Compare commits

..
Author SHA1 Message Date
jschoubben c585158836 The two seat commands appear in the usage text
Both existed and neither was listed: rename since ADR 0122, the handover since
ADR 0131. Found by asking the running binary for help and seeing only the list.
2026-09-27 23:45:59 +02:00
76 changed files with 2040 additions and 2813 deletions
+77 -28
View File
@@ -17,7 +17,12 @@ package main
import (
"context"
"crypto/sha256"
"crypto/tls"
"crypto/x509"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
"net/url"
"os"
@@ -25,6 +30,8 @@ import (
"strings"
"syscall"
amqp "github.com/rabbitmq/amqp091-go"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/builder"
"github.com/novox/mesh-controller/internal/link"
@@ -45,6 +52,7 @@ const usage = `mesh-builder — builds modules for the mesh
It consumes build requests and answers with what it made. Nothing is listened on and nothing
is dialled except the broker.
MESH_BROKER_AMQP where the broker is, with this builder's own credential
MESH_BROKER_FILE a file the mesh sealed to this machine holding the same
MESH_REGISTRY host:port to publish artifacts to, when the mesh has not said
MESH_BINDING a file the mesh wrote saying where the artifact store is
@@ -127,17 +135,32 @@ func run() error {
// machine told about both would take work from one and answer on the other, and every log line would
// say it was fine.
func takeWorkFrom(credential Credential, on string) (link.BuildMachine, error) {
// **The credential names the bus, and there is one** (novox/hq ADR 0131, design 28 task 5.5).
// A credential for the mesh's bus carries user, password and fingerprint beside the address,
// and that is enough to dial it, pinned.
if !credential.onTheNewBus() {
return nil, fmt.Errorf("the credential at hand names %q, which is not the mesh's bus", credential.URL)
}
js, err := broker.DialPinned(credential.natsURL(), credential.Fingerprint)
address, onNATS, err := broker.OnNATS()
if err != nil {
return nil, err
}
return link.MachineOverNATS(js, on), nil
if err := broker.MustBeOneBus(credential.URL, address); err != nil {
return nil, err
}
if onNATS {
js, err := broker.Dial(address)
if err != nil {
return nil, fmt.Errorf("cannot reach the bus at %s: %w", address, err)
}
return link.MachineOverNATS(js, on), nil
}
conn, err := dial(credential)
if err != nil {
// Not quoted back: the URL carries this builder's broker password.
return nil, fmt.Errorf("cannot reach the broker: %w", err)
}
channel, err := conn.Channel()
if err != nil {
conn.Close()
return nil, err
}
return link.MachineOverCurrent(conn, channel, on), nil
}
// answer does one build and says what happened, whichever way it went.
@@ -194,9 +217,6 @@ func answer(ctx context.Context, publisher builder.Publisher, on, workspace stri
})
}
result.Against = built.Against
for _, r := range built.Read {
result.Read = append(result.Read, link.ReadRepository{Repository: r.Repository, Ref: r.Ref})
}
fmt.Fprintf(os.Stderr, " built %s from %s\n", built.Manifest.Module, short(built.Commit))
}
}
@@ -422,8 +442,13 @@ func brokerFrom() (Credential, error) {
// broker is then verified against whatever this machine already trusts.
return Credential{URL: said}, nil
}
return Credential{}, fmt.Errorf(
"no MESH_BROKER_FILE: a build machine with no credential for the bus has nothing to build")
url := strings.TrimSpace(os.Getenv("MESH_BROKER_AMQP"))
if url == "" {
return Credential{}, fmt.Errorf(
"neither MESH_BROKER_FILE nor MESH_BROKER_AMQP: a builder with no broker has " +
"nothing to build")
}
return Credential{URL: url}, nil
}
// Credential is what a build machine is given so it can reach the broker.
@@ -435,24 +460,48 @@ func brokerFrom() (Credential, error) {
// **The same shape a node gets, for the same reason** (novox/hq ADR 0004): the fingerprint travels
// out of band — here, sealed with the credential — and the endpoint is verified once at connect.
type Credential struct {
URL string `json:"url"`
URL string `json:"url"`
// Fingerprint is SHA-256 over the broker certificate's DER bytes, or empty to verify the
// ordinary way.
Fingerprint string `json:"fingerprint,omitempty"`
// User and Password ride beside the address on the bus being built (design 25): a credential
// embedded in a URL leaks into every log line that prints a connection, so the mesh seals them
// as two fields and this machine joins them once, here, to dial.
User string `json:"user,omitempty"`
Password string `json:"password,omitempty"`
}
// onTheNewBus is whether a credential is for the bus being built: its address says so, and the
// mesh only ever seals such a credential with the user and password beside it.
func (c Credential) onTheNewBus() bool { return strings.HasPrefix(strings.TrimSpace(c.URL), "nats://") }
// dial opens the connection, pinning the broker's certificate when there is one to pin.
func dial(held Credential) (*amqp.Connection, error) {
if held.Fingerprint == "" {
return amqp.Dial(held.URL)
}
return amqp.DialTLS(held.URL, pinning(held.Fingerprint))
}
// natsURL is the address with this machine's credential in it, for the one dial that needs it.
func (c Credential) natsURL() string {
rest := strings.TrimPrefix(strings.TrimSpace(c.URL), "nats://")
if c.User == "" {
return "nats://" + rest
// pinning is a TLS configuration that trusts exactly one certificate.
//
// InsecureSkipVerify with a VerifyPeerCertificate is **pinning, not skipping**: the standard chain
// check is replaced, not removed, and what replaces it is stricter — one certificate is accepted
// rather than every certificate a public authority would sign.
//
// Its own function so a test can drive it against a real handshake. A pin check that is only ever
// exercised through a broker is a pin check nothing tests.
func pinning(fingerprint string) *tls.Config {
return &tls.Config{
InsecureSkipVerify: true,
VerifyPeerCertificate: func(raw [][]byte, _ [][]*x509.Certificate) error {
if len(raw) == 0 {
return errors.New("the broker presented no certificate")
}
// The leaf, and in the same spelling the mesh writes it — `sha256:` and 64 hex
// characters. Comparing a bare digest against a written fingerprint never matches,
// and the failure is indistinguishable from being pointed at the wrong broker.
sum := sha256.Sum256(raw[0])
got := "sha256:" + hex.EncodeToString(sum[:])
if got != fingerprint {
return fmt.Errorf(
"this is not the broker this builder was told about\n expected %s\n "+
"got %s\nEither this mesh's broker was replaced, or this builder is "+
"being pointed at something else. Retrying will not help",
fingerprint, got)
}
return nil
},
}
return "nats://" + c.User + ":" + c.Password + "@" + rest
}
+8 -18
View File
@@ -106,9 +106,6 @@ func buildOnce(ctx context.Context, args []string) error {
Manifest: built.Manifest,
Against: built.Against,
}
for _, r := range built.Read {
out.Read = append(out.Read, readRepository{Repository: r.Repository, Ref: r.Ref})
}
for _, made := range built.Built {
out.Made = append(out.Made, madeArtifact{Name: made.Name, Kind: made.Kind, Reference: made.Reference})
}
@@ -126,21 +123,14 @@ func buildOnce(ctx context.Context, args []string) error {
// The same fields the mesh records for a build, so a reader comparing a genesis build against an
// ordinary one is comparing the same thing said the same way.
type onceResult struct {
Module string `json:"module"`
Commit string `json:"commit"`
Repository string `json:"repository"`
Path string `json:"path,omitempty"`
Ref string `json:"ref,omitempty"`
Manifest any `json:"manifest"`
Made []madeArtifact `json:"made"`
Against []string `json:"against,omitempty"`
Read []readRepository `json:"read,omitempty"`
}
// readRepository is a repository this build read source from besides the module's own.
type readRepository struct {
Repository string `json:"repository"`
Ref string `json:"ref,omitempty"`
Module string `json:"module"`
Commit string `json:"commit"`
Repository string `json:"repository"`
Path string `json:"path,omitempty"`
Ref string `json:"ref,omitempty"`
Manifest any `json:"manifest"`
Made []madeArtifact `json:"made"`
Against []string `json:"against,omitempty"`
}
type madeArtifact struct {
+2 -2
View File
@@ -14,8 +14,8 @@ func TestBuilderDiagnosticsStayOffStdout(t *testing.T) {
allowed := map[string]bool{
"string(body)": true, // once.go: the result JSON, which IS stdout
"version)": true, // --version
`"stopping")`: true, // the loop.s shutdown line
"usage)": true, // --help text, for a human
`"stopping")`: true, // the loop.s shutdown line
"usage)": true, // --help text, for a human
}
for _, file := range []string{"once.go", "main.go"} {
src, err := os.ReadFile(file)
+2 -4
View File
@@ -15,8 +15,6 @@ import (
"strings"
"testing"
"time"
"github.com/novox/mesh-controller/internal/broker"
)
// Where a builder publishes.
@@ -195,9 +193,9 @@ func TestThePinIsComparedInTheSpellingTheMeshWritesIt(t *testing.T) {
}
}
// handshakeWith runs the pin check the builder dials with against an address.
// handshakeWith runs the builder's own pin check against an address.
func handshakeWith(address, pin string) error {
conn, err := tls.Dial("tcp", address, broker.PinnedToFingerprint(pin))
conn, err := tls.Dial("tcp", address, pinning(pin))
if err != nil {
return err
}
+4 -7
View File
@@ -17,8 +17,8 @@ import (
var aDigest = "sha256:" + strings.Repeat("e", 64)
// **A build is recorded by digest and path**, whatever address the builder pushed to — what it
// made and what it stood on both; an image the module runs from elsewhere is left where it says.
// **A build is recorded by digest and path**, whatever address the builder pushed to — and only
// what the build made is rewritten: an image the module runs from elsewhere is left where it says.
func TestABuildIsRecordedWithoutTheStoresAddress(t *testing.T) {
manifest, _ := json.Marshal(map[string]any{
"module": "gitea", "version": "1",
@@ -65,11 +65,8 @@ func TestABuildIsRecordedWithoutTheStoresAddress(t *testing.T) {
if strings.Contains(string(kept.Manifest), "anchor.internal:5100") {
t.Errorf("the recorded manifest still carries the store's address:\n%s", kept.Manifest)
}
// What the build stood on is an edge to another module's artifact, and it is recorded the way
// that artifact is: by path in the store, so the edge still names the same thing when the
// store answers at another address.
if kept.Against[0] != catalogue.ArtifactStoreScheme+"mesh-tools/runtime@"+aDigest {
t.Errorf("what the build stood on was recorded by address: %v", kept.Against)
if kept.Against[0] != "anchor.internal:5100/mesh-tools/runtime@"+aDigest {
t.Errorf("what the build stood on was rewritten: %v", kept.Against)
}
}
+1 -1
View File
@@ -88,7 +88,7 @@ func reportsReaching(t *testing.T, open *stores, reachable []link.Reach, held ..
if err := open.inventory.RecordSent(ctx, record.ID, digestOf(body)); err != nil {
t.Fatal(err)
}
if _, err := (link.Enrolment{Inventory: open.inventory}).Heard(ctx, link.Report{
if err := (link.Enrolment{Inventory: open.inventory}).Heard(ctx, link.Report{
Node: "anchor", Applied: []string{"hello-web.x"}, Declared: digestOf(body),
Firewall: "ufw", Held: held, Reachable: reachable,
}); err != nil {
+2 -2
View File
@@ -37,13 +37,13 @@ func askCommand(ctx context.Context, args []string) error {
arguments = json.RawMessage(positionals[2])
}
server, err := connectLink(ctx, nil, nil, nil)
server, err := link.Connect(nil, nil)
if err != nil {
return err
}
defer server.Close()
answer, err := link.Ask(ctx, server.Bus(), module, tool, arguments, *wait)
answer, err := link.Ask(ctx, server.Channel(), module, tool, arguments, *wait)
if err != nil {
return err
}
+84 -104
View File
@@ -2,6 +2,8 @@ package main
import (
"context"
"crypto/rand"
"encoding/base64"
"encoding/json"
"errors"
"flag"
@@ -29,51 +31,6 @@ import (
// control plane may send a machine is bounded by the declaration language. This is the shape the
// builder module will take when it is given work over the broker; today a person runs it, and the
// mesh records the result the same way either way.
// buildOn rebuilds every module the mesh holds that stands on the named module's artifacts — the
// rebuild a changed base needs, which nothing else asks for: their sources did not move, and
// "behind" does not see a base that did (novox/hq 04-ISSUES/131). Bases first among them too.
func buildOn(ctx context.Context, base string, wait time.Duration) error {
open, err := openStores(ctx)
if err != nil {
return err
}
defer open.Close()
held, err := open.inventory.Catalogued(ctx)
if err != nil {
return err
}
against, err := open.inventory.BuiltAgainst(ctx)
if err != nil {
return err
}
var on []inventory.Entry
for _, e := range held {
if standsOnModule(e, base, against) {
on = append(on, e)
}
}
if len(on) == 0 {
fmt.Printf("nothing the mesh holds stands on %s\n", base)
return nil
}
on = orderByBases(on, against)
fmt.Printf("%d module(s) stand on %s:\n", len(on), base)
var failed []string
for _, e := range on {
fmt.Printf("--- %s\n", e.Manifest.Module)
source := buildSource{Repository: e.Source.Repository, Seat: e.Source.Seat}
if err := buildOne(ctx, source, e.Source.Path, e.Source.Ref, wait); err != nil {
fmt.Printf(" %v\n", err)
failed = append(failed, e.Manifest.Module)
}
}
if len(failed) > 0 {
return fmt.Errorf("%d of %d could not be built: %s", len(failed), len(on), strings.Join(failed, ", "))
}
fmt.Printf("\n%d module(s) rebuilt on %s. `push --behind` sends them on\n", len(on), base)
return nil
}
func buildCommand(ctx context.Context, args []string) error {
set := flag.NewFlagSet("build", flag.ContinueOnError)
ref := set.String("ref", "", "the branch, tag or commit to build")
@@ -89,7 +46,6 @@ func buildCommand(ctx context.Context, args []string) error {
// retype each repository is asking them to be the loop. Naming a repository and asking which
// ones need building are different requests, so they are not combined.
behind := set.Bool("behind", false, "every module the mesh holds older than its source has")
on := set.String("on", "", "rebuild every module that stands on this module's artifacts — the rebuild a changed base needs")
// A repository on the mesh's own forge, named by its path there (novox/hq ADR 0111). Without it
// the repository is external, cloned exactly as given — see source.go.
self := set.Bool("self", false, "the repository is a path on the forge holding the git seat")
@@ -97,13 +53,6 @@ func buildCommand(ctx context.Context, args []string) error {
if err != nil {
return err
}
if *on != "" {
if len(positionals) != 0 || *behind || *self {
return errors.New("build --on <module> names a base and nothing else")
}
return buildOn(ctx, *on, *wait)
}
if *behind {
if len(positionals) != 0 || *self {
return errors.New("build <repository> or build --behind, not both: one names a " +
@@ -112,7 +61,7 @@ func buildCommand(ctx context.Context, args []string) error {
return buildBehind(ctx, *wait)
}
if len(positionals) != 1 {
return errors.New("build <repository> [--self] [--path P] [--ref R] [--wait D] [--dry-run] | build --behind | build --on <module>")
return errors.New("build <repository> [--self] [--path P] [--ref R] [--wait D] [--dry-run]")
}
source := buildSource{Repository: positionals[0]}
if *self {
@@ -132,9 +81,8 @@ func buildCommand(ctx context.Context, args []string) error {
//
// **By digest and path, never by where it was pushed** (novox/hq 04-ISSUES/102). The builder
// says `<registry>:<port>/<module>/<artifact>@sha256:…`; the mesh records the artifact-store
// reference and composes the store's address back in where a reference is used. `against` — what
// the build stood on, the catalogue's edge — is recorded the same way, so an edge names a module's
// artifact and not the machine it was pulled from.
