Two consumers may share a name; they must not share a delivery subject

novox/hq 04-ISSUES/146. A push consumer delivers onto an ordinary subject and
everything subscribed to it gets a copy. The controller holds a consumer called
'controller' on CONTROL and another called 'controller' on EVENTS, and both were
given _DELIVER.controller — so the one process, holding both subscriptions,
acted on every message twice.

Measured: one enrolment published, one message in the stream, one delivery, no
redelivery, and the controller enrolled the machine twice — the second minting a
credential that replaced the one the machine had just been handed, which is why
it then reconnected for ever as a user whose password the mesh had rotated. Every
report and every followed event doubled the same way, silently.

The stream goes in the subject because the pair is what identifies a consumer.
A subscriber's permission gains the same shape, keeping the bare name so an
existing consumer keeps working until the next assertion moves it.

Makefile

@@ -27,8 +27,18 @@ build:
 IMAGE ?= mesh-controller:$(VERSION)
 DEV_TAG ?= mesh-controller:development
 
+# The base the module declares, read from the manifest rather than written here twice.
+#
+# **`make image` was broken and stayed broken**, because the Dockerfile's fallback base was a Go
+# older than go.mod asks for: every build died at `go mod download` with "go.mod requires go >=
+# 1.26.0", and the pipeline never saw it because the pipeline passes the declared base in. Anybody
+# building the image by hand hit it and had to find the digest themselves (novox/hq 04-ISSUES/146,
+# what it cost).
+GO_BASE ?= $(shell python3 -c "import json;print(next(o['image'] for o in json.load(open('module.json'))['build']['on'] if o['arg']=='GO_BASE'))" 2>/dev/null)
+
 image:
-	docker build --build-arg VERSION=$(VERSION) -t $(IMAGE) -t $(DEV_TAG) .
+	@test -n "$(GO_BASE)" || { echo "module.json declares no GO_BASE; pass GO_BASE=<image> or fix the manifest"; exit 1; }
+	docker build --build-arg GO_BASE=$(GO_BASE) --build-arg VERSION=$(VERSION) -t $(IMAGE) -t $(DEV_TAG) .
 	@echo
 	@docker image inspect $(IMAGE) --format 'built {{.RepoTags}}  {{.Size}} bytes'
 
@@ -38,7 +48,8 @@ BUILDER_IMAGE ?= mesh-builder:$(VERSION)
 BUILDER_DEV_TAG ?= mesh-builder:development
 
 builder-image:
-	docker build -f cmd/mesh-builder/Dockerfile -t $(BUILDER_IMAGE) -t $(BUILDER_DEV_TAG) .
+	@test -n "$(GO_BASE)" || { echo "module.json declares no GO_BASE; pass GO_BASE=<image> or fix the manifest"; exit 1; }
+	docker build --build-arg GO_BASE=$(GO_BASE) -f cmd/mesh-builder/Dockerfile -t $(BUILDER_IMAGE) -t $(BUILDER_DEV_TAG) .
 	@echo
 	@docker image inspect $(BUILDER_IMAGE) --format 'built {{.RepoTags}}  {{.Size}} bytes'
 

