Run the controller as a Go bundle the host starts as a process (hq issue 213)

The controller is a Go program and was the one piece of the mesh's own Go
code still shipped and run as an image (novox/hq issue 213; ADR 0188 §1:
a module's own code is bundles; §3: a service bundle is a process).

The manifest now builds one Go bundle, `controller`, and runs it as the
process `mesh-controller` (`./mesh-controller serve`) under an account
the module declares. What the container gave it, replaced:

- host network: a process is on the host's network; nothing it reads
  names a container network
- user 65534: the account `mesh-controller`, which owns its secrets and
  its state directory
- the eight mounts: the env names the host paths the mesh already places
  (the store, broker and bus files under the state directory, the
  broker's certificate under /var/lib/mesh-broker-tls); the `broker`
  mount was read by nothing and is gone with the others
- `container-runtime` is no longer required on its machine

Its preparation is the same binary with `prepare`, as a run-once process,
and the process `replaces` the container `server`: the host keeps the
container answering until the process is running (mesh-host). Needs the
previous commit live in the running controller, and the host's
`replaces` on the controller's machine, before it is registered.

No image is built by the mesh any more. The Dockerfile stays for genesis
and the lab (`make image`, its Go base now pinned in the Makefile).

Dockerfile

@@ -1,5 +1,6 @@
 ARG GO_BASE=golang:1.25-alpine
-# The control plane's image.
+# The control plane's image — for genesis and the lab only. The mesh runs the controller as a Go
+# bundle the host starts as a process (module.json; novox/hq issue 213), and builds no image of it.
 #
 # novox/hq ADR 0006: this image is pinned by digest in the bundle the host carries, fetched on a
 # machine where no mesh exists yet, and run before there is anything to check it against. So it

Makefile

@@ -27,17 +27,21 @@ build:
 IMAGE ?= mesh-controller:$(VERSION)
 DEV_TAG ?= mesh-controller:development
 
-# The base the module declares, read from the manifest rather than written here twice.
+# The Go base the image is built on.
 #
 # **`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)
+#
+# **Pinned here since the manifest stopped building an image** (novox/hq issue 213): the mesh builds
+# the controller as a Go bundle with its own toolchain, and only `make image` — genesis and the lab —
+# still needs a Go base. The digest is the one the manifest declared until then.
+GO_BASE ?= golang@sha256:8ac98ca534ac3f51e1f420a1dd2c15e74c75cfa0f23f3ad27eb5d7236c349a0c
 
 image:
-	@test -n "$(GO_BASE)" || { echo "module.json declares no GO_BASE; pass GO_BASE=<image> or fix the manifest"; exit 1; }
+	@test -n "$(GO_BASE)" || { echo "no GO_BASE; pass GO_BASE=<image>"; exit 1; }
 	docker build --build-arg GO_BASE=$(GO_BASE) --build-arg VERSION=$(VERSION) -t $(IMAGE) -t $(DEV_TAG) .
 	@echo
 	@docker image inspect $(IMAGE) --format 'built {{.RepoTags}}  {{.Size}} bytes'
@@ -48,7 +52,7 @@ BUILDER_IMAGE ?= mesh-builder:$(VERSION)
 BUILDER_DEV_TAG ?= mesh-builder:development
 
 builder-image:
-	@test -n "$(GO_BASE)" || { echo "module.json declares no GO_BASE; pass GO_BASE=<image> or fix the manifest"; exit 1; }
+	@test -n "$(GO_BASE)" || { echo "no GO_BASE; pass GO_BASE=<image>"; 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'

README.md

@@ -193,6 +193,13 @@ passes every check that only looks at the message.
 
 ## The image
 
+**The mesh no longer runs the controller from it** (novox/hq issue 213). The module declares a Go
+bundle, `controller`, which the host on the controller's machine unpacks and runs as the process
+`mesh-controller` under the account of the same name (ADR 0188 §1, §3). The image stays for what
+still runs a container of the controller: genesis, which raises the first controller from it and
+installs the module from its manifest (mesh-host `internal/bootstrap`), and the lab. Neither is the
+mesh's own build any more — `make image` builds it.
+
 `FROM scratch`, holding one statically linked binary and nothing else — no shell, no package
 manager, no libc, no CA certificates.
 

cmd/mesh-controller/addresses_test.go

@@ -145,7 +145,7 @@ func TestTheRegistryTrustAndEveryImageFollowThePortTheNodeGaveTheStore(t *testin
 //
 // Composed from the control plane's own manifest against a real inventory: the store's module is
 // given 6852 on this node the way genesis or an operator gives it, and the control plane's
-// container is told so beside the sealed connection genesis wrote.
+// process is told so beside the sealed connection genesis wrote.
 func TestTheControlPlaneIsToldWhereTheNodePutTheStoreAndTheBroker(t *testing.T) {
 	open := aMesh(t)
 	ctx := t.Context()
@@ -157,8 +157,8 @@ func TestTheControlPlaneIsToldWhereTheNodePutTheStoreAndTheBroker(t *testing.T)
 	if err != nil {
 		t.Fatal(err)
 	}
-	control, err := withSeatPorts(m).Resolve([]catalogue.Built{{Name: "server", Kind: catalogue.ArtifactImage,
+	control, err := withSeatPorts(m).Resolve([]catalogue.Built{{Name: "controller", Kind: catalogue.ArtifactBundle,
-		Reference: "registry.example/control@" + aDigest}})
+		Reference: "https://registry.example/mesh-controller/controller.tar.gz", Digest: aDigest}})
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -200,12 +200,12 @@ func TestTheControlPlaneIsToldWhereTheNodePutTheStoreAndTheBroker(t *testing.T)
 
 	var env map[string]any
 	for _, r := range composed(t, open, "anchor").Resources {
-		if r["id"] == "mesh-controller.server" {
+		if r["id"] == "mesh-controller.controller" {
 			env, _ = r["env"].(map[string]any)
 		}
 	}
 	if env == nil {
-		t.Fatal("the control plane's container is not in its own node's declaration")
+		t.Fatal("the control plane's process is not in its own node's declaration")
 	}
 	for key, want := range map[string]string{
 		"MESH_STORE_INVENTORY_PORT": "6852",
@@ -238,7 +238,7 @@ func withSeatPorts(m catalogue.Manifest) catalogue.Manifest {
 	out := m
 	out.Resources = nil
 	for _, r := range m.Resources {
-		if r["type"] != "container" {
+		if r["type"] != "container" && r["type"] != "process" {
 			out.Resources = append(out.Resources, r)
 			continue
 		}

cmd/mesh-controller/build.go

@@ -148,6 +148,11 @@ func buildFrom(result link.BuildResult) inventory.Build {
 		// rebuild the graph rather than a list of names.
 		Path: result.Path,
 	}
+	// When it was asked, which is what orders it against another build of the same module
+	// (novox/hq 04-ISSUES/219) — not when it was heard.
+	if asked, ok := link.BuildAskedAt(result.ID); ok {
+		kept.Asked = asked
+	}
 	for _, ref := range result.Against {
 		kept.Against = append(kept.Against, catalogue.Recorded(ref))
 	}
@@ -409,7 +414,7 @@ func buildOne(ctx context.Context, source buildSource, path, ref string, wait ti
 	// Correlated by something the control plane makes, not by the module's name: two builds of one
 	// module can be in flight, and the second answer is not the first one's.
 	request := link.BuildRequest{
-		ID:         fmt.Sprintf("%s-%d", "build", time.Now().UnixNano()),
+		ID:         link.NewBuildID(time.Now()),
 		Repository: repository,
 		Path:       path,
 		Ref:        ref,
@@ -526,6 +531,9 @@ func takeIn(ctx context.Context, inv *inventory.Inventory, result link.BuildResu
 		BuiltFrom: result.Commit, Head: result.Commit,
 		// What it stood on, so registration can judge a built manifest's base (to-be 38 WP2.4).
 		Against: kept.Against,
+		// When it was asked, so an older request heard later does not replace a newer one
+		// (novox/hq 04-ISSUES/219).
+		Asked: kept.Asked,
 	}
 	if result.Source != nil && result.Source.Seat != "" {
 		recorded.Repository, recorded.Seat = result.Source.Repository, result.Source.Seat
@@ -544,6 +552,10 @@ func takeIn(ctx context.Context, inv *inventory.Inventory, result link.BuildResu
 			result.On, result.Repository, short(result.Commit), err)
 	}
 	if err := inv.RegisterModule(ctx, manifest, recorded); err != nil {
+		if errors.Is(err, inventory.ErrSuperseded) {
+			return manifest, kept, fmt.Errorf("%s built %s (%s), recorded and not registered: %w",
+				result.On, manifest.Module, short(result.Commit), err)
+		}
 		return manifest, kept, err
 	}
 	return manifest, kept, nil
@@ -573,7 +585,7 @@ func buildAndShow(ctx context.Context, source buildSource, path, ref string, wai
 	defer ask.Close()
 
 	result, err := ask.Submit(ctx, link.BuildRequest{
-		ID:         fmt.Sprintf("%s-%d", "build", time.Now().UnixNano()),
+		ID:         link.NewBuildID(time.Now()),
 		Repository: repository, Path: path, Ref: ref,
 		Held: heldBy(ctx), Seats: seatBases(ctx),
 	}, wait)

cmd/mesh-controller/build_test.go

@@ -2,9 +2,12 @@ package main
 
 import (
 	"encoding/json"
+	"errors"
 	"strings"
 	"testing"
+	"time"
 
+	"github.com/novox/mesh-controller/internal/inventory"
 	"github.com/novox/mesh-controller/internal/link"
 )
 
@@ -100,3 +103,50 @@ func TestABuildAtACommitKeepsTheBranchTheModuleFollows(t *testing.T) {
 		t.Errorf("a module first built at a commit follows %q, want the default branch", src.Ref)
 	}
 }
+
+// novox/hq 04-ISSUES/219: an older request heard after a newer one is recorded and not registered,
+// so a push sends what the newer request built.
+func TestAnOlderBuildHeardLaterDoesNotReplaceTheNewer(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	older := time.Date(2026, 10, 3, 21, 33, 45, 0, time.UTC)
+	newer := time.Date(2026, 10, 3, 21, 51, 57, 0, time.UTC)
+	result := func(asked time.Time, image string) link.BuildResult {
+		manifest, _ := json.Marshal(map[string]any{"module": "postgres", "version": image})
+		return link.BuildResult{ID: link.NewBuildID(asked), Repository: "http://forge.internal:20000/novox/mesh-catalog.git",
+			Path: "modules/postgres", Ref: "main", On: "anchor", Commit: "efff5415", Manifest: manifest,
+			Source: &link.SourceOnSeat{Seat: "git", Repository: "novox/mesh-catalog"}}
+	}
+	if _, _, err := takeIn(ctx, open.inventory, result(newer, "4bcd5f73")); err != nil {
+		t.Fatal(err)
+	}
+	_, _, err := takeIn(ctx, open.inventory, result(older, "0ab07fa9"))
+	if !errors.Is(err, inventory.ErrSuperseded) {
+		t.Fatalf("the older request's outcome was taken in as current: %v", err)
+	}
+	shelf, err := open.inventory.Catalogue(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := shelf["postgres"].Version; got != "4bcd5f73" {
+		t.Errorf("postgres is %q; want the newer request's 4bcd5f73", got)
+	}
+	if builds, _ := open.inventory.Builds(ctx, "postgres", 5); len(builds) != 2 {
+		t.Errorf("the late build was not recorded: %v", builds)
+	}
+}
+
+func TestABuildIDSaysWhenItWasAsked(t *testing.T) {
+	at := time.Date(2026, 10, 3, 21, 51, 57, 392539762, time.UTC)
+	if got, ok := link.BuildAskedAt(link.NewBuildID(at)); !ok || !got.Equal(at) {
+		t.Errorf("read back %v %v; want %v", got, ok, at)
+	}
+	if got, ok := link.BuildAskedAt("build-1791064317392539762"); !ok || got.Format(time.TimeOnly) != "21:51:57" {
+		t.Errorf("the incident's id reads as %v %v", got, ok)
+	}
+	for _, id := range []string{"b-1", "build-2", "build-", "build-x", ""} {
+		if _, ok := link.BuildAskedAt(id); ok {
+			t.Errorf("%q read as a request time", id)
+		}
+	}
+}

cmd/mesh-controller/main.go

@@ -8,6 +8,7 @@ package main
 
 import (
 	"context"
+	"errors"
 	"flag"
 	"fmt"
 	"os"
@@ -253,25 +254,34 @@ func parseAround(set *flag.FlagSet, args []string) ([]string, error) {
 // became of a build nobody was watching.
 func (b builds) Built(ctx context.Context, result link.BuildResult) error {
 	manifest, _, err := takeIn(ctx, b.inv, result)
+	// When it was asked, so a plan takes as its outcome only a build asked for it or after it
+	// (novox/hq 04-ISSUES/219). Zero when the id does not say.
+	asked, _ := link.BuildAskedAt(result.ID)
 	switch {
 	case err != nil && result.Failed != "":
 		fmt.Printf("%s: %v\n", result.ID, err)
 		if result.Module != "" {
-			planBuilt(ctx, b.open, result.Module, result.Commit, result.Failed)
+			planBuilt(ctx, b.open, result.Module, result.Commit, result.Failed, asked)
 		} else {
 			planFailedBuild(ctx, b.open, result)
 		}
 		return nil
+	case errors.Is(err, inventory.ErrSuperseded):
+		// Not a failure: the module is already at what a later request built. A plan that asked
+		// before that later request is answered by it; one that asked after it ignores this.
+		fmt.Printf("%s: %v\n", result.ID, err)
+		planBuilt(ctx, b.open, manifest.Module, result.Commit, "", asked)
+		return nil
 	case err != nil:
 		fmt.Printf("%s: heard and recorded, and not registered: %v\n", result.ID, err)
 		if manifest.Module != "" {
-			planBuilt(ctx, b.open, manifest.Module, result.Commit, err.Error())
+			planBuilt(ctx, b.open, manifest.Module, result.Commit, err.Error(), asked)
 		}
 		return nil
 	}
 	fmt.Printf("%s: %s %s registered, built on %s from %s\n",
 		result.ID, manifest.Module, manifest.Version, result.On, short(result.Commit))
 	saysWhenThePolicyActs(ctx, b.inv, manifest.Module)
-	planBuilt(ctx, b.open, manifest.Module, result.Commit, "")
+	planBuilt(ctx, b.open, manifest.Module, result.Commit, "", asked)
 	return nil
 }

cmd/mesh-controller/network_test.go

@@ -254,10 +254,11 @@ func theResolver(t *testing.T) catalogue.Manifest {
 	return m
 }
 
-// The resolver is handed every machine on the private network as a wildcard, and is handed it again
+// The resolver is handed every machine on the private network as a wildcard, the same set and the
-// when a machine leaves — through the module's own manifest asking for the fact, with no module of the
+// same source as the hosts file, and is handed it again when a machine leaves — through the
-// mesh's own in between (hal dnsmasq-app conversion, novox/hq 08-connectivity). It is the mesh's one
+// module's own manifest asking for the fact, with no module of the mesh's own in between (hal
-// resolver (ADR 0194), and the container runtime is given no resolver of its own (ADR 0196).
+// dnsmasq-app conversion, novox/hq 08-connectivity). The runtime on that machine is pointed at the
+// machine's own address, where the resolver answers for its containers.
 func TestTheResolverIsToldEveryMachineOnTheNetworkAndToldAgainWhenOneLeaves(t *testing.T) {
 	open := aMesh(t)
 	ctx := t.Context()
@@ -292,12 +293,11 @@ func TestTheResolverIsToldEveryMachineOnTheNetworkAndToldAgainWhenOneLeaves(t *t
 			t.Errorf("the resolver's machines lack %q:\n%s", want, first)
 		}
 	}
-	// The container runtime is given no resolver of its own (novox/hq ADR 0196): it copies its
-	// machine's, which name the mesh's resolver first. A `dns` key would be a second account of where a
-	// container asks, read only when the runtime starts.
 	for _, r := range composed(t, open, "anchor").Resources {
 		if r["id"] == "dnsmasq.runtime-dns" {
-			t.Errorf("the resolver still writes the runtime's own dns: %v", r)
+			if !strings.Contains(r["content"].(string), `"10.77.0.1"`) || r["into"] != "json" {
+				t.Errorf("the runtime is not pointed at this machine's own address, written into its file: %v", r)
+			}
 		}
 	}
 

cmd/mesh-controller/plan.go

@@ -657,13 +657,6 @@ func renderingFor(ctx context.Context, open *stores, node string,
 		machines[name] = at
 	}
 
-	// And every zone a module in the mesh answers itself (novox/hq ADR 0199), for the mesh's resolver
-	// to forward.
-	zones, err := zonesInTheMesh(ctx, open)
-	if err != nil {
-		return catalogue.Rendering{}, inventory.Node{}, err
-	}
-
 	// **The bus is never public** (novox/hq ADR 0169). It was a foundation port — widened from the
 	// broker's own `from: mesh` to from-anywhere on the broker's host, so a machine could enrol
 	// before it had an address on the private network. A machine joins through the tunnel now, and
@@ -733,7 +726,7 @@ func renderingFor(ctx context.Context, open *stores, node string,
 		BusMembership: memberships[node],
 		Settings:      settings, Generators: gens, Grants: grants, Needed: needed, Ports: ports,
 		Certificate: certificate, Authority: authority, Mesh: private, Names: names,
-		Machines: machines, Zones: zones,
+		Machines: machines,
 		Suffix:   overlay.Suffix(), MeshRange: meshRange, TunnelInterface: overlay.Interface, Accounts: accounts, Foundation: foundation,
 		Kept: kept, Adopted: record.Adopted, OutwardLinks: outwardLinks,
 		Given: given, Taken: taken, Seats: seats, ArtifactStore: artifactStore, Built: built,
@@ -741,71 +734,6 @@ func renderingFor(ctx context.Context, open *stores, node string,
 	}, record, nil
 }
 