// reference and composes the store's address back in where a reference is used. `against` is kept
// as announced: it is what the build stood on as the builder saw it, and the catalogue's edge.
func buildFrom(result link.BuildResult) inventory.Build {
kept := inventory.Build{
ID: result.ID, Repository: result.Repository, Ref: result.Ref,
@@ -144,13 +92,7 @@ func buildFrom(result link.BuildResult) inventory.Build {
// edges, and it is not always listening when a build happens — on a fresh mesh it cannot
// be, for exactly the modules it needs most. Keeping them is what makes a replay able to
// rebuild the graph rather than a list of names.
Path: result.Path,
}
for _, ref := range result.Against {
kept.Against = append(kept.Against, catalogue.Recorded(ref))
}
for _, r := range result.Read {
kept.Read = append(kept.Read, inventory.ReadRepository{Repository: r.Repository, Ref: r.Ref})
Path: result.Path, Against: result.Against,
}
var announced []inventory.Artifact
for _, made := range result.Made {
@@ -264,45 +206,85 @@ func builderCommand(ctx context.Context, args []string) error {
}
name := positionals[1]
// **The build machine's credential is a module's credential** (novox/hq ADR 0131, design 28
// task 5.5): minted into the mesh's records and sealed to the machine as the builder module's
// broker secret, usable at the next push — the same act `module issue` performs, and the same
// account the composed user list carries. Nothing is created on a server; the bus reads the list.
open, err := openStores(ctx)
management, err := broker.ManagementFromEnvironment()
if err != nil {
return err
}
defer open.Close()
inv := open.inventory
shelf, err := inv.Catalogue(ctx)
if err != nil {
// The same shape of secret a token carries: enough entropy that guessing is not a strategy,
// and safe to put in a URL because that is where it goes.
raw := make([]byte, 32)
if _, err := rand.Read(raw); err != nil {
return err
}
m, known := shelf[*module]
if !known {
return fmt.Errorf("%s is not in the catalogue; `module add` it first", *module)
password := base64.RawURLEncoding.EncodeToString(raw)
if err := management.CreateBuilderAccount(ctx, name, password); err != nil {
return err
}
fmt.Printf("build machine %s: ", name)
node := *forNode
if node == "" {
entries, err := inv.Catalogued(ctx)
fmt.Printf("broker account %s created, scoped to the %s queue and the %s exchange\n\n",
name, link.BuildQueue, link.Exchange)
if *forNode != "" {
known, err := broker.FromEnvironment()
if err != nil {
return fmt.Errorf("cannot deliver a credential without knowing where the broker is: %w", err)
}
inv, err := openInventory(ctx)
if err != nil {
return err
}
for _, e := range entries {
if e.Manifest.Module == *module && len(e.On) > 0 {
node = e.On[0]
}
defer inv.Close()
brokerAddr, err := brokerReachableAt(ctx, inv, known, *forNode)
if err != nil {
return err
}
// The URL and what verifies the broker, together. A mesh's broker presents a certificate
// of the mesh's own, which is in no public trust store — so a URL on its own reaches only
// a broker somebody else vouches for, and the connection fails at TLS with an error about
// an unknown authority rather than about a missing pin.
//
// **The same two facts a node's token carries** (novox/hq ADR 0004), delivered the same
// way: out of band relative to the broker, so what is trusted does not come from the thing
// being trusted.
held, err := json.Marshal(struct {
URL string `json:"url"`
Fingerprint string `json:"fingerprint,omitempty"`
}{
URL: fmt.Sprintf("amqps://%s:%s@%s/", name, password, brokerAddr),
Fingerprint: known.Fingerprint,
})
if err != nil {
return err
}
if err := inv.AcceptSecretForModule(ctx, *forNode, *module, "broker", string(held)); err != nil {
return err
}
// Not printed. It is sealed to that machine and the mesh cannot read it back, which is
// the whole point — printing it here would put the one copy that matters on a terminal.
fmt.Printf(" sealed to %s, for the %s module. It arrives with the next push.\n",
*forNode, *module)
fmt.Printf(" run `push %s` to send it\n", *forNode)
return nil
}
if node == "" {
return fmt.Errorf("%s is assigned nowhere; `assign <machine> %s` first, or say --node", *module, *module)
// The whole line only when the address is known. A URL with a placeholder where the host
// should be is a URL somebody pastes and then debugs, and the placeholder is the last thing
// they look at.
if known, err := broker.FromEnvironment(); err == nil {
fmt.Printf(" MESH_BROKER_AMQP=amqps://%s:%s@%s/\n\n", name, password, known.Address)
} else {
fmt.Printf(" the password is %s\n\n", password)
fmt.Printf(" This control plane has no %s, so it cannot say where the broker is.\n"+
" Put the password in MESH_BROKER_AMQP on the build machine.\n\n",
broker.AddressVar)
}
address, err := broker.BusAddress()
if err != nil {
return err
}
return issueOnTheNewBus(ctx, inv, m, node, address)
// Shown once, like a token, and for the same reason: what is stored is the broker's own hash
// of it, and a control plane that could show it back would be a control plane that holds it.
fmt.Println("This is the only time it is shown.")
return nil
}
// buildBehind builds every module the mesh holds older than its source has.
@@ -347,14 +329,6 @@ func buildBehind(ctx context.Context, wait time.Duration) error {
}
fmt.Println()
// Bases first: a module built before the module it stands on is built against the old one
// and reports success (novox/hq 04-ISSUES/131).
against, err := inv.BuiltAgainst(ctx)
if err != nil {
return err
}
stale = orderByBases(stale, against)
var failed []string
for _, e := range stale {
fmt.Printf("--- %s\n", e.Manifest.Module)
@@ -394,7 +368,7 @@ func buildOne(ctx context.Context, source buildSource, path, ref string, wait ti
}
defer ident.Close()
server, err := connectLink(ctx, nil, nil, nil)
server, err := link.Connect(nil, nil)
if err != nil {
return err
}
@@ -498,7 +472,7 @@ func buildAndShow(ctx context.Context, source buildSource, path, ref string, wai
return err
}
defer ident.Close()
server, err := connectLink(ctx, nil, nil, nil)
server, err := link.Connect(nil, nil)
if err != nil {
return err
}
@@ -601,10 +575,16 @@ func heldBy(ctx context.Context) map[string]string {
// **One place chooses**, as everywhere else the bus change went (novox/hq ADR 0116 step 5). On the bus
// the mesh runs on today this needs the controller's own connection, so it is handed one; on the bus
// being built it dials, because a build request is a one-shot and holds nothing else.
func askOver(_ *link.Server) (link.Builders, error) {
address, err := broker.BusAddress()
func askOver(server *link.Server) (link.Builders, error) {
address, onNATS, err := broker.OnNATS()
if err != nil {
return nil, err
}
return link.BuildsOverNATS(address)
if err := broker.MustBeOneBus(os.Getenv(broker.AMQPVarName), address); err != nil {
return nil, err
}
if onNATS {
return link.BuildsOverNATS(address)
}
return link.BuildsOverCurrent(server.Channel()), nil
}
+3 -6
View File
@@ -76,10 +76,7 @@ func run() error {
return pinCommand(ctx, args[1:], true)
case "unpin":
return pinCommand(ctx, args[1:], false)
// `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":
case "migrate":
return migrate(ctx)
case "node":
return nodeCommand(ctx, args[1:])
@@ -141,7 +138,6 @@ 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
@@ -168,6 +164,8 @@ func usage() {
upgrade <name> record ...record that they are behind, and send nothing
status [--json] what is wrong, what is quiet, and what is out of date
seats [--json] every seat this mesh defines, what it delivers, and who holds it
seat rename <from> <to> rename a seat; its former name still resolves (ADR 0122)
seat <name> --to <node>/<module> hand a seat to that assignment as one act; never empty in between (ADR 0131)
board [--listen ADDR] the same three questions, as a page that holds nothing
api --issuer URL [--listen A] assign and unassign over http, for a surface that is not here
assign <node> <module> put a module on a node
@@ -188,7 +186,6 @@ func usage() {
operator key show the operator key, and what it can recover
build <repository> [--ref R] have a build machine build it, and record what came out
build --behind build every module the mesh holds older than its source
build --on <module> rebuild every module that stands on this module's artifacts, bases first
builds [<module>] what has been built lately, and what came of it
builder issue <name> a broker account for a build machine, scoped to build work,
delivered as the builder module's broker secret (module add it first)
+89 -78
View File
@@ -2,6 +2,8 @@ package main
import (
"context"
"crypto/rand"
"encoding/base64"
"encoding/json"
"errors"
"flag"
@@ -69,20 +71,12 @@ func moduleCommand(ctx context.Context, args []string) error {
repo := set.String("source", "", "where this module comes from")
ref := set.String("ref", "", "the branch followed there")
commit := set.String("commit", "", "the commit this manifest was read at")
// **Where inside the repository the module is** (novox/hq ADR 0069). A module is a
// repository *and* a directory, and a record that carries only the repository names a
// module.json at its root — so every later build of it looks in the wrong place and fails
// with "no module.json at its root". Nine modules on this mesh were registered that way
// and none of them could be rebuilt (2026-09-28).
path := set.String("path", "", "the module's directory inside that repository")
self := set.Bool("self", false, "the source is a path on the forge holding the git seat")
positionals, err := parseAround(set, args[1:])
if err != nil {
return err
}
if len(positionals) != 1 {
return errors.New("module add <manifest.json> [--source <repo> [--self] [--path P] " +
"--ref <branch> --commit <sha>]")
return errors.New("module add <manifest.json> [--source <repo> --ref <branch> --commit <sha>]")
}
raw, err := os.ReadFile(positionals[0])
if err != nil {
@@ -92,24 +86,23 @@ func moduleCommand(ctx context.Context, args []string) error {
if err != nil {
return err
}
from, err := whereItComesFrom(*repo, *ref, *commit, *path, *self)
if err != nil {
return err
// Provenance together or not at all. A source with no commit cannot be compared against
// anything, so it would record where the module came from and still never be able to say
// the mesh is behind it — which is the one thing recording it is for.
if (*repo == "") != (*commit == "") {
return errors.New("--source and --commit go together: a source with no commit " +
"cannot be compared against anything, and a commit with no source has nothing " +
"to be compared with")
}
if err := inv.RegisterModule(ctx, m, from); err != nil {
if err := inv.RegisterModule(ctx, m, inventory.Source{
Repository: *repo, Ref: *ref, BuiltFrom: *commit,
}); err != nil {
return err
}
fmt.Printf("%s registered", m.Module)
if *commit != "" {
fmt.Printf(" from %s", short(*commit))
}
if *repo != "" && *path == "" {
// Said, not refused: a module really at the root is the ordinary case for a repository
// of its own. But a repository holding many modules and a record naming none of them is
// a module nothing can rebuild, and the person adding it is the one who knows which.
fmt.Printf("\n no directory inside %s, so it is built from that repository's root — "+
"`--path` if the module lives in a directory there", *repo)
}
if len(m.Provides) > 0 {
fmt.Printf(", providing %s", describeOffers(m.Provides))
}
@@ -268,11 +261,77 @@ func moduleCommand(ctx context.Context, args []string) error {
// made in entirely different ways: on the bus the mesh runs on today an account is a
// management call, and on the bus being built it is a row the next composition writes into
// the server's user list (novox/hq design 25 §4).
busAddress, err := broker.BusAddress()
busAddress, onNATS, err := broker.OnNATS()
if err != nil {
return err
}
return issueOnTheNewBus(ctx, inv, m, *forNode, busAddress)
if err := broker.MustBeOneBus(os.Getenv(broker.AMQPVarName), busAddress); err != nil {
return err
}
if onNATS {
return issueOnTheNewBus(ctx, inv, m, *forNode, busAddress)
}
management, err := broker.ManagementFromEnvironment()
if err != nil {
return err
}
// The foundation owns the bus; make sure it exists before a module binds onto it.
if err := management.EnsureEventExchanges(ctx); err != nil {
return err
}
secret := make([]byte, 32)
if _, err := rand.Read(secret); err != nil {
return err
}
password := base64.RawURLEncoding.EncodeToString(secret)
account, err := management.CreateModuleAccount(ctx, *forNode, module, password, m.Emits, m.Consumes)
if err != nil {
return err
}
// A consumer's queue, with its dead-letter, is the foundation's to declare — its own account
// may not (ADR 0043). Made now, so it exists before the module binds onto it.
if len(m.Consumes) > 0 {
if err := management.EnsureModuleQueue(ctx, *forNode, module); err != nil {
return err
}
}
known, err := broker.FromEnvironment()
if err != nil {
return fmt.Errorf("cannot deliver a credential without knowing where the broker is: %w", err)
}
brokerAddr, err := brokerReachableAt(ctx, inv, known, *forNode)
if err != nil {
return err
}
// The URL and what verifies the broker, together — a mesh's broker presents its own
// certificate, in no public trust store, so a URL alone fails at TLS (as `builder issue`).
held, err := json.Marshal(struct {
URL string `json:"url"`
Fingerprint string `json:"fingerprint,omitempty"`
Node string `json:"node"`
Module string `json:"module"`
}{
URL: fmt.Sprintf("amqps://%s:%s@%s/", account, password, brokerAddr),
Fingerprint: known.Fingerprint,
// The node and module the account is for, so the runtime names its queue as the mesh
// scoped it (<node>.<module>.events) without a manifest having to interpolate a node.
Node: *forNode,
Module: module,
})
if err != nil {
return err
}
if err := inv.AcceptSecretForModule(ctx, *forNode, module, "broker", string(held)); err != nil {
return err
}
fmt.Printf("broker account %s created for %s, scoped to what it emits and consumes\n",
account, module)
fmt.Printf(" sealed to %s. It arrives with the next push — `push %s` to send it\n",
*forNode, *forNode)
return nil
default:
return fmt.Errorf("module has no %q; it has add, list, moved, forget and issue", args[0])
@@ -555,15 +614,6 @@ func issueOnTheNewBus(ctx context.Context, inv *inventory.Inventory, m catalogue
if err != nil {
return err
}
return issueWith(ctx, inv, m, node, busAddress, known, reachable, user, password)
}
// issueWith is the delivery half: the minted password sealed to the machine as the module's broker
// secret, and the module's consumer created where the bus can be reached. Split from the minting
// so the move can issue every module against a bus whose address it worked out itself
// (`rollout mint`, design 28 task 5.2) rather than the one in this process's environment.
func issueWith(ctx context.Context, inv *inventory.Inventory, m catalogue.Manifest,
node, busAddress string, known broker.Broker, reachable, user, password string) error {
held, err := json.Marshal(struct {
URL string `json:"url"`
Fingerprint string `json:"fingerprint,omitempty"`
@@ -589,19 +639,14 @@ func issueWith(ctx context.Context, inv *inventory.Inventory, m catalogue.Manife
Kind: broker.KindModule, Node: node, Module: m.Module,
Emits: m.Emits, Consumes: m.Consumes, Serves: m.Tools,
}); needed {
if busAddress == "" {
fmt.Printf(" %s consumes; its consumer is created when the bus is reachable (`push`, then "+
"`rollout mint` again is harmless)\n", m.Module)
} else {
js, err := broker.Dial(busAddress)
if err != nil {
return fmt.Errorf("the credential is minted and the mesh cannot reach the bus to create "+
"how %s hears what it consumes: %w", m.Module, err)
}
defer js.Close()
if err := js.EnsureConsumer(consumer); err != nil {
return err
}
js, err := broker.Dial(busAddress)
if err != nil {
return fmt.Errorf("the credential is minted and the mesh cannot reach the bus to create "+
"how %s hears what it consumes: %w", m.Module, err)
}
defer js.Close()
if err := js.EnsureConsumer(consumer); err != nil {
return err
}
}
@@ -611,37 +656,3 @@ func issueWith(ctx context.Context, inv *inventory.Inventory, m catalogue.Manife
"machine holding mesh-broker\n")
return nil
}
// whereItComesFrom is the provenance a module handed over by hand records, and what a record must
// say to be worth anything later.