cmd/mesh-controller/buscertificate.go

@@ -0,0 +1,258 @@
+package main
+
+import (
+	"context"
+	"crypto/rand"
+	"crypto/rsa"
+	"crypto/x509"
+	"crypto/x509/pkix"
+	"encoding/pem"
+	"errors"
+	"fmt"
+	"math/big"
+	"net"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"github.com/novox/mesh-controller/internal/broker"
+)
+
+// The bus's own certificate, made by the mesh rather than borrowed from an image.
+//
+// **The foundation asked a third-party image for a tool it never said must be there** (novox/hq
+// 04-ISSUES/146). The bootstrap made this certificate by running `openssl` inside the broker's
+// image, which worked while the broker was one that happened to carry it and stopped the day the
+// bus changed: the new one has a shell and no openssl, so the step exited 127 and no mesh could be
+// raised. Substituting another image the bundle names does not help — none of them carry it
+// either.
+//
+// So the program that needs a certificate makes one. It is the mesh's own binary, already on the
+// machine at this point in the bootstrap (the schema step ran it), and it needs nothing from the
+// image it writes into but a mounted directory.
+//
+// **Self-signed, and that is the design** — a host pins this server's exact certificate and
+// authenticates with a password (novox/hq ADR 0004). There is no authority above it to ask, and at
+// this moment in a bootstrap there is no mesh to ask one of.
+//
+// Idempotent, because the step is applied again on every reconcile and a second certificate would
+// be one the hosts that pinned the first no longer believe.
+
+// busCertificateNames is what the bus is reached by: the container name on a mesh network, and the
+// loopback address the machine's own foundation dials.
+var busCertificateNames = []string{"mesh-broker"}
+
+const busCertificateLife = 10 * 365 * 24 * time.Hour
+
+// busCertificate makes the bus's certificate in a directory, or says whether one is there.
+//
+//	broker certificate --into /tls           make it if it is not there
+//	broker certificate --check --into /tls   exit non-zero unless a usable pair is
+func busCertificate(args []string) error {
+	into, check := "", false
+	for i := 0; i < len(args); i++ {
+		switch args[i] {
+		case "--check":
+			check = true
+		case "--into":
+			if i+1 >= len(args) {
+				return errors.New("--into needs a directory")
+			}
+			into = args[i+1]
+			i++
+		default:
+			return fmt.Errorf("broker certificate [--check] --into <directory>: %q", args[i])
+		}
+	}
+	if into == "" {
+		return errors.New("broker certificate [--check] --into <directory>")
+	}
+	crt, key := filepath.Join(into, "tls.crt"), filepath.Join(into, "tls.key")
+
+	if usable, err := busCertificateUsable(crt, key); err != nil {
+		return err
+	} else if usable {
+		fmt.Printf("the bus already has a certificate at %s, and it was left alone\n", crt)
+		return nil
+	}
+	if check {
+		// Said as a failure, because that is what the caller asked: a bootstrap's verify runs
+		// this and a false answer is what makes the step run.
+		return fmt.Errorf("no usable certificate and key at %s", into)
+	}
+	return writeBusCertificate(crt, key)
+}
+
+// busCertificateUsable says whether a certificate and its key are both there and parse.
+//
+// Both, and parsed rather than stat'ed: a half-written pair is the state a bootstrap interrupted
+// between the two files leaves behind, and a step that treated it as done would hand the server a
+// certificate with no key and report success.
+func busCertificateUsable(crt, key string) (bool, error) {
+	certPEM, err := os.ReadFile(crt)
+	if errors.Is(err, os.ErrNotExist) {
+		return false, nil
+	}
+	if err != nil {
+		return false, err
+	}
+	keyPEM, err := os.ReadFile(key)
+	if errors.Is(err, os.ErrNotExist) {
+		return false, nil
+	}
+	if err != nil {
+		return false, err
+	}
+	if _, err := tlsPairParses(certPEM, keyPEM); err != nil {
+		return false, nil
+	}
+	return true, nil
+}
+
+func tlsPairParses(certPEM, keyPEM []byte) (*x509.Certificate, error) {
+	block, _ := pem.Decode(certPEM)
+	if block == nil || block.Type != "CERTIFICATE" {
+		return nil, errors.New("not a certificate")
+	}
+	certificate, err := x509.ParseCertificate(block.Bytes)
+	if err != nil {
+		return nil, err
+	}
+	keyBlock, _ := pem.Decode(keyPEM)
+	if keyBlock == nil {
+		return nil, errors.New("not a key")
+	}
+	if _, err := x509.ParsePKCS8PrivateKey(keyBlock.Bytes); err != nil {
+		if _, err := x509.ParsePKCS1PrivateKey(keyBlock.Bytes); err != nil {
+			return nil, err
+		}
+	}
+	return certificate, nil
+}
+
+func writeBusCertificate(crt, key string) error {
+	private, err := rsa.GenerateKey(rand.Reader, 2048)
+	if err != nil {
