Compare commits

..
Author SHA1 Message Date
jschoubben e2ee0dfe98 Merge pull request 'The bus account has JetStream, and the control plane's client has its own inbox' (#105) from fix/the-bus-account-has-jetstream into main 2026-09-27 23:40:38 +00:00
jschoubben 70341cfbc7 The bus account has JetStream, and the control plane's client has its own inbox
Two refusals the first live connections met. A user in the MESH account was told
"JetStream not enabled for account" the first time it bound a consumer: with
accounts defined, JetStream is enabled per account, not only globally — the
account's setting, which the mesh owns, not the server's block, which it does not.
And the control plane's client used a random inbox prefix where it is granted
exactly _INBOX.<its user>.>, so the server's first answer could not reach it. The
prefix now follows from the user in the URL, for every principal that dials so.
2026-09-28 01:40:10 +02:00
jschoubben 77643aa3f4 Merge pull request 'The control plane pins the bus's certificate, and keeps its password out of errors' (#104) from fix/the-controller-pins-the-bus-certificate into main 2026-09-27 23:35:56 +00:00
jschoubben 1fd6194ff8 The control plane pins the bus's certificate, and keeps its password out of errors
The bus presents the mesh's own certificate, which names nothing a public verifier
accepts; the client verified by name and failed against a bus that was answering
("certificate is not valid for any names", 2026-09-28). It now pins the leaf's
fingerprint from MESH_BROKER_CERTIFICATE, as every host does. And a connection
error named the whole URL, password included — the address alone now.
2026-09-28 01:35:20 +02:00
jschoubben c37018fdd2 Merge pull request 'The control plane serves and pushes on the bus it is told to' (#103) from feat/the-controller-serves-on-nats into main 2026-09-27 23:30:52 +00:00
5 changed files with 67 additions and 8 deletions
+2 -2
View File
@@ -60,7 +60,7 @@ func connectLink(ctx context.Context, inv *inventory.Inventory, enroller link.En
js, err := broker.Dial(busAddress)
if err != nil {
return nil, fmt.Errorf("the mesh is on the bus at %s and this control plane cannot reach it: %w",
busAddress, err)
broker.BareAddress(busAddress), err)
}
return link.ConnectNats(js, enroller, listener), nil
}
@@ -726,7 +726,7 @@ func raiseTheBus(ctx context.Context, inv *inventory.Inventory, address string)
js, err := broker.Dial(address)
if err != nil {
return fmt.Errorf("the mesh is on the bus at %s and this control plane cannot reach it: %w",
address, err)
broker.BareAddress(address), err)
}
defer js.Close()
+53 -4
View File
@@ -1,8 +1,14 @@
package broker
import (
"crypto/sha256"
"crypto/tls"
"crypto/x509"
"encoding/hex"
"errors"
"fmt"
"os"
"strings"
"time"
"github.com/nats-io/nats.go"
@@ -24,21 +30,64 @@ type JetStream struct {
// Dial connects and returns the controller's JetStream handle.
func Dial(url string, opts ...nats.Option) (*JetStream, error) {
// A name, because a connection nobody can identify in the server's own monitoring is one
// nobody can attribute a problem to.
opts = append(opts, nats.Name("mesh-controller"), nats.Timeout(10*time.Second))
// **Pinned, not named.** The bus presents the mesh's own certificate, which names nothing a
// public verifier would accept (design 25 §4: a host pins the server's exact certificate and
// checks nothing else, and so does this). Without this, the first connection failed with
// "certificate is not valid for any names" against a bus that was answering (2026-09-28).
if path := strings.TrimSpace(os.Getenv(CertificateVar)); path != "" {
pinned, err := pinnedTo(path)
if err != nil {
return nil, err
}
opts = append(opts, nats.Secure(pinned))
}
// **Its own inbox, and nothing wider.** Every principal is granted `_INBOX.<its user>.>` and
// no other inbox; the client's default prefix is random, and the server refused the first
// subscription to it (2026-09-28). The user is in the URL, so the prefix follows from it.
