cmd/mesh-controller/main.go

@@ -76,7 +76,10 @@ func run() error {
 		return pinCommand(ctx, args[1:], true)
 	case "unpin":
 		return pinCommand(ctx, args[1:], false)
-	case "migrate":
+	// `prepare` is how the mesh asks any module to bring its state to the shape this version needs
+	// (novox/hq ADR 0135), and the control plane answers it the same way as everything else — its
+	// own schema is not a special case. `migrate` remains the word a person types.
+	case "prepare", "migrate":
 		return migrate(ctx)
 	case "node":
 		return nodeCommand(ctx, args[1:])
@@ -138,6 +141,7 @@ func usage() {
 	fmt.Fprint(os.Stderr, `mesh-controller — the control plane
 
   migrate                        bring each context's schema up to date
+  prepare                        the same, asked the way the mesh asks any module (ADR 0135)
   node add <name> [--adopted]    create a node record; --adopted: the machine is in use
   node list                      the nodes this mesh knows about
   node show <name>               what one machine reported it can do, and why

internal/catalogue/declaration.go

@@ -623,6 +623,9 @@ func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[stri
 		// one of them as its environment without saying so (ADR 0086, issue 041).
 		secretFiles := secretFilesOf(resources)
 
+		// Which of this module's resources its preparation runs before, if it prepares anything.
+		prepareBefore := preparationTarget(m)
+
 		for _, unsettled := range resources {
 			resource, err := ApplySettings(unsettled, with.Settings[m.Module])
 			if err != nil {
@@ -708,6 +711,18 @@ func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[stri
 			if renamed := reflectsRenamed(m.Module, resource["reload-on"]); renamed != nil {
 				copied["reload-on"] = renamed
 			}
+			// **A version prepares its state before it runs** (novox/hq ADR 0135). Derived from the
+			// module's own resource rather than declared beside it: what prepares the state is the
+			// module's own code, so what it is given has to be what that code is given — and a
+			// second resource written by hand is a second copy to drift from the first. Placed
+			// immediately before it, because a run-once step stops everything the declaration
+			// places after it (ADR 0052), which is how a version whose preparation failed does not
+			// serve.
+			if prepareBefore != "" && fmt.Sprint(resource["id"]) == prepareBefore {
+				step := prepared(copied)
+				owner[fmt.Sprint(step["id"])] = m.Module
+				out = append(out, step)
+			}
 			owner[fmt.Sprint(copied["id"])] = m.Module
 			out = append(out, copied)
 		}
@@ -1610,3 +1625,73 @@ func atMachinePort(serves map[string]any, module string, ports map[string]map[in
 func AtPublishedPort(values map[string]any, module string, published map[int]int) map[string]any {
 	return atMachinePort(values, module, map[string]map[int]int{module: published})
 }
+
+// PreparationArgument is how the mesh asks a module to prepare its state: one word, to the module's
+// own program, whatever that program is (novox/hq ADR 0135).
+//
+// **One word for every kind of module.** A module built as a Go binary receives it as its argument;
+// one built as a bundle receives it through the runtime, whose entry takes the same word. So the
+// mesh has one way of asking and a module has one way of answering, and neither learns the other's
+// shape.
+const PreparationArgument = "prepare"
+
+// preparationTarget is the resource a module's preparation runs before: its own workload.
+//
+// The first container carrying an artifact this module built, and not itself a step — that is the
+// thing that runs the module's code, and therefore the thing whose state must be ready. Empty when
+// the module prepares nothing, or when nothing it declares could run its code.
+//
+// **A module with two own workloads gates the first of them.** Five modules in the catalogue declare
+// more than one container of their own, none of them preparing anything today. If one ever does and
+// its second workload shares the state, the gate is in front of the first — stated here because the
+// alternative is a field asking an author to restate what the mesh can see.
+func preparationTarget(m Manifest) string {
+	if !m.Prepares {
+		return ""
+	}
+	for _, r := range m.Resources {
+		if fmt.Sprint(r["type"]) != "container" || !ownArtifact(r, m.Module) {
+			continue
+		}
+		if once, _ := r["run-once"].(bool); once {
+			continue
+		}
+		return fmt.Sprint(r["id"])
+	}
+	return ""
+}
+
+// ownArtifact is whether a resource runs something this module built, in either spelling a manifest
+// may be in: naming the artifact, before a build resolved it, or carrying the reference a build
+// recorded — this mesh's own store, under this module's name.
+func ownArtifact(resource map[string]any, module string) bool {
+	if named, _ := resource["artifact"].(string); named != "" {
+		return true
+	}
+	image, _ := resource["image"].(string)
+	return strings.HasPrefix(image, ArtifactStoreScheme+module+"/")
+}
+
+// prepared is the module's own resource as the step that prepares its state: the same image, the same
+// context, run to completion with the mesh's preparation argument.
+//
+// Three things are taken away rather than copied, each because the step runs while the version it
+// prepares for is still running. A published port cannot be bound twice, and a step that tried would
+// fail for a reason that has nothing to do with the state. A fixed address cannot be held twice, for
+// the same reason. And a cadence is what a step is the opposite of: a container runs once and gates,
+// or on a schedule, or stays up, never two (ADR 0053).
+func prepared(from map[string]any) map[string]any {
+	step := map[string]any{}
+	for k, v := range from {
+		step[k] = v
+	}
+	step["id"] = fmt.Sprint(from["id"]) + ".prepare"
+	step["name"] = fmt.Sprint(from["name"]) + "-prepare"
+	step["run-once"] = true
+	step["args"] = []any{PreparationArgument}
+	delete(step, "ports")
+	delete(step, "ip")
+	delete(step, "schedule")
+	delete(step, "reload-on")
+	return step
+}

