Serve a per-node state to a bundle as one state: get by the key's node, keys and watch over every node's bucket, a later bucket too

The provisioner, the assigner and the view read every node's composition (ADR 0593 §6); the runtime followed mesh-sdk's membership.StateIssued PerNode and process.NodeFamily on its own connection.

Claude-Session: https://claude.ai/code/session_01NcbgfJ9Gum47zkFKWRaovL

node-tools/internal/bus/per_node.go

@@ -0,0 +1,185 @@
+package bus
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"sort"
+	"strings"
+	"sync"
+
+	"github.com/nats-io/nats.go"
+	"github.com/nats-io/nats.go/jetstream"
+)
+
+// A state its owner keeps one bucket per node (novox/hq ADR 0593 §6: each node's engine writes its own `composed-<node>`,
+// and the provisioner, the assigner and the view read them all) is served to a bundle as one state, as mesh-sdk's
+// process.NodeFamily serves it to a process: a key is read from the bucket its first part names, the keys and a watch
+// go over every bucket of the prefix, and a watch takes in a bucket created later, heard by the bus's creation
+// advisory, so a node added later is heard with no timer. This runtime holds its own connection, not mesh-sdk's, so
+// the same rules are written here over it; the two subjects below are the ones the grants part grants a reader.
+const (
+	familyListSubject     = "$JS.API.STREAM.NAMES"
+	familyCreatedAdvisory = "$JS.EVENT.ADVISORY.STREAM.CREATED."
+)
+
+func perNodeRefusal(module, name, what string) error {
+	return fmt.Errorf("%s's state %s is kept one bucket per node and read only: no %s of it as one state (novox/hq ADR 0593 §6)",
+		module, name, what)
+}
+
+// nodeBucketOf is the state of the one node a key names: its first part, which must be a node's name.
+func nodeBucketOf(s StateIssued, key string) (StateIssued, error) {
+	node, _, ok := strings.Cut(key, ".")
+	if !ok || node == "" {
+		return s, fmt.Errorf("%q names no node: a key of the per-node state %s starts <node>.", key, s.Name)
+	}
+	s.Bucket += node
+	return s, nil
+}
+
+// perNodeNodes are the nodes whose bucket of the family the bus holds now, sorted.
+func (c *Conn) perNodeNodes(s StateIssued) ([]string, error) {
+	ctx, cancel := context.WithTimeout(context.Background(), StateTimeout)
+	defer cancel()
+	js, err := jetstream.New(c.nc)
+	if err != nil {
+		return nil, err
+	}
+	names := js.KeyValueStoreNames(ctx)
+	var nodes []string
+	for name := range names.Name() {
+		if node, ok := strings.CutPrefix(name, s.Bucket); ok && node != "" {
+			nodes = append(nodes, node)
+		}
+	}
+	if err := names.Error(); err != nil && !errors.Is(err, jetstream.ErrEndOfData) {
+		return nil, fmt.Errorf("the state %s: listing the buckets %s*: %w", s.Name, s.Bucket, err)
+	}
+	sort.Strings(nodes)
+	return nodes, nil
+}
+
+func (c *Conn) perNodeKeys(s StateIssued) ([]string, error) {
+	nodes, err := c.perNodeNodes(s)