//
// **A module is a repository and a directory inside it** (novox/hq ADR 0069). A record carrying only
// the repository names a module.json at its root, so every later build of it looks in the wrong
// place — nine modules on this mesh were registered that way and none of them could be rebuilt
// (2026-09-28). The directory cannot be checked from here, because the control plane does not clone;
// what can be checked is that the record is whole.
func whereItComesFrom(repository, ref, commit, path string, self bool) (inventory.Source, error) {
// Provenance together or not at all. A source with no commit cannot be compared against
// anything, so it would record where the module came from and still never be able to say the
// mesh is behind it — which is the one thing recording it is for.
if (repository == "") != (commit == "") {
return inventory.Source{}, errors.New("--source and --commit go together: a source with " +
"no commit cannot be compared against anything, and a commit with no source has " +
"nothing to be compared with")
}
// A directory or a forge with no repository is half a location, and the half it keeps is the
// half nothing can be found with.
if repository == "" && (path != "" || self) {
return inventory.Source{}, errors.New("--path and --self say where inside a source and " +
"which forge holds it, so they need --source: without one there is nothing for them " +
"to be part of")
}
from := inventory.Source{Repository: repository, Ref: ref, BuiltFrom: commit, Path: path}
if self {
if err := onASeat(repository); err != nil {
return inventory.Source{}, err
}
from.Seat = gitSeat
}
return from, nil
}
+1 -10
View File
@@ -537,15 +537,6 @@ func onTheNetwork(ctx context.Context, inv *inventory.Inventory,
if err != nil {
return nil, err
}
// **With the seat holders on record**, or a machine running the next holder of a seat beside
// the current one resolves as two holders, is refused, and drops out of the map — taking the
// address every other machine composes for what it offers (novox/hq ADR 0131). Found live:
// the control node vanished from the private network the moment the new bus was assigned
// beside the old one.
holdings, err := inv.Holdings(ctx)
if err != nil {
return nil, err
}
var out []inventory.Overlay
for _, p := range places {
if p.Address == "" {
@@ -558,7 +549,7 @@ func onTheNetwork(ctx context.Context, inv *inventory.Inventory,
caps, _ := inv.ProfileOf(ctx, p.Name)
got, err := catalogue.Resolve(shelf, assigned,
catalogue.Node{Name: p.Name, Site: p.Site, Capabilities: caps},
catalogue.World{Unchecked: true, Holdings: holdings})
catalogue.World{Unchecked: true})
if err != nil {
continue
}
+10
View File
@@ -10,6 +10,7 @@ import (
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
"github.com/novox/mesh-controller/internal/token"
)
@@ -257,6 +258,15 @@ func tokenCommand(ctx context.Context, args []string) error {
// chicken-and-egg entirely: the mesh runs the broker, so a joining node's credentials can
// exist before it does. The one-time secret IS the password, so a node's first connection is
// already authenticated and enrolment is what happens over it.
if management, err := broker.ManagementFromEnvironment(); err == nil {
if err := management.CreateNodeAccount(ctx, issued.Node.Name, issued.Secret); err != nil {
return err
}
fmt.Printf("broker account %s created, scoped to %s and the %s exchange\n\n",
issued.Node.Name, link.QueueFor(issued.Node.Name), link.Exchange)
} else if !errors.Is(err, broker.ErrNotConfigured) {
return err
}
made := token.Token{Node: issued.Node.Name, Signer: key.Public, Secret: issued.Secret,
Adopted: issued.Node.Adopted}
+3 -7
View File
@@ -189,17 +189,13 @@ func readPrivateKey(path string) (string, error) {
func personIssue(ctx context.Context, args []string) error {
set := flag.NewFlagSet("operator issue", flag.ContinueOnError)
invokes := set.String("invokes", "", "the tools this person may call, comma-separated, or * for every one")
// Flags on either side of the name, because the usage this command prints puts them after it —
// and the standard parser stops at the first thing that is not a flag, so the order the command
// documents was the one order it refused (2026-09-28).
positionals, err := parseAround(set, args)
if err != nil {
if err := set.Parse(args); err != nil {
return err
}
if len(positionals) != 1 {
if set.NArg() != 1 {
return errors.New("operator issue <name> --invokes <tool,tool|*>")
}
name := positionals[0]
name := set.Arg(0)
if *invokes == "" {
return errors.New(
"say what this person may call: --invokes mesh-catalog.catalog_tools,gitea.repo_create, " +
-212
View File
@@ -1,212 +0,0 @@
package main
import (
"strings"
"testing"
"time"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
)
// entry is a module as the catalogue holds it: built, so its manifest carries no `build` any more.
func entry(module string, _ ...string) inventory.Entry {
return inventory.Entry{Manifest: catalogue.Manifest{Module: module}}
}
// stoodOn is what each module's newest build recorded it was handed.
func stoodOn(edges map[string][]string) map[string][]string {
out := map[string][]string{}
for module, bases := range edges {
for _, b := range bases {
out[module] = append(out[module], catalogue.ArtifactStoreScheme+b+"/runtime@sha256:"+strings.Repeat("0", 64))
}
}
return out
}
// A module built before the module it stands on is built against the old one and reports success
// (novox/hq 04-ISSUES/131). So bases come first, however the set arrived.
func TestBasesAreBuiltBeforeWhatStandsOnThem(t *testing.T) {
in := []inventory.Entry{entry("app"), entry("runtime"), entry("other"), entry("base")}
edges := stoodOn(map[string][]string{"app": {"runtime"}, "runtime": {"base"}})
got := orderByBases(in, edges)
pos := map[string]int{}
for i, e := range got {
pos[e.Manifest.Module] = i
}
if !(pos["base"] < pos["runtime"] && pos["runtime"] < pos["app"]) {
t.Fatalf("bases not first: %v", pos)
}
if len(got) != 4 {
t.Fatalf("an entry was lost or doubled: %d", len(got))
}
// A base outside the set is not waited for: it is not being rebuilt.
got = orderByBases([]inventory.Entry{entry("app")}, stoodOn(map[string][]string{"app": {"elsewhere"}}))
if len(got) != 1 {
t.Fatalf("a dependency outside the set changed the set: %v", got)
}
}
// A module registered from its manifest and never built still names its bases there; once built,
// the recorded edge is what says so. Both are read, and a module never stands on itself.
func TestWhatStandsOnAModuleIsReadFromItsBuildOrItsManifest(t *testing.T) {
built := entry("gitea")
edges := stoodOn(map[string][]string{"gitea": {"mesh-tools"}})
if !standsOnModule(built, "mesh-tools", edges) {
t.Fatal("a recorded edge was not read")
}
if standsOnModule(built, "gitea", edges) || standsOnModule(built, "postgres", edges) {
t.Fatal("an edge was invented")
}
fresh := inventory.Entry{Manifest: catalogue.Manifest{Module: "plex", Build: &catalogue.Build{
On: []catalogue.BuildsOn{{Arg: "RUNTIME_BASE", Module: "mesh-tools", Artifact: "runtime"}},
}}}
if !standsOnModule(fresh, "mesh-tools", nil) {
t.Fatal("a manifest's own base was not read")
}
}
// A merge names a repository the way the forge does; a source is recorded the way a build was
// asked for. The two meet on owner/repo and branch, whichever form the record took.
func TestAMergeMatchesTheSourcesBuiltFromIt(t *testing.T) {
m := link.SourceMoved{Owner: "novox", Repo: "mesh-controller", Base: "main",
CloneURL: "http://forge.internal:20000/novox/mesh-controller.git"}
for _, s := range []inventory.Source{
{Repository: "http://forge.internal:20000/novox/mesh-controller.git", Ref: "main"},
{Repository: "novox/mesh-controller", Seat: "git", Ref: ""},
{Repository: "https://elsewhere.example/novox/mesh-controller", Ref: "main"},
} {
if !sourceIs(s, m) {
t.Errorf("%+v was not matched by the merge", s)
}
}
for _, s := range []inventory.Source{
{Repository: "novox/mesh-host", Seat: "git"},
{Repository: "http://forge.internal:20000/novox/mesh-controller.git", Ref: "release"},
} {
if sourceIs(s, m) {
t.Errorf("%+v was matched by a merge that is not its", s)
}
}
}
// A merge made before the source was last seen is history: it does not move the source, and a
// merge that says nothing about when it was made is taken as news.
func TestAMergeOlderThanTheLastLookIsHistory(t *testing.T) {
seen := time.Date(2026, 9, 28, 3, 0, 0, 0, time.UTC)
if !isHistory("2026-09-28T02:00:00Z", seen) {
t.Fatal("an older merge was taken as news")
}
if isHistory("2026-09-28T04:00:00Z", seen) {
t.Fatal("a newer merge was taken as history")
}
if isHistory("", seen) || isHistory("2026-09-28T02:00:00Z", time.Time{}) {
t.Fatal("a merge or a source with no time on it was refused")
}
}
// A module as the catalogue holds it: built from a repository, at a directory inside it.
func fromRepo(module, repository, path string) inventory.Entry {
return inventory.Entry{
Manifest: catalogue.Manifest{Module: module},
Source: inventory.Source{Repository: repository, Path: path, Ref: "main"},
}
}
// A merge rebuilds the modules whose own directories it changed, and everything when what it changed
// is shared. One repository holding many modules is the ordinary case here, and rebuilding all of
// them for a change to one is what exhausted a registry's pull limit the first night this ran.
func TestAMergeRebuildsTheModulesItChanged(t *testing.T) {
const repo = "http://forge.internal:20000/novox/mesh-catalog.git"
gitea := fromRepo("gitea", repo, "modules/gitea")
keycloak := fromRepo("keycloak", repo, "modules/keycloak")
known := []inventory.Entry{gitea, keycloak, fromRepo("plex", repo, "modules/plex")}
candidates := []inventory.Entry{gitea, keycloak}
merge := func(paths []string, truncated bool) link.SourceMoved {
return link.SourceMoved{Owner: "novox", Repo: "mesh-catalog", Base: "main",
Paths: paths, PathsTruncated: truncated}
}
named := func(entries []inventory.Entry) string {
var names []string
for _, e := range entries {
names = append(names, e.Manifest.Module)
}
return strings.Join(names, ",")
}
for _, c := range []struct {
what string
m link.SourceMoved
want string
}{
{"one module's own files", merge([]string{"modules/gitea/index.ts", "modules/gitea/client.ts"}, false), "gitea"},
{"two modules' files", merge([]string{"modules/gitea/index.ts", "modules/keycloak/module.json"}, false), "gitea,keycloak"},
{"a file they share", merge([]string{"tsconfig.json"}, false), "gitea,keycloak"},
{"a module the mesh does not hold", merge([]string{"modules/plex/index.ts"}, false), ""},
{"nothing said about the files", merge(nil, false), "gitea,keycloak"},
{"more files than were listed", merge([]string{"modules/gitea/index.ts"}, true), "gitea,keycloak"},
} {
if got := named(whatTheMergeTouched(candidates, known, c.m)); got != c.want {
t.Errorf("%s: rebuilt %q, wanted %q", c.what, got, c.want)
}
}
}
// A module whose recipe packages source from another repository is affected when that repository
// moves — the manifest the mesh keeps says nothing about it, so the record of what the build read is
// the only thing that can say so.
func TestAModuleIsAffectedByTheRepositoryItPackages(t *testing.T) {
m := link.SourceMoved{Owner: "novox", Repo: "mesh-controller", Base: "main",
CloneURL: "http://forge.internal:20000/novox/mesh-controller.git"}
for _, read := range [][]inventory.ReadRepository{
{{Repository: "http://forge.internal:20000/novox/mesh-controller.git", Ref: "main"}},
{{Repository: "novox/mesh-controller"}},
{{Repository: "https://elsewhere.example/novox/other"}, {Repository: "novox/mesh-controller.git", Ref: "main"}},
} {
if !readsFrom(read, m) {
t.Errorf("%+v was not matched by the merge", read)
}
}
for _, read := range [][]inventory.ReadRepository{
nil,
{{Repository: "novox/mesh-host", Ref: "main"}},
{{Repository: "novox/mesh-controller", Ref: "release"}},
} {
if readsFrom(read, m) {
t.Errorf("%+v was matched by a merge that is not its", read)
}
}
}
// What a module handed over by hand records about where it came from, and what is refused.
func TestWhatAHandedOverModuleRecordsAboutItsSource(t *testing.T) {
// The whole location: a repository on the mesh's own forge, the directory inside it, the branch
// and the commit the manifest was read at.
from, err := whereItComesFrom("novox/mesh-catalog", "main", "c0ffee", "modules/gitea", true)
if err != nil {
t.Fatal(err)
}
if from.Path != "modules/gitea" || from.Seat != "git" || from.Repository != "novox/mesh-catalog" {
t.Fatalf("the source records as %+v", from)
}
// A manifest with no provenance at all is legitimate: fixing something in a hurry.
if from, err := whereItComesFrom("", "", "", "", false); err != nil || from != (inventory.Source{}) {
t.Fatalf("a manifest handed over with no provenance was refused: %+v, %v", from, err)
}
for _, c := range []struct {
what string
repository, ref, commit, path string
self bool
}{
{what: "a source with no commit", repository: "novox/mesh-catalog", commit: ""},
{what: "a commit with no source", commit: "c0ffee"},
{what: "a directory inside nothing", path: "modules/gitea"},
{what: "a forge holding nothing", self: true},
{what: "an address given as a path on the forge", repository: "http://forge.internal:20000/novox/x.git", commit: "c0ffee", self: true},
} {
if _, err := whereItComesFrom(c.repository, c.ref, c.commit, c.path, c.self); err == nil {
t.Errorf("%s was recorded as a source", c.what)
}
}
}
+1 -6
View File
@@ -636,13 +636,8 @@ func renderingFor(ctx context.Context, open *stores, node string,
if err != nil {
return catalogue.Rendering{}, inventory.Node{}, err
}
memberships, err := inv.BusMemberships(ctx)
if err != nil {
return catalogue.Rendering{}, inventory.Node{}, err
}
return catalogue.Rendering{
BusMembership: memberships[node],
Settings: settings, Generators: gens, Grants: grants, Needed: needed, Ports: ports,
Settings: settings, Generators: gens, Grants: grants, Needed: needed, Ports: ports,
Certificate: certificate, Authority: authority, Mesh: private, Names: names,
Machines: machines,
Suffix: overlay.Suffix(), MeshRange: meshRange, Accounts: accounts, Foundation: foundation,
+31 -100
View File
@@ -38,27 +38,6 @@ func reportUnhostable(node string, plan catalogue.Resolution) {
// nothing in it was wrong, and no one edit was the one that should have been a new file.
// serve is the control plane running: one connection to the broker, one queue, one consumer.