internal/catalogue/manifest.go

@@ -225,6 +225,19 @@ type Manifest struct {
 	// subscription to the queue it writes to (design 29 §2).
 	Uses []string `json:"uses,omitempty"`
 
+	// Prepares says this module has state that must be brought to the shape this version needs
+	// before this version runs, and that the module's own code does it (novox/hq ADR 0135).
+	//
+	// **A word, not an arrangement.** The mesh runs the module's own program in its preparation
+	// mode, in the module's own context — every binding, credential and setting its code receives,
+	// because it *is* its code. Nothing here names a container, a command, a mount or a variable:
+	// the module already said all of that once, and a second copy is a second thing to drift.
+	//
+	// **Declared, never inferred.** The control plane cannot read what is inside an artifact, so a
+	// module that ships a migration and does not say this breaks on its first upgrade. That is
+	// stated in the record rather than guarded here, because nothing mechanical can guard it.
+	Prepares bool `json:"prepares,omitempty"`
+
 	// Tools are the tools this module answers — request and reply, awaited.
 	//
 	// **New, and not `serves`**, which this manifest already uses for the facts a consumer needs
@@ -1276,6 +1289,17 @@ func ParseManifest(raw []byte) (Manifest, error) {
 				"program that reads what the mesh delivered and reconciles",
 			m.Module, r["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
+	// cannot compose. Said here, where the manifest is read, rather than by a declaration that
+	// 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 — "+
+				"the preparation is this module's own program, so there has to be one for the mesh to "+
+				"run it in", m.Module))
+	}
 	// **A run-once container is a step the host runs to completion** (novox/hq ADR 0052). It is a
 	// boolean modifier on the container shape — the host runs the container, requires it to exit 0,
 	// and starts whatever the declaration places after it only once it has. A value that is not a