+	if err != nil {
+		return nil, err
+	}
+	keys := []string{}
+	for _, node := range nodes {
+		one := s
+		one.Bucket += node
+		ctx, cancel := context.WithTimeout(context.Background(), StateTimeout)
+		kv, err := c.bucket(ctx, one)
+		if err == nil {
+			var k []string
+			k, err = keysOf(ctx, kv)
+			keys = append(keys, k...)
+		}
+		cancel()
+		if err != nil {
+			return nil, err
+		}
+	}
+	sort.Strings(keys)
+	return keys, nil
+}
+
+// perNodeWatch is StateWatch over every bucket of the family, and over a bucket created later. A pattern whose first
+// part names a node watches that node's bucket only.
+func (c *Conn) perNodeWatch(module string, s StateIssued, filter string, deliver func(StateChange) error) (func(), error) {
+	var mu sync.Mutex
+	one := func(ch StateChange) error {
+		mu.Lock()
+		defer mu.Unlock()
+		return deliver(ch)
+	}
+	var (
+		wmu     sync.Mutex
+		watched = map[string]bool{}
+		stops   []func()
+		done    bool
+		sub     *nats.Subscription
+	)
+	add := func(node string) error {
+		wmu.Lock()
+		if watched[node] || done {
+			wmu.Unlock()
+			return nil
+		}
+		watched[node] = true
+		wmu.Unlock()
+		bs := s
+		bs.Bucket += node
+		ctx, cancel := context.WithTimeout(context.Background(), StateTimeout)
+		kv, err := c.bucket(ctx, bs)
+		cancel()
+		if err != nil {
+			return err
+		}
+		stop, err := c.watchBucket(module, s.Name, kv, filter, one)
+		if err != nil {
+			return err
+		}
+		wmu.Lock()
+		if done {
+			wmu.Unlock()
+			stop()
+			return nil
+		}
+		stops = append(stops, stop)
+		wmu.Unlock()
+		return nil
+	}
+	stopAll := func() {
+		wmu.Lock()
+		done = true
+		all := stops
+		stops = nil
+		s := sub
+		wmu.Unlock()
+		if s != nil {
+			_ = s.Unsubscribe()
+		}
+		for _, stop := range all {
+			stop()
+		}
+	}
+	if first, _, _ := strings.Cut(filter, "."); filter != ">" && first != "*" && first != ">" {
+		if err := add(first); err != nil {
+			stopAll()
+			return nil, err
+		}
+		return stopAll, nil
+	}
+	// Heard before the buckets are listed, so a bucket created between the two is not missed.
+	subject := familyCreatedAdvisory + "*"
+	sb, err := c.nc.Subscribe(subject, func(m *nats.Msg) {
+		bucket, isKV := strings.CutPrefix(m.Subject, familyCreatedAdvisory+"KV_")
+		if node, ok := strings.CutPrefix(bucket, s.Bucket); isKV && ok && node != "" {
+			go func() {
+				if err := add(node); err != nil {
+					c.Logf("[mesh-tools] %s did not take in the new bucket %s%s of %s: %v", module, s.Bucket, node, s.Name, err)
+				}
+			}()
+		}
+	})
+	if err != nil {
+		return nil, fmt.Errorf("the state %s: hearing new buckets %s*: %w", s.Name, s.Bucket, err)
+	}
+	wmu.Lock()
+	sub = sb
+	wmu.Unlock()
+	nodes, err := c.perNodeNodes(s)
+	if err != nil {
+		stopAll()
+		return nil, err
+	}
+	for _, node := range nodes {
+		if err := add(node); err != nil {
+			stopAll()
+			return nil, err
+		}
+	}
+	return stopAll, nil
+}