// connectLink opens the controller's link over whichever bus this process is on (design 25: one
// variable moves it). The streams and this controller's consumers are raised first on the new bus,
// so nothing served here finds them missing.
func connectLink(ctx context.Context, inv *inventory.Inventory, enroller link.Enroller, listener link.Listener) (*link.Server, error) {
busAddress, err := broker.BusAddress()
if err != nil {
return nil, err
}
if inv != nil {
if err := raiseTheBus(ctx, inv, busAddress); err != nil {
return nil, err
}
}
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",
broker.BareAddress(busAddress), err)
}
return link.ConnectNats(js, enroller, listener), nil
}
func serve(ctx context.Context) error {
open, err := openStores(ctx)
if err != nil {
@@ -82,6 +61,11 @@ func serve(ctx context.Context) error {
}
fmt.Printf("signing as %s\n", key.Fingerprint()[:16])
management, err := broker.ManagementFromEnvironment()
if err != nil && !errors.Is(err, broker.ErrNotConfigured) {
return err
}
// Where the broker is and what to expect there, so a node can be told how to come back
// without a person and a new token.
known, err := broker.FromEnvironment()
@@ -96,10 +80,17 @@ func serve(ctx context.Context) error {
// **Which bus this mesh is on, read once** (novox/hq ADR 0116 step 5). Both clients ship; both
// being live is refused, because a mesh half on each is one where a declaration goes out on one
// and the report comes back on the other, and every component logs success while it happens.
busAddress, onNATS, err := broker.OnNATS()
if err != nil {
return err
}
if err := broker.MustBeOneBus(os.Getenv(broker.AMQPVarName), busAddress); err != nil {
return err
}
work := link.Enrolment{Inventory: inv, Identity: ident, Broker: known,
OnNATS: true}
server, err := connectLink(ctx, inv, work, work)
work := link.Enrolment{Inventory: inv, Identity: ident, Management: management, Broker: known,
OnNATS: onNATS}
server, err := link.Connect(work, work)
if err != nil {
return err
}
@@ -109,6 +100,11 @@ func serve(ctx context.Context) error {
// somebody deleted, a mesh raised from a restored backup, or a bus whose data directory was
// replaced all have records and no objects — and a node whose consumer is missing hears nothing
// while everything else about it looks correct.
if onNATS {
if err := raiseTheBus(ctx, inv, busAddress); err != nil {
return err
}
}
// And build results nobody was waiting for. A build triggered any other way than `build`
// would otherwise be reported into the void, which is the same as not reporting it.
server.Records(builds{inv})
@@ -162,13 +158,13 @@ func declare(ctx context.Context, args []string) error {
return err
}
server, err := connectLink(ctx, nil, nil, nil)
server, err := link.Connect(nil, nil)
if err != nil {
return err
}
defer server.Close()
if err := link.Declare(ctx, server.Bus(), ident, node, raw, 15*time.Second); err != nil {
if err := link.Declare(ctx, link.OverCurrent{Channel: server.Channel()}, ident, node, raw, 15*time.Second); err != nil {
return err
}
fmt.Printf("sent %s a signed declaration (%d bytes)\n", node, len(raw))
@@ -275,7 +271,7 @@ func pushCommand(ctx context.Context, args []string) error {
return err
}
server, err := connectLink(ctx, nil, nil, nil)
server, err := link.Connect(nil, nil)
if err != nil {
return err
}
@@ -336,7 +332,7 @@ func pushCommand(ctx context.Context, args []string) error {
if err != nil {
return err
}
if err := link.Declare(ctx, server.Bus(), ident, s.node, body, 15*time.Second); err != nil {
if err := link.Declare(ctx, link.OverCurrent{Channel: server.Channel()}, ident, s.node, body, 15*time.Second); err != nil {
return err
}
// After it is away, not before. A digest recorded for something that failed to send would
@@ -419,7 +415,7 @@ func pushCommand(ctx context.Context, args []string) error {
return declarationWith(held, open, node, plan, settings, gens, Allocating)
},
func(s readyNode, body []byte) error {
if err := link.Declare(ctx, server.Bus(), ident, s.node, body,
if err := link.Declare(ctx, link.OverCurrent{Channel: server.Channel()}, ident, s.node, body,
15*time.Second); err != nil {
return err
}
@@ -632,7 +628,7 @@ func sendTo(ctx context.Context, open *stores, names []string) error {
len(refusals), strings.Join(refusals, "\n\n"))
}
server, err := connectLink(ctx, nil, nil, nil)
server, err := link.Connect(nil, nil)
if err != nil {
return err
}
@@ -643,7 +639,7 @@ func sendTo(ctx context.Context, open *stores, names []string) error {
if err != nil {
return err
}
if err := link.Declare(ctx, server.Bus(), ident, s.node, body, 15*time.Second); err != nil {
if err := link.Declare(ctx, link.OverCurrent{Channel: server.Channel()}, ident, s.node, body, 15*time.Second); err != nil {
return err
}
record, err := inv.NodeByName(ctx, s.node)
@@ -708,7 +704,7 @@ 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",
broker.BareAddress(address), err)
address, err)
}
defer js.Close()
@@ -743,75 +739,10 @@ func raiseTheBus(ctx context.Context, inv *inventory.Inventory, address string)
// The work queues of the mesh's own roles (novox/hq ADR 0121). The queue before the holder,
// deliberately: work queues until somebody arrives to do it, so assigning a build machine a week
// after something started asking for builds flushes the backlog instead of having lost it.
// With the seats' holders, so each role's work queue gets the consumer its holder takes
// work from. Passed as nil until the first live raise, which left the build machine bound to a
// consumer nothing had created (2026-09-28).
holders, err := seatHolders(ctx, inv)
if err != nil {
if err := broker.RaiseSeats(js, inventory.MeshSeats(), nil); err != nil {
return err
}
if err := broker.RaiseSeats(js, inventory.MeshSeats(), holders); err != nil {
return err
}
// And how every module hears what it consumes. Derived from the same records the user list is
// composed from, so a module the mesh grants a consumer's subjects has that consumer waiting.
// Done on every raise, not only when a credential is issued: every module moved onto this bus
// by the rollout was issued on the old one, and came up with nothing to bind to (2026-09-28).
records, err := inv.BusRecords(ctx)
if err != nil {
return err
}
users, err := broker.Users(records)
if err != nil {
return err
}
hearing := 0
for _, p := range users {
consumer, needed := broker.ConsumerFor(p)
if !needed {
continue
}
if err := js.EnsureConsumer(consumer); err != nil {
return fmt.Errorf("how %s on %s hears what it consumes: %w", p.Module, p.Node, err)
}
hearing++
}
fmt.Printf("the bus at %s has its streams, %d machine(s) can hear a declaration, and %d module(s) "+
"can hear what they consume\n", broker.BareAddress(address), len(names), hearing)
fmt.Printf("the bus at %s has its streams, and %d machine(s) can hear a declaration\n",
address, len(names))
return nil
}
// seatHolders is who holds each of the mesh's seats, by seat name: the record where a handover
// wrote one, and the assigned module claiming the seat otherwise — the same derivation the
// resolver makes, read from the catalogue rather than re-resolved.
func seatHolders(ctx context.Context, inv *inventory.Inventory) (map[string]broker.Holder, error) {
out := map[string]broker.Holder{}
entries, err := inv.Catalogued(ctx)
if err != nil {
return nil, err
}
for _, e := range entries {
if len(e.On) == 0 {
continue
}
for _, c := range e.Manifest.Claims {
seat, known := catalogue.SeatNamed(c.Name)
if !known {
continue
}
if _, taken := out[seat.Name]; !taken {
out[seat.Name] = broker.Holder{Node: e.On[0], Module: e.Manifest.Module}
}
}
}
recorded, err := inv.Holdings(ctx)
if err != nil {
return nil, err
}
for _, h := range recorded {
if seat, known := catalogue.SeatNamed(h.Claim); known {
out[seat.Name] = broker.Holder{Node: h.Node, Module: h.Module}
}
}
return out, nil
}
+3 -266
View File
@@ -2,10 +2,8 @@ package main
import (
"context"
"encoding/json"
"errors"
"fmt"
"os"
"strings"
"time"
@@ -14,7 +12,6 @@ import (
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/secrets"
)
// Moving the mesh's own traffic to the bus being built (novox/hq ADR 0116 step 5).
@@ -34,21 +31,12 @@ import (
// ability to change things, not the services its modules are serving — measured on 2026-09-27, when
// a seat emptied mid-change and the control plane looped for two hours while every service stayed up.
const rolloutUsage = "rollout check | rollout mint [--again] | rollout hand <node> | rollout --confirm"
const rolloutUsage = "rollout check | rollout --confirm"
func rolloutCommand(ctx context.Context, args []string) error {
switch {
case len(args) == 1 && args[0] == "check":
return rolloutCheck(ctx)
case len(args) == 1 && args[0] == "mint":
return rolloutMint(ctx, false)
case len(args) == 2 && args[0] == "hand":
return rolloutHand(ctx, args[1])
case len(args) == 2 && args[0] == "mint" && args[1] == "--again":
// Every credential minted afresh, whether or not one exists — for a mint that was wrong
// before anything was pushed. Afterwards nothing that received the old one still works,
// which is fine exactly when nothing received it.
return rolloutMint(ctx, true)
case len(args) == 1 && args[0] == "--confirm":
return errors.New(
"the rollout itself is not built yet: `rollout check` answers whether it could run, and " +
@@ -127,13 +115,9 @@ func readinessOf(ctx context.Context, inv *inventory.Inventory) (broker.Readines
if address != "" {
// One dial, briefly. "Is it answering" is the one fact records cannot hold, and a mesh about
// to move onto a server that is not there should hear it here rather than afterwards.
//
// **Dialled the way the mesh dials it** — credential and pin — because a bare connect to a
// bus that requires TLS and a user fails at the handshake, and the check then reported a
// standing server as absent (seen live, 2026-09-28).
if js, err := broker.Dial(address, nats.Timeout(5*time.Second)); err == nil {
if conn, err := nats.Connect(broker.BareAddress(address), nats.Timeout(5*time.Second)); err == nil {
state.ServerStanding = true
js.Close()
conn.Close()
}
}
@@ -206,250 +190,3 @@ func wasSentTheUserList(ctx context.Context, inv *inventory.Inventory, node stri
// notReadyOf is the readiness reasoning, named here so a test can reach it without the command's
// printing. The reasoning itself is the broker package's, where it is pure.
func notReadyOf(state broker.Readiness) []string { return broker.NotReady(state) }
// rolloutMint gives every principal the new bus will have a credential it does not yet have, and
// puts each where its owner reads it (novox/hq design 28, task 5.2): a machine's as a membership
// sealed into its declaration, a module's as its broker secret, the control plane's own as its
// `bus` secret. Idempotent: what already has a hash is left alone, so running it again is harmless.
//
// **Before anything moves, and it is what makes moving possible.** A machine moved without a
// credential cannot come back, and afterwards there is no bus to tell it anything over — which is
// why `rollout check` refuses until this has run. The bus's address is worked out here, from where
// the module that provides it is assigned, rather than read from this process's environment: this
// process is still on the old bus when this runs, and must be.
func rolloutMint(ctx context.Context, again bool) error {
open, err := openStores(ctx)
if err != nil {
return err
}
defer open.Close()
inv := open.inventory
known, err := broker.FromEnvironment()
if err != nil {
return fmt.Errorf("the bus's certificate is not known to this process, and every membership "+
"must carry its fingerprint: %w", err)
}
shelf, err := inv.Catalogue(ctx)
if err != nil {
return err
}
entries, err := inv.Catalogued(ctx)
if err != nil {
return err
}
var busNode, controllerNode string
for _, e := range entries {
switch {
case e.Manifest.ClaimsSeat("mesh-broker") && providesBus(e.Manifest) && len(e.On) > 0:
busNode = e.On[0]
case e.Manifest.Module == "mesh-controller" && len(e.On) > 0:
controllerNode = e.On[0]
}
}
if busNode == "" {
return errors.New("no assigned module provides mesh-bus and claims mesh-broker, so there is no " +
"bus to mint credentials for — register and assign it first")
}
onNetwork, err := whereEveryoneIs(ctx, inv, shelf)
if err != nil {
return err
}
busHost := onNetwork[busNode]
if busHost == "" {
// **The hub is not in that map.** The machine that took over the tunnel is where the current
// bus already answers, and every machine dials it at the address the mesh handed them — so
// when the new bus runs on the same machine, that address is the one to tell them, with the
// new port. Found live: the control node is the hub, and the map lists the machines placed
// around it.
// The host alone: no scheme (BareAddress adds one where none was, which is the wrong
// direction here — every URL built below adds its own) and no port.
_, _, host := broker.CredentialIn(known.Address)
if host == "" {
host = known.Address
}
if _, after, hasScheme := strings.Cut(host, "://"); hasScheme {
host = after
}
host = strings.TrimSpace(host)
if i := strings.LastIndex(host, ":"); i > 0 && !strings.Contains(host[i:], "]") {
host = host[:i]
}
if host == "" {
return fmt.Errorf("%s runs the new bus and has no address on the private network, and the "+
"current bus's address is unknown too, so no machine could be told where it is", busNode)
}
busHost = host
}
busAddress := busHost + ":4222"
records, err := inv.BusRecords(ctx)
if err != nil {
return err
}
users, err := broker.Users(records)
if err != nil {
return err
}
kept, err := inv.BusUsers(ctx)
if err != nil {
return err
}
hashes := make(map[string]string, len(kept))
for name, u := range kept {
hashes[name] = u.PasswordHash
}
_, missing := broker.WithPasswords(users, hashes)
wanted := map[string]bool{}
for _, m := range missing {
wanted[m] = true
}
var machines, modules, skipped int
for _, p := range users {
if !again && !wanted[p.Username()] {
continue
}
switch p.Kind {
case broker.KindController:
if controllerNode == "" {
return errors.New("the control plane is not assigned anywhere, so its credential has nowhere to go")
}
password, err := inv.MintBusPassword(ctx, inventory.BusUser{Username: p.Username(), Kind: inventory.BusController})
if err != nil {
return err
}
url := "nats://" + p.Username() + ":" + password + "@" + busAddress
if err := inv.AcceptSecretForModule(ctx, controllerNode, "mesh-controller", "bus", url); err != nil {
return fmt.Errorf("the control plane's credential is minted and could not be sealed to %s: %w", controllerNode, err)
}
fmt.Printf("control plane: credential minted, sealed to %s as its `bus` secret\n", controllerNode)
case broker.KindNode:
password, err := inv.MintBusPassword(ctx, inventory.BusUser{Username: p.Username(), Kind: inventory.BusNode, Node: p.Node})
if err != nil {
return err
}
membership, _ := json.Marshal(map[string]string{
"broker": busAddress, "fingerprint": known.Fingerprint, "password": password, "transport": "nats",
})
key, err := inv.SealingKeyOf(ctx, p.Node)
if err != nil {
return fmt.Errorf("%s has no sealing key, so its membership cannot be sealed to it: %w", p.Node, err)
}
sealed, err := secrets.Seal(key, membership)
if err != nil {
return err
}
if err := inv.PutBusMembership(ctx, p.Node, sealed); err != nil {
return err
}
machines++
case broker.KindModule:
if p.Module == "mesh-controller" {
// The control plane is a module too, and its `broker` secret is the old bus's
// credential it is still using while this runs. Writing the new bus's blob there
// cut the mesh off from its own old bus mid-move (2026-09-28). Its new-bus credential
// is the controller principal's `bus` secret above; nothing else is needed here.
skipped++
continue
}
m, inShelf := shelf[p.Module]
if !inShelf {
skipped++
continue
}
if _, reads := m.OwnSecrets["broker"]; !reads {
fmt.Printf(" %s on %s speaks on the bus but declares no `broker` secret to receive a credential in; skipped\n", p.Module, p.Node)
skipped++
continue
}
password, err := inv.MintBusPassword(ctx, inventory.BusUser{Username: p.Username(), Kind: inventory.BusModule, Node: p.Node, Module: p.Module})
if err != nil {
return err
}
if err := issueWith(ctx, inv, m, p.Node, "", known, busAddress, p.Username(), password); err != nil {
return err
}
modules++
default:
skipped++
}
}
fmt.Printf("minted for %d machine(s) and %d module runtime(s); %d skipped; the bus is at %s\n",
machines, modules, skipped, busAddress)
fmt.Println(" each machine's membership and each module's credential arrive with the next push of its machine;")
fmt.Println(" push the machine running the bus first, so the bus stands with its user list before anything dials it")
return nil
}
// providesBus is whether a manifest provides the mesh's bus.
func providesBus(m catalogue.Manifest) bool {
for _, o := range m.Provides {
if o.Name == "mesh-bus" {
return true
}
}
return false
}
// rolloutHand mints a machine its credential for the new bus afresh and prints its membership
// once, for an operator to carry by hand — the rescue for a machine that cannot be reached over
// any bus: rotated while it still held the old password, or reachable only by ssh. The plaintext
// exists on this terminal and then only where it is written; the store keeps the hash, and the
// sealed copy in the machine's declaration is replaced too, so the next push says the same.