-// zonesInTheMesh is every zone a module in the mesh declares, where the mesh placed it (novox/hq ADR
-// 0199): the zone settled from that node's settings, the node's private address, the port the
-// answering listen is published on there.
-//
-// Read across every machine's resolution, as the roster once read routed names: a node whose set does
-// not compose declares nothing and is passed over, so one broken machine does not cost the rest their
-// zones; a store that cannot be read is raised, naming the machine, because returning the zones
-// without it would withdraw them from the resolver as if the operator had (novox/hq 04-ISSUES/152).
-// What the mesh refuses about the zones together — one declared twice, one shadowing the mesh's
-// suffix or a node's public domain — is refused here, by name.
-func zonesInTheMesh(ctx context.Context, open *stores) ([]catalogue.ZoneAt, error) {
-	inv := open.inventory
-	places, err := inv.Overlays(ctx)
-	if err != nil {
-		return nil, fmt.Errorf("where the machines are cannot be read: %w", err)
-	}
-	address := map[string]string{}
-	for _, p := range places {
-		if strings.TrimSpace(p.Address) != "" {
-			address[p.Name] = p.Address
-		}
-	}
-	nodes, err := inv.Nodes(ctx)
-	if err != nil {
-		return nil, fmt.Errorf("which machines the mesh has cannot be read: %w", err)
-	}
-	var zones []catalogue.ZoneAt
-	var public []string
-	for _, n := range nodes {
-		plan, _, err := planFor(ctx, open, n.Name)
-		switch {
-		case unresolvable(err):
-			continue
-		case err != nil:
-			return nil, fmt.Errorf("the zones %s answers cannot be read: %w", n.Name, err)
-		}
-		if plan.PublicDomain != "" {
-			public = append(public, plan.PublicDomain)
-		}
-		for _, m := range plan.Modules {
-			if m.Zone == nil {
-				continue
-			}
-			at := address[n.Name]
-			if at == "" {
-				// Not on the private network yet: nothing could reach its answerer.
-				continue
-			}
-			published, layers, err := portsGivenOn(ctx, inv, n.Name, m)
-			if err != nil {
-				return nil, fmt.Errorf("the zone %s declares on %s cannot be read: %w", m.Module, n.Name, err)
-			}
-			z, err := catalogue.ZoneOn(m, layers, published, n.Name, at)
-			if err != nil {
-				return nil, err
-			}
-			zones = append(zones, *z)
-		}
-	}
-	if problems := catalogue.ZonesProblems(zones, overlay.Suffix(), public); len(problems) > 0 {
-		return nil, fmt.Errorf("the mesh's zones cannot be forwarded:\n  - %s", strings.Join(problems, "\n  - "))
-	}
-	return zones, nil
-}
-
 // certificateFor is what the mesh certifies about one machine's internal name.
 //
 // It reaches across two contexts and reads neither one's store from the other: `inventory` knows

cmd/mesh-controller/plans_one_at_a_time_test.go

@@ -0,0 +1,47 @@
+package main
+
+import (
+	"testing"
+	"time"
+
+	"github.com/novox/mesh-controller/internal/inventory"
+)
+
+// novox/hq issue 213: for the moment a machine hands its controller over, the container and the
+// process both run the plan timer on one store. Only the one holding the plans moves them; the other
+// leaves them alone, and moves them once they are let go.
+func TestAControllerLeavesThePlansToTheOneHoldingThem(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	now := time.Now().UTC()
+	// Every tier done: the next step is the plan's last, and needs nothing but the store.
+	plan := inventory.Plan{ID: "plan-213", Repository: "r", Commit: "abc", Created: now, Updated: now,
+		State: inventory.PlanRolling, Tier: 1, Tiers: [][]string{{"app"}},
+		Modules: map[string]*inventory.PlanModule{"app": {State: "built"}}}
+	if err := open.inventory.SavePlan(ctx, plan); err != nil {
+		t.Fatal(err)
+	}
+
+	// The other controller: its own connections to the same store, holding the plans.
+	other, err := inventory.Open(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(other.Close)
+	release, err := other.HoldPlans(ctx, false)
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(release) // before the close above: a pool waits for a connection still held
+
+	advancePlans(ctx, open)
+	if p, err := open.inventory.PlanByID(ctx, "plan-213"); err != nil || !p.Open() {
+		t.Fatalf("a controller moved a plan another held: %+v %v", p, err)
+	}
+
+	release()
+	advancePlans(ctx, open)
+	if p, err := open.inventory.PlanByID(ctx, "plan-213"); err != nil || p.State != inventory.PlanDone {
+		t.Fatalf("the plan did not move once it was let go: %+v %v", p, err)
+	}
+}

cmd/mesh-controller/release_plan.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"errors"
 	"flag"
 	"fmt"
 	"sort"
@@ -288,8 +289,23 @@ func askTier(ctx context.Context, inv *inventory.Inventory, p *inventory.Plan) e
 
 // planBuilt marks a module built (or failed) in every open plan whose current tier holds it, and
 // advances what that completes. Called from the daemon's take-in of every outcome.
-func planBuilt(ctx context.Context, open *stores, module, commit, failed string) {
+//
+// **Only a build asked at or after the plan's ask is its outcome** (novox/hq 04-ISSUES/219). Two
+// plans a few minutes apart both ask for a module; the earlier plan's build, finishing late, is not
+// the later plan's answer — it stood on the bases from before the later plan's merge, and taking it
+// would send machines, and the next tier, what the later merge replaced. asked is zero when the
+// build's request time is not known, and such an outcome is taken as before.
+func planBuilt(ctx context.Context, open *stores, module, commit, failed string, asked time.Time) {
 	inv := open.inventory
+	// One controller works the plans at a time (novox/hq issue 213); an outcome waits its turn rather
+	// than write over what the holder is about to save. Not taken, it is still in the build records,
+	// which the holder settles the plan from (issue 214).
+	release, err := inv.HoldPlans(ctx, true)
+	if err != nil {
+		fmt.Printf("plans: %s's outcome is left to the build records: %v\n", module, err)
+		return
+	}
+	defer release()
 	plans, err := inv.OpenPlans(ctx)
 	if err != nil {
 		fmt.Printf("plans: cannot read them: %v\n", err)
@@ -315,6 +331,9 @@ func planBuilt(ctx context.Context, open *stores, module, commit, failed string)
 			state = &inventory.PlanModule{}
 			p.Modules[module] = state
 		}
+		if askedBefore(asked, state.AskedAt) {
+			continue
+		}
 		if failed != "" {
 			state.State = "failed"
 			state.Why = failed
@@ -333,13 +352,30 @@ func planBuilt(ctx context.Context, open *stores, module, commit, failed string)
 			fmt.Printf("%s: %s; the tiers after it are not asked\n", p.ID, p.Note)
 		}
 	}
-	advancePlans(ctx, open)
+	advanceHeld(ctx, open)
 }
 
 // advancePlans moves every open plan as far as the facts allow: a tier whose modules are all built
 // and whose gates are applied gives way to the next; the last tier done is the plan done. Called
 // after every outcome and on a timer, so a plan waiting on a machine's report moves when it comes.
+//
+// **One controller at a time** (novox/hq issue 213). A plan is read, changed and saved whole; two
+// controllers — the old and the new while a machine hands its controller over — would each ask a
+// tier the other had just asked. Taken without waiting: whoever holds the plans is moving them.
 func advancePlans(ctx context.Context, open *stores) {
+	release, err := open.inventory.HoldPlans(ctx, false)
+	if err != nil {
+		if !errors.Is(err, inventory.ErrPlansBusy) {
+			fmt.Printf("plans: cannot hold them: %v\n", err)
+		}
+		return
+	}
+	defer release()
+	advanceHeld(ctx, open)
+}
+
+// advanceHeld is advancePlans for a caller already holding the plans.
+func advanceHeld(ctx context.Context, open *stores) {
 	inv := open.inventory
 	plans, err := inv.OpenPlans(ctx)
 	if err != nil {
@@ -549,7 +585,8 @@ func planFailedBuild(ctx context.Context, open *stores, result link.BuildResult)
 	}
 	for _, e := range entries {
 		if repositoryMatches(e.Source.Repository, result.Repository) && e.Source.Path == result.Path {
-			planBuilt(ctx, open, e.Manifest.Module, result.Commit, result.Failed)
+			asked, _ := link.BuildAskedAt(result.ID)
+			planBuilt(ctx, open, e.Manifest.Module, result.Commit, result.Failed, asked)
 			return
 		}
 	}
@@ -666,6 +703,19 @@ func plansCommand(ctx context.Context, args []string) error {
 		}
 		p.State = inventory.PlanFailed
 		p.Note = "stopped by hand at tier " + fmt.Sprint(p.Tier)
+		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)
+		}
+		p.State = inventory.PlanFailed
+		p.Note = "stopped by hand at tier " + fmt.Sprint(p.Tier)
 		if err := inv.SavePlan(ctx, p); err != nil {
 			return err
 		}
@@ -791,6 +841,11 @@ func settleFromRecords(p *inventory.Plan, tier []string, recorded map[string][]i
 			if b.At.Before(*s.AskedAt) {
 				break
 			}
+			// Recorded after the ask and asked before it: an earlier ask's late outcome, not this
+			// one's (novox/hq 04-ISSUES/219).
+			if askedBefore(b.Asked, s.AskedAt) {
+				continue
+			}
 			outcome = &b
 		}
 		if outcome == nil {
@@ -812,3 +867,9 @@ func settleFromRecords(p *inventory.Plan, tier []string, recorded map[string][]i
 	}
 	return changed
 }
+
+// askedBefore is whether a build asked at asked was asked before a plan asked for its module — and
+// so is not that plan's outcome (novox/hq 04-ISSUES/219). False when either time is not known.
+func askedBefore(asked time.Time, planAsked *time.Time) bool {
+	return !asked.IsZero() && planAsked != nil && asked.Before(*planAsked)
+}

cmd/mesh-controller/release_plan_test.go

@@ -155,6 +155,24 @@ func TestAPlanSettlesAnAskedBuildFromTheRecords(t *testing.T) {
 		t.Errorf("an ask with no record after it was settled: %+v", s)
 	}
 
+	// novox/hq 04-ISSUES/219: a build recorded after the ask but asked before it — an earlier
+	// plan's late outcome — is not this ask's, built or failed.
+	r := inventory.Plan{ID: "plan-3", Tiers: [][]string{{"postgres"}},
+		Modules: map[string]*inventory.PlanModule{"postgres": {State: "asked", AskedAt: &asked}}}
+	late := map[string][]inventory.Build{"postgres": {
+		{ID: "build-old", Commit: "efff5415", Asked: asked.Add(-18 * time.Minute), At: asked.Add(12 * time.Minute)},
+	}}
+	if settleFromRecords(&r, r.Tiers[0], late) || r.Modules["postgres"].State != "asked" {
+		t.Errorf("an earlier ask's late outcome settled this ask: %+v", r.Modules["postgres"])
+	}
+	// Newest heard first: the earlier ask's late outcome, then this ask's own, heard before it.
+	late["postgres"] = append(late["postgres"], inventory.Build{ID: "build-mine", Commit: "4bcd5f73",
+		Asked: asked.Add(time.Second), At: asked.Add(5 * time.Minute)})
+	if !settleFromRecords(&r, r.Tiers[0], late) || r.Modules["postgres"].State != "built" ||
+		r.Modules["postgres"].Commit != "4bcd5f73" {
+		t.Errorf("this ask's own outcome, heard before the earlier ask's, did not settle it: %+v", r.Modules["postgres"])
+	}
+
 	// A failure recorded after the ask fails the plan, as hearing it would have.
 	q := inventory.Plan{ID: "plan-2", Tiers: [][]string{{"x"}},
 		Modules: map[string]*inventory.PlanModule{"x": {State: "asked", AskedAt: &asked}}}

cmd/mesh-controller/upgrades.go

@@ -315,6 +315,13 @@ func (f following) SourceMoved(ctx context.Context, m link.SourceMoved) error {
 	for _, e := range moved {
 		movedNames = append(movedNames, e.Manifest.Module)
 	}
+	// Written and its first tier asked as one act on the plans (novox/hq issue 213): a timer on
+	// another controller reading it between the two would ask the tier again.
+	release, err := inv.HoldPlans(ctx, true)
+	if err != nil {
+		return notNow(err)
+	}
+	defer release()
 	plan := planOfMerge(m, movedNames, edges)
 	if hasCycle(plan.Tiers, edges) {
 		fmt.Printf("  the last tier depends on itself: %s — built together, in no order\n",

internal/builder/builder.go

@@ -593,6 +593,12 @@ func one(ctx context.Context, run Runner, publish Publisher,
 		if err != nil {
 			return catalogue.Built{}, fmt.Errorf("%s: writing %s's launchers failed: %w", module, a.Name, err)
 		}
+		if chain.Bundler != "" {
+			say("bundle", "bundling each entrypoint into one file")
+			if compiled, err = bundled(ctx, run, tree, chain, base, a, launchers); err != nil {
+				return catalogue.Built{}, fmt.Errorf("%s: bundling %s failed: %w", module, a.Name, err)
+			}
+		}
 		say("bundle", "compiled, packing")
 		body, err := pack(compiled)
 		if err != nil {
@@ -974,7 +980,7 @@ func compile(ctx context.Context, run Runner, tree string, chain Toolchain,
 	if _, err := run(ctx, tree, "docker", invocation...); err != nil {
 		return "", err
 	}
-	if chain.Dependencies != "" {
+	if chain.Dependencies != "" && chain.Bundler == "" {
 		// **What the bundle runs with, from the image it was compiled in** (Toolchain.Dependencies).
 		// A second run in the same image rather than a shell wrapped around the compiler: the
 		// compile line stays a plain command a reader can run by hand, and the copy is one more
@@ -1224,3 +1230,95 @@ func writeLaunchers(root string, chain Toolchain, a catalogue.Artifact) (map[str
 	}
 	return out, nil
 }
+
+// bundledSuffix is where a bundle's one-file output is written, beside what the compiler wrote.
+const bundledSuffix = ".bundled"
+
+// bundled makes every entrypoint and every launcher of a compiled bundle ONE file, in the toolchain
+// image's bundler, and answers the directory to pack (novox/hq ADR 0193).
+//
+// **What a launched bundle runs is what it imports, and nothing else.** Every served bundle is its
+// own process, so it carries its own copy of the SDK and its own dependencies inlined — the
+// toolchain's whole node_modules no longer travels in every bundle. An entrypoint a process runs by
+// name (`node daemon/index.js`) is bundled in place under its own name; a launcher keeps its name
+// and its first line, and stays executable. A package the bundler cannot inline is named by the
+// artifact (`external`), kept as an import, and only then is the toolchain's runtime directory
+// copied beside the files. CommonJS inlined into an ES module still finds `require`.
+func bundled(ctx context.Context, run Runner, tree string, chain Toolchain, base string,
+	a catalogue.Artifact, launchers map[string]string) (string, error) {
+	const within = "/app/modules/module"
+	out, final := Out(a.Name), Out(a.Name)+bundledSuffix
+	if err := os.RemoveAll(filepath.Join(tree, final)); err != nil {
+		return "", err
+	}
+	if err := os.MkdirAll(filepath.Join(tree, final), 0o755); err != nil {
+		return "", err
+	}
+	common := []string{"--bundle", "--platform=node", "--format=esm", "--target=node22",
+		"--outbase=" + out, "--outdir=" + final, "--log-level=warning",
+		"--banner:js=import { createRequire as __meshRequire } from 'node:module'; const require = __meshRequire(import.meta.url);"}
+	for _, x := range a.External {
+		common = append(common, "--external:"+x)
+	}
+	var plain []string
+	for _, e := range a.Entrypoints {
+		if strings.HasSuffix(e, ".js") {
+			plain = append(plain, out+"/"+e)
+		}
+	}
+	var launch []string
+	for _, l := range sortedValues(launchers) {
+		launch = append(launch, out+"/"+l)
+	}
+	// Refused by name in an image that predates the bundler, as the dependencies copy is: a bundle
+	// packed without it would carry nothing it imports. Run as itself: npm installs esbuild's native
+	// binary in place of its script, which `node` cannot run.
+	guard := `test -x "$0" || { echo "the toolchain image carries no bundler at $0: it predates one-file bundles, rebuild mesh-tools first" >&2; exit 1; }; exec "$0" "$@"`
+	step := func(entries []string, extra ...string) error {
+		if len(entries) == 0 {
+			return nil
+		}
+		invocation := []string{"run", "--rm", "--volume", tree + ":" + within, "--workdir", within, base,
+			"sh", "-c", guard, chain.Bundler}
+		invocation = append(invocation, entries...)
+		invocation = append(invocation, common...)
+		invocation = append(invocation, extra...)
+		_, err := run(ctx, tree, "docker", invocation...)
+		return err
+	}
+	if err := step(plain); err != nil {
+		return "", err
+	}
+	if err := step(launch, "--out-extension:.js=.mjs"); err != nil {
+		return "", err
+	}
+	// Plain `.js` output is an ES module; said once, as the runtime directory used to say it.
+	if err := os.WriteFile(filepath.Join(tree, final, "package.json"), []byte(`{"type":"module","private":true}`+"\n"), 0o644); err != nil {
+		return "", err
+	}
+	for _, l := range launchers {
+		path := filepath.Join(tree, final, filepath.FromSlash(l))
+		if _, err := os.Stat(path); err == nil {
+			if err := os.Chmod(path, 0o755); err != nil {
+				return "", err
+			}
+		}
+	}
+	if len(a.External) > 0 && chain.Dependencies != "" {
+		copying := []string{"run", "--rm", "--volume", tree + ":" + within, "--workdir", within, base,
+			"sh", "-c", `cp -a "$0/node_modules" "$1/"`, chain.Dependencies, final}
+		if _, err := run(ctx, tree, "docker", copying...); err != nil {
+			return "", fmt.Errorf("copying the packages %s keeps external: %w", a.Name, err)
+		}
+	}
+	return filepath.Join(tree, final), nil
+}
+
+func sortedValues(m map[string]string) []string {
+	out := make([]string, 0, len(m))
+	for _, v := range m {
+		out = append(out, v)
+	}
+	sort.Strings(out)
+	return out
+}

internal/builder/bundle_test.go

@@ -83,25 +83,49 @@ func TestABundleIsCompiledAndPackedWithNoDockerfile(t *testing.T) {
 		t.Fatalf("the bundle was not pinned: %v", got.Manifest.Resources[0])
 	}
 