+		return err
+	}
+	serial, err := rand.Int(rand.Reader, new(big.Int).Lsh(big.NewInt(1), 128))
+	if err != nil {
+		return err
+	}
+	template := &x509.Certificate{
+		SerialNumber:          serial,
+		Subject:               pkix.Name{CommonName: busCertificateNames[0]},
+		DNSNames:              busCertificateNames,
+		IPAddresses:           []net.IP{net.ParseIP("127.0.0.1")},
+		NotBefore:             time.Now().Add(-time.Hour),
+		NotAfter:              time.Now().Add(busCertificateLife),
+		KeyUsage:              x509.KeyUsageDigitalSignature | x509.KeyUsageKeyEncipherment,
+		ExtKeyUsage:           []x509.ExtKeyUsage{x509.ExtKeyUsageServerAuth},
+		BasicConstraintsValid: true,
+	}
+	der, err := x509.CreateCertificate(rand.Reader, template, template, &private.PublicKey, private)
+	if err != nil {
+		return err
+	}
+	pkcs8, err := x509.MarshalPKCS8PrivateKey(private)
+	if err != nil {
+		return err
+	}
+
+	// **The key first, and only then the certificate**, so the pair a reader finds is never a
+	// certificate whose key has not been written yet — the one order in which an interruption
+	// leaves something that looks finished (novox/hq 04-ISSUES/014, a key present and unusable).
+	if err := os.WriteFile(key, pem.EncodeToMemory(&pem.Block{Type: "PRIVATE KEY", Bytes: pkcs8}), 0o600); err != nil {
+		return err
+	}
+	if err := os.WriteFile(crt, pem.EncodeToMemory(&pem.Block{Type: "CERTIFICATE", Bytes: der}), 0o644); err != nil {
+		return err
+	}
+	fmt.Printf("made the bus a certificate for %v, valid until %s\n  %s\n  %s\n",
+		busCertificateNames, template.NotAfter.Format(time.RFC3339), crt, key)
+	return nil
+}
+
+// busAccounts writes the mesh's composed user list to a file.
+//
+// **For genesis, where no declaration can deliver it** (novox/hq 04-ISSUES/146). Everywhere else
+// the list reaches the machine running the bus as a resource of the module that holds it — which
+// requires that machine to be an enrolled node, and at genesis it is not: the first node cannot
+// enrol because the account it would enrol with cannot be composed onto a bus it has no declaration
+// for. The installer breaks that circle by placing the file itself, once, and the module takes the
+// file over from its first push.
+//
+// The same composition, not a second one: this asks the store for the same records and renders them
+// with the same composer the declaration uses. A genesis that hand-wrote an account would be a
+// second statement of who may say what, able to disagree with the first.
+//
+// **It writes to standard output unless told a file**, and that is the point: the control plane
+// composes and says what it composed, and whoever is raising the machine puts it where that
+// machine's bus reads it. A control plane that wrote into the bus's own directory would have to
+// know where that is and how to make the server re-read it — which is the module's knowledge, and
+// the module is what takes this over on the first push.
+//
+//	broker accounts > /var/lib/mesh-bus-conf/accounts.conf
+func busAccounts(ctx context.Context, args []string) error {
+	into := ""
+	for i := 0; i < len(args); i++ {
+		switch args[i] {
+		case "--into":
+			if i+1 >= len(args) {
+				return errors.New("--into needs a file")
+			}
+			into = args[i+1]
+			i++
+		default:
+			return fmt.Errorf("broker accounts --into <file>: %q", args[i])
+		}
+	}
+
+	open, err := openStores(ctx)
+	if err != nil {
+		return err
+	}
+	defer open.Close()
+
+	records, err := open.inventory.BusRecords(ctx)
+	if err != nil {
+		return err
+	}
+	users, err := broker.Users(records)
+	if err != nil {
+		return err
+	}
+	kept, err := open.inventory.BusUsers(ctx)
+	if err != nil {
+		return err
+	}
+	hashes := make(map[string]string, len(kept))
+	for name, u := range kept {
+		hashes[name] = u.PasswordHash
+	}
+	filled, missing := broker.WithPasswords(users, hashes)
+	if len(missing) > 0 {
+		// To standard error, always: the composed file may be going to standard output, and a
+		// remark in the middle of it is a configuration the server refuses to parse.
+		fmt.Fprintf(os.Stderr, "leaving out %d user(s) the mesh has minted no credential for: %s\n",
+			len(missing), strings.Join(missing, ", "))
+	}
+	if len(filled) == 0 {
+		return errors.New("not one user has a credential, so this list would refuse every " +
+			"connection in the mesh")
+	}
+	accounts, err := broker.ComposeAccounts(filled)
+	if err != nil {
+		return err
+	}
+	if into == "" {
+		fmt.Print(accounts)
+		return nil
+	}
+	if err := os.WriteFile(into, []byte(accounts), 0o600); err != nil {
+		return err
+	}
+	fmt.Printf("wrote %d user(s) to %s\n", len(filled), into)
+	return nil
+}