func rolloutHand(ctx context.Context, node string) error {
open, err := openStores(ctx)
if err != nil {
return err
}
defer open.Close()
inv := open.inventory
known, err := broker.FromEnvironment()
if err != nil {
return fmt.Errorf("the bus's certificate is not known to this process: %w", err)
}
busAddress, _, err := broker.OnNATS()
if err != nil {
return err
}
if busAddress == "" {
return errors.New("this control plane is not on the new bus, so there is no membership to hand out")
}
_, _, bare := broker.CredentialIn(busAddress)
if _, after, has := strings.Cut(bare, "://"); has {
bare = after
}
if _, err := inv.NodeByName(ctx, node); err != nil {
return err
}
p := broker.Principal{Kind: broker.KindNode, Node: node}
password, err := inv.MintBusPassword(ctx, inventory.BusUser{Username: p.Username(), Kind: inventory.BusNode, Node: node})
if err != nil {
return err
}
membership, _ := json.Marshal(map[string]string{
"broker": bare, "fingerprint": known.Fingerprint, "password": password, "transport": "nats",
})
key, err := inv.SealingKeyOf(ctx, node)
if err != nil {
return err
}
sealed, err := secrets.Seal(key, membership)
if err != nil {
return err
}
if err := inv.PutBusMembership(ctx, node, sealed); err != nil {
return err
}
// The one line of output is the membership itself, so it can be piped to the machine without
// being read on the way. Everything else goes to stderr.
fmt.Fprintf(os.Stderr, "%s's credential is minted afresh. Write this to %s on it and restart its host; "+
"then push the machine running the bus so the user list carries the new hash.\n",
node, catalogue.BusMembershipPath)
fmt.Println(string(membership))
return nil
}
-304
View File
@@ -6,9 +6,7 @@ import (
"flag"
"fmt"
"strings"
"time"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
)
@@ -220,305 +218,3 @@ func notNow(err error) error {
}
return err
}
// SourceMoved is the forge announcing a merge: every module recorded as built from that
// repository and branch is marked as moved to the merge commit, and built — bases first, so a
// module that stands on another's artifact is built after it and not against the old one
// (novox/hq 04-ISSUES/131). Nothing is pushed here: what a finished build does to the machines
// running the module is the upgrade's decision, taken when the catalogue announces it.
func (f following) SourceMoved(ctx context.Context, m link.SourceMoved) error {
inv := f.open.inventory
entries, err := inv.Catalogued(ctx)
if err != nil {
return notNow(err)
}
read, err := inv.ReadRepositories(ctx)
if err != nil {
return notNow(err)
}
// Two kinds of module are affected by one merge, and they are affected differently.
//
// A module **built from** this repository and branch has moved: the mesh records the new commit
// as what its source now has, and only what the merge actually changed is rebuilt. A module that
// only **packages source from** it has not moved — its own source is somewhere else, at the
// commit it already records — so it is rebuilt and its record left alone. Writing this commit as
// its source would make it permanently behind a repository its manifest does not come from.
var from, packaging []inventory.Entry
already := 0
for _, e := range entries {
switch {
case sourceIs(e.Source, m):
if e.Source.BuiltFrom == m.Commit {
already++
continue
}
// **A merge older than the last look at the source is history, not a move.** The forge
// announces what it finds merged, and an old merge surfacing late would otherwise move
// the recorded head backwards and rebuild everything built from that repository, once
// per old merge (2026-09-28).
if isHistory(m.MergedAt, e.Source.Seen) {
continue
}
from = append(from, e)
case readsFrom(read[e.Manifest.Module], m):
packaging = append(packaging, e)
}
}
if len(from) == 0 && len(packaging) == 0 {
// "Already built from it" and "nothing reads it" are different facts, and reading the first
// as the second sends somebody looking for a broken trigger when the mesh is up to date.
if already > 0 {
fmt.Printf("%s/%s merged into %s (%.8s); %d module(s) the mesh holds are already built "+
"from it\n", m.Owner, m.Repo, m.Base, m.Commit, already)
return nil
}
fmt.Printf("%s/%s merged into %s (%.8s); nothing the mesh holds reads it\n",
m.Owner, m.Repo, m.Base, m.Commit)
return nil
}
// The same judgement for the packaging kind, against the newest look at that repository by
// anything built from it: they keep no record of it themselves, and a replayed old merge should
// not rebuild them either.
if isHistory(m.MergedAt, lastLookAt(entries, m)) {
packaging = nil
}
touched := whatTheMergeTouched(from, entries, m)
for _, e := range touched {
if err := inv.SourceMoved(ctx, e.Manifest.Module, m.Commit); err != nil {
return notNow(err)
}
}
moved := append(append([]inventory.Entry{}, touched...), packaging...)
if len(moved) == 0 {
fmt.Printf("%s/%s merged into %s (%.8s); it changed nothing any module the mesh holds is "+
"built from\n", m.Owner, m.Repo, m.Base, m.Commit)
return nil
}
against, err := inv.BuiltAgainst(ctx)
if err != nil {
return notNow(err)
}
ordered := orderByBases(moved, against)
names := make([]string, 0, len(ordered))
for _, e := range ordered {
names = append(names, e.Manifest.Module)
}
fmt.Printf("%s/%s merged into %s (%.8s); building %s\n",
m.Owner, m.Repo, m.Base, m.Commit, strings.Join(names, ", "))
if len(packaging) > 0 {
var also []string
for _, e := range packaging {
also = append(also, e.Manifest.Module)
}
fmt.Printf(" %s package source from it, so they are rebuilt and their own source record "+
"is left where it is\n", strings.Join(also, ", "))
}
var failed []string
for _, e := range ordered {
source := buildSource{Repository: e.Source.Repository, Seat: e.Source.Seat}
if err := buildOne(ctx, source, e.Source.Path, e.Source.Ref, 20*time.Minute); err != nil {
fmt.Printf(" %s: %v\n", e.Manifest.Module, err)
failed = append(failed, e.Manifest.Module)
// A base that failed is a reason to stop: what stands on it would be built against
// the old one, and report success (novox/hq 04-ISSUES/131).
if standsOn(ordered, e.Manifest.Module, against) {
fmt.Printf(" stopping: %s is a base of what was still to build\n", e.Manifest.Module)
break
}
}
}
if len(failed) > 0 {
fmt.Printf("%d of %d not built: %s\n", len(failed), len(ordered), strings.Join(failed, ", "))
}
return nil
}
// sourceIs is whether a recorded source is the repository and branch a merge announced. A source on
// the git seat is recorded as its path on the forge; one elsewhere as the URL it was cloned from.
// An empty recorded ref is the repository's default branch, which is what a merge into the base
// branch of the forge's default means.
func sourceIs(s inventory.Source, m link.SourceMoved) bool {
if !sameRepository(s.Repository, m) {
return false
}
return s.Ref == "" || s.Ref == m.Base
}
// sameRepository is whether a recorded repository is the one a merge names, in either spelling it
// may have been recorded in: a path on the git seat, or the URL it was cloned from.
func sameRepository(repository string, m link.SourceMoved) bool {
want := strings.ToLower(m.Owner + "/" + m.Repo)
repo := strings.ToLower(strings.TrimSuffix(repository, ".git"))
return repo == want || strings.HasSuffix(repo, "/"+want) ||
(m.CloneURL != "" && repo == strings.ToLower(strings.TrimSuffix(m.CloneURL, ".git")))
}
// readsFrom is whether a module's build read the repository a merge names: the second repository its
// recipe packages source from. Its ref must be the branch that moved, or unset — the same rule a
// module's own source follows.
func readsFrom(read []inventory.ReadRepository, m link.SourceMoved) bool {
for _, r := range read {
if sameRepository(r.Repository, m) && (r.Ref == "" || r.Ref == m.Base) {
return true
}
}
return false
}
// lastLookAt is the most recent look at this repository by anything built from it.
func lastLookAt(entries []inventory.Entry, m link.SourceMoved) time.Time {
var newest time.Time
for _, e := range entries {
if sameRepository(e.Source.Repository, m) && e.Source.Seen.After(newest) {
newest = e.Source.Seen
}
}
return newest
}
// whatTheMergeTouched narrows the modules built from a repository to the ones the merge changed.
//
// **A change inside no module's own directory is a change to what they share.** The forge lists the
// files a merge changed; a module is affected when one of them is inside its own directory, when it
// is built from the repository's root — everything there is its source — or when some changed file
// belongs to no module's directory at all, which is how a shared file, a build recipe or a
// dependency at the root rebuilds everything built from that repository.
//
// A change inside *another* module's directory is that module's business and not this one's, even
// when the mesh does not hold that module: `known` is every module this repository is known to hold,
// whatever branch it was registered from. That is also the limit of this — a repository whose shared
// code sits inside a directory the mesh has never seen a module in reads as shared, and everything
// is rebuilt. Rebuilding too much is the safe direction: the fault this whole path exists for is a
// mesh that believes it is current and is not (novox/hq 04-ISSUES/131).
func whatTheMergeTouched(candidates, known []inventory.Entry, m link.SourceMoved) []inventory.Entry {
// Nothing said about the files, or not all of them said: everything built from it is affected.
if len(m.Paths) == 0 || m.PathsTruncated {
return candidates
}
var dirs []string
for _, e := range known {
if e.Source.Path != "" && sameRepository(e.Source.Repository, m) {
dirs = append(dirs, e.Source.Path)
}
}
for _, p := range m.Paths {
if !insideAny(p, dirs) {
return candidates
}
}
var out []inventory.Entry
for _, e := range candidates {
if e.Source.Path == "" || anyInside(m.Paths, e.Source.Path) {
out = append(out, e)
}
}
return out
}
// inside is whether a changed file is in a directory: that directory itself, or under it.
func inside(path, dir string) bool {
dir = strings.Trim(dir, "/")
path = strings.TrimPrefix(path, "/")
return path == dir || strings.HasPrefix(path, dir+"/")
}
// insideAny is whether a changed file is in any of these directories.
func insideAny(path string, dirs []string) bool {
for _, dir := range dirs {
if inside(path, dir) {
return true
}
}
return false
}
// anyInside is whether any of these changed files is in a directory.
func anyInside(paths []string, dir string) bool {
for _, p := range paths {
if inside(p, dir) {
return true
}
}
return false
}
// orderByBases is the entries with every base before what stands on it: a module whose build stood
// on another's artifact comes after that module. Entries outside the set are not waited for — they
// are not being rebuilt. Stable for what has no order between it.
//
// `against` is what each module's newest build stood on (inventory.BuiltAgainst): the edges are
// derived from builds, not declared, because a recorded manifest no longer carries `build.on`.
func orderByBases(entries []inventory.Entry, against map[string][]string) []inventory.Entry {
inSet := map[string]bool{}
for _, e := range entries {
inSet[e.Manifest.Module] = true
}
var out []inventory.Entry
placed := map[string]bool{}
var place func(e inventory.Entry, seen map[string]bool)
place = func(e inventory.Entry, seen map[string]bool) {
name := e.Manifest.Module
if placed[name] || seen[name] {
return
}
seen[name] = true
for _, base := range entries {
if base.Manifest.Module != name && inSet[base.Manifest.Module] && standsOnModule(e, base.Manifest.Module, against) {
place(base, seen)
}
}
placed[name] = true
out = append(out, e)
}
for _, e := range entries {
place(e, map[string]bool{})
}
return out
}
// standsOn is whether anything in the set is built on the named module's artifacts.
func standsOn(entries []inventory.Entry, module string, against map[string][]string) bool {
for _, e := range entries {
if standsOnModule(e, module, against) {
return true
}
}
return false
}
// standsOnModule is whether an entry's build stood on the named module: by what its newest build
// recorded it was handed (`artifact-store://<module>/<artifact>@…`, the module's own artifact), or
// — for a module registered from a manifest and not yet built — by the base its manifest names.
func standsOnModule(e inventory.Entry, module string, against map[string][]string) bool {
if e.Manifest.Module == module {
return false
}
if e.Manifest.Build != nil {
for _, on := range e.Manifest.Build.On {
if on.Module == module {
return true
}
}
}
prefix := catalogue.ArtifactStoreScheme + module + "/"
for _, ref := range against[e.Manifest.Module] {
if strings.HasPrefix(ref, prefix) {
return true
}
}
return false
}
// isHistory is whether a merge made at mergedAt predates the last time the source was seen. A merge
// with no time on it is taken as news: refusing it would silence a forge that says less.
func isHistory(mergedAt string, seen time.Time) bool {
if mergedAt == "" || seen.IsZero() {
return false
}
at, err := time.Parse(time.RFC3339, mergedAt)
if err != nil {
return false
}
return at.Before(seen)
}
+2 -1
View File
@@ -4,7 +4,7 @@ go 1.26.0
require (
github.com/jackc/pgx/v5 v5.10.0
github.com/nats-io/nats.go v1.54.0
github.com/rabbitmq/amqp091-go v1.14.0
golang.org/x/crypto v0.57.0
)
@@ -13,6 +13,7 @@ require (
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
github.com/jackc/puddle/v2 v2.2.2 // indirect
github.com/klauspost/compress v1.20.0 // indirect
github.com/nats-io/nats.go v1.54.0 // indirect
github.com/nats-io/nkeys v0.4.16 // indirect
github.com/nats-io/nuid v1.0.1 // indirect
golang.org/x/net v0.58.0 // indirect
+4
View File
@@ -19,11 +19,15 @@ github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OSON2c=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/rabbitmq/amqp091-go v1.14.0 h1:RSaT7aOKt/OrkVUyswPDW29lnRz9psuGmfZFBmLqLek=
github.com/rabbitmq/amqp091-go v1.14.0/go.mod h1:Hy4jKW5kQART1u+JkDTF9YYOQUHXqMuhrgxOEeS7G4o=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
golang.org/x/crypto v0.57.0 h1:3ZVCjf8Ggz7zneR/EHRVx68Ctf+2pmIMP2UFhh9cC6M=
golang.org/x/crypto v0.57.0/go.mod h1:Fdz0i5U6CoizGwLda9DttjSk6qlZo25zYNtR+ycvuZA=
golang.org/x/net v0.58.0 h1:ynWG7rqYi4ccpTEuPZ2QGWHktVEM9DMCj9yzDE0Q7To=
+67
View File
@@ -0,0 +1,67 @@
package broker_test
import (
"regexp"
"testing"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/link"
)
// The names are written twice, so a test keeps them agreeing.
//
// `link` imports `broker`, so `broker` cannot import `link` — the queue and exchange names
// therefore exist in both. A scoped account naming a queue nothing publishes to produces a
// builder that takes no work and says nothing about why, which is the worst kind of silence.
//
// An external test package, because it may import both without either importing the other.
func TestTheNamesTheBrokerScopesAreTheNamesTheLinkUses(t *testing.T) {
for _, agreed := range []struct {
what string
scoped string
actually string
}{
{"the build queue", broker.BuildQueueName, link.BuildQueue},
{"the exchange", broker.ExchangeName, link.Exchange},
{"a node's queue", broker.QueueFor("somewhere"), link.QueueFor("somewhere")},
} {
if agreed.scoped != agreed.actually {
t.Errorf("%s: the broker scopes %q and the link uses %q",
agreed.what, agreed.scoped, agreed.actually)
}
}
}
func TestABuilderMayWriteToAReplyQueueAndReadNoNodesDeclarations(t *testing.T) {
// The scoping, checked as patterns rather than by connecting: what it may write must include
// the queue an asker actually waits on, and what it may read must not include any node's.