-	// **And what it runs with, from the image it was compiled in** (novox/hq to-be 38 WP3). A
+	// **One file per entrypoint and launcher, in the toolchain's bundler** (novox/hq ADR 0193). A
-	// second run in the same toolchain image copies the toolchain's runtime directory — the
+	// second run in the same toolchain image bundles each into the artifact's bundled output, the SDK
-	// `"type": "module"` package.json and the pruned node_modules — into the output's root, and
+	// inlined, refusing by name in an image that predates the bundler; and the toolchain's
-	// refuses by name when the image carries none rather than packing a bundle that starts nowhere.
+	// node_modules is no longer copied into a bundle that keeps nothing external.
-	var copied string
+	var bundling []string
 	for _, line := range r.ran {
-		if strings.HasPrefix(line, "docker run") && strings.Contains(line, "/app/runtime") {
+		if strings.HasPrefix(line, "docker run") && strings.Contains(line, "esbuild") {
-			copied = line
+			bundling = append(bundling, line)
 		}
 	}
-	if copied == "" {
+	if len(bundling) != 2 {
-		t.Fatalf("the bundle's dependencies were not copied in after the compile:\n%s", strings.Join(r.ran, "\n"))
+		t.Fatalf("want one bundling run for the entrypoints and one for the launchers:\n%s", strings.Join(r.ran, "\n"))
 	}
-	if !strings.Contains(copied, "mesh-tools/build@sha256:") || !strings.Contains(copied, "predates") ||
+	for _, want := range []string{"mesh-tools/build@sha256:", "predates one-file bundles", "--bundle", "--format=esm",
-		!strings.Contains(copied, Out("code")) {
+		"--platform=node", "--outdir=" + Out("code") + ".bundled", Out("code") + "/index.js"} {
-		t.Fatalf("the copy does not run in the same toolchain, refuse an older image by name, or land in the artifact's output: %s", copied)
+		if !strings.Contains(bundling[0], want) {
+			t.Errorf("the entrypoints' bundling lacks %q: %s", want, bundling[0])
 		}
-	if strings.Index(strings.Join(r.ran, "\n"), "--outDir") > strings.Index(strings.Join(r.ran, "\n"), "/app/runtime") {
+	}
-		t.Fatal("the dependencies were copied before the compile wrote its output")
+	if !strings.Contains(bundling[1], Out("code")+"/index.serve.mjs") || !strings.Contains(bundling[1], "--out-extension:.js=.mjs") {
+		t.Errorf("the launcher is not bundled under its own name: %s", bundling[1])
+	}
+	if strings.Contains(strings.Join(r.ran, "\n"), "/app/runtime") {
+		t.Errorf("the toolchain's node_modules was copied into a bundle that keeps nothing external:\n%s", strings.Join(r.ran, "\n"))
+	}
+	if strings.Index(strings.Join(r.ran, "\n"), "--outDir") > strings.Index(strings.Join(r.ran, "\n"), "esbuild") {
+		t.Fatal("the bundler ran before the compile wrote its output")
+	}
+}
+
+// A bundle naming packages it keeps external is bundled with them as imports, and carries the
+// toolchain's node_modules for them — the one case it still does.
+func TestABundleKeepingAPackageExternalCarriesTheToolchainsModules(t *testing.T) {
+	manifest := strings.Replace(aBundle, `"entrypoints":["index.js"]`, `"entrypoints":["index.js"],"external":["sharp"]`, 1)
+	r, workspace := aRepository(t, manifest, map[string]string{"index.ts": "console.log(1)"})
+	held := map[string]string{"mesh-tools/build": "registry.invalid/mesh-tools/build@sha256:" + strings.Repeat("b", 64)}
+	if _, err := Build(context.Background(), compiling{r}.run, r,
+		"https://forge.invalid/greeter.git", "", "", workspace, held, Npmrc{}, GitCredential{}, nil); err != nil {
+		t.Fatal(err)
+	}
+	all := strings.Join(r.ran, "\n")
+	if !strings.Contains(all, "--external:sharp") || !strings.Contains(all, "/app/runtime") {
+		t.Errorf("an external package was not kept as an import with the toolchain's modules beside it:\n%s", all)
 	}
 }
 

internal/builder/standing_on_test.go

@@ -200,3 +200,23 @@ func TestWhatABuildReadIsTheRepositoriesItsRecipesName(t *testing.T) {
 		t.Fatal("a module whose recipes name no other repository read one")
 	}
 }
+
+// novox/hq 04-ISSUES/212: a toolchain stands on the SDK's published package, and is built with the
+// exact version the mesh published — an argument that changes when the SDK does, so a rebuild after
+// a release never reuses an install of the version before it.
+func TestAPackageTheMeshPublishedIsPassedByItsExactVersion(t *testing.T) {
+	manifest := catalogue.Manifest{
+		Module: "mesh-tools",
+		Build: &catalogue.Build{
+			On: []catalogue.BuildsOn{{Arg: "MESH_SDK", Module: "mesh-sdk", Artifact: "lib"}},
+		},
+	}
+	held := map[string]string{"mesh-sdk/lib": "@novox/mesh-sdk@0.1.6"}
+	args, resolved, err := standingOn(context.Background(), manifest, held, noMirror)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if fmt.Sprint(args) != "[--build-arg MESH_SDK=@novox/mesh-sdk@0.1.6]" || fmt.Sprint(resolved) != "[@novox/mesh-sdk@0.1.6]" {
+		t.Errorf("the package was passed as %v, recorded as %v", args, resolved)
+	}
+}

internal/builder/toolchain.go

@@ -73,7 +73,16 @@ type Toolchain struct {
 	//
 	// A toolchain image without the directory fails the build by name rather than packing a bundle
 	// that starts nowhere: the image predates this and must be rebuilt first.
+	//
+	// *Since the bundler (below):* copied only for a bundle that names packages it keeps external,
+	// which cannot be inlined; a bundle with none carries no node_modules at all.
 	Dependencies string
+	// Bundler is the bundler inside the toolchain image that makes each compiled entrypoint and each
+	// launcher ONE self-contained file (novox/hq ADR 0193): every served bundle is its own process
+	// now, so each carries its own copy of what it imports — the SDK included — and nothing else.
+	// A bundle shrinks from the toolchain's whole node_modules to the code it runs. Empty for a
+	// language whose build is already one file.
+	Bundler string
 	// SystemStamp is the variable this language's linker fills with the artifact's declared system,
 	// for a language whose binaries are pinned to one at link time (novox/hq ADR 0005).
 	//
@@ -139,6 +148,7 @@ var toolchains = []Toolchain{
 		Unit:         UnitSources,
 		SourceExt:    ".ts",
 		Dependencies: "/app/runtime",
+		Bundler:      "/app/node_modules/esbuild/bin/esbuild",
 	},
 	{
 		Language: "go",

internal/catalogue/a_service_process_test.go

@@ -0,0 +1,166 @@
+package catalogue
+
+import (
+	"encoding/json"
+	"strings"
+	"testing"
+)
+
+// novox/hq issue 213 (ADR 0188 §1, §3): a module's own Go service is a bundle the host runs as a
+// process, not an image. Each test holds one thing that had to change in the composer for the
+// controller to be declared that way.
+
+const aServiceDigest = "sha256:dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd"
+
+// aServiceModule is the controller's shape in miniature: it answers tools of its own, its code is a
+// Go bundle a process runs as an account it declares, its secrets belong to that account, it
+// prepares its state, and its process replaces the container it used to run as.
+func aServiceModule(t *testing.T) Manifest {
+	t.Helper()
+	raw := `{
+	  "module": "svc", "version": "1", "tools": ["status"], "prepares": true,
+	  "own-secrets": {"store": "${dir:state}/store"},
+	  "secrets-owner": "svc",
+	  "resources": [
+	    {"id": "state", "type": "directory", "mode": "0700", "place": "mesh", "owner": "svc"},
+	    {"id": "service", "type": "process", "name": "svc", "artifact": "code",
+	     "run": ["./svc", "serve"], "user": "svc", "replaces": ["server"],
+	     "env": {"SVC_STORE_FILE": "${dir:state}/store", "SVC_STORE_PORT": "${seat:mesh-store:5432}"}},
+	    {"id": "account", "type": "user", "name": "svc", "shell": "/usr/bin/nologin", "home": "/var/lib/svc"}
+	  ],
+	  "build": {"artifacts": [{"name": "code", "kind": "bundle", "language": "go", "system": "arch",
+	    "from": "cmd/svc", "binary": "svc"}]}
+	}`
+	m, err := ParseManifest([]byte(raw))
+	if err != nil {
+		t.Fatalf("the service's manifest is refused: %v", err)
+	}
+	resolved, err := m.Resolve([]Built{{Name: "code", Kind: ArtifactBundle,
+		Reference: ArtifactStoreScheme + "svc/code@" + aServiceDigest, Digest: aServiceDigest}})
+	if err != nil {
+		t.Fatal(err)
+	}
+	return resolved
+}
+
+func composeTheService(t *testing.T, with Rendering) []map[string]any {
+	t.Helper()
+	with.Needed = map[string]map[string]string{"svc": {"store": "sealed-store"}}
+	with.ArtifactStore = "anchor.internal:5100"
+	out, err := Resolution{Node: "anchor", Modules: []Manifest{aServiceModule(t)}}.Declaration(with)
+	if err != nil {
+		t.Fatalf("the service does not compose: %v", err)
+	}
+	return out
+}
+
+func indexOf(out []map[string]any, id string) int {
+	for i, r := range out {
+		if r["id"] == id {
+			return i
+		}
+	}
+	return -1
+}
+
+// A module that declares tools has every bundle served by the node's runtime unless it says
+// otherwise — and the controller declares the verbs it answers as tools. Its service bundle is run
+// by its own process; launched a second time by the runtime it would be a second controller
+// pretending to be an MCP server.
+func TestABundleItsOwnProcessRunsIsNotServedByTheRuntime(t *testing.T) {
+	m := aServiceModule(t)
+	if len(m.Bundles) != 1 {
+		t.Fatalf("the service's bundle was not kept: %+v", m.Bundles)
+	}
+	if loads := m.Bundles[0].Loads; len(loads) != 0 {
+		t.Fatalf("the runtime would launch the service's own bundle as tools: %v", loads)
+	}
+	// And a bundle no resource runs still is served, as a module declaring tools always had it.
+	tools := Manifest{Module: "t", Version: "1", Tools: []string{"x"},
+		Build: &Build{Artifacts: []Artifact{{Name: "tools", Kind: ArtifactBundle, Language: "go",
+			System: "arch", From: "cmd/t"}}}}
+	resolved, err := tools.Resolve([]Built{{Name: "tools", Kind: ArtifactBundle,
+		Reference: ArtifactStoreScheme + "t/tools@" + aServiceDigest, Digest: aServiceDigest}})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if loads := resolved.Bundles[0].Loads; len(loads) != 1 || loads[0] != "t" {
+		t.Fatalf("a tools bundle nothing runs is no longer served: %v", loads)
+	}
+}
+
+// The account is created before anything is given to it. Its secrets are mesh-computed and so
+// placed before the module's own resources; given to a user the machine did not have yet, they were
+// refused on the first apply and the process started without them.
+func TestAModulesAccountComesBeforeWhatBelongsToIt(t *testing.T) {
+	out := composeTheService(t, Rendering{})
+	account, secret := indexOf(out, "svc.account"), indexOf(out, "svc."+NeedID("store"))
+	if account < 0 || secret < 0 {
+		t.Fatalf("the account or the secret is missing: %v", out)
+	}
+	if account > secret {
+		t.Fatalf("the secret owned by svc is written before svc exists: account at %d, secret at %d",
+			account, secret)
+	}
+	if owner := out[secret]["owner"]; owner != "svc" {
+		t.Errorf("the secret belongs to %v, not the account its process runs as", owner)
+	}
+}
+
+// The process is the module's program; its preparation is the same program asked to prepare, as a
+// step before it — with the same account and environment, and handing nothing over.
+func TestAProcessIsPreparedByItsOwnProgram(t *testing.T) {
+	out := composeTheService(t, Rendering{})
+	step, process := indexOf(out, "svc.service-prepare"), indexOf(out, "svc.service")
+	if step < 0 || process < 0 || step > process {
+		t.Fatalf("the preparation is not a step before the process (%d, %d): %v", step, process, out)
+	}
+	s := out[step]
+	if s["type"] != "process" || s["run-once"] != true || s["name"] != "svc-prepare" {
+		t.Errorf("the preparation is not a run-once process: %v", s)
+	}
+	if run, _ := json.Marshal(s["run"]); string(run) != `["./svc","prepare"]` {
+		t.Errorf("the preparation runs %s", run)
+	}
+	if s["user"] != "svc" || s["source"] != out[process]["source"] {
+		t.Errorf("the preparation does not run the same bundle as the same account: %v", s)
+	}
+	if env, _ := s["env"].(map[string]any); env["SVC_STORE_FILE"] == nil {
+		t.Errorf("the preparation is not given the process's environment: %v", s["env"])
+	}
+	if _, has := s["replaces"]; has {
+		t.Errorf("the preparation would hand over what the process replaces: %v", s)
+	}
+	if _, has := s["args"]; has {
+		t.Errorf("the preparation carries a container's args: %v", s)
+	}
+}
+
+// What the process replaces is named as the host recorded it, `<module>.<id>`; unprefixed, the host
+// matches nothing and removes the container first, as before.
+func TestWhatAProcessReplacesIsNamedAsTheHostRecordedIt(t *testing.T) {
+	out := composeTheService(t, Rendering{})
+	p := out[indexOf(out, "svc.service")]
+	if got, _ := json.Marshal(p["replaces"]); string(got) != `["svc.server"]` {
+		t.Fatalf("the process replaces %s", got)
+	}
+}
+
+func TestWhatReplacesMayNameIsRefusedNearItsAuthor(t *testing.T) {
+	for what, resource := range map[string]string{
+		"a container":        `{"id":"c","type":"container","name":"c","image":"x@` + aServiceDigest + `","replaces":["old"]}`,
+		"a step":             `{"id":"p","type":"process","name":"p","run":["./p"],"run-once":true,"replaces":["old"]}`,
+		"something declared": `{"id":"p","type":"process","name":"p","run":["./p"],"replaces":["p"]}`,
+		"another module's":   `{"id":"p","type":"process","name":"p","run":["./p"],"replaces":["other.old"]}`,
+		"not a list":         `{"id":"p","type":"process","name":"p","run":["./p"],"replaces":"old"}`,
+	} {
+		raw := `{"module":"m","version":"1","resources":[` + resource + `]}`
+		if _, err := ParseManifest([]byte(raw)); err == nil || !strings.Contains(err.Error(), "replace") {
+			t.Errorf("replaces on %s was accepted: %v", what, err)
+		}
+	}
+	ok := `{"module":"m","version":"1","resources":[{"id":"p","type":"process","name":"p","run":["./p"],"replaces":["old"]}]}`
+	if _, err := ParseManifest([]byte(ok)); err != nil {
+		t.Errorf("a process replacing what its module no longer declares was refused: %v", err)
+	}
+}

internal/catalogue/bound_into_files.go

@@ -21,9 +21,8 @@ import (
 // formats and gains no fields.
 //
 // **It stays name-agnostic** ([ADR 0027]). The mesh does not learn what a `postgres-database` is:
-// `at`, `as`, `from` and `address` (the providing machine's private address, novox/hq ADR 0194) are
+// `at`, `as` and `from` are facts about any provision at all, and everything else comes from what
-// facts about any provision at all, and everything else comes from what the provider said it
+// the provider said it serves — whose keys are agreed by the requirement's name, not by this file.
-// serves — whose keys are agreed by the requirement's name, not by this file.
 
 // bound is where a module says a value from one of its bindings belongs:
 // ${bound:<provision>.<key>}.

internal/catalogue/bound_into_files_test.go

@@ -232,34 +232,3 @@ func TestTwoModulesOnOneNodeAreTwoIdentities(t *testing.T) {
 		t.Fatal("one module on two machines shares an identity")
 	}
 }
-
-// A machine's resolver configuration must name its resolver by address — it cannot resolve the name
-// of the thing it resolves names with (novox/hq ADR 0194). So a binding offers the providing
-// machine's private address beside its name, and only when the machine has one.
-func TestABindingOffersTheProvidersAddress(t *testing.T) {
-	consumer := func() Resolution {
-		return Resolution{
-			Node: "workstation",
-			Modules: []Manifest{{
-				Module:   "resolv-conf",
-				Requires: []string{"wildcard-resolution"},
-				Resources: []map[string]any{{
-					"id": "resolv", "type": "file", "path": "/etc/resolv.conf", "mode": "0644",
-					"content": "nameserver ${bound:wildcard-resolution:address}\n",
-				}},
-			}},
-			Needs: []Needed{{Name: "wildcard-resolution", From: "anchor", At: "anchor.internal", For: "resolv-conf"}},
-		}
-	}
-	out, err := consumer().Declaration(Rendering{Machines: map[string]string{"anchor.internal": "10.77.0.1"}})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if got := fileNamed(out, "resolv-conf.resolv")["content"]; got != "nameserver 10.77.0.1\n" {
-		t.Fatalf("the resolver is not named by its address: %q", got)
-	}
-	// A machine with no address yet: refused, never written with a blank where the address belongs.
-	if _, err := consumer().Declaration(Rendering{}); err == nil {
-		t.Fatal("a file naming an address the mesh does not have was composed")
-	}
-}

internal/catalogue/build.go

@@ -77,6 +77,7 @@ func (m Manifest) Resolve(built []Built) (Manifest, error) {
 	// build compare equal.
 	out.Bundles = nil
 	if m.Build != nil {
+		run := runByAResource(m)
 		for _, a := range m.Build.Artifacts {
 			if a.Kind != ArtifactBundle {
 				continue
@@ -84,8 +85,13 @@ func (m Manifest) Resolve(built []Built) (Manifest, error) {
 			made := by[a.Name]
 			// What the runtime loads: what the artifact said, else every entrypoint of a module
 			// that declares tools, else nothing (the field's own rule; see Artifact.Loads).
+			//
+			// **Never, unasked, a bundle one of the module's own resources runs** (novox/hq issue 213).
+			// A process the host runs is the module's service, not its tools: the controller declares
+			// the verbs it answers as `tools` and serves them itself, and its bundle would otherwise
+			// have been launched a second time by the node's runtime, as an MCP child it is not.
 			loads := append([]string(nil), a.Loads...)
-			if a.Loads == nil && len(m.Tools) > 0 {
+			if a.Loads == nil && len(m.Tools) > 0 && !run[a.Name] {
 				loads = append([]string(nil), a.Entrypoints...)
 				// A bundle compiled to a binary has no entrypoints: the binary is what it is, and what
 				// the runtime starts to serve it (novox/hq ADR 0193). So a Go tools bundle is served
@@ -214,6 +220,11 @@ func (b *Build) problems(module string) []string {
 		// A bundle's source is the module's own directory by definition, and what it needs to say
 		// is which compiler — because the mesh chooses that, and cannot choose for a module that
 		// has not said.
+		if len(a.External) > 0 && (a.Kind != ArtifactBundle || a.Language != "typescript") {
+			problems = append(problems, fmt.Sprintf(
+				"%s: %q names packages it keeps external, and only a TypeScript bundle is bundled into "+
+					"one file with some kept out (novox/hq ADR 0193)", module, a.Name))
+		}
 		if len(a.Env) > 0 && a.Kind != ArtifactBundle {
 			problems = append(problems, fmt.Sprintf(
 				"%s: %q is a %q and says what it is given (env). Only a bundle the node's runtime "+
@@ -448,6 +459,18 @@ func BinaryOf(a Artifact) string {
 	return a.Name
 }
 