cmd/mesh-controller/buscertificate_test.go

@@ -0,0 +1,121 @@
+package main
+
+import (
+	"crypto/tls"
+	"crypto/x509"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// novox/hq 04-ISSUES/146. The bootstrap could not make the bus a certificate: it asked an image for
+// `openssl` and the image it asks has none. What replaces it is this command, so what is checked is
+// what the bootstrap needs from it — a pair a TLS server can actually load, made once and only once.
+
+func TestTheBusCertificateLoadsAsAServersWould(t *testing.T) {
+	into := t.TempDir()
+	if err := busCertificate([]string{"--into", into}); err != nil {
+		t.Fatalf("the bus could not be given a certificate: %v", err)
+	}
+
+	// The check a cheaper test would not make. The key was present and valid and the server could
+	// not start, once, because nothing loaded the pair the way a server loads it
+	// (novox/hq 04-ISSUES/014).
+	pair, err := tls.LoadX509KeyPair(filepath.Join(into, "tls.crt"), filepath.Join(into, "tls.key"))
+	if err != nil {
+		t.Fatalf("a TLS server cannot load what was written: %v", err)
+	}
+	leaf := pair.Leaf
+	if leaf == nil {
+		if leaf, err = x509.ParseCertificate(pair.Certificate[0]); err != nil {
+			t.Fatal(err)
+		}
+	}
+	if err := leaf.VerifyHostname("mesh-broker"); err != nil {
+		t.Errorf("the certificate is not for the name the bus is reached by: %v", err)
+	}
+	if len(leaf.IPAddresses) == 0 || leaf.IPAddresses[0].String() != "127.0.0.1" {
+		t.Errorf("the certificate does not cover the loopback address the foundation dials: %v", leaf.IPAddresses)
+	}
+
+	// The key is not readable by anything else on the machine; the certificate is public and is.
+	key, err := os.Stat(filepath.Join(into, "tls.key"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if key.Mode().Perm() != 0o600 {
+		t.Errorf("the key is %v", key.Mode().Perm())
+	}
+	crt, err := os.Stat(filepath.Join(into, "tls.crt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if crt.Mode().Perm() != 0o644 {
+		t.Errorf("the certificate is %v, which the server runs as another user cannot read", crt.Mode().Perm())
+	}
+}
+
+// **Made once.** The step is applied again on every reconcile, and a second certificate is one the
+// hosts that pinned the first no longer believe (novox/hq ADR 0004).
+func TestTheBusCertificateIsMadeOnce(t *testing.T) {
+	into := t.TempDir()
+	if err := busCertificate([]string{"--into", into}); err != nil {
+		t.Fatal(err)
+	}
+	first, err := os.ReadFile(filepath.Join(into, "tls.crt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := busCertificate([]string{"--into", into}); err != nil {
+		t.Fatal(err)
+	}
+	again, err := os.ReadFile(filepath.Join(into, "tls.crt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(first) != string(again) {
+		t.Fatal("running it twice replaced the certificate every host had pinned")
+	}
+}
+
+// The verify half: false before, true after, which is what makes the bootstrap run the step at all.
+func TestTheCheckIsFalseUntilThereIsAPair(t *testing.T) {
+	into := t.TempDir()
+	if err := busCertificate([]string{"--check", "--into", into}); err == nil {
+		t.Fatal("an empty directory reported a usable certificate")
+	}
+	if err := busCertificate([]string{"--into", into}); err != nil {
+		t.Fatal(err)
+	}
+	if err := busCertificate([]string{"--check", "--into", into}); err != nil {
+		t.Fatalf("the certificate it just made does not satisfy its own check: %v", err)
+	}
+}
+
+// A half-written pair is not a pair. An interrupted bootstrap leaves exactly this, and a step that
+// called it done would hand the server a certificate with no key and report success.
+func TestACertificateWithoutItsKeyIsNotUsable(t *testing.T) {
+	into := t.TempDir()
+	if err := busCertificate([]string{"--into", into}); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.Remove(filepath.Join(into, "tls.key")); err != nil {
+		t.Fatal(err)
+	}
+	if err := busCertificate([]string{"--check", "--into", into}); err == nil {
+		t.Fatal("a certificate with no key passed the check")
+	}
+	if err := busCertificate([]string{"--into", into}); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := tls.LoadX509KeyPair(filepath.Join(into, "tls.crt"), filepath.Join(into, "tls.key")); err != nil {
+		t.Fatalf("it did not replace the unusable pair: %v", err)
+	}
+}
+
+func TestWhereToWriteIsRequired(t *testing.T) {
+	if err := busCertificate(nil); err == nil || !strings.Contains(err.Error(), "--into") {
+		t.Fatalf("it did not ask where to write: %v", err)
+	}
+}

cmd/mesh-controller/main.go

@@ -88,7 +88,7 @@ func run() error {
 	case "identity":
 		return identityCommand(ctx, args[1:])
 	case "broker":
-		return brokerCommand(args[1:])
+		return brokerCommand(ctx, args[1:])
 	case "serve":
 		return serve(ctx)
 	case "upgrade":

cmd/mesh-controller/nodes.go

@@ -363,9 +363,15 @@ func identityCommand(ctx context.Context, args []string) error {
 	return nil
 }
 
-func brokerCommand(args []string) error {
+func brokerCommand(ctx context.Context, args []string) error {
+	if len(args) > 0 && args[0] == "certificate" {
+		return busCertificate(args[1:])
+	}
+	if len(args) > 0 && args[0] == "accounts" {
+		return busAccounts(ctx, args[1:])
+	}
 	if len(args) == 0 || args[0] != "show" {
-		return errors.New("broker show")
+		return errors.New("broker show | broker certificate [--check] --into <directory> | broker accounts --into <file>")
 	}
 	known, err := broker.FromEnvironment()
 	if errors.Is(err, broker.ErrNotConfigured) {

internal/broker/genesis_template_test.go

@@ -62,6 +62,22 @@ func TestTheInstallersFirstUserListIsWhatTheControllerWouldCompose(t *testing.T)
 