if user, _, _ := CredentialIn(url); user != "" {
opts = append(opts, nats.CustomInboxPrefix("_INBOX."+user))
}
// The address in an error is the address alone. The URL carries this controller's password,
// and an error here is written on the assumption it will be logged.
where := BareAddress(url)
conn, err := nats.Connect(url, opts...)
if err != nil {
return nil, fmt.Errorf("connecting to the bus at %s: %w", url, err)
return nil, fmt.Errorf("connecting to the bus at %s: %w", where, err)
}
js, err := conn.JetStream()
if err != nil {
conn.Close()
return nil, fmt.Errorf("the bus at %s has no JetStream: %w", url, err)
return nil, fmt.Errorf("the bus at %s has no JetStream: %w", where, err)
}
return &JetStream{conn: conn, js: js}, nil
}
// pinnedTo is a TLS configuration that accepts exactly the certificate in the file and no other:
// the leaf's SHA-256, compared on every handshake, with the name and the chain deliberately not
// consulted — a self-signed certificate with no names is the ordinary case for a mesh's bus.
func pinnedTo(path string) (*tls.Config, error) {
want, err := FingerprintOf(path)
if err != nil {
return nil, err
}
return &tls.Config{
InsecureSkipVerify: true, //nolint:gosec // replaced by the pin below, which is stricter
MinVersion: tls.VersionTLS12,
VerifyPeerCertificate: func(rawCerts [][]byte, _ [][]*x509.Certificate) error {
if len(rawCerts) == 0 {
return errors.New("the bus presented no certificate")
}
sum := sha256.Sum256(rawCerts[0])
got := "sha256:" + hex.EncodeToString(sum[:])
if got != want {
return fmt.Errorf("the bus presented a certificate this mesh does not know (%s…), expected %s…", got[:23], want[:23])
}
return nil
},
}, nil
}
// Conn is the connection itself, for what the mesh keeps off JetStream on purpose — a heartbeat,
// a tool call — where a lost message is answered by the next one or by a timeout the caller
// already handles (design 25 §3).
+4 -1
View File
@@ -521,7 +521,10 @@ func ComposeAccounts(principals []Principal) (string, error) {
// One account for the mesh: accounts in NATS isolate subject spaces entirely, and the mesh is
// one space (design 25 §4). The cost of that — that permissions are the only isolation — is
// paid in the scoping of every inbox and every ack subject.
b.WriteString("accounts {\n MESH {\n users = [\n")
// JetStream is enabled per account once accounts exist at all: with only the global block set,
// a user in MESH is told "JetStream not enabled for account" the first time it binds a
// consumer, which is the first thing every host does (2026-09-28).
b.WriteString("accounts {\n MESH {\n jetstream: enabled\n users = [\n")
for _, p := range sorted {
perms, err := PermissionsFor(p)
if err != nil {
+1
View File
@@ -21,6 +21,7 @@ jetstream {
accounts {
MESH {
jetstream: enabled
users = [
{ user: "controller", password: "$2a$11$cccccccccccccccccccccc", permissions: {
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "_INBOX.enrol.>", "mesh.control.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>"] }
+7 -1
View File
@@ -186,7 +186,13 @@ func TestWhatTheMeshWritesIsUsersAndNothingAboutTheServer(t *testing.T) {
}
// None of the server's own settings. Each of these in the mesh's file is a value the controller
// would then own, and the module could no longer change its own image without the mesh agreeing.
for _, absent := range []string{"port:", "http:", "jetstream", "tls {", "store_dir", "cert_file"} {
// `jetstream {` is the server's block (its store, its limits); `jetstream: enabled` inside the
// account is the account's, and the mesh owns the account — a user in it is told "JetStream
// not enabled for account" without it (2026-09-28).
if !strings.Contains(got, "jetstream: enabled") {
t.Errorf("the account does not enable JetStream, so no user in it can bind a consumer")
}
for _, absent := range []string{"port:", "http:", "jetstream {", "tls {", "store_dir", "cert_file"} {
if strings.Contains(got, absent) {
t.Errorf("the accounts file contains %q, which belongs to the module that raises the "+
"server, not to the mesh", absent)