+// runByAResource is the artifacts one of a module's own resources names — a process that runs it,
+// a step, an archive that unpacks it — by name.
+func runByAResource(m Manifest) map[string]bool {
+	named := map[string]bool{}
+	for _, r := range m.Resources {
+		if a, ok := r["artifact"].(string); ok && a != "" {
+			named[a] = true
+		}
+	}
+	return named
+}
+
 // undeliveredBundles says which of a module's bundles nothing would ever put on a machine (novox/hq
 // 04-ISSUES/216). A bundle reaches a machine three ways: the node's runtime serves it (it says
 // `loads`, or its module declares `tools`), a resource names it (a process, a step, an archive), or
@@ -458,12 +481,7 @@ func undeliveredBundles(m Manifest) []string {
 	if m.Build == nil || m.Module == RuntimeModule {
 		return nil
 	}
-	named := map[string]bool{}
+	named := runByAResource(m)
-	for _, r := range m.Resources {
-		if a, ok := r["artifact"].(string); ok && a != "" {
-			named[a] = true
-		}
-	}
 	var problems []string
 	for _, a := range m.Build.Artifacts {
 		if a.Kind != ArtifactBundle || named[a.Name] || len(a.Loads) > 0 || len(m.Tools) > 0 {

internal/catalogue/controller_is_a_process_test.go

@@ -0,0 +1,131 @@
+package catalogue
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"strings"
+	"testing"
+)
+
+// novox/hq issue 213: the controller is a Go program and was the one piece of the mesh's own Go
+// code still shipped as an image (ADR 0188 §1). Its own manifest, composed for the machine that runs
+// it, is a Go bundle run by the host as a process — and no container.
+func TestTheControllerIsAProcessAndNoContainer(t *testing.T) {
+	raw, err := os.ReadFile("../../module.json")
+	if err != nil {
+		t.Fatal(err)
+	}
+	m, err := ParseManifest(raw)
+	if err != nil {
+		t.Fatalf("the controller's own manifest does not parse:\n%v", err)
+	}
+	if m.Build == nil || len(m.Build.Artifacts) != 1 {
+		t.Fatalf("the controller builds %+v; it is one bundle", m.Build)
+	}
+	a := m.Build.Artifacts[0]
+	if a.Kind != ArtifactBundle || a.Language != "go" || a.System == "" || BinaryOf(a) != "mesh-controller" {
+		t.Fatalf("the controller's artifact is %+v, not a Go bundle naming its system and binary", a)
+	}
+	for _, c := range m.Capabilities {
+		if c == "container-runtime" {
+			t.Error("the controller still requires a container runtime on its machine")
+		}
+	}
+
+	digest := "sha256:" + strings.Repeat("c", 64)
+	control, err := m.Resolve([]Built{{Name: a.Name, Kind: ArtifactBundle,
+		Reference: ArtifactStoreScheme + "mesh-controller/" + a.Name + "@" + digest, Digest: digest}})
+	if err != nil {
+		t.Fatal(err)
+	}
+	// The node's runtime does not launch it: it serves its seat's verbs itself.
+	if loads := control.Bundles[0].Loads; len(loads) != 0 {
+		t.Errorf("the node's runtime would launch the controller as a tools bundle: %v", loads)
+	}
+
+	needed := map[string]map[string]string{"mesh-controller": {}}
+	for name := range m.OwnSecrets {
+		needed["mesh-controller"][name] = "sealed-" + name
+	}
+	out, err := Resolution{Node: "anchor", Modules: []Manifest{control}}.Declaration(Rendering{
+		Needed: needed, ArtifactStore: "anchor.internal:5100",
+		Seats: map[string]map[int]int{"mesh-store": {5432: 6852}},
+	})
+	if err != nil {
+		t.Fatalf("the controller does not compose: %v", err)
+	}
+
+	var process, step map[string]any
+	account, firstSecret := -1, -1
+	for i, r := range out {
+		switch {
+		case r["type"] == "container":
+			t.Errorf("the controller's declaration still runs a container: %v", r)
+		case r["id"] == "mesh-controller.controller":
+			process = r
+		case r["id"] == "mesh-controller.controller-prepare":
+			step = r
+			if process != nil {
+				t.Error("the controller's preparation is placed after the process it prepares for")
+			}
+		case r["type"] == "user" && r["name"] == "mesh-controller":
+			account = i
+		case strings.HasPrefix(fmt.Sprint(r["id"]), "mesh-controller.needs-") && firstSecret < 0:
+			firstSecret = i
+		}
+	}
+	if process == nil {
+		t.Fatalf("the controller's process is not in its declaration: %v", out)
+	}
+	if run, _ := json.Marshal(process["run"]); string(run) != `["./mesh-controller","serve"]` {
+		t.Errorf("the controller is run as %s, not its own bundle's binary", run)
+	}
+	if process["source"] != "anchor.internal:5100/mesh-controller/"+a.Name+"@"+digest || process["digest"] != digest {
+		t.Errorf("the controller's bundle is fetched from %v (%v)", process["source"], process["digest"])
+	}
+	// The user: an account the host declares, which owns what the process reads.
+	if process["user"] != "mesh-controller" || account < 0 {
+		t.Errorf("the controller runs as %v, and the account declared is at %d", process["user"], account)
+	}
+	if firstSecret >= 0 && account > firstSecret {
+		t.Error("the controller's secrets are written before the account they belong to exists")
+	}
+	for _, r := range out {
+		if strings.HasPrefix(fmt.Sprint(r["id"]), "mesh-controller.needs-") && r["owner"] != "mesh-controller" {
+			t.Errorf("%v belongs to %v, which the controller's process cannot read", r["id"], r["owner"])
+		}
+	}
+	if dir := fileNamed(out, "mesh-controller.mesh-state"); dir == nil || dir["owner"] != "mesh-controller" {
+		t.Errorf("the controller's state directory is not its account's to enter: %v", dir)
+	}
+	// Each mount became a path the process reads: nothing it is told is a path inside a container.
+	state := fmt.Sprint(fileNamed(out, "mesh-controller.mesh-state")["path"])
+	env, _ := process["env"].(map[string]any)
+	for key, value := range env {
+		v := fmt.Sprint(value)
+		if strings.HasPrefix(v, "/run/secrets") || strings.HasPrefix(v, "/broker-tls") {
+			t.Errorf("%s=%s is a path inside the container the controller no longer runs in", key, v)
+		}
+		if strings.HasSuffix(key, "_FILE") && !strings.HasPrefix(v, state+"/") {
+			t.Errorf("%s=%s is not one of the files the mesh places for it", key, v)
+		}
+	}
+	if env["MESH_BROKER_CERTIFICATE"] != "/var/lib/mesh-broker-tls/tls.crt" {
+		t.Errorf("the controller reads the broker's certificate from %v", env["MESH_BROKER_CERTIFICATE"])
+	}
+	if env["MESH_STORE_INVENTORY_PORT"] != "6852" {
+		t.Errorf("the controller is told the store is on %v; the node put it on 6852", env["MESH_STORE_INVENTORY_PORT"])
+	}
+	// The handover: the container it ran as goes only once this is running.
+	if got, _ := json.Marshal(process["replaces"]); string(got) != `["mesh-controller.server"]` {
+		t.Errorf("the controller's process replaces %s, not the container it ran as", got)
+	}
+	// And its state is prepared first, by the same program as the same account.
+	if step == nil || step["run-once"] != true || step["user"] != "mesh-controller" {
+		t.Fatalf("the controller's preparation is %v", step)
+	}
+	if run, _ := json.Marshal(step["run"]); string(run) != `["./mesh-controller","prepare"]` {
+		t.Errorf("the controller's preparation runs %s", run)
+	}
+}

internal/catalogue/declaration.go

@@ -155,10 +155,6 @@ type Rendering struct {
 	// standing beside the machines and looking as real as they do.
 	Machines map[string]string
 
-	// Zones is every zone a module in the mesh answers itself, where it is answered (novox/hq ADR
-	// 0199): the mesh's resolver forwards each one there.
-	Zones []ZoneAt
-
 	Settings   SettingsBy
 	Generators map[string]Generator
 	// Grants are the credentials this node must create, for the provisions it offers. Passed in
@@ -697,7 +693,15 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
 
 		// Now, and not before: a module whose resources are computed replaces them wholesale, and
 		// merging earlier would throw away the files it still needs.
-		resources = append(append([]map[string]any{}, first...), resources...)
+		//
+		// **Except the module's own accounts, which go before even those** (novox/hq issue 213). What
+		// the mesh computes may belong to one: a module whose code runs as an account it declares has
+		// its secrets written owned by that account, and a file given to a user the machine does not
+		// have yet fails — so on the first apply the secrets were refused, the process started without
+		// them, and the second apply healed it, which is the fault the paragraph above describes.
+		// An account depends on nothing the mesh computes.
+		accounts, rest := accountsFirst(resources)
+		resources = append(append(accounts, first...), rest...)
 
 		// 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
@@ -736,16 +740,6 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
 				known[provision] = values
 			}
 		}
-		// And the providing machine's private address, beside its name (novox/hq ADR 0194). A name is
-		// what nearly every consumer wants; the one that cannot use it is a machine's resolver
-		// configuration, which must reach the resolver before it can resolve anything — the resolver's
-		// own name included. Absent when the machine has no address yet, so a file naming it is refused
-		// rather than written with a blank where an address belongs.
-		for _, values := range known {
-			if address := with.Machines[values["at"]]; address != "" {
-				values["address"] = address
-			}
-		}
 		// And what the module is called through each requirement it contributes to (novox/hq
 		// 04-ISSUES/122) — the same composition its binding file carries.
 		for provision, values := range known {
@@ -886,6 +880,12 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
 			if renamed := reflectsRenamed(m.Module, resource["reload-on"]); renamed != nil {
 				copied["reload-on"] = renamed
 			}
+			// And what a process replaces (novox/hq issue 213): a resource of this module's that it
+			// no longer declares, named as the host recorded it, or the host hands nothing over and
+			// removes it first.
+			if renamed := reflectsRenamed(m.Module, resource["replaces"]); renamed != nil {
+				copied["replaces"] = renamed
+			}
 			// **What reads one of this module's own secrets is restarted when it changes** (novox/hq
 			// issue 203, issue 206). A credential is re-issued by the mesh, and a container that
 			// mounted the old file keeps the old one open: the build machine ran for an hour on a
@@ -915,7 +915,7 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
 		// plane's; making a name resolve is the module's software. Emitted as ordinary files under
 		// this module's name, so they are applied, reported and removed exactly as anything else
 		// it declares.
-		given, err := FactsWithZonesInto(m, r, with.Names, with.Machines, with.Accounts, with.Suffix, with.Zones)
+		given, err := FactsInto(m, r, with.Names, with.Machines, with.Accounts, with.Suffix)
 		if err != nil {
 			return nil, err
 		}
@@ -2024,12 +2024,18 @@ func preparationTarget(m Manifest) string {
 		return ""
 	}
 	for _, r := range m.Resources {
-		if fmt.Sprint(r["type"]) != "container" || !ownArtifact(r, m.Module) {
+		// A container, or a process the host runs from a bundle the module built (novox/hq issue
+		// 213): the same program in the same context, hosted as a unit rather than a container.
+		kind := fmt.Sprint(r["type"])
+		if (kind != "container" && kind != "process") || !ownArtifact(r, m.Module) {
 			continue
 		}
 		if once, _ := r["run-once"].(bool); once {
 			continue
 		}
+		if r["schedule"] != nil {
+			continue
+		}
 		return fmt.Sprint(r["id"])
 	}
 	return ""
@@ -2043,7 +2049,10 @@ func ownArtifact(resource map[string]any, module string) bool {
 		return true
 	}
 	image, _ := resource["image"].(string)
-	return strings.HasPrefix(image, ArtifactStoreScheme+module+"/")
+	// A process or an archive carries what was built as its source (novox/hq issue 213).
+	source, _ := resource["source"].(string)
+	return strings.HasPrefix(image, ArtifactStoreScheme+module+"/") ||
+		strings.HasPrefix(source, ArtifactStoreScheme+module+"/")
 }
 
 // prepared is the module's own resource as the step that prepares its state: the same image, the same
@@ -2065,7 +2074,19 @@ func prepared(from map[string]any) map[string]any {
 	step["id"] = fmt.Sprint(from["id"]) + "-prepare"
 	step["name"] = fmt.Sprint(from["name"]) + "-prepare"
 	step["run-once"] = true
+	if fmt.Sprint(from["type"]) == "process" {
+		// A process says its whole command: the program, then its arguments. The step is the same
+		// program asked to prepare (novox/hq issue 213). It replaces nothing — what the process
+		// replaces is handed over to the process, never to the step that runs before it — and a
+		// step is not restarted, it runs again when what it reads changed, which `restart-on` says.
+		run := stringsIn(from["run"])
+		if len(run) > 0 {
+			step["run"] = []any{run[0], PreparationArgument}
+		}
+		delete(step, "replaces")
+	} else {
 		step["args"] = []any{PreparationArgument}
+	}
 	delete(step, "ports")
 	delete(step, "ip")
 	delete(step, "schedule")
@@ -2210,3 +2231,16 @@ func withRestartOn(have any, add []string) []any {
 	}
 	return out
 }
+
+// accountsFirst splits a module's resources into its accounts and everything else, each in the order
+// written.
+func accountsFirst(resources []map[string]any) (accounts, rest []map[string]any) {
+	for _, r := range resources {
+		if fmt.Sprint(r["type"]) == "user" {
+			accounts = append(accounts, r)
+			continue
+		}
+		rest = append(rest, r)
+	}
+	return accounts, rest
+}

internal/catalogue/foundation_manifests_test.go

@@ -1,6 +1,7 @@
 package catalogue
 
 import (
+	"encoding/json"
 	"fmt"
 	"os"
 	"reflect"
@@ -170,7 +171,7 @@ func TestTheForgeHoldsTheNpmAndGitSeats(t *testing.T) {
 // **And the forge's own address follows it**, composed from the manifest in the catalogue beside
 // this checkout (novox/hq 04-ISSUES/088).
 //
-// The forge is reached a third way that neither test above covers: by its own sidecar, over the
+// The forge is reached a third way that neither test above covers: by its own code, over the
 // machine's loopback, told where to go in its environment. The `2999:3000` mapping that lets the
 // forge go on binding 3000 does nothing for a caller dialling the machine — so a literal there is
 // wrong on every node whose assignment differs, and wrong for a second reason on a node given the
@@ -178,13 +179,13 @@ func TestTheForgeHoldsTheNpmAndGitSeats(t *testing.T) {
 // in an `env` at all is a declaration, not a manifest.
 func TestTheForgesOwnAddressFollowsThePortTheNodeGaveIt(t *testing.T) {
 	forge, err := catalogueManifest(t, "gitea").Resolve([]Built{{
-		Name: "runtime", Kind: ArtifactImage,
+		Name: "code", Kind: ArtifactBundle,
-		Reference: "registry.example/gitea-runtime@sha256:" + strings.Repeat("a", 64),
+		Reference: ArtifactStoreScheme + "gitea/code/blobs/" + bundleDigest, Digest: bundleDigest,
 	}})
 	if err != nil {
 		t.Fatalf("the forge's manifest does not resolve against its own build: %v", err)
 	}
-	r := Resolution{Node: "anchor", Modules: []Manifest{forge}, Needs: []Needed{
+	r := Resolution{Node: "anchor", Modules: []Manifest{forge, theRuntime(t)}, Needs: []Needed{
 		{Name: "postgres-database", For: "gitea", From: "anchor", At: "127.0.0.1",
 			Serves: map[string]any{"port": float64(5432)}, Sealed: "sealed-db"},
 		{Name: "route", For: "gitea", From: "anchor"},
@@ -194,8 +195,8 @@ func TestTheForgesOwnAddressFollowsThePortTheNodeGaveIt(t *testing.T) {
 
 	// The number this node was given for the forge — the one the machine it is about to run on
 	// already publishes.
-	out, err := r.Declaration(Rendering{
+	out, err := r.Declaration(Rendering{ArtifactStore: "anchor.internal:5101",
-		Needed: map[string]map[string]string{"gitea": {"broker": "sealed-broker"}},
+		Needed: map[string]map[string]string{RuntimeModule: {"broker": "sealed-broker"}},
 		Given:  map[string]map[int]int{"gitea": {3000: 2999}},
 	})
 	if err != nil {
@@ -210,14 +211,19 @@ func TestTheForgesOwnAddressFollowsThePortTheNodeGaveIt(t *testing.T) {
 	if published := fmt.Sprint(server["ports"]); !strings.Contains(published, "2999:3000") {
 		t.Fatalf("the forge is not published on the port this node gave it: %v", server["ports"])
 	}
-	runtime := fileNamed(out, "gitea.runtime")
+	// The forge's own code runs in the node's runtime (novox/hq ADR 0198), given its words there.
+	runtime := fileNamed(out, RuntimeModule+"."+RuntimeProcessID())
 	if runtime == nil {
-		t.Fatalf("the forge's sidecar is not in the declaration: %v", out)
+		t.Fatalf("the node's runtime is not in the declaration: %v", ids(out))
 	}
-	env, _ := runtime["env"].(map[string]any)
+	env, _ := runtime["env"].(map[string]string)
-	if env["MESH_GITEA_URL"] != "http://127.0.0.1:2999" {
+	var given map[string]map[string]string
-		t.Fatalf("the forge's sidecar dials %v while the machine publishes the forge on 2999 — "+
+	if err := json.Unmarshal([]byte(env[RuntimeToolEnv]), &given); err != nil {
-			"whatever reads it dials a dead port", env["MESH_GITEA_URL"])
+		t.Fatalf("the runtime's %s is not JSON: %q", RuntimeToolEnv, env[RuntimeToolEnv])
+	}
+	if given["gitea"]["MESH_GITEA_URL"] != "http://127.0.0.1:2999" {
+		t.Fatalf("the forge's code dials %v while the machine publishes the forge on 2999 — "+
+			"whatever reads it dials a dead port", given["gitea"]["MESH_GITEA_URL"])
 	}
 }
 
@@ -229,13 +235,13 @@ func declaredGiteaSsh(t *testing.T, given map[int]int) map[string]any {
 	t.Helper()
 	forge := catalogueManifest(t, "gitea")
 	resolved, err := forge.Resolve([]Built{{
-		Name: "runtime", Kind: ArtifactImage,
+		Name: "code", Kind: ArtifactBundle,
-		Reference: "registry.example/gitea-runtime@sha256:" + strings.Repeat("a", 64),
+		Reference: ArtifactStoreScheme + "gitea/code/blobs/" + bundleDigest, Digest: bundleDigest,
 	}})
 	if err != nil {
 		t.Fatalf("the forge's manifest does not resolve against its own build: %v", err)
 	}
-	r := Resolution{Node: "anchor", Modules: []Manifest{resolved}, Needs: []Needed{
+	r := Resolution{Node: "anchor", Modules: []Manifest{resolved, theRuntime(t)}, Needs: []Needed{
 		{Name: "postgres-database", For: "gitea", From: "anchor", At: "127.0.0.1",
 			Serves: map[string]any{"port": float64(5432)}, Sealed: "sealed-db"},
 		{Name: "route", For: "gitea", From: "anchor"},
@@ -246,8 +252,8 @@ func declaredGiteaSsh(t *testing.T, given map[int]int) map[string]any {
 	for k, v := range given {
 		givenPorts[k] = v
 	}
-	out, err := r.Declaration(Rendering{
+	out, err := r.Declaration(Rendering{ArtifactStore: "anchor.internal:5101",
-		Needed: map[string]map[string]string{"gitea": {"broker": "sealed-broker"}},
+		Needed: map[string]map[string]string{RuntimeModule: {"broker": "sealed-broker"}},
 		Ports:  map[string]map[int]int{"gitea": givenPorts},
 		Given:  map[string]map[int]int{"gitea": given},
 	})

internal/catalogue/manifest.go

@@ -540,10 +540,6 @@ type Manifest struct {
 	// `restart-on` names to restart when the roster changes.
 	Facts map[string]RosterFile `json:"facts,omitempty"`
 