//
// This exists because the first version scoped writes to `amq.gen-*` — the name one broker
// happens to generate — and the builder built, could not answer, and the connection simply
// closed saying only "not allowed to publish to exchange \'\'". Answering through the
// exchange is what removed the need for any of that.
write := regexp.MustCompile("^" + regexp.QuoteMeta(broker.ExchangeName) + "$")
if !write.MatchString(broker.ExchangeName) {
t.Error("a builder may not write to the exchange, so it can take work and never answer")
}
// And not the default exchange, where permission is per exchange rather than per queue — a
// builder allowed to use it could publish into any node's queue.
//
// Confirmed against a real broker as well, and worth recording how that nearly went wrong:
// an unconfirmed publish is asynchronous, so a refusal arrives as a channel close afterwards
// and a naive check reports success. With publisher confirms the broker's refusal is
// immediate. **A negative security assertion made against an asynchronous call is not an
// assertion.**
if write.MatchString("") {
t.Error("a builder may publish to the default exchange, and so into any node's queue")
}
read := regexp.MustCompile("^" + regexp.QuoteMeta(broker.BuildQueueName) + "$")
if !read.MatchString(broker.BuildQueueName) {
t.Error("a builder may not read the build queue")
}
if read.MatchString(link.QueueFor("someone-else")) {
// A build machine is not a node, and a node's queue carries its declarations.
t.Error("a builder may read another machine's declarations")
}
}
-13
View File
@@ -66,19 +66,6 @@ func FromEnvironment() (Broker, error) {
if err != nil {
return Broker{}, err
}
// **One bus, one address** (novox/hq ADR 0131). Everything the mesh hands out — a token, a
// machine's membership, a person's credential — must name the bus the control plane itself is
// connected to; the setting above predates the move and, on a mesh that has moved, still names
// the broker it moved from. The first person issued after the move was handed the retired
// broker's port and could not connect to anything (2026-09-28).
//
// Read from the credential rather than from a second setting somebody keeps in step: the
// control plane cannot be wrong about where it is connected.
if bus, on, err := OnNATS(); err == nil && on {
if where := strings.TrimPrefix(BareAddress(bus), "nats://"); where != "" {
address = where
}
}
return Broker{Address: address, Fingerprint: fingerprint}, nil
}
+13
View File
@@ -194,3 +194,16 @@ func TestTheAddressPortFollowsThePortTwin(t *testing.T) {
t.Fatalf("the address is %q; the node put the bus on 5679", b.Address)
}
}
func TestTheManagementPortFollowsThePortTwin(t *testing.T) {
t.Setenv(ManagementVar, "http://guest:guest@127.0.0.1:15672")
t.Setenv(ManagementVar+"_FILE", "")
t.Setenv(ManagementVar+"_PORT", "15673")
m, err := ManagementFromEnvironment()
if err != nil {
t.Fatal(err)
}
if m.base.Host != "127.0.0.1:15673" {
t.Fatalf("the management API is at %q; the node put it on 15673", m.base.Host)
}
}
+4 -67
View File
@@ -1,14 +1,8 @@
package broker
import (
"crypto/sha256"
"crypto/tls"
"crypto/x509"
"encoding/hex"
"errors"
"fmt"
"os"
"strings"
"time"
"github.com/nats-io/nats.go"
@@ -30,78 +24,21 @@ 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", where, err)
return nil, fmt.Errorf("connecting to the bus at %s: %w", url, err)
}
js, err := conn.JetStream()
if err != nil {
conn.Close()
return nil, fmt.Errorf("the bus at %s has no JetStream: %w", where, err)
return nil, fmt.Errorf("the bus at %s has no JetStream: %w", url, 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 PinnedToFingerprint(want), nil
}
// DialPinned is Dial with the server's certificate pinned by a fingerprint the caller already holds
// — a module or a build machine that was handed one beside its credential, and has no file.
func DialPinned(url, fingerprint string, opts ...nats.Option) (*JetStream, error) {
if strings.TrimSpace(fingerprint) != "" {
opts = append(opts, nats.Secure(PinnedToFingerprint(fingerprint)))
}
return Dial(url, opts...)
}
// PinnedToFingerprint accepts exactly the certificate with this SHA-256 and no other.
func PinnedToFingerprint(want string) *tls.Config {
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
},
}
}
// 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).
+366
View File
@@ -0,0 +1,366 @@
package broker
import (
"bytes"
"context"
"encoding/json"
"fmt"
"github.com/novox/mesh-controller/internal/envfile"
"io"
"net/http"
"net/url"
"regexp"
"strings"
"time"
)
// The mesh runs the broker, so there is no chicken-and-egg in a node needing an account before it
// can connect: the account is created when the token is issued, and the one-time secret in that
// token IS the password. A node's first connection is already authenticated, and enrolment is
// what happens over it.
//
// novox/hq ADR 0004's *a node holds its own identity and nothing else* is why the account is per
// node rather than shared. A shared enrolment account would let any node consume another's queue,
// which is the shared-credential fault that record exists to remove, reappearing at the transport.
// ManagementVar holds the broker's management API, credentials included.
const ManagementVar = "MESH_BROKER_MANAGEMENT"
// safeName is what a node may be called at the broker.
//
// The name goes into a URL path and into permission patterns, which are regular expressions. A
// name carrying a `.` or a `*` would silently widen what that node may reach — so it is
// constrained here rather than escaped later, because an escape that is forgotten once is a node
// reading everybody's queues.
var safeName = regexp.MustCompile(`^[a-z0-9][a-z0-9-]{0,62}$`)
// Management is the broker's administrative interface.
type Management struct {
base *url.URL
client *http.Client
}
// ManagementFromEnvironment reads where the management API is, if it is configured.
//
// On the port MESH_BROKER_MANAGEMENT_PORT names when the node moved it (novox/hq 04-ISSUES/102);
// the URL's own port otherwise.
func ManagementFromEnvironment() (*Management, error) {
raw, err := envfile.Placed(ManagementVar)
if err != nil {
return nil, err
}
if raw == "" {
return nil, ErrNotConfigured
}
base, err := url.Parse(raw)
if err != nil || base.Host == "" {
// The value carries a password, so it is not quoted back.
return nil, fmt.Errorf("%s is not a usable URL", ManagementVar)
}
return &Management{base: base, client: &http.Client{Timeout: 15 * time.Second}}, nil
}
// QueueFor is the queue a node consumes from. One per node, named after it.
func QueueFor(node string) string { return "node." + node }
// ExchangeName is where nodes publish what they have to say. One exchange, and the control plane
// is the only consumer behind it (novox/hq ADR 0006 — one consumer, so two cannot silently split
// the traffic between them).
const ExchangeName = "mesh"
// BuildQueueName is where build work waits. Duplicated from `link` rather than imported, for the
// same reason QueueFor above is: this package must not depend on the one that uses it, and a
// constant that differed would be caught by the test that asserts they agree.
const BuildQueueName = "builds"
// The events bus (novox/hq ADR 0042): one topic exchange every event rides, a second for tool
// RPC kept apart, and a dead-letter home for a poison event. The foundation owns these — a module's
// account cannot declare them, only bind its own queue to the events one.
const (
EventsExchangeName = "mesh.events"
RPCExchangeName = "mesh.rpc"
DeadExchangeName = "mesh.events.dead"
)
// ModuleQueueFor is the durable queue a module consumes its events from — one per module per node
// (novox/hq ADR 0042), named so the account that may read it is exactly this module's.
func ModuleQueueFor(node, module string) string { return node + "." + module + ".events" }
// modulePermissions is a module's authority on the bus, derived from its manifest (novox/hq
// ADR 0043): what it consumes and what it emits, and nothing else. Pure, so the scope is tested as
// patterns without a broker — the way a builder's is.
//
// A note on the limit: the broker's write permission is per exchange, not per routing key (LavinMQ
// has no topic permissions), so an emitting module is granted the events exchange whole. ADR 0042's
// origin reservation — a module publishes only under `module.<self>.*` — is stamped by the sdk, not
// enforced here; that gap is the broker's, and is recorded rather than hidden. A pure consumer like
// the audit logger is unaffected: it is granted no write to the exchange at all.
func modulePermissions(node, module string, emits, consumes []string) (configure, write, read string) {
queue := regexp.QuoteMeta(ModuleQueueFor(node, module))
events := regexp.QuoteMeta(EventsExchangeName)
rpc := regexp.QuoteMeta(RPCExchangeName)
// A module serves each of its tools on its own queue, namespaced by the module (novox/hq
// ADR 0047) — serve.<module>.<tool> — so the account may declare, bind and read exactly its own,
// and no other module's.
serve := "serve\\." + regexp.QuoteMeta(module) + "\\..*"
// Declare its own events queue and its own tool serve queues.
configure = "^(" + queue + "|" + serve + ")$"
// Write to bind its queue and serve queues (binding is a write on the queue), and to the RPC
// exchange to publish replies (ADR 0047: replies ride mesh.rpc, never the default exchange, which
// would let it publish into any queue). To the events exchange only if it emits.
writes := []string{queue, serve, rpc}
if len(emits) > 0 {
writes = append(writes, events)
}
write = "^(" + strings.Join(writes, "|") + ")$"
// Read its own queue and serve queues to consume them, and the RPC exchange to bind its serve
// queues onto. The events exchange to bind onto only if it consumes.
reads := []string{queue, serve, rpc}
if len(consumes) > 0 {
reads = append(reads, events)
}
read = "^(" + strings.Join(reads, "|") + ")$"
return configure, write, read
}
// CreateModuleAccount gives an assigned module its own broker account, scoped by what it emits and
// consumes (novox/hq ADR 0043). The account name carries the node so the same module on two machines
// holds two accounts, each sealed to its own; the permissions carry the module so one module cannot
// read another's queue. Generic — the builder is one instance of this rule, not a separate kind.
func (m *Management) CreateModuleAccount(ctx context.Context, node, module, password string, emits, consumes []string) (string, error) {
if !safeName.MatchString(node) {
return "", fmt.Errorf("%q cannot be part of a broker account: it is a permission pattern", node)
}
if !safeName.MatchString(module) {
return "", fmt.Errorf("%q cannot be part of a broker account: it is a permission pattern", module)
}
account := node + "-" + module
if !safeName.MatchString(account) {
return "", fmt.Errorf("%q is not a usable broker account name", account)
}
if err := m.put(ctx, "/api/users/"+url.PathEscape(account),
map[string]string{"password": password, "tags": ""}); err != nil {
return "", fmt.Errorf("cannot create the broker account for %s on %s: %w", module, node, err)
}
configure, write, read := modulePermissions(node, module, emits, consumes)
if err := m.put(ctx, "/api/permissions/%2f/"+url.PathEscape(account), map[string]string{
"configure": configure, "write": write, "read": read,
}); err != nil {
return "", fmt.Errorf("cannot scope the broker account for %s on %s: %w", module, node, err)
}
return account, nil
}
// EnsureModuleQueue declares a consuming module's queue with its dead-letter exchange, idempotently.
// The foundation declares it because a scoped module account may not: the broker refuses a queue with
// a dead-letter exchange to a non-administrator (novox/hq ADR 0043), so a consumer passively checks
// the queue the mesh made rather than declaring its own.
func (m *Management) EnsureModuleQueue(ctx context.Context, node, module string) error {
queue := ModuleQueueFor(node, module)
if err := m.put(ctx, "/api/queues/%2f/"+url.PathEscape(queue), map[string]any{
"durable": true,
"arguments": map[string]any{"x-dead-letter-exchange": DeadExchangeName},
}); err != nil {
return fmt.Errorf("cannot declare the queue for %s on %s: %w", module, node, err)
}
return nil
}
// EnsureEventExchanges declares the bus's exchanges and the dead-letter home, idempotently. The
// foundation owns them (a module's account may not declare an exchange), and a dead-letter exchange
// with no queue behind it drops what it receives — so a durable queue bound to `#` retains a poison
// event for inspection, which is the whole reason the trail exists.
func (m *Management) EnsureEventExchanges(ctx context.Context) error {
for _, exchange := range []string{EventsExchangeName, RPCExchangeName, DeadExchangeName} {
if err := m.put(ctx, "/api/exchanges/%2f/"+url.PathEscape(exchange),
map[string]any{"type": "topic", "durable": true}); err != nil {
return fmt.Errorf("cannot declare the %s exchange: %w", exchange, err)
}
}
if err := m.put(ctx, "/api/queues/%2f/"+url.PathEscape(DeadExchangeName),
map[string]any{"durable": true}); err != nil {
return fmt.Errorf("cannot declare the dead-letter queue: %w", err)
}
if err := m.post(ctx, "/api/bindings/%2f/e/"+url.PathEscape(DeadExchangeName)+
"/q/"+url.PathEscape(DeadExchangeName), map[string]string{"routing_key": "#"}); err != nil {
return fmt.Errorf("cannot bind the dead-letter queue: %w", err)
}
return nil
}
// CreateNodeAccount gives a node its own broker account, with the token's secret as the password.
//
// Scoped so a node can reach its own queue and the one exchange, and nothing else. The patterns
// are anchored: a node called `laptop` must not be able to read `laptop-of-somebody-else`.
func (m *Management) CreateNodeAccount(ctx context.Context, node, password string) error {
if !safeName.MatchString(node) {
return fmt.Errorf(
"%q cannot be a broker account name: it becomes part of a permission pattern, so it "+
"is lower-case letters, digits and dashes", node)
}
if err := m.put(ctx, "/api/users/"+url.PathEscape(node),
map[string]string{"password": password, "tags": ""}); err != nil {
return fmt.Errorf("cannot create the broker account for %s: %w", node, err)
}
queue := regexp.QuoteMeta(QueueFor(node))
if err := m.put(ctx, "/api/permissions/%2f/"+url.PathEscape(node), map[string]string{
"configure": "^" + queue + "$",
"write": "^(" + regexp.QuoteMeta(ExchangeName) + "|" + queue + ")$",
"read": "^" + queue + "$",
}); err != nil {
return fmt.Errorf("cannot scope the broker account for %s: %w", node, err)
}
return nil
}
// CreateBuilderAccount scopes an account to taking build work and answering it.
//
// **A build machine is not a node**, and giving it a node's account would let it read another
// machine's declarations. What it needs is narrower and different: read the build queue, and
// write to the exchange and to whatever temporary queue an asker is waiting on.
//
// The reply queues are the reason `write` is not simply the exchange. `RequestBuild` declares an
// exclusive queue with a generated name and waits on it, so a builder that could not write to it
// could take work and never answer — which is the failure that looks like a builder that is not
// running.
func (m *Management) CreateBuilderAccount(ctx context.Context, name, password string) error {
if !safeName.MatchString(name) {
return fmt.Errorf(
"%q cannot be a broker account name: it becomes part of a permission pattern, so it "+
"is lower-case letters, digits and dashes", name)
}
if err := m.put(ctx, "/api/users/"+url.PathEscape(name),
map[string]string{"password": password, "tags": ""}); err != nil {
return fmt.Errorf("cannot create the broker account for %s: %w", name, err)
}
builds := regexp.QuoteMeta(BuildQueueName)
if err := m.put(ctx, "/api/permissions/%2f/"+url.PathEscape(name), map[string]string{
// It declares the build queue, because whichever builder starts first must be able to —
// and a queue nobody may declare is a queue that exists only if the control plane has
// already run, which makes the order they start in matter.
"configure": "^" + builds + "$",
// Two exchanges, and nothing else. **Not the default exchange**: permission there is
// granted per exchange rather than per queue, so a builder allowed to use it could
// publish into any node's queue — the privilege a build machine most obviously should
// not have. Answers go through the node exchange; announcing what was built goes through
// the events exchange, which is a different act with a different audience (novox/hq
// ADR 0072). A builder that could answer and not announce would leave the module graph
// knowing less than the registry does.
"write": "^(" + regexp.QuoteMeta(ExchangeName) + "|" + regexp.QuoteMeta(EventsExchangeName) + ")$",
// The build queue and nothing else. Not another machine's declarations.