 // theCarriedAccounts is the accounts file the installer's template writes at genesis.
 func theCarriedAccounts(t *testing.T) string {
+	t.Helper()
+	for _, r := range theTemplate(t) {
+		if r["id"] == "bus-accounts" {
+			content, _ := r["content"].(string)
+			if content == "" {
+				t.Fatal("the template's accounts file is empty, so the bus would refuse every connection")
+			}
+			return content
+		}
+	}
+	t.Fatal("the template carries no accounts file, so a mesh raised from it has a bus nobody may use")
+	return ""
+}
+
+// theTemplate is the installer's bundle, as resources.
+func theTemplate(t *testing.T) []map[string]any {
 	t.Helper()
 	path := filepath.Join("..", "..", "..", "mesh-host", "examples", "foundation-first-node-nats.lock")
 	raw, err := os.ReadFile(path)
@@ -81,17 +97,7 @@ func theCarriedAccounts(t *testing.T) string {
 	if err := json.Unmarshal([]byte(strings.Join(lines, "\n")), &bundle); err != nil {
 		t.Fatalf("the template is not readable: %v", err)
 	}
-	for _, r := range bundle.Resources {
-		if r["id"] == "bus-accounts" {
-			content, _ := r["content"].(string)
-			if content == "" {
-				t.Fatal("the template's accounts file is empty, so the bus would refuse every connection")
-			}
-			return content
-		}
-	}
-	t.Fatal("the template carries no accounts file, so a mesh raised from it has a bus nobody may use")
-	return ""
+	return bundle.Resources
 }
 
 // subjectsIn reads one allow-list out of a composed accounts file.

internal/broker/jetstream.go

@@ -184,7 +184,20 @@ func (j *JetStream) EnsureConsumer(c Consumer) error {
 	// without the other is refused by the server with a message that does not say which half is
 	// missing.
 	if c.Queue != "" || c.Push {
-		want.DeliverSubject = "_DELIVER." + c.Name
+		// **Per consumer, which means per stream as well as per name** (novox/hq 04-ISSUES/146).
+		// A push consumer delivers onto an ordinary subject, and everything subscribed to that
+		// subject gets a copy. The controller holds a consumer called `controller` on CONTROL and
+		// another called `controller` on EVENTS, and both were given `_DELIVER.controller` — so the
+		// one process, holding both subscriptions, acted on every message twice. It enrolled a
+		// joining machine twice from one request, minting a second credential that replaced the one
+		// the machine had just been given; the same doubling applied to every report and every
+		// event the controller follows.
+		//
+		// The stream is in the name because the pair is what identifies a consumer — the server
+		// scopes a durable's name to its stream, and this subject is the only place that scoping
+		// was dropped. Already within what the controller may subscribe (`_DELIVER.controller.>`),
+		// so no permission moves.
+		want.DeliverSubject = DeliverSubjectFor(c)
 	}
 
 	switch _, err := j.js.ConsumerInfo(c.Stream, c.Name); {

internal/broker/nats.go

@@ -269,7 +269,13 @@ func PermissionsFor(p Principal) (Permissions, error) {
 			"mesh.control." + p.Node + ".>",
 			"$JS.API.CONSUMER.INFO.NODES." + p.Node,
 		}
-		sub = []string{"mesh.node." + p.Node + ".declare", "_DELIVER." + p.Node}
+		// The deliver subject carries the stream as well as the consumer's name, so what a
+		// subscriber is permitted has to carry it too (novox/hq 04-ISSUES/146). The bare name
+		// stays: an existing consumer keeps delivering where it always did until the controller's
+		// next assertion moves it, and a permission that only allowed the new shape would refuse
+		// every node in the mesh for exactly as long as that took.
+		sub = []string{"mesh.node." + p.Node + ".declare",
+			"_DELIVER." + p.Node, "_DELIVER." + p.Node + ".>"}
 
 	case KindModule:
 		// 1. Its own namespace: it publishes its events there and serves its tools there. Nothing
@@ -323,7 +329,7 @@ func PermissionsFor(p Principal) (Permissions, error) {
 			// take work over the new bus was refused the asking (2026-09-28).
 			worker := "SEAT_" + upperSnake(s.Name) + "_worker"
 			stream := seatStreamName(s.Name)
-			sub = append(sub, "_DELIVER."+worker)
+			sub = append(sub, "_DELIVER."+worker, "_DELIVER."+worker+".>")
 			pub = append(pub, "$JS.API.CONSUMER.INFO."+stream+"."+worker, "$JS.ACK."+stream+"."+worker+".>")
 			for _, a := range s.Accepts {
 				sub = append(sub, seatSubject(s, "accept", a))

internal/broker/streams.go

@@ -94,6 +94,24 @@ func MeshStreams() []Stream {
 	}
 }
 
+// DeliverSubjectFor is where a push consumer's messages land.
+//
+// **Per consumer, which means per stream as well as per name** (novox/hq 04-ISSUES/146). A push
+// consumer delivers onto an ordinary subject, and everything subscribed to that subject gets a
+// copy. The controller holds a consumer called `controller` on CONTROL and another called
+// `controller` on EVENTS; while both were given `_DELIVER.controller`, the one process holding
+// both subscriptions acted on every message twice — a joining machine was enrolled twice from one
+// request, and the second enrolment minted a credential that replaced the one the machine had just
+// been handed. Every report and every followed event doubled the same way, silently: nothing is
+// redelivered, no count is wrong, the work simply happens twice.
+//
+// The stream belongs in it because the pair is what identifies a consumer — the server scopes a
+// durable's name to its stream, and this subject was the one place that scoping was dropped. It
+// stays inside what a controller may already subscribe (`_DELIVER.controller.>`).
+func DeliverSubjectFor(c Consumer) string {
+	return "_DELIVER." + c.Name + "." + c.Stream
+}
+
 // An Asserter is the part of a JetStream connection stream assertion needs. Narrow on purpose: it
 // keeps this testable without a server, and keeps the client library out of everything that only
 // wants to know what the streams are.