-	// Zone is the zone of names this module answers itself, and the listen that answers it (novox/hq
-	// ADR 0199). The mesh's resolver forwards the zone to it; nothing here names an address.
-	Zone *Zone `json:"zone,omitempty"`
-
 	// Certificate is where this module wants a certificate for its machine's name inside the
 	// mesh, and where the key that goes with it can be found.
 	//
@@ -761,6 +757,11 @@ type Artifact struct {
 	// list twice. A module declaring no tools has nothing the runtime loads, whatever it compiles.
 	Loads []string `json:"loads,omitempty"`
 
+	// External are packages a TypeScript bundle keeps as imports rather than inlining — a native
+	// addon, a package that reads its own files — and so carries the toolchain's node_modules for
+	// (novox/hq ADR 0193). Absent for nearly every bundle, which is then one file per entrypoint.
+	External []string `json:"external,omitempty"`
+
 	// Env is what a tools bundle is given on a machine (novox/hq ADR 0192): words and their values,
 	// paths and constants composed with ${dir:…} and ${port:…} exactly as a container's environment
 	// is, never a secret's content. The node's runtime hands it to this bundle and to no other.
@@ -1514,6 +1515,53 @@ func ParseManifest(raw []byte) (Manifest, error) {
 				"program that reads what the mesh delivered and reconciles",
 			m.Module, r["id"]))
 	}
+	// **What a process replaces is something the module no longer declares** (novox/hq issue 213).
+	// The host keeps it running until the process is, then removes it: so it is named by the id the
+	// module used to give it, it is never a resource the module still declares — that would be
+	// applied and removed by one declaration — and only a process that stays up has anything to
+	// hand over to. Said here, near the author, as the host would refuse it far away.
+	ids := map[string]bool{}
+	for _, r := range m.Resources {
+		ids[fmt.Sprint(r["id"])] = true
+	}
+	for _, r := range m.Resources {
+		raw, present := r["replaces"]
+		if !present {
+			continue
+		}
+		if fmt.Sprint(r["type"]) != "process" {
+			problems = append(problems, fmt.Sprintf(
+				"%s: %v says what it replaces, and only a process does", m.Module, r["id"]))
+			continue
+		}
+		if once, _ := r["run-once"].(bool); once || r["schedule"] != nil {
+			problems = append(problems, fmt.Sprintf(
+				"%s: %v replaces something and runs once or on a schedule — only a process that stays "+
+					"up is there a moment later to hand over to", m.Module, r["id"]))
+		}
+		list, ok := raw.([]any)
+		if !ok {
+			problems = append(problems, fmt.Sprintf(
+				"%s: %v replaces %v; replaces is a list of the ids this module no longer declares",
+				m.Module, r["id"], raw))
+			continue
+		}
+		for _, item := range list {
+			id, ok := item.(string)
+			switch {
+			case !ok || strings.TrimSpace(id) == "":
+				problems = append(problems, fmt.Sprintf(
+					"%s: %v replaces %v, which is not an id", m.Module, r["id"], item))
+			case strings.Contains(id, "."):
+				problems = append(problems, fmt.Sprintf(
+					"%s: %v replaces %q; a process replaces only a resource of its own module, named "+
+						"by its own id", m.Module, r["id"], id))
+			case ids[id]:
+				problems = append(problems, fmt.Sprintf(
+					"%s: %v replaces %q, which this module still declares", m.Module, r["id"], id))
+			}
+		}
+	}
 	// **A module that prepares its state must have code the mesh can run** (novox/hq ADR 0135). The
 	// preparation is the module's own program in its preparation mode, so it is derived from the
 	// resource that runs that program — and a module declaring none has asked for something the mesh
@@ -1521,7 +1569,7 @@ func ParseManifest(raw []byte) (Manifest, error) {
 	// quietly prepares nothing.
 	if m.Prepares && preparationTarget(m) == "" {
 		problems = append(problems, fmt.Sprintf(
-			"%s says it prepares its state, and declares no container running an artifact it built — "+
+			"%s says it prepares its state, and declares no container or process running an artifact it built — "+
 				"the preparation is this module's own program, so there has to be one for the mesh to "+
 				"run it in", m.Module))
 	}
@@ -1746,7 +1794,6 @@ func ParseManifest(raw []byte) (Manifest, error) {
 		}
 	}
 
-	problems = append(problems, zoneProblems(m)...)
 	if len(problems) > 0 {
 		sort.Strings(problems)
 		return Manifest{}, fmt.Errorf("this manifest cannot be used:\n  - %s",

internal/catalogue/port_into.go

@@ -31,7 +31,7 @@ import (
 //
 // So a module asks. `${port:8080}` is "the machine-side port you gave me for the 8080 I said I
 // listen on", and the module writes that where it would otherwise have written a literal — in a
-// file's content, or in a value of a container's `env`.
+// file's content, or in a value of a container's or a process's `env`.
 //
 // **The environment is filled by the control plane, exactly as a bound value is.** A port is not
 // secret — the mesh holds it in the clear — so there is nothing for the host to be the only
@@ -64,7 +64,12 @@ func portsUsed(content string) []int {
 }
 
 // portInto replaces a resource's ${port:…} placeholders with what this machine assigned — in a
-// file's content, and in a value of a container's environment.
+// file's content, and in a value of a container's or a process's environment.
+//
+// **A process's environment is a container's** (novox/hq to-be 38 WP4c). A module's code moving out
+// of its container becomes a process on the machine and still has to be told what the container
+// was told; filled for one kind and not the other, the literal reached the process and was read as
+// a port, and the modules that moved first wrote their run-once steps a 0600 env file instead.
 //
 // A port the module did not say it listens on is refused, for the same reason a binding's unknown
 // key is: the module is asking about something it never declared, and the answer would be a guess.
@@ -84,7 +89,7 @@ func portInto(resource map[string]any, module string, listens []Listening, with
 		}
 		resource["content"] = filled
 
-	case "container":
+	case "container", "process":
 		env, ok := resource["env"].(map[string]any)
 		if !ok {
 			return nil
@@ -106,8 +111,8 @@ func portInto(resource map[string]any, module string, listens []Listening, with
 				continue
 			}
 			value, err := portsFilledInto(written,
-				fmt.Sprintf("%s's container %s sets %s to something that",
+				fmt.Sprintf("%s's %s %s sets %s to something that",
-					module, resource["name"], key), module, listens, with)
+					module, resource["type"], resource["name"], key), module, listens, with)
 			if err != nil {
 				return err
 			}

internal/catalogue/process_env_test.go

@@ -0,0 +1,80 @@
+package catalogue
+
+import (
+	"strings"
+	"testing"
+)
+
+// **A process's environment is composed as a container's is** (novox/hq to-be 38 WP4c).
+//
+// A module's code moving out of its container becomes a process on the machine, and what its
+// container's environment asked for — the port this machine gave the module, the place it put the
+// module's directory — it still has to be told. Filled for a container and not for a process, the
+// literal `${port:8080}` reached the process as its environment and was read as a port; the modules
+// that moved first wrote their run-once steps an env file instead.
+func processModule(env map[string]any) Manifest {
+	return Manifest{
+		Module:  "showcase",
+		Listens: []Listening{{Port: 8080, From: FromMesh}},
+		Resources: []map[string]any{
+			{"id": "data", "type": "directory", "mode": "0700"},
+			{"id": "setup", "type": "process", "name": "showcase-setup", "run-once": true,
+				"run": []any{"/usr/bin/showcase", "setup"}, "env": env},
+		},
+	}
+}
+
+func TestAProcessIsToldItsPortAndItsPlaceInItsEnvironment(t *testing.T) {
+	env := map[string]any{
+		"SHOWCASE_URL":  "http://127.0.0.1:${port:8080}",
+		"SHOWCASE_DATA": "${dir:data}/objects",
+		"SHOWCASE_DB":   "127.0.0.1:${seat:mesh-store:5432}",
+		"GREETING":      "hello",
+	}
+	out, err := Resolution{Node: "anchor", Modules: []Manifest{processModule(env)}}.Declaration(Rendering{
+		Ports: map[string]map[int]int{"showcase": {8080: 21000}},
+		Seats: map[string]map[int]int{"mesh-store": {5432: 6852}},
+	})
+	if err != nil {
+		t.Fatalf("a process asking for its port and its place does not compose: %v", err)
+	}
+	setup := fileNamed(out, "showcase.setup")
+	if setup == nil {
+		t.Fatalf("the process is not in the declaration: %v", out)
+	}
+	got, _ := setup["env"].(map[string]any)
+	for key, want := range map[string]string{
+		"SHOWCASE_URL":  "http://127.0.0.1:21000",
+		"SHOWCASE_DATA": "/var/lib/showcase/data/objects",
+		"SHOWCASE_DB":   "127.0.0.1:6852",
+		"GREETING":      "hello",
+	} {
+		if got[key] != want {
+			t.Errorf("the process is told %s=%v, want %q", key, got[key], want)
+		}
+	}
+	if env["SHOWCASE_URL"] != "http://127.0.0.1:${port:8080}" {
+		t.Fatalf("composing for one machine edited the module's own manifest: %v", env)
+	}
+}
+
+// An unknown reference in a process's environment is refused as a container's is, naming the
+// process and the variable — left alone, it would reach the machine as a literal.
+func TestAProcessAskingAboutAnUndeclaredPortIsRefused(t *testing.T) {
+	env := map[string]any{"SHOWCASE_URL": "http://127.0.0.1:${port:9999}"}
+	_, err := Resolution{Node: "anchor", Modules: []Manifest{processModule(env)}}.Declaration(Rendering{})
+	if err == nil {
+		t.Fatal("a process was told a port its module never said it listens on")
+	}
+	for _, said := range []string{"showcase-setup", "SHOWCASE_URL", "${port:9999}", "8080"} {
+		if !strings.Contains(err.Error(), said) {
+			t.Errorf("the refusal does not say %q: %v", said, err)
+		}
+	}
+
+	env = map[string]any{"SHOWCASE_DATA": "${dir:date}/objects"}
+	if _, err := (Resolution{Node: "anchor", Modules: []Manifest{processModule(env)}}).Declaration(Rendering{}); err == nil ||
+		!strings.Contains(err.Error(), "${dir:date}") {
+		t.Fatalf("a process naming no directory of its module was not refused: %v", err)
+	}
+}

internal/catalogue/resolver_manifests_test.go

@@ -48,12 +48,9 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
 	}
 	for _, want := range []string{
 		"\nno-resolv\n", "\nserver=1.1.1.1\n", "\nserver=8.8.8.8\n",
-		// The private address and loopback, never a LAN's (novox/hq ADR 0194): a device that is not a
+		// Loopback is the mesh-wide setting's default; a machine answering its own LAN adds its
-		// member cannot reach what the mesh's names point at.
+		// address there (novox/hq issue 198).
-		"\nlisten-address=127.0.0.1\n", "\nlisten-address=${machine:address}\n", "\nbind-dynamic\n",
+		"\nlisten-address=${setting:listen-addresses}\n", "\nlisten-address=${machine:address}\n", "\nbind-dynamic\n",
-		// No hosts file and no operator's files: the mesh's resolver answers every node (ADR 0199).
-		"\nno-hosts\n",
-		"\nconf-file=" + m.Facts["zones"].Path + "\n",
 		"\ndomain-needed\n", "\nbogus-priv\n",
 		"\nconf-file=" + m.Facts["node-zones"].Path + "\n",
 	} {
@@ -76,15 +73,7 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
 			t.Errorf("the resolver listens on %s", taken)
 		}
 	}
-	// Never a directory or a file the operator keeps: a line written for one machine's programs would
+	// And the file that decides what the machine asks names it there, alone.
-	// become an answer for every node (ADR 0199).
-	for _, never := range []string{"conf-dir=", "addn-hosts=", "listen-address=${setting:"} {
-		if strings.Contains(config, never) {
-			t.Errorf("the mesh's resolver still reads or listens on %q", never)
-		}
-	}
-	// And the file that decides what the machine asks names the mesh's resolver first, by address,
-	// and a public one second, asked only when the first is silent (ADR 0196).
 	var resolv string
 	for _, r := range catalogueManifest(t, "resolv-conf").Resources {
 		if r["path"] == "/etc/resolv.conf" {
@@ -97,16 +86,13 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
 			nameservers = append(nameservers, strings.TrimPrefix(line, "nameserver "))
 		}
 	}
-	if len(nameservers) != 2 || nameservers[0] != "${bound:wildcard-resolution:address}" || nameservers[1] != "1.1.1.1" {
+	if len(nameservers) != 1 || nameservers[0] != "127.0.0.1" {
-		t.Errorf("resolv.conf names %v; the mesh's resolver by address first, a public one second", nameservers)
+		t.Errorf("resolv.conf names %v; the predecessor's names the mesh's resolver alone at 127.0.0.1", nameservers)
 	}
-	if !strings.Contains(resolv, "\noptions timeout:1 attempts:1") {
+	// The split-DNS alternative points at the same address, or a machine that keeps
-		t.Errorf("the fallback is not reached after one short attempt:\n%s", resolv)
-	}
-	// The split-DNS alternative points at the same resolver, or a machine that keeps
 	// systemd-resolved in charge would route the mesh's suffix to nothing.
 	for _, r := range catalogueManifest(t, "resolved-split-dns").Resources {
-		if content, _ := r["content"].(string); content != "" && !strings.Contains(content, "DNS=${bound:wildcard-resolution:address}\n") {
+		if content, _ := r["content"].(string); content != "" && !strings.Contains(content, "DNS=127.0.0.1\n") {
 			t.Errorf("resolved-split-dns does not point at the resolver's address:\n%s", content)
 		}
 	}
@@ -114,8 +100,7 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
 
 // The resolver and what points the machine at it compose on one machine, and what arrives is the
 // mesh's account of every machine as a wildcard, the suffix kept local, the daemon restarting on
-// that file, the machine pointed at the resolver by address, and the runtime given no resolver of
+// that file, and the runtime pointed at this machine's own address.
-// its own but kept running across a restart (ADR 0196).
 func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
 	got, err := Resolve(resolverShelf(t), []string{"dnsmasq", "resolv-conf"},
 		Node{Name: "anchor", At: "anchor.internal"}, World{})
@@ -130,7 +115,6 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
 		// issue 111) — the resolver's zones read only the second, and in this scenario the two
 		// happen to be the same map, since nothing routed is part of it.
 		Names: twoMachines, Machines: twoMachines, Suffix: "internal",
-		Zones:    []ZoneAt{{Zone: "incus", Address: "10.42.0.2", Port: 5353}},
 		Needed:   map[string]map[string]string{"dnsmasq": {"broker": "sealed"}},
 		Settings: SettingsBy{"dnsmasq": {{From: "the mesh", Values: map[string]any{"listen-addresses": "127.0.0.1"}}}},
 	})
@@ -160,29 +144,24 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
 	for _, id := range service["restart-on"].([]any) {
 		reflects[id.(string)] = true
 	}
-	if !reflects["dnsmasq.config"] || !reflects["dnsmasq.fact-node-zones"] || !reflects["dnsmasq.fact-zones"] {
+	if !reflects["dnsmasq.config"] || !reflects["dnsmasq.fact-node-zones"] {
-		t.Errorf("the daemon does not restart on its configuration, the machines and the zones: %v", service["restart-on"])
+		t.Errorf("the daemon does not restart on its configuration and the machines file both: %v", service["restart-on"])
-	}
-	if z, _ := ids["dnsmasq.fact-zones"]["content"].(string); !strings.Contains(z, "server=/incus/10.42.0.2#5353\n") {
-		t.Errorf("the resolver was not told to forward the zone to its answerer:\n%s", z)
 	}
 
-	// The runtime's own file, written into (novox/hq ADR 0102) with one key, by what decides how the
+	// The runtime's own file, written into (novox/hq ADR 0102) with the keys this module states:
-	// machine resolves: a restart keeps every container running. No `dns` — a container copies its
+	// where containers resolve, and that a restart keeps them running — because the runtime reads
-	// machine's resolvers (ADR 0196), and the mesh's resolver is not written into the runtime twice.
+	// `dns` only when it starts, and the one restart that needs is the operator's (issue 110).
-	if ids["dnsmasq.runtime-dns"] != nil {
+	runtime := ids["dnsmasq.runtime-dns"]
-		t.Errorf("the resolver still writes the runtime's dns: %v", ids["dnsmasq.runtime-dns"])
-	}
-	runtime := ids["resolv-conf.runtime-config"]
 	if runtime == nil || runtime["path"] != "/etc/docker/daemon.json" || runtime["into"] != "json" {
-		t.Fatalf("live-restore is not written into the runtime's file: %v", runtime)
+		t.Fatalf("the runtime's dns is not written into its file: %v", runtime)
 	}
 	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 || keys["live-restore"] != true {
+	dns, _ := keys["dns"].([]any)
-		t.Errorf("the runtime is given %v; live-restore and nothing else", keys)
+	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.
@@ -192,10 +171,10 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
 			continue
 		}
 		if _, restarts := r["restart-on"]; restarts {
-			t.Errorf("the runtime is ordered restarted, which stops every container (ADR 0102): %v", r)
+			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 == "resolv-conf.runtime-config" {
+			if on == "dnsmasq.runtime-dns" {
 				reloaded = true
 			}
 		}
@@ -205,8 +184,8 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
 	}
 
 	resolv := ids["resolv-conf.resolv"]
-	if resolv == nil || !strings.Contains(resolv["content"].(string), "\nnameserver 10.42.0.1\nnameserver 1.1.1.1\n") {
+	if resolv == nil || !strings.Contains(resolv["content"].(string), "\nnameserver 127.0.0.1\n") {
-		t.Fatalf("the machine is not pointed at the resolver by address, with the public fallback: %v", resolv)
+		t.Fatalf("the machine is not pointed at the resolver: %v", resolv)
 	}
 }
 

internal/catalogue/roster.go

@@ -61,16 +61,6 @@ type rosterView struct {
 	Suffix   string
 	Names    []rosterEntry
 	Machines []rosterEntry
-	// Zones is every zone a module in the mesh answers itself, with where its answerer is (novox/hq
-	// ADR 0199) — what the mesh's resolver forwards. Ordered by zone.
-	Zones []rosterZone
-}
-
-// rosterZone is one zone as a template sees it: the zone, and the address and port answering it.
-type rosterZone struct {
-	Zone    string
-	Address string
-	Port    int
 }
 