"read": "^" + builds + "$",
}); err != nil {
return fmt.Errorf("cannot scope the broker account for %s: %w", name, err)
}
return nil
}
// RemoveNodeAccount withdraws a node's access.
func (m *Management) RemoveNodeAccount(ctx context.Context, node string) error {
if !safeName.MatchString(node) {
return fmt.Errorf("%q is not a broker account name", node)
}
return m.do(ctx, http.MethodDelete, "/api/users/"+url.PathEscape(node), nil)
}
// Accounts lists the broker's users, so a picture can be read from the system rather than assumed
// (novox/hq ADR 0018).
func (m *Management) Accounts(ctx context.Context) ([]string, error) {
body, err := m.get(ctx, "/api/users")
if err != nil {
return nil, err
}
var users []struct {
Name string `json:"name"`
}
if err := json.Unmarshal(body, &users); err != nil {
return nil, err
}
names := make([]string, 0, len(users))
for _, u := range users {
names = append(names, u.Name)
}
return names, nil
}
func (m *Management) put(ctx context.Context, path string, body any) error {
return m.do(ctx, http.MethodPut, path, body)
}
func (m *Management) post(ctx context.Context, path string, body any) error {
return m.do(ctx, http.MethodPost, path, body)
}
func (m *Management) get(ctx context.Context, path string) ([]byte, error) {
request, err := m.request(ctx, http.MethodGet, path, nil)
if err != nil {
return nil, err
}
response, err := m.client.Do(request)
if err != nil {
return nil, err
}
defer response.Body.Close()
if response.StatusCode >= 300 {
return nil, fmt.Errorf("the broker's management API answered %s to GET %s",
response.Status, path)
}
return io.ReadAll(io.LimitReader(response.Body, 1<<20))
}
func (m *Management) do(ctx context.Context, method, path string, body any) error {
request, err := m.request(ctx, method, path, body)
if err != nil {
return err
}
response, err := m.client.Do(request)
if err != nil {
return err
}
defer response.Body.Close()
if response.StatusCode >= 300 {
detail, _ := io.ReadAll(io.LimitReader(response.Body, 4096))
return fmt.Errorf("the broker's management API answered %s to %s %s: %s",
response.Status, method, path, strings.TrimSpace(string(detail)))
}
return nil
}
func (m *Management) request(ctx context.Context, method, path string, body any) (*http.Request, error) {
var payload io.Reader
if body != nil {
raw, err := json.Marshal(body)
if err != nil {
return nil, err
}
payload = bytes.NewReader(raw)
}
// Path joined by hand rather than through url.Parse: %2f is the default vhost and must reach
// the broker still encoded. Parsing would decode it to a slash and address a different route.
target := strings.TrimSuffix(m.base.String(), "/")
if user := m.base.User; user != nil {
target = strings.TrimSuffix(m.base.Scheme+"://"+m.base.Host, "/")
}
request, err := http.NewRequestWithContext(ctx, method, target+path, payload)
if err != nil {
return nil, err
}
if user := m.base.User; user != nil {
password, _ := user.Password()
request.SetBasicAuth(user.Username(), password)
}
if body != nil {
request.Header.Set("Content-Type", "application/json")
}
return request, nil
}
+96
View File
@@ -0,0 +1,96 @@
package broker_test
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"regexp"
"strings"
"testing"
"github.com/novox/mesh-controller/internal/broker"
)
// The audit logger consumes everything and emits nothing. Its account must let it declare and read
// its own queue and read the events exchange to bind onto — and must not reach another module's
// queue, nor grant any write to the events exchange (novox/hq ADR 0043).
func TestAConsumerReadsItsOwnQueueAndTheEventsExchangeAndNoOthers(t *testing.T) {
// Rebuilt through CreateModuleAccount's own path by asking for the same scope it would apply.
// The queue this module reads:
mine := broker.ModuleQueueFor("anchor", "audit-logger")
other := broker.ModuleQueueFor("anchor", "plex")
read := scope(t, "read", "anchor", "audit-logger", nil, []string{"#"})
if !read.MatchString(mine) {
t.Error("the audit logger may not read its own queue, so it consumes nothing")
}
if !read.MatchString(broker.EventsExchangeName) {
t.Error("the audit logger may not read the events exchange, so it cannot bind onto it")
}
if read.MatchString(other) {
t.Error("the audit logger may read another module's queue")
}
// It emits nothing, so it is granted no write to the events exchange — only its own queue, to bind.
write := scope(t, "write", "anchor", "audit-logger", nil, []string{"#"})
if write.MatchString(broker.EventsExchangeName) {
t.Error("a pure consumer was granted write to the events exchange")
}
if !write.MatchString(mine) {
t.Error("the audit logger may not write to its own queue, so it cannot bind it")
}
}
// An emitter is granted the events exchange to write; a consumer is not.
func TestAnEmitterMayWriteTheEventsExchangeAndAConsumerMayNot(t *testing.T) {
emitter := scope(t, "write", "anchor", "umami", []string{"module.umami.site.created"}, nil)
if !emitter.MatchString(broker.EventsExchangeName) {
t.Error("an emitting module may not write the events exchange, so it cannot emit")
}
}
// scope reconstructs one of the three permission patterns CreateModuleAccount would apply, by
// reading it back from a captured request against a stub management API.
func scope(t *testing.T, which, node, module string, emits, consumes []string) *regexp.Regexp {
t.Helper()
pat := capturePermission(t, which, node, module, emits, consumes)
re, err := regexp.Compile(pat)
if err != nil {
t.Fatalf("the %s pattern does not compile: %v", which, err)
}
return re
}
// capturePermission runs CreateModuleAccount against a stub management API and returns the pattern
// it set for `which` ("configure"/"write"/"read"). The scope is tested where it is applied, not
// reconstructed by the test — so a change to the mapping cannot pass a test that hard-codes the old
// one.
func capturePermission(t *testing.T, which, node, module string, emits, consumes []string) string {
t.Helper()
var captured map[string]string
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if strings.HasPrefix(r.URL.Path, "/api/permissions/") {
_ = json.NewDecoder(r.Body).Decode(&captured)
}
w.WriteHeader(http.StatusNoContent)
}))
defer server.Close()
t.Setenv(broker.ManagementVar, server.URL)
m, err := broker.ManagementFromEnvironment()
if err != nil {
t.Fatalf("stub management not usable: %v", err)
}
if _, err := m.CreateModuleAccount(context.Background(), node, module, "pw", emits, consumes); err != nil {
t.Fatalf("CreateModuleAccount: %v", err)
}
if captured == nil {
t.Fatal("no permissions were set")
}
pattern, ok := captured[which]
if !ok {
t.Fatalf("no %s permission was set; got %v", which, captured)
}
return pattern
}
+10 -60
View File
@@ -169,11 +169,7 @@ func PermissionsFor(p Principal) (Permissions, error) {
// The controller owns the mesh's own traffic and the streams. It is the only writer of
// stream definitions (design 25 §3), so it alone reaches the JetStream API.
pub = []string{"mesh.control.>", "mesh.node.>", "$JS.API.>"}
// **And where its consumers deliver.** A push consumer delivers on `_DELIVER.<its name>`,
// and a client bound to it subscribes exactly that; the server refused it for every
// principal the first time one bound a consumer (2026-09-28). Each kind below is granted
// its own consumers' delivery subjects and no other's.
sub = []string{"mesh.control.>", "$JS.API.>", "_DELIVER." + ControllerName, "_DELIVER." + ControllerName + ".>"}
sub = []string{"mesh.control.>", "$JS.API.>"}
// Work the mesh's own flows submit to a role, and the outcomes they wait on (ADR 0121). A
// build is the one today: the controller asks, and reads the answer from the seat's event
@@ -181,19 +177,6 @@ func PermissionsFor(p Principal) (Permissions, error) {
for _, seat := range meshSeatsTheControllerUses {
pub = append(pub, "mesh.seat."+seat+".accept.>")
}
// **And what the mesh says it did** (novox/hq ADR 0134). The control plane states its own
// facts under the seat it holds, because a role's events belong to the role and keep their
// address while the holder is replaced. Named one by one rather than as a whole namespace:
// least authority, and a fact nothing states is authority nobody uses.
for _, event := range ControllerStates {
pub = append(pub, seatEventSubject(ControllerSeat, event))
}
// Every module's tools: **the control plane is the way in** (novox/hq ADR 0095). A person
// or an agent asks through it and every question passes one process where an audit
// belongs — so it, alone among principals, may call any tool by name. The first `ask` on
// the new bus was refused the publish (2026-09-28).
pub = append(pub, "mesh.mod.*.tool.>")
// The two events it reacts to, and its ack subject on the stream they arrive from
// (streams.go). **Each named, not a pattern**: `mesh.mod.*.event.>` would make the
@@ -261,15 +244,8 @@ func PermissionsFor(p Principal) (Permissions, error) {
case KindNode:
// A host publishes its own node's control traffic and subscribes its own declaration —
// and nothing of any other node's.
// And binding to its consumer, which asks the server about it (CONSUMER.INFO) — the one
// thing the host does that nothing granted. Found the first time a machine dialled a
// permissioned server: "this node cannot read its declarations" (2026-09-28). The ack and
// the inbox are granted below with every principal's.
pub = []string{
"mesh.control." + p.Node + ".>",
"$JS.API.CONSUMER.INFO.NODES." + p.Node,
}
sub = []string{"mesh.node." + p.Node + ".declare", "_DELIVER." + p.Node}
pub = []string{"mesh.control." + p.Node + ".>"}
sub = []string{"mesh.node." + p.Node + ".declare"}
case KindModule:
// 1. Its own namespace: it publishes its events there and serves its tools there. Nothing
@@ -279,13 +255,9 @@ func PermissionsFor(p Principal) (Permissions, error) {
for _, e := range p.Emits {
pub = append(pub, own+".event."+e)
}
// Every tool under its own name, not a list: the tools a module serves are what its code
// answers, and a second copy of that list in the manifest would be a second source of
// truth for the mesh to keep in step (2026-09-28: every module that served a tool was
// refused the subscription, because none had written the list twice). Nothing is given
// away — no other principal may subscribe this namespace, and a caller's authority is
// still granted per tool, by name, on the publish side.
sub = append(sub, own+".tool.>")
for _, t := range p.Serves {
sub = append(sub, own+".tool."+t)
}
// 2. What it consumes, by the emitter's own subject — an event is addressed to its
// emitter, because the emitter's identity is the meaning (ADR 0118).
@@ -305,26 +277,8 @@ func PermissionsFor(p Principal) (Permissions, error) {
}
}
// 2c. Its own consumer, which it **pulls**: the runtime asks for the next message and is
// answered on its own inbox, so what it needs is to ask about the consumer and to ask it
// for messages — its own consumer's name, and no other's. Pulled rather than pushed
// because that is the one shape a runtime's client binds without creating anything; the
// controller and the hosts are pushed to. Named here rather than through ConsumerFor,
// which asks for these permissions to build the consumer and would ask forever. A
// subject for a consumer that turns out not to exist grants nothing anybody can use.
pub = append(pub,
"$JS.API.CONSUMER.INFO."+consumerStream(p)+"."+consumerDurable(p),
"$JS.API.CONSUMER.MSG.NEXT."+consumerStream(p)+"."+consumerDurable(p))
// 3. Seats it holds: full participation.
for _, s := range p.Holds {
// Taking work from the role's queue: the worker consumer it binds (asked about,
// delivered on, acknowledged), each on the seat's own stream. The first machine to
// take work over the new bus was refused the asking (2026-09-28).
worker := "SEAT_" + upperSnake(s.Name) + "_worker"
stream := seatStreamName(s.Name)
sub = append(sub, "_DELIVER."+worker)
pub = append(pub, "$JS.API.CONSUMER.INFO."+stream+"."+worker, "$JS.ACK."+stream+"."+worker+".>")
for _, a := range s.Accepts {
sub = append(sub, seatSubject(s, "accept", a))
}
@@ -372,10 +326,9 @@ func PermissionsFor(p Principal) (Permissions, error) {
return Permissions{
Publish: pub,
Subscribe: sub,
// A module answers what it was asked — a tool call reaches it on its own namespace, so the
// authority is bounded by having been asked — and so does the controller. A node and a
// person are never asked anything, and are granted nothing here.
AllowResponses: p.Kind == KindModule || p.Kind == KindController,
// Only something that serves is ever answering. A pure consumer is granted nothing here.
AllowResponses: p.Kind == KindModule && (len(p.Serves) > 0 || len(p.Holds) > 0) ||
p.Kind == KindController,
}, nil
}
@@ -561,10 +514,7 @@ 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.
// 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")
b.WriteString("accounts {\n MESH {\n users = [\n")
for _, p := range sorted {
perms, err := PermissionsFor(p)
if err != nil {
+10 -45
View File
@@ -1,7 +1,6 @@
package broker
import (
"slices"
"strings"
"testing"
)
@@ -90,30 +89,17 @@ func TestAnInboxIsScopedToItsOwner(t *testing.T) {
}
// A responder answers on the caller's inbox, which it has no permission for. allow_responses is
// what makes a scoped inbox workable at all — the authority is bounded by having been asked. A
// module is asked on its own namespace and may answer; a node and a person are never asked.
func TestOnlyWhatCanBeAskedMayAnswer(t *testing.T) {
module, _ := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "audit",
// what makes a scoped inbox workable at all — the authority is bounded by having been asked.
func TestOnlySomethingThatServesMayAnswer(t *testing.T) {
serving, _ := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "billing",
Serves: []string{"status"}, PasswordHash: "x"})
if !serving.AllowResponses {
t.Fatal("a module serving a tool cannot answer the caller's inbox")
}
consumer, _ := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "audit",
Consumes: []string{"shop.order.placed"}, PasswordHash: "x"})
if !module.AllowResponses {
t.Fatal("a module cannot answer a tool call on its own namespace")
}
node, _ := PermissionsFor(Principal{Kind: KindNode, Node: "one", PasswordHash: "x"})
if node.AllowResponses {
t.Fatal("a node was granted the right to answer, and nothing asks a node anything")
}
}
// A module serves every tool under its own name, and no other module's.
func TestAModuleServesItsOwnNamespaceAndNoOthers(t *testing.T) {
p, _ := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "gitea", PasswordHash: "x"})
if !slices.Contains(p.Subscribe, "mesh.mod.gitea.tool.>") {
t.Fatalf("a module may not serve its own tools: %v", p.Subscribe)
}
for _, s := range p.Subscribe {
if strings.HasPrefix(s, "mesh.mod.") && !strings.HasPrefix(s, "mesh.mod.gitea.") {
t.Fatalf("a module may subscribe another's namespace: %s", s)
}
if consumer.AllowResponses {
t.Fatal("a pure consumer was granted the right to answer, which nothing asked it to do")
}
}
@@ -338,24 +324,3 @@ func admits(pattern, subject []string) bool {
}
return len(pattern) == len(subject)
}
// A module pulls its own consumer — asks about it, asks it for messages — and no other module's.
func TestAModulePullsItsOwnConsumerAndNoOthers(t *testing.T) {
p, _ := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "audit",
Consumes: []string{"shop.order.placed"}, PasswordHash: "x"})
for _, want := range []string{"$JS.API.CONSUMER.INFO.EVENTS.one_audit", "$JS.API.CONSUMER.MSG.NEXT.EVENTS.one_audit"} {
if !slices.Contains(p.Publish, want) {
t.Errorf("a module cannot bind its own consumer: %v lacks %s", p.Publish, want)
}
}
for _, s := range p.Publish {
if strings.Contains(s, "CONSUMER.") && !strings.HasSuffix(s, ".one_audit") {
t.Errorf("a module may reach another consumer: %s", s)
}
}
for _, s := range p.Subscribe {
if strings.HasPrefix(s, "_DELIVER.") {
t.Errorf("a module is granted a push delivery it never binds: %s", s)
}
}
}
+19 -11
View File
@@ -68,16 +68,24 @@ func BareAddress(address string) string {
return "nats://" + bare
}
// BusAddress is where the mesh's bus is, with this process's credential, and refuses to be empty:
// there is one bus, and a control plane without it can hold records and answer nothing (novox/hq
// ADR 0131, design 28 task 5.5).
func BusAddress() (string, error) {
address, _, err := OnNATS()
if err != nil {
return "", err
// MustBeOneBus refuses a configuration that names both buses for the mesh's own traffic.