node-tools/internal/bus/state.go

@@ -28,6 +28,10 @@ type StateIssued struct {
 	Name   string `json:"name"`
 	Bucket string `json:"bucket"`
 	Writes bool   `json:"writes,omitempty"`
+	// PerNode says the state is kept one bucket per node (novox/hq ADR 0593 §6, mesh-sdk membership.StateIssued): Bucket is
+	// then the buckets' prefix, each bucket the prefix and a node's name, and a key's first part names its node. It is read
+	// only, served as one state (per_node.go).
+	PerNode bool `json:"per-node,omitempty"`
 }
 
 // StateEntry is one key's current value.
@@ -81,6 +85,9 @@ func (c *Conn) issuedState(module, name string) (StateIssued, error) {
 		module, name, issued)
 }
 
+// errNoBucket marks a bucket the bus does not hold yet.
+var errNoBucket = errors.New("no such bucket")
+
 func (c *Conn) bucket(ctx context.Context, s StateIssued) (jetstream.KeyValue, error) {
 	js, err := jetstream.New(c.nc)
 	if err != nil {
@@ -90,7 +97,7 @@ func (c *Conn) bucket(ctx context.Context, s StateIssued) (jetstream.KeyValue, e
 	if err != nil {
 		if errors.Is(err, jetstream.ErrBucketNotFound) {
 			return nil, fmt.Errorf("the state %q is issued and its bucket is not on the bus yet: the mesh "+
-				"creates it from the catalogue on its next raise", s.Name)
+				"creates it from the catalogue on its next raise: %w", s.Name, errNoBucket)
 		}
 		return nil, err
 	}
@@ -114,10 +121,18 @@ func (c *Conn) StateGet(module, name, key string) (*StateEntry, error) {
 	if err := checkKey(key); err != nil {
 		return nil, err
 	}
+	if s.PerNode {
+		if s, err = nodeBucketOf(s, key); err != nil {
+			return nil, err
+		}
+	}
 	ctx, cancel := context.WithTimeout(context.Background(), StateTimeout)
 	defer cancel()
 	kv, err := c.bucket(ctx, s)
 	if err != nil {
+		if s.PerNode && errors.Is(err, errNoBucket) {
+			return nil, nil
+		}
 		return nil, err
 	}
 	e, err := kv.Get(ctx, key)
@@ -149,6 +164,9 @@ func (c *Conn) StateHistory(module, name, key string) ([]StateKept, error) {
 	if err := checkKey(key); err != nil {
 		return nil, err
 	}
+	if s.PerNode {
+		return nil, perNodeRefusal(module, name, "history")
+	}
 	ctx, cancel := context.WithTimeout(context.Background(), StateTimeout)
 	defer cancel()
 	kv, err := c.bucket(ctx, s)
@@ -199,6 +217,9 @@ func (c *Conn) StateInfo(module, name string) (*StateInfo, error) {
 	if err != nil {
 		return nil, err
 	}
+	if s.PerNode {
+		return nil, perNodeRefusal(module, name, "fill")
+	}
 	ctx, cancel := context.WithTimeout(context.Background(), StateTimeout)
 	defer cancel()
 	kv, err := c.bucket(ctx, s)
@@ -325,12 +346,20 @@ func (c *Conn) StateKeys(module, name string) ([]string, error) {
 	if err != nil {
 		return nil, err
 	}
+	if s.PerNode {
+		return c.perNodeKeys(s)
+	}
 	ctx, cancel := context.WithTimeout(context.Background(), StateTimeout)
 	defer cancel()
 	kv, err := c.bucket(ctx, s)
 	if err != nil {
 		return nil, err
 	}
+	return keysOf(ctx, kv)
+}
+
+// keysOf is every key with a current value in one bucket, sorted.
+func keysOf(ctx context.Context, kv jetstream.KeyValue) ([]string, error) {
 	lister, err := kv.ListKeys(ctx)
 	if err != nil {
 		return nil, err
@@ -392,12 +421,20 @@ func (c *Conn) StateWatch(module, name, pattern string, deliver func(StateChange
 		}
 		filter = strings.Join(parts, ".")
 	}
+	if s.PerNode {
+		return c.perNodeWatch(module, s, filter, deliver)
+	}
 	ctx, cancel := context.WithTimeout(context.Background(), StateTimeout)
 	kv, err := c.bucket(ctx, s)
 	cancel()
 	if err != nil {
 		return nil, err
 	}
+	return c.watchBucket(module, name, kv, filter, deliver)
+}
+
+// watchBucket is StateWatch over one bucket: the current values, then every change.
+func (c *Conn) watchBucket(module, name string, kv jetstream.KeyValue, filter string, deliver func(StateChange) error) (stop func(), err error) {
 	watching, stopWatching := context.WithCancel(context.Background())
 	w, err := kv.Watch(watching, filter)
 	if err != nil {