 // rosterEntry is one machine as a template sees it: its bare name, its full mesh name, its address,
@@ -90,12 +80,6 @@ type rosterEntry struct {
 // `machines` is only the machines — the two must not be confused (novox/hq 04-ISSUES/111), so both
 // are given and the template chooses.
 func FactsInto(m Manifest, r Resolution, every, machines, accounts map[string]string, suffix string) ([]map[string]any, error) {
-	return FactsWithZonesInto(m, r, every, machines, accounts, suffix, nil)
-}
-
-// FactsWithZonesInto is FactsInto with the mesh's zones in the view, for a template that ranges them.
-func FactsWithZonesInto(m Manifest, r Resolution, every, machines, accounts map[string]string, suffix string,
-	zones []ZoneAt) ([]map[string]any, error) {
 	if len(m.Facts) == 0 {
 		return nil, nil
 	}
@@ -110,7 +94,6 @@ func FactsWithZonesInto(m Manifest, r Resolution, every, machines, accounts map[
 		Suffix:   strings.TrimPrefix(suffixOr(suffix), "."),
 		Names:    entriesFrom(every, accounts, suffix),
 		Machines: entriesFrom(machines, accounts, suffix),
-		Zones:    zonesFrom(zones),
 	}
 
 	out := make([]map[string]any, 0, len(names))
@@ -240,13 +223,3 @@ func sortedNames(addresses map[string]string) []string {
 	sort.Strings(out)
 	return out
 }
-
-// zonesFrom is the zones a template ranges, ordered by zone so two renderings of one mesh are one file.
-func zonesFrom(zones []ZoneAt) []rosterZone {
-	out := make([]rosterZone, 0, len(zones))
-	for _, z := range zones {
-		out = append(out, rosterZone{Zone: z.Zone, Address: z.Address, Port: z.Port})
-	}
-	sort.Slice(out, func(i, j int) bool { return out[i].Zone < out[j].Zone })
-	return out
-}

internal/catalogue/seat_into.go

@@ -43,8 +43,8 @@ import (
 var ofSeat = regexp.MustCompile(`\$\{seat:([a-z0-9][a-z0-9-]*):([0-9]+)\}`)
 
 // seatInto replaces a resource's ${seat:…} placeholders with where this machine put each seat's
-// holder — in a file's content, and in a value of a container's environment. The same two places
+// holder — in a file's content, and in a value of a container's or a process's environment. The
-// portInto fills, for the same reason: they are where a process reads a number from.
+// same places portInto fills, for the same reason: they are where a program reads a number from.
 func seatInto(resource map[string]any, module string, with Rendering) error {
 	switch fmt.Sprint(resource["type"]) {
 	case "file":
@@ -58,7 +58,7 @@ func seatInto(resource map[string]any, module string, with Rendering) error {
 		}
 		resource["content"] = filled
 
-	case "container":
+	case "container", "process":
 		env, ok := resource["env"].(map[string]any)
 		if !ok {
 			return nil
@@ -78,8 +78,8 @@ func seatInto(resource map[string]any, module string, with Rendering) error {
 				continue
 			}
 			value, err := seatsFilledInto(written,
-				fmt.Sprintf("%s's container %s sets %s to something that",
+				fmt.Sprintf("%s's %s %s sets %s to something that",
-					module, resource["name"], key), with)
+					module, resource["type"], resource["name"], key), with)
 			if err != nil {
 				return err
 			}

internal/catalogue/seat_into_test.go

@@ -101,7 +101,7 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
 	}
 	// The manifest itself names them now; withSeatPorts is a no-op on it, and this holds it so.
 	for _, r := range m.Resources {
-		if r["type"] != "container" {
+		if r["type"] != "process" {
 			continue
 		}
 		env, _ := r["env"].(map[string]any)
@@ -113,8 +113,9 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
 	}
 	m = withSeatPorts(m)
 	control, err := m.Resolve([]Built{{
-		Name: "server", Kind: ArtifactImage,
+		Name: "controller", Kind: ArtifactBundle,
-		Reference: ArtifactStoreScheme + "mesh-controller/server@sha256:" + strings.Repeat("c", 64),
+		Reference: ArtifactStoreScheme + "mesh-controller/controller@sha256:" + strings.Repeat("c", 64),
+		Digest:    "sha256:" + strings.Repeat("c", 64),
 	}})
 	if err != nil {
 		t.Fatal(err)
@@ -135,9 +136,9 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
 	if err != nil {
 		t.Fatalf("the control plane does not compose: %v", err)
 	}
-	server := fileNamed(out, "mesh-controller.server")
+	server := fileNamed(out, "mesh-controller.controller")
 	if server == nil {
-		t.Fatalf("the control plane's container is not in the declaration: %v", out)
+		t.Fatalf("the control plane's process is not in the declaration: %v", out)
 	}
 	env, _ := server["env"].(map[string]any)
 	for key, want := range map[string]string{
@@ -151,8 +152,8 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
 			t.Errorf("the control plane is told %s=%v; the node put it on %s", key, env[key], want)
 		}
 	}
-	if got := server["image"]; got != "anchor.internal:5100/mesh-controller/server@sha256:"+strings.Repeat("c", 64) {
+	if got := server["source"]; got != "anchor.internal:5100/mesh-controller/controller@sha256:"+strings.Repeat("c", 64) {
-		t.Errorf("the control plane's own image is %v, not routed through the store", got)
+		t.Errorf("the control plane's own bundle is fetched from %v, not routed through the store", got)
 	}
 
 	// And on a mesh where the foundation is where genesis raised it, nothing is added.
@@ -160,7 +161,7 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	env, _ = fileNamed(out, "mesh-controller.server")["env"].(map[string]any)
+	env, _ = fileNamed(out, "mesh-controller.controller")["env"].(map[string]any)
 	if env["MESH_STORE_INVENTORY_PORT"] != "" {
 		t.Errorf("with no settings, the control plane is told %v", env)
 	}
@@ -186,7 +187,7 @@ func withSeatPorts(m Manifest) Manifest {
 	out := m
 	out.Resources = nil
 	for _, r := range m.Resources {
-		if r["type"] != "container" {
+		if r["type"] != "container" && r["type"] != "process" {
 			out.Resources = append(out.Resources, r)
 			continue
 		}

internal/catalogue/seats.go

@@ -107,31 +107,7 @@ var defaultSeats = []Seat{
 	// that machine unresolvable in the meantime. Deleted once no registered manifest claims it.
 	{Name: "mesh-build-machine", Scope: ScopeMesh,
 		Accepts: []string{"build"}, Emits: []string{"started", "built", "log.*"}, Decision: "novox/hq ADR 0190"},
-	// **The mesh's one resolver** (novox/hq ADR 0194, 0196): every node's internal domain, held in one
-	// place, and every node and container asks it first. Delivers what a machine's resolver
-	// configuration requires, so that requirement resolves to the holder wherever it is placed.
-	{Name: "mesh-dns-resolver", Scope: ScopeMesh, Delivers: "wildcard-resolution", Decision: "novox/hq ADR 0194"},
-	// **Retired by ADR 0194, kept while a manifest still claims it** — the same reason as
-	// mesh-build-machine above: a machine still holds it until the mesh's resolver replaces it, and
-	// removing the row first would make that machine unresolvable. Deleted once nothing claims it.
 	{Name: "node-dns-resolver", Scope: ScopeNode, Decision: "novox/hq ADR 0121"},
-	// **A machine's /etc/hosts is one module's** (novox/hq ADR 0199): its holder writes the machine's
-	// own lines and keeps every other line as the operator's, changed through these three verbs on that
-	// machine alone. The controller holds none of it.
-	{Name: "node-hosts-file", Scope: ScopeNode, Decision: "novox/hq ADR 0199",
-		Serves: []Verb{
-			{Name: "entries", Description: "Every line of this machine's /etc/hosts, each marked whose it is: " +
-				"the operator's, or the block of the module or tool that writes it.",
-				Input: schema(map[string]string{}, nil)},
-			{Name: "add", Description: "Add one address and its names to the operator's lines of this machine's " +
-				"/etc/hosts — a name for this machine's own programs, not the mesh's.",
-				Input: schema(map[string]string{"address": "the IPv4 or IPv6 address",
-					"names": "the names for it, separated by spaces"}, []string{"address", "names"})},
-			{Name: "remove", Description: "Remove one name, or every line of one address, from the operator's " +
-				"lines of this machine's /etc/hosts. A line a module writes is refused, naming the module.",
-				Input: schema(map[string]string{"name": "a host name, or an address to remove every line of"},
-					[]string{"name"})},
-		}},
 	// The intrusion prevention's verbs (novox/hq ADR 0179): what a person asks a machine's ban list
 	// whatever keeps it — who is banned and why, ban one address, let one go. Every holder serves all
 	// four; the jails themselves are composed from the modules the machine runs (to-be 31).

internal/catalogue/seats_test.go

@@ -44,10 +44,10 @@ func TestTheSeatsAreAClosedSetAndEachNamesItsDecision(t *testing.T) {
 			delivered[s.Delivers] = s.Name
 		}
 	}
-	// Nineteen since mesh-dns-resolver (novox/hq ADR 0194) and node-hosts-file (ADR 0199) — two fewer
+	// Seventeen since node-build-agent (novox/hq ADR 0190) — sixteen once the retired
-	// once the retired mesh-build-machine and node-dns-resolver rows go, when no manifest claims either.
+	// mesh-build-machine row goes, when no registered manifest claims it any more.
-	if len(Seats()) != 19 {
+	if len(Seats()) != 17 {
-		t.Errorf("the mesh defines %d seats rather than 19; the set is closed, so a change here is "+
+		t.Errorf("the mesh defines %d seats rather than 17; the set is closed, so a change here is "+
 			"a decision (novox/hq ADR 0110): %s", len(Seats()), seatNames())
 	}
 }

internal/catalogue/zones.go

@@ -1,117 +0,0 @@
-package catalogue
-
-import (
-	"fmt"
-	"sort"
-	"strings"
-)
-
-// Zones: names a module answers itself (novox/hq ADR 0199).
-//
-// The mesh's resolver holds each node's internal domain and nothing else (ADR 0191, 0194). A module
-// whose names are its own — the lab's scenario machines, known only while a scenario runs — declares
-// the zone it answers and the listen that answers it; the controller hands the resolver's holder every
-// zone with the declaring node's private address and the port that listen is published on, and the
-// holder forwards the zone there. **A definition names no address** (ADR 0112): the zone is a setting,
-// the listen is the module's own, and where they are is the mesh's fact.
-
-// Zone is the manifest's declaration that a module answers the names in one zone.
-type Zone struct {
-	// Name is the zone: a label or a dotted name, normally `${setting:<key>}`, so the operator chooses
-	// it and the definition does not.
-	Name string `json:"name"`
-	// Listen names one of the module's listens: the DNS answerer for the zone.
-	Listen string `json:"listen"`
-}
-
-// ZoneAt is a declared zone where the mesh placed it: what the resolver's holder forwards, and where.
-type ZoneAt struct {
-	Zone    string
-	Node    string
-	Module  string
-	Address string
-	Port    int
-}
-
-// zoneProblems is what is wrong with a module's zone declaration on its own, before any node.
-func zoneProblems(m Manifest) []string {
-	if m.Zone == nil {
-		return nil
-	}
-	var problems []string
-	if strings.TrimSpace(m.Zone.Name) == "" {
-		problems = append(problems, fmt.Sprintf("%s declares a zone with no name", m.Module))
-	}
-	if !m.hasListen(m.Zone.Listen) {
-		problems = append(problems, fmt.Sprintf(
-			"%s declares zone %q answered by listen %q, and has no listen of that name",
-			m.Module, m.Zone.Name, m.Zone.Listen))
-	}
-	return problems
-}
-
-func (m Manifest) hasListen(name string) bool {
-	if name == "" {
-		return false
-	}
-	for _, l := range m.Listens {
-		if l.Name == name {
-			return true
-		}
-	}
-	return false
-}
-
-// ZoneOn is one module's zone as one node places it: the name settled from the node's settings, the
-// port its answering listen is published on there. Nothing when the module declares no zone.
-func ZoneOn(m Manifest, layers []Layer, published map[int]int, node, address string) (*ZoneAt, error) {
-	if m.Zone == nil {
-		return nil, nil
-	}
-	settled, err := Settle(map[string]any{"zone": m.Zone.Name}, layers)
-	if err != nil {
-		return nil, fmt.Errorf("%s's zone on %s: %w", m.Module, node, err)
-	}
-	zone := strings.Trim(strings.ToLower(fmt.Sprint(settled["zone"])), ".")
-	var port int
-	for _, l := range m.Listens {
-		if l.Name == m.Zone.Listen {
-			port = l.Port
-			if at, given := published[l.Port]; given {
-				port = at
-			}
-		}
-	}
-	return &ZoneAt{Zone: zone, Node: node, Module: m.Module, Address: address, Port: port}, nil
-}
-
-// ZonesProblems is what the mesh refuses about its zones together: one zone declared twice, a zone
-// that is the mesh's suffix or under it, a zone that is a node's public domain or under one. A module
-// may not shadow names the mesh's resolver or the public DNS answers.
-func ZonesProblems(zones []ZoneAt, suffix string, publicDomains []string) []string {
-	var problems []string
-	under := func(zone, domain string) bool {
-		domain = strings.Trim(strings.ToLower(domain), ".")
-		return domain != "" && (zone == domain || strings.HasSuffix(zone, "."+domain))
-	}
-	seen := map[string]ZoneAt{}
-	for _, z := range zones {
-		if other, twice := seen[z.Zone]; twice && (other.Node != z.Node || other.Module != z.Module) {
-			problems = append(problems, fmt.Sprintf("zone %q is declared by %s on %s and by %s on %s; one module answers a zone",
-				z.Zone, other.Module, other.Node, z.Module, z.Node))
-		}
-		seen[z.Zone] = z
-		if under(z.Zone, suffix) {
-			problems = append(problems, fmt.Sprintf("%s on %s declares zone %q, which is the mesh's own suffix or under it",
-				z.Module, z.Node, z.Zone))
-		}
-		for _, d := range publicDomains {
-			if under(z.Zone, d) {
-				problems = append(problems, fmt.Sprintf("%s on %s declares zone %q, which is the public domain %q or under it",
-					z.Module, z.Node, z.Zone, d))
-			}
-		}
-	}
-	sort.Strings(problems)
-	return problems
-}

internal/catalogue/zones_test.go

@@ -1,78 +0,0 @@
-package catalogue
-
-import (
-	"strings"
-	"testing"
-)
-
-// A zone names the listen that answers it, or there is nothing to forward to (novox/hq ADR 0199).
-func TestAZoneMustNameOneOfTheModulesListens(t *testing.T) {
-	_, err := ParseManifest([]byte(`{"module":"lab","version":"1",
-		"listens":[{"name":"dns","port":5353,"protocol":"udp","from":"mesh","why":"the lab's names"}],
-		"zone":{"name":"${setting:zone}","listen":"web"}}`))
-	if err == nil || !strings.Contains(err.Error(), `has no listen of that name`) {
-		t.Fatalf("a zone answered by a listen the module does not have was accepted: %v", err)
-	}
-	if _, err := ParseManifest([]byte(`{"module":"lab","version":"1",
-		"listens":[{"name":"dns","port":5353,"protocol":"udp","from":"mesh","why":"the lab's names"}],
-		"zone":{"name":"${setting:zone}","listen":"dns"}}`)); err != nil {
-		t.Fatalf("a well-formed zone was refused: %v", err)
-	}
-}
-
-// The zone is the operator's (a setting) and the port is where this machine publishes the listen —
-// neither is the definition's to state.
-func TestAZoneIsPlacedFromTheNodesSettingAndPublishedPort(t *testing.T) {
-	m := Manifest{Module: "lab", Zone: &Zone{Name: "${setting:zone}", Listen: "dns"},
-		Listens: []Listening{{Name: "dns", Port: 5353, From: FromMesh}}}
-	z, err := ZoneOn(m, []Layer{{From: "node", Values: map[string]any{"zone": "Incus."}}},
-		map[int]int{5353: 15353}, "workstation", "10.77.0.3")
-	if err != nil {
-		t.Fatal(err)
-	}
-	if z.Zone != "incus" || z.Address != "10.77.0.3" || z.Port != 15353 || z.Node != "workstation" {
-		t.Fatalf("the zone was placed as %+v", *z)
-	}
-	if _, err := ZoneOn(m, nil, nil, "workstation", "10.77.0.3"); err == nil {
-		t.Fatal("a zone nobody named was placed")
-	}
-}
-
-// One module answers a zone, and none may shadow the mesh's names or a public domain.
-func TestTheMeshRefusesAZoneTwiceOrOneThatShadows(t *testing.T) {
-	one := ZoneAt{Zone: "incus", Node: "workstation", Module: "lab", Address: "10.77.0.3", Port: 53}
-	if p := ZonesProblems([]ZoneAt{one}, "internal", []string{"example.tld"}); len(p) != 0 {
-		t.Fatalf("one ordinary zone was refused: %v", p)
-	}
-	twice := one
-	twice.Node, twice.Module = "laptop", "other"
-	cases := map[string][]ZoneAt{
-		"declared by":       {one, twice},
-		"mesh's own suffix": {{Zone: "lab.internal", Node: "a", Module: "m"}},
-		"public domain":     {{Zone: "dev.example.tld", Node: "a", Module: "m"}},
-	}
-	for want, zones := range cases {
-		p := strings.Join(ZonesProblems(zones, "internal", []string{"example.tld"}), "\n")
-		if !strings.Contains(p, want) {
-			t.Errorf("not refused for %q: %q", want, p)
-		}
-	}
-}
-
-// The resolver's template sees every zone with where it is answered, in zone order.
-func TestTheResolversTemplateRangesTheZones(t *testing.T) {
-	m := Manifest{Module: "dnsmasq", Facts: map[string]RosterFile{"zones": {
-		Path:     "/etc/mesh-resolver/zones.conf",
-		Template: "{{range .Zones}}server=/{{.Zone}}/{{.Address}}#{{.Port}}\n{{end}}",
-	}}}
-	out, err := FactsWithZonesInto(m, Resolution{Node: "anchor"}, nil, nil, nil, "", []ZoneAt{
-		{Zone: "zeta", Address: "10.77.0.2", Port: 53},
-		{Zone: "incus", Address: "10.77.0.3", Port: 15353},
-	})
-	if err != nil {
-		t.Fatal(err)
-	}
-	if got := out[0]["content"]; got != "server=/incus/10.77.0.3#15353\nserver=/zeta/10.77.0.2#53\n" {
-		t.Fatalf("the resolver was told %q", got)
-	}
-}

internal/inventory/builds.go

@@ -42,9 +42,29 @@ type Build struct {
 	// Failed is the builder's own words, empty when it worked.
 	Failed string
 	Made   []Artifact
+	// Asked is when the build was requested, zero when that is not known (an id of another shape,
+	// or a build recorded before the mesh kept it). **What orders one build of a module against
+	// another** (novox/hq 04-ISSUES/219): builds in flight together finish in any order, and the
+	// one asked last stood on the newest bases.
+	Asked time.Time
+	// At is when the outcome was recorded — when it finished, not when it was asked.
 	At time.Time
 }
 
