes into every container as `--add-host`; a route name
-	// mapped to the serving node's address rides the same mechanism.
+	names := map[string]string{
+		"anchor.internal": "10.42.0.1",
+		"git.example.tld": "10.42.0.1",
+	}
 	got := containersOf(t, Resolution{Node: "anchor", Modules: []Manifest{{
 		Module: "app",
 		Resources: []map[string]any{{"id": "web", "type": "container", "name": "web",
 			"image": "registry.example/web@sha256:" + strings.Repeat("a", 64)}},
-	}}}, Rendering{Names: map[string]string{
-		"anchor.internal": "10.42.0.1",
-		"git.example.tld": "10.42.0.1",
-	}})
+	}}}, Rendering{Names: names})
 	if len(got) != 1 {
 		t.Fatalf("expected one container, got %d", len(got))
 	}
-	given := namesOf(got[0])
-	var sawNode, sawRoute bool
-	for _, h := range given {
-		if h == "anchor.internal:10.42.0.1" {
-			sawNode = true
-		}
-		if h == "git.example.tld:10.42.0.1" {
+	if given := namesOf(got[0]); len(given) != 0 {
+		t.Fatalf("the routed name was copied into the container, where it would go stale: %v", given)
+	}
+	var sawRoute bool
+	for _, e := range entriesFrom(names, nil, "internal") {
+		if e.Name == "git.example.tld" && e.Address == "10.42.0.1" {
 			sawRoute = true
 		}
 	}
-	if !sawNode {
-		t.Fatalf("the container lost the mesh's node names: %v", given)
-	}
 	if !sawRoute {
-		t.Fatalf("the routed name was not published to the serving node: %v", given)
+		t.Fatalf("the routed name is not in the roster the machine's resolver answers from")
+	}
+}
+
+// novox/hq issue 139, ADR 0151: `<label>.<node>.internal` is answered by every machine's resolver as
+// "anything under that node's name goes to that node", so the node in a route's internal name must
+// be the one whose proxy answers it. Composed under the consumer's own name, a route served from
+// another machine got an internal name that resolved to a machine with nothing listening, while the
+// public name — published at the serving node's address — worked.
+func TestARoutesInternalNameIsComposedUnderTheNodeThatServesIt(t *testing.T) {
+	hub := proxy()
+	hub.Provides = FromAnywhere("reverse-proxy")
+	got, err := Resolve(shelf(hub, labelled("board", "git", 8080)), []string{"board"},
+		withPrivateAddress("laptop.internal"), World{Offered: map[string][]Provider{
+			"reverse-proxy": {{Node: "anchor", At: "anchor.internal", Module: "traefik"}},
+		}})
+	if err != nil {
+		t.Fatal(err)
+	}
+	// Gathered the way the control plane gathers a consumer's contribution for a provider on
+	// another machine.
+	values, asks, err := got.ContributionsFrom("reverse-proxy", "board", nil)
+	if err != nil || !asks {
+		t.Fatalf("the route was not contributed: %v %v", asks, err)
+	}
+	if values["internal-name"] != "git.anchor.internal" {
+		t.Fatalf("the internal name does not say where the request arrives: %v", values)
 	}
 }

internal/overlay/generator.go

@@ -169,10 +169,12 @@ func (g *Generator) Graph() Graph { return g.graph }
 //
 //   - No floor: no header, no localhost, no `127.0.1.1` — those are the machine's, above the region.
 //   - A machine's own line is marked, and its mesh name resolves to its mesh address, not loopback.
-//   - `.Names` is every name the mesh serves (issue 111), so a container reaching a routed name
-//     finds the machine serving it; machines with no address yet are already left out of the set.
+//   - `.Names` is every name the mesh serves (issue 111), so anything on the machine reaching a
+//     routed name through its resolver finds the machine serving it; machines with no address yet
+//     are already left out of the set. A routed name is one alias, itself — a machine has a bare
+//     name beside its full one, a routed name has nothing beside it (issue 157).
 const hostsTemplate = "# The mesh's names. This region is replaced whenever a machine joins or leaves.\n" +
-	"{{range .Names}}{{.Address}}\t{{.FQDN}}\t{{.Name}}{{if eq .Name $.Node}}\t# this machine{{end}}\n{{end}}"
+	"{{range .Names}}{{.Address}}\t{{.FQDN}}{{if ne .Name .FQDN}}\t{{.Name}}{{end}}{{if eq .Name $.Node}}\t# this machine{{end}}\n{{end}}"
 
 // Manifest is the module the mesh provides for itself.
 //