internal/catalogue/prepares_test.go

@@ -0,0 +1,135 @@
+package catalogue
+
+import (
+	"encoding/json"
+	"fmt"
+	"testing"
+)
+
+// A module version prepares its state before it runs (novox/hq ADR 0135).
+//
+// What the mesh derives is the module's own resource, run once with one word, placed immediately in
+// front of the thing it prepares for. What matters in these tests is that the derivation is a copy
+// rather than a second description: the failure it replaces was a hand-written step repeating six
+// fields of the resource it preceded, each free to drift from it.
+
+func aPreparingModule() Manifest {
+	return Manifest{
+		Module:   "gitea",
+		Prepares: true,
+		Resources: []map[string]any{
+			{"id": "state", "type": "directory", "path": "/var/lib/gitea", "mode": "0700"},
+			{"id": "server", "type": "container", "name": "mesh-gitea-server",
+				"image": "gitea/gitea@" + digest, "ports": []any{"3000:3000"}},
+			{"id": "runtime", "type": "container", "name": "mesh-gitea",
+				"image": ArtifactStoreScheme + "gitea/runtime@" + digest, "network": "host",
+				"env":     map[string]any{"MESH_GITEA_STATE_DIR": "/run/state"},
+				"volumes": []any{"/var/lib/gitea:/run/state:ro"},
+				"ports":   []any{"9000:9000"}},
+		},
+	}
+}
+
+func declaredFor(t *testing.T, m Manifest) []map[string]any {
+	t.Helper()
+	// The manifest as the mesh holds it: a build resolved the module's own artifact into the
+	// reference it recorded, which is also how the composition knows whose code a resource runs.
+	out, err := Resolution{Node: "anchor", Modules: []Manifest{m}}.Declaration(
+		Rendering{ArtifactStore: "anchor.internal:5100"})
+	if err != nil {
+		t.Fatal(err)
+	}
+	return out
+}
+
+func idsOf(resources []map[string]any) []string {
+	var ids []string
+	for _, r := range resources {
+		ids = append(ids, fmt.Sprint(r["id"]))
+	}
+	return ids
+}
+
+// The step runs the module's own code, and comes immediately before it — not before the upstream
+// server the module packages, which may be the very thing the state lives in.
+func TestThePreparationRunsTheModulesOwnCodeAndComesRightBeforeIt(t *testing.T) {
+	out := declaredFor(t, aPreparingModule())
+	ids := idsOf(out)
+	at := -1
+	for i, id := range ids {
+		if id == "gitea.runtime.prepare" {
+			at = i
+		}
+	}
+	if at < 0 {
+		t.Fatalf("nothing prepares this module's state: %v", ids)
+	}
+	if ids[at+1] != "gitea.runtime" {
+		t.Fatalf("the preparation is not immediately before the module's own code: %v", ids)
+	}
+	for _, id := range ids[:at] {
+		if id == "gitea.runtime" {
+			t.Fatalf("the module's own code runs before its state is prepared: %v", ids)
+		}
+	}
+}
+
+// It is given exactly what the module's own code is given. Asserted field by field against the
+// resource it was derived from, because writing it twice is the fault this replaces.
+func TestThePreparationIsGivenWhatTheModuleIsGiven(t *testing.T) {
+	out := declaredFor(t, aPreparingModule())
+	declared := byID(out)
+	step, workload := declared["gitea.runtime.prepare"], declared["gitea.runtime"]
+	if step == nil || workload == nil {
+		t.Fatalf("expected both, got %v", idsOf(out))
+	}
+	for _, field := range []string{"image", "network", "env", "volumes", "type"} {
+		if fmt.Sprint(step[field]) != fmt.Sprint(workload[field]) {
+			t.Errorf("the preparation's %s is %v and the module's is %v", field, step[field], workload[field])
+		}
+	}
+	if once, _ := step["run-once"].(bool); !once {
+		t.Error("the preparation is not a step, so nothing waits for it and nothing is gated by it")
+	}
+	if fmt.Sprint(step["args"]) != fmt.Sprint([]any{PreparationArgument}) {
+		t.Errorf("the preparation is asked for as %v", step["args"])
+	}
+	if fmt.Sprint(step["name"]) == fmt.Sprint(workload["name"]) {
+		t.Error("the preparation and the workload have one name, so one removes the other")
+	}
+	// A published port cannot be bound twice, and the version being replaced is still running.
+	if _, published := step["ports"]; published {
+		t.Errorf("the preparation publishes a port the running version holds: %v", step["ports"])
+	}
+}
+
+// A module that says nothing about preparing gets nothing, which is most modules.
+func TestAModuleThatPreparesNothingGetsNoStep(t *testing.T) {
+	m := aPreparingModule()
+	m.Prepares = false
+	for _, id := range idsOf(declaredFor(t, m)) {
+		if id == "gitea.runtime.prepare" {
+			t.Fatal("a module that prepares nothing was given a preparation")
+		}
+	}
+}
+
+// A module whose own code the mesh cannot find has nothing to ask, and saying so where the manifest
+// is read beats a declaration that quietly prepares nothing.
+func TestAModuleThatPreparesAndRunsNoneOfItsOwnCodeIsRefused(t *testing.T) {
+	m := Manifest{
+		Module:   "gitea",
+		Prepares: true,
+		Resources: []map[string]any{
+			// Only the upstream server it packages: nothing here runs gitea's own code.
+			{"id": "server", "type": "container", "name": "mesh-gitea-server", "image": "gitea/gitea@" + digest},
+		},
+	}
+	raw, err := json.Marshal(m)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err := ParseManifest(raw); err == nil {
+		t.Fatal("a module that prepares its state with nothing of its own to run was accepted")
+	}
+}

module.json

@@ -27,6 +27,7 @@
     "bus": "/var/lib/mesh/mesh-controller/bus"
   },
   "secrets-owner": "65534:65534",
+  "prepares": true,
   "resources": [
     {
       "id": "mesh-state",
@@ -34,30 +35,6 @@
       "path": "/var/lib/mesh/mesh-controller",
       "mode": "0700"
     },
-    {
-      "id": "migrate",
-      "type": "container",
-      "name": "mesh-controller-migrate",
-      "run-once": true,
-      "network": "host",
-      "args": [
-        "migrate"
-      ],
-      "env": {
-        "MESH_STORE_INVENTORY_FILE": "/run/secrets/inventory",
-        "MESH_STORE_IDENTITY_FILE": "/run/secrets/identity",
-        "MESH_STORE_LICENCES_FILE": "/run/secrets/licences",
-        "MESH_STORE_INVENTORY_PORT": "${seat:mesh-store:5432}",
-        "MESH_STORE_IDENTITY_PORT": "${seat:mesh-store:5432}",
-        "MESH_STORE_LICENCES_PORT": "${seat:mesh-store:5432}"
-      },
-      "volumes": [
-        "/var/lib/mesh/mesh-controller/inventory:/run/secrets/inventory:ro",
-        "/var/lib/mesh/mesh-controller/identity:/run/secrets/identity:ro",
-        "/var/lib/mesh/mesh-controller/licences:/run/secrets/licences:ro"
-      ],
-      "artifact": "server"
-    },
     {
       "id": "server",
       "type": "container",