internal/broker/streams_test.go

@@ -233,3 +233,30 @@ func containsStep(steps []string, want string) bool {
 	}
 	return false
 }
+
+// **Two consumers may share a name, and must not share a delivery subject** (novox/hq
+// 04-ISSUES/146).
+//
+// A push consumer delivers onto an ordinary subject and everything subscribed to it gets a copy.
+// The controller holds a consumer called `controller` on CONTROL and another called `controller` on
+// EVENTS; while both were given `_DELIVER.controller`, the one process holding both subscriptions
+// acted on every message twice — a joining machine enrolled twice from one request, with the second
+// enrolment minting a credential that replaced the one the machine had just been handed.
+//
+// Checked here rather than against a server because it is a property of what the mesh asks for, and
+// because the failure it produces is silent: every count is right, nothing is redelivered, and the
+// work simply happens twice.
+func TestNoTwoConsumersDeliverOntoTheSameSubject(t *testing.T) {
+	seen := map[string]string{}
+	for _, c := range MeshConsumers() {
+		if !c.Push && c.Queue == "" {
+			continue
+		}
+		subject := DeliverSubjectFor(c)
+		if other, taken := seen[subject]; taken {
+			t.Errorf("%s on %s and %s deliver onto %s, so whoever holds both acts on every "+
+				"message twice", c.Name, c.Stream, other, subject)
+		}
+		seen[subject] = c.Name + " on " + c.Stream
+	}
+}

internal/broker/testdata/composed.conf

@@ -34,11 +34,11 @@ accounts {
       } }
       { user: "node.one", password: "$2a$11$nnnnnnnnnnnnnnnnnnnnnn", permissions: {
         publish: { allow: ["$JS.ACK.NODES.one.>", "$JS.API.CONSUMER.INFO.NODES.one", "mesh.control.one.>"] }
-        subscribe: { allow: ["_DELIVER.one", "_INBOX.node.one.>", "mesh.node.one.declare"] }
+        subscribe: { allow: ["_DELIVER.one", "_DELIVER.one.>", "_INBOX.node.one.>", "mesh.node.one.declare"] }
       } }
       { user: "one.telegram", password: "$2a$11$tttttttttttttttttttttt", permissions: {
         publish: { allow: ["$JS.ACK.EVENTS.one_telegram.>", "$JS.ACK.SEAT_TELEGRAM_SENDER.SEAT_TELEGRAM_SENDER_worker.>", "$JS.API.CONSUMER.INFO.EVENTS.one_telegram", "$JS.API.CONSUMER.INFO.SEAT_TELEGRAM_SENDER.SEAT_TELEGRAM_SENDER_worker", "$JS.API.CONSUMER.MSG.NEXT.EVENTS.one_telegram", "mesh.seat.telegram-sender.event.delivered", "mesh.seat.telegram-sender.event.failed"] }
-        subscribe: { allow: ["_DELIVER.SEAT_TELEGRAM_SENDER_worker", "_INBOX.one.telegram.>", "mesh.mod.telegram.tool.>", "mesh.seat.telegram-sender.accept.send"] }
+        subscribe: { allow: ["_DELIVER.SEAT_TELEGRAM_SENDER_worker", "_DELIVER.SEAT_TELEGRAM_SENDER_worker.>", "_INBOX.one.telegram.>", "mesh.mod.telegram.tool.>", "mesh.seat.telegram-sender.accept.send"] }
         allow_responses: { max: 1, ttl: "1m" }
       } }
       { user: "two.audit", password: "$2a$11$aaaaaaaaaaaaaaaaaaaaaa", permissions: {