+// AskedOrAt is when the build was asked, or when it was recorded when that is not known — the
+// order the mesh had before it kept the request time.
+func (b Build) AskedOrAt() time.Time {
+	if !b.Asked.IsZero() {
+		return b.Asked
+	}
+	return b.At
+}
+
+// newestRequestFirst is the ordering every "what a module currently is" question uses: the newest
+// request wins, whenever it finished (novox/hq 04-ISSUES/219). A build whose request time is not
+// known is placed at the moment it was recorded, which is the rule that held before.
+const newestRequestFirst = `coalesce(asked, at) desc, at desc`
+
 // ReadRepository is a repository a build read source from besides the module's own.
 type ReadRepository struct {
 	Repository string `json:"repository"`
@@ -83,13 +103,17 @@ func (i *Inventory) RecordBuild(ctx context.Context, b Build) error {
 	if b.Module != "" {
 		module = &b.Module
 	}
+	var asked *time.Time
+	if !b.Asked.IsZero() {
+		asked = &b.Asked
+	}
 	_, err = i.store.Pool().Exec(ctx,
 		`insert into build (id, repository, ref, module, commit_hash, built_on, failed, made,
-		                    source_path, manifest, built_against, built_contexts)
+		                    source_path, manifest, built_against, built_contexts, asked)
-		 values ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12)
+		 values ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12, $13)
 		 on conflict (id) do nothing`,
 		b.ID, b.Repository, b.Ref, module, b.Commit, b.On, b.Failed, made,
-		b.Path, manifestOrNil(b.Manifest), against, read)
+		b.Path, manifestOrNil(b.Manifest), against, read, asked)
 	return err
 }
 
@@ -102,11 +126,11 @@ func (i *Inventory) Builds(ctx context.Context, module string, limit int) ([]Bui
 	if limit <= 0 {
 		limit = 20
 	}
-	query := `select id, repository, ref, coalesce(module,''), commit_hash, built_on, failed, made, at
+	query := `select id, repository, ref, coalesce(module,''), commit_hash, built_on, failed, made, asked, at
 	          from build order by at desc limit $1`
 	args := []any{limit}
 	if module != "" {
-		query = `select id, repository, ref, coalesce(module,''), commit_hash, built_on, failed, made, at
+		query = `select id, repository, ref, coalesce(module,''), commit_hash, built_on, failed, made, asked, at
 		         from build where module = $2 order by at desc limit $1`
 		args = append(args, module)
 	}
@@ -121,10 +145,14 @@ func (i *Inventory) Builds(ctx context.Context, module string, limit int) ([]Bui
 	for rows.Next() {
 		var b Build
 		var made []byte
+		var asked *time.Time
 		if err := rows.Scan(&b.ID, &b.Repository, &b.Ref, &b.Module, &b.Commit,
-			&b.On, &b.Failed, &made, &b.At); err != nil {
+			&b.On, &b.Failed, &made, &asked, &b.At); err != nil {
 			return nil, err
 		}
+		if asked != nil {
+			b.Asked = *asked
+		}
 		if err := json.Unmarshal(made, &b.Made); err != nil {
 			return nil, err
 		}
@@ -135,8 +163,9 @@ func (i *Inventory) Builds(ctx context.Context, module string, limit int) ([]Bui
 
 // Held is every artifact this mesh has built, keyed "<module>/<artifact>".
 //
-// **The newest successful build of each module wins**, which is the same rule the rest of the mesh
+// **The successful build of each module asked last wins**, which is the same rule the rest of the
-// uses for what a module currently is. A module rebuilt to something broken and then rebuilt again
+// mesh uses for what a module currently is — asked last, not finished last (novox/hq
+// 04-ISSUES/219): an older request that finishes later stood on older bases. A module rebuilt to something broken and then rebuilt again
 // is at the second one; a module whose last build failed is at the last one that worked, because a
 // failure published nothing and the thing it published before is still what exists.
 //
@@ -147,7 +176,7 @@ func (i *Inventory) Held(ctx context.Context) (map[string]string, error) {
 		`select distinct on (module) module, made
 		   from build
 		  where module is not null and module <> '' and failed = ''
-		  order by module, at desc`)
+		  order by module, `+newestRequestFirst)
 	if err != nil {
 		return nil, err
 	}
@@ -185,7 +214,7 @@ func (i *Inventory) BuiltAgainst(ctx context.Context) (map[string][]string, erro
 		`select distinct on (module) module, built_against
 		   from build
 		  where module is not null and module <> '' and failed = ''
-		  order by module, at desc`)
+		  order by module, `+newestRequestFirst)
 	if err != nil {
 		return nil, err
 	}
@@ -223,7 +252,7 @@ func (i *Inventory) ReadRepositories(ctx context.Context) (map[string][]ReadRepo
 		`select distinct on (module) module, built_contexts
 		   from build
 		  where module is not null and module <> '' and failed = ''
-		  order by module, at desc`)
+		  order by module, `+newestRequestFirst)
 	if err != nil {
 		return nil, err
 	}
@@ -274,7 +303,7 @@ func manifestOrNil(raw []byte) any {
 // follows when it decides whether to announce at all.
 //
 // One row per module and commit: a module built twice at the same commit is one fact, and the
-// latest row is the one whose artifacts are current.
+// row asked last is the one whose artifacts are current (novox/hq 04-ISSUES/219).
 func (i *Inventory) Announceable(ctx context.Context) ([]Build, error) {
 	rows, err := i.store.Pool().Query(ctx,
 		`select distinct on (module, commit_hash)
@@ -282,7 +311,7 @@ func (i *Inventory) Announceable(ctx context.Context) ([]Build, error) {
 		        source_path, manifest, built_against, at
 		   from build
 		  where failed = '' and module is not null and module <> '' and commit_hash <> ''
-		  order by module, commit_hash, at desc`)
+		  order by module, commit_hash, `+newestRequestFirst)
 	if err != nil {
 		return nil, err
 	}

internal/inventory/busrecords.go

@@ -49,6 +49,12 @@ func (i *Inventory) BusRecords(ctx context.Context) (broker.Records, error) {
 		}
 	}
 
+	// Who holds each seat held once for the mesh, where the mesh recorded it (novox/hq issue 218).
+	holdings, err := i.Holdings(ctx)
+	if err != nil {
+		return broker.Records{}, fmt.Errorf("cannot read who holds the mesh's seats: %w", err)
+	}
+
 	out := broker.Records{Assigned: map[string][]broker.Declared{}, People: map[string][]string{},
 		Interchangeable: map[string]bool{}}
 	for _, n := range nodes {
@@ -72,7 +78,9 @@ func (i *Inventory) BusRecords(ctx context.Context) (broker.Records, error) {
 					"%s is assigned to %s and is not in the catalogue, so what it may say cannot "+
 						"be derived", module, n.Name)
 			}
-			out.Assigned[n.Name] = append(out.Assigned[n.Name], declaredFor(m, seats))
+			d := declaredFor(m, seats)
+			d.Holds = heldHere(d.Holds, holdings, n.Name, module)
+			out.Assigned[n.Name] = append(out.Assigned[n.Name], d)
 			if m.Instances == catalogue.InstancesInterchangeable {
 				out.Interchangeable[m.Module] = true
 			}
@@ -183,3 +191,33 @@ func (i *Inventory) NodesWithALiveToken(ctx context.Context) ([]string, error) {
 	}
 	return out, rows.Err()
 }
+
+// heldHere keeps of what a module claims only the seats it holds on this machine (novox/hq issue 218).
+// A seat held once per machine is held by every assignment that claims it. A seat held once for the
+// mesh is held by one assignment: where the mesh recorded who holds it, a claim on any other machine
+// grants nothing and issues nothing — or the module would serve the role's verbs from a machine that
+// is not the role's, and a question to the mesh's store would be answered from the wrong database. A
+// mesh seat with no holder on record is left as it was derived.
+func heldHere(claimed []broker.Seat, holdings []catalogue.Held, node, module string) []broker.Seat {
+	recorded := map[string][]catalogue.Held{}
+	for _, h := range holdings {
+		if h.Scope == catalogue.ScopeMesh {
+			recorded[h.Claim] = append(recorded[h.Claim], h)
+		}
+	}
+	var out []broker.Seat
+	for _, s := range claimed {
+		holders, onRecord := recorded[s.Name]
+		if s.Scope != catalogue.ScopeMesh || !onRecord {
+			out = append(out, s)
+			continue
+		}
+		for _, h := range holders {
+			if h.Node == node && h.Module == module {
+				out = append(out, s)
+				break
+			}
+		}
+	}
+	return out
+}

internal/inventory/catalogue.go

@@ -17,6 +17,10 @@ import (
 // ErrNoSuchModule is what the mesh says about a module it has never been told about.
 var ErrNoSuchModule = errors.New("no module of that name")
 
+// ErrSuperseded is a registration from a build asked before the one the module is already at
+// (novox/hq 04-ISSUES/219). The build is recorded; what the module is does not change.
+var ErrSuperseded = errors.New("a build asked later is already what the module is")
+
 // ErrStillAssigned is why a module cannot be forgotten.
 //
 // Its own error because it is not a fault: it means a machine is running that module now, and
@@ -47,6 +51,10 @@ type Source struct {
 	// itself no longer carries its build (novox/hq to-be 38 WP2.4). Empty for a manifest handed over
 	// by hand, which carries its `build.on` itself.
 	Against []string
+	// Asked is when the build this manifest came from was requested (novox/hq 04-ISSUES/219). Zero
+	// is a manifest handed over by hand, or a build whose request time is not known: either is
+	// taken as asked at the moment it is registered.
+	Asked time.Time
 }
 
 // Current reports whether what the mesh holds is what the source last had.
@@ -97,13 +105,23 @@ func (i *Inventory) RegisterModule(ctx context.Context, m catalogue.Manifest, fr
 		return err
 	}
 
+	asked := from.Asked
+	if asked.IsZero() {
+		asked = time.Now()
+	}
+
 	// A module registered without provenance keeps whatever it had. Handing over a manifest by
 	// hand is a legitimate way to fix something in a hurry, and it should not silently erase the
 	// record of where the module normally comes from — which is the only thing that would say,
 	// afterwards, that the machine is running something nobody can rebuild.
-	_, err = i.store.Pool().Exec(ctx,
+	//
-		`insert into module (name, manifest, version, source, source_path, source_seat, ref, built_from, source_head)
+	// **An older request never replaces a newer one** (novox/hq 04-ISSUES/219). Builds of one
-		 values ($1, $2, nullif($3,''), nullif($4,''), $7, $8, nullif($5,''), nullif($6,''), nullif($6,''))
+	// module in flight together finish in any order, and each stood on the bases the mesh held when
+	// it was asked; the one asked later is what the module is, whichever is heard last. An outcome
+	// of an earlier request is kept in the build records and changes nothing here.
+	tag, err := i.store.Pool().Exec(ctx,
+		`insert into module (name, manifest, version, source, source_path, source_seat, ref, built_from, source_head, built_asked)
+		 values ($1, $2, nullif($3,''), nullif($4,''), $7, $8, nullif($5,''), nullif($6,''), nullif($6,''), $9)
 		 on conflict (name) do update set
 		     manifest   = excluded.manifest,
 		     version    = excluded.version,
@@ -115,9 +133,23 @@ func (i *Inventory) RegisterModule(ctx context.Context, m catalogue.Manifest, fr
 		                        else excluded.source_seat end,
 		     ref        = coalesce(excluded.ref, module.ref),
 		     built_from = coalesce(excluded.built_from, module.built_from),
-		     source_head = coalesce(excluded.built_from, module.source_head)`,
+		     source_head = coalesce(excluded.built_from, module.source_head),
-		m.Module, raw, m.Version, from.Repository, from.Ref, from.BuiltFrom, from.Path, from.Seat)
+		     built_asked = excluded.built_asked
+		 where module.built_asked is null or module.built_asked <= excluded.built_asked`,
+		m.Module, raw, m.Version, from.Repository, from.Ref, from.BuiltFrom, from.Path, from.Seat, asked)
+	if err != nil {
 		return err
+	}
+	if tag.RowsAffected() == 0 {
+		var current time.Time
+		if err := i.store.Pool().QueryRow(ctx,
+			`select built_asked from module where name = $1`, m.Module).Scan(&current); err != nil {
+			return err
+		}
+		return fmt.Errorf("%w: %s is at a build asked %s, and this one was asked %s",
+			ErrSuperseded, m.Module, current.UTC().Format(time.RFC3339), asked.UTC().Format(time.RFC3339))
+	}
+	return nil
 }
 
 // registeredInThatShape is whether the catalogue already holds this module as a tools container on

internal/inventory/dependencies_test.go

@@ -100,3 +100,23 @@ func TestABundleStandsOnTheToolchainItIsCompiledIn(t *testing.T) {
 		}
 	}
 }
+
+// novox/hq 04-ISSUES/212: a toolchain standing on the SDK's package is planned after the SDK, so a
+// release of the SDK rebuilds the toolchain, and every bundle compiled in it after that.
+func TestAToolchainStandingOnTheSDKFollowsIt(t *testing.T) {
+	entries := []Entry{
+		{Manifest: catalogue.Manifest{Module: "mesh-sdk"}},
+		{Manifest: catalogue.Manifest{Module: "mesh-tools", Build: &catalogue.Build{
+			On: []catalogue.BuildsOn{{Arg: "MESH_SDK", Module: "mesh-sdk", Artifact: "lib"}}}}},
+	}
+	edges := dependenciesOf(entries, nil, nil)
+	found := false
+	for _, e := range edges {
+		if e.From == "mesh-tools" && e.To == "mesh-sdk" {
+			found = true
+		}
+	}
+	if !found {
+		t.Errorf("no edge from the toolchain to the SDK: %v", edges)
+	}
+}

internal/inventory/heldhere_test.go

@@ -0,0 +1,32 @@
+package inventory
+
+import (
+	"testing"
+
+	"github.com/novox/mesh-controller/internal/broker"
+	"github.com/novox/mesh-controller/internal/catalogue"
+)
+
+// novox/hq issue 218: a seat held once for the mesh is granted and issued only to the holder on record;
+// a node seat to every machine's claimant; a mesh seat with no holder on record as derived.
+func TestOnlyTheRecordedHolderHoldsAMeshSeat(t *testing.T) {
+	claimed := []broker.Seat{
+		{Name: "mesh-store", Scope: catalogue.ScopeMesh},
+		{Name: "node-packet-filter", Scope: catalogue.ScopeNode},
+		{Name: "unrecorded", Scope: catalogue.ScopeMesh},
+	}
+	holdings := []catalogue.Held{{Claim: "mesh-store", Scope: catalogue.ScopeMesh, Node: "control", Module: "postgres"}}
+	names := func(ss []broker.Seat) (out []string) {
+		for _, s := range ss {
+			out = append(out, s.Name)
+		}
+		return
+	}
+	if got := names(heldHere(claimed, holdings, "control", "postgres")); len(got) != 3 {
+		t.Errorf("the holder lost a seat: %v", got)
+	}
+	got := names(heldHere(claimed, holdings, "other", "postgres"))
+	if len(got) != 2 || got[0] != "node-packet-filter" || got[1] != "unrecorded" {
+		t.Errorf("a claimant on another machine holds %v; want the node seat and the unrecorded one, not the store", got)
+	}
+}

internal/inventory/hold.go

@@ -87,3 +87,62 @@ func (i *Inventory) tryHold(ctx context.Context, sorted []string) (func(), strin
 	}
 	return release, "", nil
 }
+
+// ErrPlansBusy is the plans held by another act — on a machine replacing its controller, the other
+// controller — for longer than a caller waits, or at all for one that does not wait.
+var ErrPlansBusy = errors.New("another controller is working the plans")
+
+// HoldPlans makes working the plans one act at a time, across every controller on the store
+// (novox/hq issue 213). A plan is read, changed and written whole; two controllers doing that at
+// once — the old and the new for the moment a machine hands its controller over, or a controller
+// and a person's `plans stop` — each act on what the other has not saved yet: a tier asked twice,
+// an outcome written over. A session-level advisory lock on one connection, released by the
+// returned function and by the session ending, so a controller that dies holding it holds nothing.
+//
+// wait false gives ErrPlansBusy at once when another holds them — the timer's way: the holder is
+// moving the plans already. wait true looks again every HoldPoll for up to HoldWaitFor — an
+// outcome's or a merge's way, which must be written.
+func (i *Inventory) HoldPlans(ctx context.Context, wait bool) (func(), error) {
+	deadline := time.Now().Add(HoldWaitFor)
+	for {
+		release, took, err := i.tryLock(ctx, "mesh-plans")
+		if err != nil || took {
+			return release, err
+		}
+		if !wait || time.Now().After(deadline) {
+			return nil, ErrPlansBusy
+		}
+		select {
+		case <-ctx.Done():
+			return nil, ctx.Err()
+		case <-time.After(HoldPoll):
+		}
+	}
+}
+
+// tryLock takes one named advisory lock on a connection of its own, or gives the connection back.
+func (i *Inventory) tryLock(ctx context.Context, key string) (func(), bool, error) {
+	conn, err := i.store.Pool().Acquire(ctx)
+	if err != nil {
+		return nil, false, err
+	}
+	var once sync.Once
+	release := func() {
+		once.Do(func() {
+			if _, err := conn.Exec(context.WithoutCancel(ctx), `select pg_advisory_unlock_all()`); err != nil {
+				_ = conn.Conn().Close(context.WithoutCancel(ctx))
+			}
+			conn.Release()
+		})
+	}
+	var took bool
+	if err := conn.QueryRow(ctx, `select pg_try_advisory_lock(hashtext($1)::bigint)`, key).Scan(&took); err != nil {
+		release()
+		return nil, false, err
+	}
+	if !took {
+		release()
+		return nil, false, nil
+	}
+	return release, true, nil
+}

internal/inventory/hold_plans_test.go

@@ -0,0 +1,38 @@
+package inventory
+
+import (
+	"errors"
+	"testing"
+	"time"
+)
+
+// novox/hq issue 213: while a machine hands its controller over from the container to the process,
+// two controllers run on one store for a moment. Working the plans is one act at a time across them.
+func TestThePlansAreWorkedByOneControllerAtATime(t *testing.T) {
+	first := ForTest(t)
+	// A second controller: its own connections to the same store.
+	second, err := Open(t.Context())
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(second.Close)
+
+	release, err := first.HoldPlans(t.Context(), false)
+	if err != nil {
+		t.Fatalf("the plans could not be held when nobody held them: %v", err)
+	}
+	t.Cleanup(release) // a pool closing waits for a connection still held; release is idempotent
+	if _, err := second.HoldPlans(t.Context(), false); !errors.Is(err, ErrPlansBusy) {
+		t.Fatalf("a second controller held the plans while the first did: %v", err)
+	}
+	// A waiter gets them once they are let go.
+	was := HoldPoll
+	HoldPoll = 10 * time.Millisecond
+	defer func() { HoldPoll = was }()
+	go func() { time.Sleep(50 * time.Millisecond); release() }()
+	again, err := second.HoldPlans(t.Context(), true)
+	if err != nil {
+		t.Fatalf("a waiting controller never got the plans once they were let go: %v", err)
+	}
+	again()
+}