node-tools/internal/bus/state_pernode_test.go

@@ -0,0 +1,111 @@
+//go:build integration
+
+package bus_test
+
+import (
+	"errors"
+	"fmt"
+	"reflect"
+	"sort"
+	"strings"
+	"sync"
+	"testing"
+
+	"github.com/novox/mesh-tools/node-tools/internal/bus"
+	mt "github.com/novox/mesh-tools/node-tools/internal/meshtest"
+)
+
+// **A state its owner keeps one bucket per node is served to a bundle as one state** (novox/hq ADR 0593 §6: each node's
+// engine writes its own `composed-<node>`, and the provisioner reads them all). Get goes to the bucket the key's first
+// part names, Keys and Watch over every bucket of the prefix, a bucket created during the watch included, and a bucket
+// that only starts like the prefix is never read.
+func TestAPerNodeStateIsServedAcrossEveryNodesBucket(t *testing.T) {
+	mesh := mt.New(t)
+	a, b := mesh.Bucket(t, "composed-a"), mesh.Bucket(t, "composed-b")
+	other := mesh.Bucket(t, "composedx-z")
+	for kv, key := range map[interface {
+		Put(string, []byte) (uint64, error)
+	}]string{a: "a.m1.f1", b: "b.m2.f2", other: "z.m3.f3"} {
+		if _, err := kv.Put(key, []byte(`{"v":1}`)); err != nil {
+			t.Fatal(err)
+		}
+	}
+	prov := mt.MembershipOf("mesh-provisioner", "anchor", false, nil)
+	prov.State = []bus.StateIssued{{Name: "mesh-host.composed", Bucket: "composed-", PerNode: true}}
+	mesh.Issue(t, prov)
+	conn, err := bus.Connect(bus.Credential{URL: mt.URL(t), Module: "node-tools", Node: "anchor"})
+	if err != nil {
+		t.Fatal(err)
+	}
+	conn.Logf = func(string, ...any) {}
+	t.Cleanup(conn.Close)
+	conn.Follow("mesh-provisioner")
+	mt.Until(t, func() error {
+		if conn.Membership("mesh-provisioner") == nil {
+			return errors.New("not issued yet")
+		}
+		return nil
+	})
+
+	if e, err := conn.StateGet("mesh-provisioner", "mesh-host.composed", "b.m2.f2"); err != nil || e == nil || e.Key != "b.m2.f2" {
+		t.Fatalf("get from the second node's bucket: %+v, %v", e, err)
+	}
+	if e, err := conn.StateGet("mesh-provisioner", "mesh-host.composed", "q.m.f"); err != nil || e != nil {
+		t.Fatalf("a key of a node with no bucket should read as none: %+v, %v", e, err)
+	}
+	if e, err := conn.StateGet("mesh-provisioner", "mesh-host.composed", "z.m3.f3"); err != nil || e != nil {
+		t.Fatalf("the look-alike bucket was read: %+v, %v", e, err)
+	}
+	if _, err := conn.StateGet("mesh-provisioner", "mesh-host.composed", "nonode"); err == nil {
+		t.Fatal("a key naming no node should be refused")
+	}
+	if keys, err := conn.StateKeys("mesh-provisioner", "mesh-host.composed"); err != nil || !reflect.DeepEqual(keys, []string{"a.m1.f1", "b.m2.f2"}) {
+		t.Fatalf("keys across the buckets: %v, %v", keys, err)
+	}
+	if _, err := conn.StatePut("mesh-provisioner", "mesh-host.composed", "a.m1.f9", []byte(`{}`)); err == nil {
+		t.Fatal("a per-node state is read only")
+	}
+
+	var mu sync.Mutex
+	var current, live []string
+	stop, err := conn.StateWatch("mesh-provisioner", "mesh-host.composed", "", func(ch bus.StateChange) error {
+		mu.Lock()
+		defer mu.Unlock()
+		if ch.Current {
+			current = append(current, ch.Key)
+		} else {
+			live = append(live, ch.Key)
+		}
+		return nil
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(stop)
+	mu.Lock()
+	sort.Strings(current)
+	if !reflect.DeepEqual(current, []string{"a.m1.f1", "b.m2.f2"}) {
+		t.Fatalf("current values: %v", current)
+	}
+	mu.Unlock()
+
+	// A third node's bucket, created during the watch, and a change in a first one.
+	c := mesh.Bucket(t, "composed-c")
+	if _, err := c.Put("c.m4.f4", []byte(`{"v":1}`)); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := a.Put("a.m1.f5", []byte(`{"v":1}`)); err != nil {
+		t.Fatal(err)
+	}
+	mt.Until(t, func() error {
+		mu.Lock()
+		defer mu.Unlock()
+		got := strings.Join(append(append([]string(nil), current...), live...), ",")
+		for _, want := range []string{"a.m1.f5", "c.m4.f4"} {
+			if !strings.Contains(got, want) {
+				return fmt.Errorf("%s not heard yet: current %v, changes %v", want, current, live)
+			}
+		}
+		return nil
+	})
+}