internal/catalogue/catrust_manifest_test.go

@@ -0,0 +1,71 @@
+package catalogue
+
+import (
+	"os"
+	"strings"
+	"testing"
+)
+
+// **A machine trusts the mesh's authority because a module put its root there** (novox/hq ADR
+// 0147, issue 129). The module carries a shell script and a unit, and both are worthless unless
+// the mesh fills in where the authority is — which is the one thing about it the manifest cannot
+// state, because the authority's address is a fact about the mesh and not about the module.
+//
+// So what is checked here is the rendering, not the parsing: the script the machine will run
+// names the authority it was bound to, and the unit runs that script both ways. The verification
+// itself — a plain client trusting an internal name on a machine holding this, and failing on one
+// that does not — is the lab's, and cannot be had here.
+func TestCaTrustRendersTheAuthorityItWasBoundTo(t *testing.T) {
+	raw, err := os.ReadFile("../../../mesh-catalog/modules/ca-trust/module.json")
+	if err != nil {
+		t.Skipf("the catalogue is not beside this checkout: %v", err)
+	}
+	m, err := ParseManifest(raw)
+	if err != nil {
+		t.Fatalf("the trust module does not parse:\n%v", err)
+	}
+
+	r := Resolution{
+		Node:    "workstation",
+		Modules: []Manifest{m},
+		Needs: []Needed{{
+			Name: "internal-acme-ca", From: "anchor", At: "anchor.internal", For: "ca-trust",
+			Serves: map[string]any{
+				"port": float64(9000), "path": "/acme/acme/directory", "roots": "/roots.pem",
+			},
+		}},
+	}
+	out, err := r.Declaration(Rendering{})
+	if err != nil {
+		t.Fatalf("the trust module could not be composed for a machine: %v", err)
+	}
+
+	script := fileNamed(out, "ca-trust.anchor")
+	if script == nil {
+		t.Fatalf("nothing writes the script the unit runs: %v", out)
+	}
+	body, _ := script["content"].(string)
+	if !strings.Contains(body, "https://anchor.internal:9000/roots.pem") {
+		t.Errorf("the script does not fetch from the authority it was bound to:\n%s", body)
+	}
+	if script["mode"] != "0755" {
+		t.Errorf("the script is written %v, which systemd cannot execute", script["mode"])
+	}
+
+	unit := fileNamed(out, "ca-trust.unit")
+	if unit == nil {
+		t.Fatalf("no unit: %v", out)
+	}
+	text, _ := unit["content"].(string)
+	// Both halves. A unit that only installs the anchor leaves a machine trusting an authority
+	// nobody assigned it to any more, which is the half issue 129 asked for by name.
+	for _, want := range []string{
+		"ExecStart=" + script["path"].(string) + " install",
+		"ExecStop=" + script["path"].(string) + " remove",
+		"RemainAfterExit=yes",
+	} {
+		if !strings.Contains(text, want) {
+			t.Errorf("the unit does not say %q:\n%s", want, text)
+		}
+	}
+}

internal/inventory/busrecords_test.go

@@ -8,6 +8,7 @@ import (
 
 	"github.com/novox/mesh-controller/internal/broker"
 	"github.com/novox/mesh-controller/internal/catalogue"
+	"golang.org/x/crypto/bcrypt"
 )
 
 // Reading the bus's user list out of the mesh's records, against a real store.
@@ -164,3 +165,63 @@ func granted(all []string, one string) bool {
 	}
 	return false
 }
+
+// **A token is an account on the bus, or it is a string nothing accepts** (novox/hq 04-ISSUES/146).
+//
+// The composed list names an enrolment user for every machine with a live token, and nothing minted
+// a credential for it — so the composer left it out as a user with no password, and every enrolment
+// since the mesh moved to this bus was refused by the server before the mesh heard of it. Nothing
+// caught it because nothing had enrolled since.
+//
+// The password cannot be minted, because it is the token's own secret: the machine will present
+// exactly that string. So this checks the two halves that make the account usable — that a row
+// exists under the name the composer asks for, and that the secret handed out is what that row
+// accepts.
+func TestIssuingATokenRecordsTheAccountItIsThePasswordOf(t *testing.T) {
+	inv, ctx := aMeshWith(t)
+	if _, err := inv.AddNode(ctx, "joiner"); err != nil {
+		t.Fatal(err)
+	}
+	issued, err := inv.IssueToken(ctx, "joiner", time.Hour)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	name := broker.Principal{Kind: broker.KindEnrolment, Node: "joiner"}.Username()
+	users, err := inv.BusUsers(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	user, has := users[name]
+	if !has {
+		t.Fatalf("no bus account for %q; the composer would leave the enrolment out and the "+
+			"machine would be refused before the mesh heard of it: %v", name, users)
+	}
+	if user.Kind != BusEnrolment || user.Node != "joiner" {
+		t.Errorf("the account is %+v, not this node's enrolment", user)
+	}
+	if err := bcrypt.CompareHashAndPassword([]byte(user.PasswordHash), []byte(issued.Secret)); err != nil {
+		t.Error("the account does not accept the secret the token carries, so presenting the " +
+			"token would be refused by the server")
+	}
+
+	// And the composition contains it, which is the thing the server reads.
+	records, err := inv.BusRecords(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	derived, err := broker.Users(records)
+	if err != nil {
+		t.Fatal(err)
+	}
+	hashes := map[string]string{}
+	for n, u := range users {
+		hashes[n] = u.PasswordHash
+	}
+	_, missing := broker.WithPasswords(derived, hashes)
+	for _, m := range missing {
+		if m == name {
+			t.Fatal("the enrolment user is composed without a password, which is a user nobody can be")
+		}
+	}
+}