internal/inventory/migrations/0055-an-older-build-never-replaces-a-newer.sql

@@ -0,0 +1,23 @@
+-- A build is ordered by when it was asked, not when it finished (novox/hq 04-ISSUES/219).
+--
+-- Two builds of one module can be in flight together — two merge plans a few minutes apart, each
+-- asking for everything standing on what it changed — and they finish in any order. Each build
+-- stands on the bases the mesh held when it was *asked*, so the one asked later is the newer one.
+-- The mesh ordered builds by `at`, which is when the outcome was recorded, and registered whatever
+-- it heard last: an older request that took longer replaced a newer one as what the module is, and
+-- the next push sent machines an image built on a base the mesh had already replaced.
+--
+-- `build.asked` is when the build was requested, read from the correlation id the controller wrote
+-- (`build-<unix nanoseconds>`). Nullable: an id of any other shape says no request time, and such a
+-- build is placed where it was recorded, which is the order the mesh had before this.
+alter table build add column asked timestamptz;
+
+update build
+   set asked = to_timestamp((substring(id from '^build-([0-9]{19})$'))::numeric / 1000000000)
+ where id ~ '^build-[0-9]{19}$';
+
+-- `module.built_asked` is when the build the module's registered manifest came from was asked, so
+-- a later-heard outcome of an earlier request is recorded and not registered. A manifest handed over
+-- by hand is a request made when it is handed over. Null for a module registered before this was
+-- kept: its next registration, whichever it is, sets it.
+alter table module add column built_asked timestamptz;

internal/inventory/older_build_test.go

@@ -0,0 +1,124 @@
+package inventory
+
+import (
+	"context"
+	"errors"
+	"testing"
+	"time"
+
+	"github.com/novox/mesh-controller/internal/catalogue"
+)
+
+// novox/hq 04-ISSUES/219: two builds of one module in flight together, the one asked first heard
+// last. The newer request stood on the newer base; the older one's late outcome is recorded and is
+// not what the module is.
+
+func postgresBuild(id string, asked time.Time, image string) Build {
+	b := aBuild(id, "postgres", "")
+	b.Asked = asked
+	b.Against = []string{"mesh-tools/runtime@sha256:" + id}
+	b.Made = []Artifact{{Name: "server", Kind: "image", Reference: "postgres@sha256:" + image}}
+	return b
+}
+
+func TestAnOlderRequestFinishingLaterIsNotWhatTheModuleHolds(t *testing.T) {
+	inv := fresh(t)
+	ctx := context.Background()
+	older := time.Date(2026, 10, 3, 21, 33, 45, 0, time.UTC)
+	newer := time.Date(2026, 10, 3, 21, 51, 57, 0, time.UTC)
+
+	// The newer request finishes first, the older one last — recorded in that order.
+	if err := inv.RecordBuild(ctx, postgresBuild("newer", newer, "4bcd5f73")); err != nil {
+		t.Fatal(err)
+	}
+	if err := inv.RecordBuild(ctx, postgresBuild("older", older, "0ab07fa9")); err != nil {
+		t.Fatal(err)
+	}
+
+	held, err := inv.Held(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := held["postgres/server"]; got != "postgres@sha256:4bcd5f73" {
+		t.Errorf("postgres holds %q; want the newer request's image 4bcd5f73", got)
+	}
+	against, err := inv.BuiltAgainst(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := against["postgres"]; len(got) != 1 || got[0] != "mesh-tools/runtime@sha256:newer" {
+		t.Errorf("postgres stands on %v; want what the newer request stood on", got)
+	}
+
+	// Both are still recorded, the late one first as what happened lately.
+	builds, err := inv.Builds(ctx, "postgres", 5)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(builds) != 2 || builds[0].ID != "older" || !builds[0].Asked.Equal(older) {
+		t.Fatalf("both builds, newest heard first, with when they were asked: %+v", builds)
+	}
+}
+
+func TestABuildWithNoKnownRequestTimeIsOrderedByWhenItWasRecorded(t *testing.T) {
+	// What the mesh did before it kept the request time, so a row from before still answers.
+	inv := fresh(t)
+	ctx := context.Background()
+	for _, id := range []string{"first", "second"} {
+		b := aBuild(id, "shell", "")
+		b.Made = []Artifact{{Name: "config", Kind: "archive", Reference: "…/" + id}}
+		if err := inv.RecordBuild(ctx, b); err != nil {
+			t.Fatal(err)
+		}
+	}
+	held, err := inv.Held(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := held["shell/config"]; got != "…/second" {
+		t.Errorf("shell holds %q; want the one recorded last", got)
+	}
+}
+
+func TestARegistrationFromAnOlderRequestDoesNotReplaceANewerOne(t *testing.T) {
+	inv := fresh(t)
+	ctx := context.Background()
+	older := time.Date(2026, 10, 3, 21, 33, 45, 0, time.UTC)
+	newer := time.Date(2026, 10, 3, 21, 51, 57, 0, time.UTC)
+	from := func(asked time.Time) Source {
+		return Source{Repository: "novox/mesh-catalog", Seat: "git", Path: "modules/postgres",
+			BuiltFrom: "efff5415", Asked: asked}
+	}
+
+	if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "postgres", Version: "fixed"}, from(newer)); err != nil {
+		t.Fatal(err)
+	}
+	err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "postgres", Version: "stale"}, from(older))
+	if !errors.Is(err, ErrSuperseded) {
+		t.Fatalf("an older request's registration was not refused as superseded: %v", err)
+	}
+	shelf, err := inv.Catalogue(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := shelf["postgres"].Version; got != "fixed" {
+		t.Fatalf("postgres is %q; want the newer request's manifest", got)
+	}
+
+	// A later request, and a manifest handed over by hand — asked when it is handed over — both
+	// replace it as before.
+	if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "postgres", Version: "later"},
+		from(newer.Add(time.Minute))); err != nil {
+		t.Fatal(err)
+	}
+	if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "postgres", Version: "by-hand"}, Source{}); err != nil {
+		t.Fatal(err)
+	}
+	if shelf, _ := inv.Catalogue(ctx); shelf["postgres"].Version != "by-hand" {
+		t.Fatalf("postgres is %q; want the manifest handed over by hand", shelf["postgres"].Version)
+	}
+	src, err := inv.SourceOf(ctx, "postgres")
+	if err != nil || src.Repository != "novox/mesh-catalog" {
+		t.Fatalf("a hand registration erased the provenance: %+v %v", src, err)
+	}
+}

internal/link/build.go

@@ -2,6 +2,9 @@ package link
 
 import (
 	"encoding/json"
+	"strconv"
+	"strings"
+	"time"
 )
 
 // Asking a machine to build a module, and hearing what came out.
@@ -17,6 +20,32 @@ import (
 // holds no opinion about what they contain, and a host that also built things would be a host
 // with a container runtime requirement and a git dependency (novox/hq ADR 0005).
 
+// NewBuildID is the correlation for a build asked at that moment: `build-<unix nanoseconds>`.
+//
+// **The id carries when the build was asked, and that is read back** (novox/hq 04-ISSUES/219). Builds
+// of one module can be in flight together and finish in any order; what a module currently is must
+// be the newest *request's* outcome, not the last one heard, and the id is the one thing every
+// outcome echoes whichever builder answered it. One place writes the shape and one reads it.
+func NewBuildID(asked time.Time) string {
+	return "build-" + strconv.FormatInt(asked.UnixNano(), 10)
+}
+
+// BuildAskedAt is when the build with this id was asked, as NewBuildID wrote it. False for an id
+// of any other shape — one written before this was read, or by hand — whose request time the mesh
+// does not know.
+func BuildAskedAt(id string) (time.Time, bool) {
+	digits, ok := strings.CutPrefix(id, "build-")
+	if !ok || digits == "" {
+		return time.Time{}, false
+	}
+	nanos, err := strconv.ParseInt(digits, 10, 64)
+	// A number too small to be a moment this mesh could have asked at is a name, not a time.
+	if err != nil || nanos < time.Date(2020, 1, 1, 0, 0, 0, 0, time.UTC).UnixNano() {
+		return time.Time{}, false
+	}
+	return time.Unix(0, nanos).UTC(), true
+}
+
 // BuildRequest is one module to build.
 type BuildRequest struct {
 	// ID correlates the answer with the asking. Not the module name: two builds of one module can

internal/link/receive_nats.go

@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"log"
 	"strings"
 	"time"
 
@@ -78,10 +79,15 @@ func (n *natsInbound) Receive(ctx context.Context, act func(context.Context, Con
 	// than creating one here: the consumer is an object with a configuration — ack policy, ack
 	// wait, redelivery — and a client that creates its own would be a second opinion about it.
 	control := make(chan *nats.Msg, Prefetch)
-	said, err := js.ChanSubscribe("", control, nats.Bind("CONTROL", broker.ControllerName))
+	said, err := standingBy(ctx, log.Default(), "CONTROL", func() (*nats.Subscription, error) {
+		return js.ChanSubscribe("", control, nats.Bind("CONTROL", broker.ControllerName))
+	})
 	if err != nil {
 		return fmt.Errorf("subscribing to what nodes say: %w", err)
 	}
+	if said == nil {
+		return nil // stopped while standing by
+	}
 	defer func() { _ = said.Unsubscribe() }()
 
 	// Heartbeats, on core NATS and off any stream (design 25 §3). Their own subscription because
@@ -97,10 +103,15 @@ func (n *natsInbound) Receive(ctx context.Context, act func(context.Context, Con
 	var events chan *nats.Msg
 	if len(n.follows) > 0 {
 		events = make(chan *nats.Msg, Prefetch)
-		followed, err := js.ChanSubscribe("", events, nats.Bind("EVENTS", broker.ControllerName))
+		followed, err := standingBy(ctx, log.Default(), "EVENTS", func() (*nats.Subscription, error) {
+			return js.ChanSubscribe("", events, nats.Bind("EVENTS", broker.ControllerName))
+		})
 		if err != nil {
 			return fmt.Errorf("subscribing to what the catalogue says: %w", err)
 		}
+		if followed == nil {
+			return nil
+		}
 		defer func() { _ = followed.Unsubscribe() }()
 	}
 
@@ -324,3 +335,44 @@ func (m *natsControl) forget() {
 type replyAddressed struct {
 	ReplyTo string `json:"reply_to,omitempty"`
 }
+
+// StandbyPoll is how often a controller standing by looks again for its consumers. A variable so a
+// test need not wait.
+var StandbyPoll = 2 * time.Second
+
+// standingBy binds one of the controller's consumers, waiting while another controller holds it.
+//
+// **Two controllers, one consumer** (novox/hq issue 213). The controller's consumers are push
+// consumers with no delivery group, so the server lets one subscription bind each — on purpose:
+// two would each act on every message (issue 146). When a machine hands its controller over from
+// the container to the process, the host starts the process first and removes the container only
+// once the process is up; the process then finds the consumers bound. Exiting on that would never
+// be up, so the container would never go. It stands by instead — the seat's verbs are already
+// served from a queue group, and the plans wait on their lock — and binds as soon as the other lets
+// go. Nil and no error is ctx ending while it waited.
+func standingBy(ctx context.Context, logger interface{ Printf(string, ...any) }, stream string,
+	bind func() (*nats.Subscription, error)) (*nats.Subscription, error) {
+	said := false
+	for {
+		sub, err := bind()
+		if err == nil {
+			if said {
+				logger.Printf("took the controller's consumer on %s: the controller that held it let go", stream)
+			}
+			return sub, nil
+		}
+		if !strings.Contains(err.Error(), "already bound") {
+			return nil, err
+		}
+		if !said {
+			logger.Printf("another controller holds the controller's consumer on %s; standing by "+
+				"until it lets go", stream)
+			said = true
+		}
+		select {
+		case <-ctx.Done():
+			return nil, nil
+		case <-time.After(StandbyPoll):
+		}
+	}
+}

internal/link/standby_nats_test.go

@@ -0,0 +1,69 @@
+package link
+
+import (
+	"context"
+	"encoding/json"
+	"os"
+	"testing"
+	"time"
+
+	"github.com/novox/mesh-controller/internal/broker"
+)
+
+// novox/hq issue 213: while a machine hands its controller over, the new controller (the process)
+// is started while the old one (the container) still holds the controller's consumers. It must not
+// exit — the host would read that as a replacement that did not come up and never remove the
+// container — and must not act on what the old one is handed. It stands by, and takes the consumers
+// when the old one lets go.
+func TestNatsASecondControllerStandsByAndTakesOverWhenTheFirstLetsGo(t *testing.T) {
+	js := aBus(t)
+	was := StandbyPoll
+	StandbyPoll = 50 * time.Millisecond
+	defer func() { StandbyPoll = was }()
+
+	old := &counted{}
+	_, stopOld := servingOn(t, js, old)
+	eventually(t, "the first controller binding its consumer", func() bool {
+		info, err := js.Context().ConsumerInfo("CONTROL", broker.ControllerName)
+		return err == nil && info.PushBound
+	})
+
+	// The new one, on a connection of its own as the process would have.
+	second, err := broker.Dial(os.Getenv("MESH_TEST_NATS"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(second.Close)
+	fresh := &counted{}
+	s := &Server{inbound: Nats(second), bus: OverNATS{Conn: second.Conn(), JS: second.Context()},
+		listener: fresh, log: quiet()}
+	ctx, stopNew := context.WithCancel(context.Background())
+	defer stopNew()
+	ended := make(chan error, 1)
+	go func() { ended <- s.Serve(ctx) }()
+
+	select {
+	case err := <-ended:
+		t.Fatalf("the second controller stopped instead of standing by: %v", err)
+	case <-time.After(500 * time.Millisecond):
+	}
+
+	report := func(declared string) {
+		body, _ := json.Marshal(Report{Node: "anchor", Declared: declared, Applied: []string{"store"}})
+		if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
+			t.Fatal(err)
+		}
+	}
+	report("d1")
+	eventually(t, "the holding controller hearing the report", func() bool { return old.count() == 1 })
+	if fresh.count() != 0 {
+		t.Fatal("the controller standing by acted on a report the holder was handed")
+	}
+
+	stopOld()
+	report("d2")
+	eventually(t, "the second controller taking over once the first let go", func() bool { return fresh.count() == 1 })
+	if old.count() != 1 {
+		t.Errorf("the first controller heard %d reports", old.count())
+	}
+}

internal/store/manifest_test.go

@@ -30,7 +30,7 @@ func TestTheManifestsOwnPlaceholderUnfilledLeavesTheStoreWhereTheFileSays(t *tes
 	}
 	var written string
 	for _, r := range m.Resources {
-		if r.Type == "container" {
+		if r.Type == "process" {
 			written = r.Env["MESH_STORE_INVENTORY_PORT"]
 		}
 	}

module.json

@@ -2,9 +2,6 @@
   "module": "mesh-controller",
   "version": "1",
   "slug": "control",
-  "capabilities": [
-    "container-runtime"
-  ],
   "claims": [
     {
       "name": "mesh-controller",
@@ -26,7 +23,7 @@
     "broker-address": "${dir:mesh-state}/broker-address",
     "bus": "${dir:mesh-state}/bus"
   },
-  "secrets-owner": "65534:65534",
+  "secrets-owner": "mesh-controller",
   "prepares": true,
   "tools": [
     "tools",
@@ -43,62 +40,58 @@
     "build"
   ],
   "resources": [
+    {
+      "id": "account",
+      "type": "user",
+      "name": "mesh-controller",
+      "shell": "/usr/bin/nologin",
+      "home": "/var/lib/mesh-controller"
+    },
     {
       "id": "mesh-state",
       "type": "directory",
       "mode": "0700",
-      "place": "mesh"
+      "place": "mesh",
+      "owner": "mesh-controller"
     },
     {
-      "id": "server",
+      "id": "controller",
-      "type": "container",
+      "type": "process",
       "name": "mesh-controller",
-      "network": "host",
+      "artifact": "controller",
-      "args": [
+      "run": [
+        "./mesh-controller",
         "serve"
       ],
+      "user": "mesh-controller",
       "env": {
-        "MESH_BROKER_CERTIFICATE": "/broker-tls/tls.crt",
+        "MESH_BROKER_CERTIFICATE": "/var/lib/mesh-broker-tls/tls.crt",
-        "MESH_STORE_INVENTORY_FILE": "/run/secrets/inventory",
+        "MESH_STORE_INVENTORY_FILE": "${dir:mesh-state}/inventory",
-        "MESH_STORE_IDENTITY_FILE": "/run/secrets/identity",
+        "MESH_STORE_IDENTITY_FILE": "${dir:mesh-state}/identity",
-        "MESH_STORE_LICENCES_FILE": "/run/secrets/licences",
+        "MESH_STORE_LICENCES_FILE": "${dir:mesh-state}/licences",
-        "MESH_BROKER_MANAGEMENT_FILE": "/run/secrets/broker-management",
+        "MESH_BROKER_MANAGEMENT_FILE": "${dir:mesh-state}/broker-management",
-        "MESH_BROKER_ADDRESS_FILE": "/run/secrets/broker-address",
+        "MESH_BROKER_ADDRESS_FILE": "${dir:mesh-state}/broker-address",
         "MESH_STORE_INVENTORY_PORT": "${seat:mesh-store:5432}",
         "MESH_STORE_IDENTITY_PORT": "${seat:mesh-store:5432}",
         "MESH_STORE_LICENCES_PORT": "${seat:mesh-store:5432}",
         "MESH_BROKER_MANAGEMENT_PORT": "${seat:mesh-broker:15672}",
         "MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}",
-        "MESH_BUS_NATS_FILE": "/run/secrets/bus"
+        "MESH_BUS_NATS_FILE": "${dir:mesh-state}/bus"
       },
-      "volumes": [
+      "replaces": [
-        "/var/lib/mesh-broker-tls:/broker-tls:ro",
+        "server"
-        "${dir:mesh-state}/inventory:/run/secrets/inventory:ro",
-        "${dir:mesh-state}/identity:/run/secrets/identity:ro",
-        "${dir:mesh-state}/licences:/run/secrets/licences:ro",
-        "${dir:mesh-state}/broker:/run/secrets/broker:ro",
-        "${dir:mesh-state}/bus:/run/secrets/bus:ro",
-        "${dir:mesh-state}/broker-management:/run/secrets/broker-management:ro",
-        "${dir:mesh-state}/broker-address:/run/secrets/broker-address:ro"
-      ],
-      "artifact": "server",
-      "restart-on": [
-        "control-env"
       ]
     }
   ],
   "build": {
     "artifacts": [
       {
-        "name": "server",
+        "name": "controller",
-        "kind": "image",
+        "kind": "bundle",
-        "from": "Dockerfile"
+        "language": "go",
-      }
+        "system": "arch",
-    ],
+        "from": "cmd/mesh-controller",
-    "on": [
+        "binary": "mesh-controller"
-      {
-        "arg": "GO_BASE",
-        "image": "golang@sha256:8ac98ca534ac3f51e1f420a1dd2c15e74c75cfa0f23f3ad27eb5d7236c349a0c"
       }
     ]
   }