internal/inventory/bususers.go

@@ -51,6 +51,40 @@ const (
 // reply, into a module's sealed environment — and the mesh keeps only the hash, so a credential is
 // never recoverable from the store. A caller that loses it must mint again, which is a rotation and
 // is meant to feel like one.
+// RecordBusPassword records a hash for a password the caller already holds.
+//
+// **For the one credential the mesh does not choose**: an enrolment token's secret is the password
+// of the user that presents it (novox/hq ADR 0004, design 25 §6), so the token cannot be given a
+// minted password — it already has one, and the machine will connect with exactly that string.
+// Everything else goes through Mint, which chooses and returns the plaintext once.
+func (i *Inventory) RecordBusPassword(ctx context.Context, u BusUser, password string) error {
+	if u.Username == "" || u.Kind == "" {
+		return errors.New("a bus user needs a username and a kind")
+	}
+	if password == "" {
+		return errors.New("a bus user needs a password")
+	}
+	hash, err := bcrypt.GenerateFromPassword([]byte(password), bcrypt.DefaultCost)
+	if err != nil {
+		return fmt.Errorf("cannot hash a bus password: %w", err)
+	}
+	return i.writeBusUser(ctx, u, string(hash))
+}
+
+// writeBusUser is the row, whoever chose the password.
+func (i *Inventory) writeBusUser(ctx context.Context, u BusUser, hash string) error {
+	if _, err := i.store.Pool().Exec(ctx,
+		`insert into bus_user (username, kind, node, module, password_hash)
+		 values ($1, $2, $3, $4, $5)
+		 on conflict (username) do update
+		   set kind = excluded.kind, node = excluded.node, module = excluded.module,
+		       password_hash = excluded.password_hash, minted_at = now()`,
+		u.Username, u.Kind, u.Node, u.Module, hash); err != nil {
+		return fmt.Errorf("cannot record the bus user %s: %w", u.Username, err)
+	}
+	return nil
+}
+
 func (i *Inventory) MintBusPassword(ctx context.Context, u BusUser) (string, error) {
 	if u.Username == "" || u.Kind == "" {
 		return "", errors.New("a bus user needs a username and a kind")
@@ -69,14 +103,8 @@ func (i *Inventory) MintBusPassword(ctx context.Context, u BusUser) (string, err
 		return "", fmt.Errorf("cannot hash a bus password: %w", err)
 	}
 
-	if _, err := i.store.Pool().Exec(ctx,
-		`insert into bus_user (username, kind, node, module, password_hash)
-		 values ($1, $2, $3, $4, $5)
-		 on conflict (username) do update
-		   set kind = excluded.kind, node = excluded.node, module = excluded.module,
-		       password_hash = excluded.password_hash, minted_at = now()`,
-		u.Username, u.Kind, u.Node, u.Module, string(hash)); err != nil {
-		return "", fmt.Errorf("cannot record the bus user %s: %w", u.Username, err)
+	if err := i.writeBusUser(ctx, u, string(hash)); err != nil {
+		return "", err
 	}
 	return password, nil
 }

internal/inventory/nodes.go

@@ -14,6 +14,7 @@ import (
 	"time"
 
 	"github.com/jackc/pgx/v5"
+	"github.com/novox/mesh-controller/internal/broker"
 	"github.com/novox/mesh-controller/internal/store"
 )
 
@@ -263,6 +264,29 @@ func (i *Inventory) IssueToken(ctx context.Context, nodeName string, validFor ti
 		return Issued{}, err
 	}
 
+	// **And the account that secret is the password of** (novox/hq 04-ISSUES/146). The composed
+	// user list names an enrolment user for every node with a live token, and nothing minted a
+	// credential for it — so the composer left it out as a user with no password and every
+	// enrolment was refused by the server before the mesh heard of it.
+	//
+	// Recorded rather than minted: the token's secret IS the password, which is what lets a
+	// machine's first connection be authenticated by the thing it is enrolling with. It cannot be
+	// chosen here, because it has already been handed to whoever will present it.
+	//
+	// Outside the transaction on purpose. The token is what the mesh promised; a credential that
+	// the next composition rewrites anyway is not worth failing an issue over, and a token with no
+	// account is recoverable by issuing another, while an account with no token is a user nobody
+	// can be.
+	if err := i.RecordBusPassword(ctx, BusUser{
+		Username: broker.Principal{Kind: broker.KindEnrolment, Node: node.Name}.Username(),
+		Kind:     BusEnrolment,
+		Node:     node.Name,
+	}, secret); err != nil {
+		return Issued{}, fmt.Errorf(
+			"the token for %s was issued and the bus account it is the password of was not "+
+				"recorded, so this token cannot connect: %w", node.Name, err)
+	}
+
 	return Issued{Node: node, Secret: secret, Expires: expires}, nil
 }