//
// **Both clients ship and that is the point; both being live is not.** The rollout moves every node
// at once (ADR 0116 step 5): a mesh half on each is one where a declaration goes out on one bus and
// the report comes back on the other, and nothing anywhere says so — every component would log
// success. Refused at start, where it can be said in one sentence.
func MustBeOneBus(amqp, nats string) error {
if strings.TrimSpace(amqp) != "" && strings.TrimSpace(nats) != "" {
return fmt.Errorf(
"this control plane is told about both buses (%s and %s) and can only be on one. A mesh "+
"half on each is one where a declaration goes out on one and the report comes back "+
"on the other, and every component reports success while it happens. The rollout "+
"moves every node at once: unset %s to stay, or unset %s to move",
AMQPVarName, NATSVar, NATSVar, AMQPVarName)
}
if address == "" {
return "", fmt.Errorf("this control plane has no %s, so it cannot reach the mesh's bus", NATSVar)
}
return address, nil
return nil
}
// AMQPVarName is the variable naming the bus the mesh runs on today. Named here rather than
// imported from the link package, for the one direction of dependency.
const AMQPVarName = "MESH_BROKER_AMQP"
+32
View File
@@ -1,11 +1,43 @@
package broker
import (
"strings"
"testing"
)
// Which bus the mesh is on is one fact, and being told about both is refused.
//
// **Not a warning.** A mesh half on each bus is one where a declaration goes out on one and the
// report comes back on the other, and every component reports success while it happens — which is
// the exact failure ADR 0074 exists to catch, arriving through configuration instead of through code.
func TestBeingToldAboutBothBusesIsRefused(t *testing.T) {
err := MustBeOneBus("amqps://broker:5671/", "nats://bus:4222")
if err == nil {
t.Fatal("a control plane told about both buses was allowed to start")
}
// The remedy is in the words, because whoever reads this has to choose one and the wrong choice
// is a rollout half done.
for _, want := range []string{AMQPVarName, NATSVar, "unset"} {
if !strings.Contains(err.Error(), want) {
t.Errorf("the refusal does not mention %s: %v", want, err)
}
}
}
// One bus, or none, is ordinary. None is a control plane that publishes nothing and holds records,
// which several of its own commands are.
func TestOneBusOrNeitherIsAllowed(t *testing.T) {
for _, c := range []struct{ what, amqp, nats string }{
{"the bus the mesh runs on today", "amqps://broker:5671/", ""},
{"the bus being built", "", "nats://bus:4222"},
{"neither", "", ""},
{"neither, with whitespace for an address", " ", "\t"},
} {
if err := MustBeOneBus(c.amqp, c.nats); err != nil {
t.Errorf("%s was refused: %v", c.what, err)
}
}
}
// The controller's own credential arrives in its address, and has to be readable out of it — its user
// is created by the installer at a bootstrap password, before the controller exists to mint one.
-30
View File
@@ -1,30 +0,0 @@
package broker_test
import (
"slices"
"testing"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/link"
)
// The facts the control plane states are named twice — in the grant that permits them and in the code
// that states them — because `link` imports `broker` and the dependency cannot go the other way. So a
// test keeps them agreeing: a subject the grant omits is refused at the moment the mesh has something
// to say, and one the grant adds that nothing states is authority nobody uses.
//
// An external test package, because it may import both while neither imports the other.
func TestTheFactsTheGrantPermitsAreTheFactsTheMeshStates(t *testing.T) {
if broker.ControllerSeat != link.MeshControllerSeat {
t.Fatalf("the grant is written for the %q seat and the mesh states its facts under %q",
broker.ControllerSeat, link.MeshControllerSeat)
}
for _, event := range []string{link.KeyApplied, link.KeyRefused, link.KeyBuiltBefore} {
if !slices.Contains(broker.ControllerStates, event) {
t.Errorf("the mesh states %q and its account may not publish it", event)
}
}
if len(broker.ControllerStates) != 3 {
t.Errorf("the grant permits %v, which is more than the mesh states", broker.ControllerStates)
}
}
-14
View File
@@ -160,17 +160,6 @@ func Overlaps() []string {
// ack subject is derived from (nats.go: `$JS.ACK.<stream>.controller.>`).
const ControllerName = "controller"
// ControllerSeat is the role the control plane holds, and ControllerStates are the facts it states
// under it (novox/hq ADR 0134).
//
// **Written here as well as in `link`, and a test keeps them agreeing.** `link` imports `broker`, so
// `broker` cannot import `link`; a grant naming a subject the controller never publishes is authority
// nobody uses, and a controller publishing one the grant omits is refused at the moment it has
// something to say.
const ControllerSeat = "mesh-controller"
var ControllerStates = []string{"applied", "refused", "built-before"}
// ControllerFollows are the events the controller reacts to: the catalogue saying a module's
// current version moved, and a catalogue that has just started saying it may have missed builds.
//
@@ -186,9 +175,6 @@ var ControllerFollows = []string{
// message on the control branch. Same three audiences, one publish: whoever asked, this, and the
// catalogue.
seatEventSubject("mesh-build-machine", "built"),
// The forge's merges: what moved a source, so the mesh builds what that source produces
// without anybody telling it (novox/hq 04-ISSUES/131). Appended, because the index is a name.
moduleEventSubject("gitea", "pull.merged"),
}
// moduleEventSubject is where one module's event lands. The same derivation PermissionsFor uses, so
+10 -13
View File
@@ -21,11 +21,10 @@ jetstream {
accounts {
MESH {
jetstream: enabled
users = [
{ user: "controller", password: "$2a$11$cccccccccccccccccccccc", permissions: {
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "_INBOX.enrol.>", "mesh.control.>", "mesh.mod.*.tool.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>", "mesh.seat.mesh-controller.event.applied", "mesh.seat.mesh-controller.event.built-before", "mesh.seat.mesh-controller.event.refused"] }
subscribe: { allow: ["$JS.API.>", "_DELIVER.controller", "_DELIVER.controller.>", "_INBOX.controller.>", "mesh.control.>", "mesh.mod.gitea.event.pull.merged", "mesh.mod.mesh-catalog.event.catching-up", "mesh.mod.mesh-catalog.event.upgraded", "mesh.seat.mesh-build-machine.event.built"] }
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "_INBOX.enrol.>", "mesh.control.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>"] }
subscribe: { allow: ["$JS.API.>", "_INBOX.controller.>", "mesh.control.>", "mesh.mod.mesh-catalog.event.catching-up", "mesh.mod.mesh-catalog.event.upgraded", "mesh.seat.mesh-build-machine.event.built"] }
allow_responses: { max: 1, ttl: "1m" }
} }
{ user: "enrol.one", password: "$2a$11$eeeeeeeeeeeeeeeeeeeeee", permissions: {
@@ -33,23 +32,21 @@ accounts {
subscribe: { allow: ["_INBOX.enrol.one.>"] }
} }
{ user: "node.one", password: "$2a$11$nnnnnnnnnnnnnnnnnnnnnn", permissions: {
publish: { allow: ["$JS.ACK.NODES.one.>", "$JS.API.CONSUMER.INFO.NODES.one", "mesh.control.one.>"] }
subscribe: { allow: ["_DELIVER.one", "_INBOX.node.one.>", "mesh.node.one.declare"] }
publish: { allow: ["$JS.ACK.NODES.one.>", "mesh.control.one.>"] }
subscribe: { allow: ["_INBOX.node.one.>", "mesh.node.one.declare"] }
} }
{ user: "one.telegram", password: "$2a$11$tttttttttttttttttttttt", permissions: {
publish: { allow: ["$JS.ACK.EVENTS.one_telegram.>", "$JS.ACK.SEAT_TELEGRAM_SENDER.SEAT_TELEGRAM_SENDER_worker.>", "$JS.API.CONSUMER.INFO.EVENTS.one_telegram", "$JS.API.CONSUMER.INFO.SEAT_TELEGRAM_SENDER.SEAT_TELEGRAM_SENDER_worker", "$JS.API.CONSUMER.MSG.NEXT.EVENTS.one_telegram", "mesh.seat.telegram-sender.event.delivered", "mesh.seat.telegram-sender.event.failed"] }
subscribe: { allow: ["_DELIVER.SEAT_TELEGRAM_SENDER_worker", "_INBOX.one.telegram.>", "mesh.mod.telegram.tool.>", "mesh.seat.telegram-sender.accept.send"] }
publish: { allow: ["$JS.ACK.EVENTS.one_telegram.>", "mesh.seat.telegram-sender.event.delivered", "mesh.seat.telegram-sender.event.failed"] }
subscribe: { allow: ["_INBOX.one.telegram.>", "mesh.mod.telegram.tool.status", "mesh.seat.telegram-sender.accept.send"] }
allow_responses: { max: 1, ttl: "1m" }
} }
{ user: "two.audit", password: "$2a$11$aaaaaaaaaaaaaaaaaaaaaa", permissions: {
publish: { allow: ["$JS.ACK.EVENTS.two_audit.>", "$JS.API.CONSUMER.INFO.EVENTS.two_audit", "$JS.API.CONSUMER.MSG.NEXT.EVENTS.two_audit"] }
subscribe: { allow: ["_INBOX.two.audit.>", "mesh.mod.audit.tool.>", "mesh.mod.shop.event.order.placed"] }
allow_responses: { max: 1, ttl: "1m" }
publish: { allow: ["$JS.ACK.EVENTS.two_audit.>"] }
subscribe: { allow: ["_INBOX.two.audit.>", "mesh.mod.shop.event.order.placed"] }
} }
{ user: "two.shop", password: "$2a$11$ssssssssssssssssssssss", permissions: {
publish: { allow: ["$JS.ACK.EVENTS.two_shop.>", "$JS.API.CONSUMER.INFO.EVENTS.two_shop", "$JS.API.CONSUMER.MSG.NEXT.EVENTS.two_shop", "mesh.mod.shop.event.order.placed", "mesh.seat.telegram-sender.accept.send"] }
subscribe: { allow: ["_INBOX.two.shop.>", "mesh.mod.shop.tool.>"] }
allow_responses: { max: 1, ttl: "1m" }
publish: { allow: ["$JS.ACK.EVENTS.two_shop.>", "mesh.mod.shop.event.order.placed", "mesh.seat.telegram-sender.accept.send"] }
subscribe: { allow: ["_INBOX.two.shop.>"] }
} }
]
}
+1 -7
View File
@@ -186,13 +186,7 @@ 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.
// `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"} {
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)
+15 -68
View File
@@ -61,12 +61,6 @@ type Result struct {
Commit string
// Built is each artifact, for reporting.
Built []catalogue.Built
// Read is every repository this build read source from besides the module's own — the second
// repository an artifact's recipe names (ArtifactContext). Reported because the manifest the
// mesh keeps carries no build section, so nothing else could say that a merge there is a
// change to this module (novox/hq 04-ISSUES/131).
Read []catalogue.ArtifactContext
}
// GitCredential is the forge credential a clone may present when the server asks for one.
@@ -175,8 +169,6 @@ func Build(ctx context.Context, run Runner, publish Publisher,
}
var built []catalogue.Built
// stoodOn is every base the build was handed, as resolved — the edges the catalogue derives.
var stoodOn []string
if manifest.Build != nil {
// What this module said it stands on, answered with what this mesh actually holds. Done
// before anything is built, so a missing base is refused in front of the person who can
@@ -194,12 +186,11 @@ func Build(ctx context.Context, run Runner, publish Publisher,
}
return from, nil
}
args, bases, err := standingOn(ctx, manifest, held, mirror)
args, err := standingOn(ctx, manifest, held, mirror)
if err != nil {
say("bases", "UNMET: %v", err)
return Result{}, err
}
stoodOn = bases
if len(args) > 0 {
say("bases", "%d resolved from what the mesh holds", len(args)/2)
}
@@ -226,7 +217,7 @@ func Build(ctx context.Context, run Runner, publish Publisher,
}
say("done", "%s at %s — %d artifact(s) pinned", manifest.Module, short(commit), len(built))
return Result{Manifest: resolved, Commit: commit, Built: built,
Against: against(within, manifest, stoodOn), Read: readBy(manifest)}, nil
Against: against(within, manifest)}, nil
}
// Log is where a build says what it is doing, step by step. Nil is silent — the tests pass none,
@@ -348,27 +339,14 @@ func describe(path string) string {
// allowed to name — a tag is something somebody else can move under you.
var pinnedImage = regexp.MustCompile(`[A-Za-z0-9][A-Za-z0-9._/:-]*@sha256:[0-9a-f]{64}`)
// against is what this module's image artifacts are built on top of: every base the mesh resolved
// and handed the recipe as a build argument (`build.on`), and any image a recipe pins by digest
// itself. Nothing is guessed: a reference that was neither resolved nor written down is not
// reported.
//
// **The resolved bases are the edges.** A recipe reads its base from an argument (`FROM
// ${RUNTIME_BASE}`), so the digest is never in the file, and a derivation that read files alone
// recorded no edge for any module on the mesh — which is why nothing knew what a changed base
// meant to rebuild (novox/hq 04-ISSUES/131).
func against(within string, manifest catalogue.Manifest, resolved []string) []string {
// against reads what this module's image artifacts are built on top of, out of the files that
// build them. Nothing is guessed: a reference that is not written down is not reported.
func against(within string, manifest catalogue.Manifest) []string {
if manifest.Build == nil {
return nil
}
seen := map[string]bool{}
var out []string
for _, r := range resolved {
if r != "" && !seen[r] {
seen[r] = true
out = append(out, r)
}
}
for _, a := range manifest.Build.Artifacts {
if a.Kind != catalogue.ArtifactImage || a.From == "" {
continue
@@ -726,42 +704,40 @@ var _ io.Writer = (*stringWriter)(nil)
// built cannot be built here yet, and the useful sentence names which module is missing — not the
// one a container runtime produces when a recipe's first line refers to an image nobody has.
//
// The order is fixed so two builds of one commit invoke the same command. Returned alongside the
// arguments is every reference they resolved to, which is what the build stood on.
// The order is fixed so two builds of one commit invoke the same command.
func standingOn(ctx context.Context, manifest catalogue.Manifest, held map[string]string,
mirror func(ctx context.Context, from, repository string) (string, error)) ([]string, []string, error) {
mirror func(ctx context.Context, from, repository string) (string, error)) ([]string, error) {
if manifest.Build == nil || len(manifest.Build.On) == 0 {
return nil, nil, nil
return nil, nil
}
on := append([]catalogue.BuildsOn{}, manifest.Build.On...)
sort.Slice(on, func(i, j int) bool { return on[i].Arg < on[j].Arg })
var args, resolved []string
var args []string
for _, base := range on {
if base.Image != "" {
// A vendor's image, declared (novox/hq 04-ISSUES/064, ADR 0097). Pinned, because a tag
// is what somebody else can move; copied into the mesh's registry, because a build
// that reaches a public registry on its own is a build that works sometimes.
if base.Arg == "" || base.Module != "" || base.Artifact != "" {
return nil, nil, fmt.Errorf(
return nil, fmt.Errorf(
"%s stands on the image %s, and a base is either a module's artifact or an "+
"image — never both — read from one build argument", manifest.Module, base.Image)
}
if !strings.Contains(base.Image, "@sha256:") {
return nil, nil, fmt.Errorf(
return nil, fmt.Errorf(
"%s stands on the image %q, which is not pinned by digest. A tag is what "+
"somebody else can move; name it as <image>@sha256:…", manifest.Module, base.Image)
}
reference, err := mirror(ctx, base.Image, manifest.Module+"/on-"+strings.ToLower(base.Arg))
if err != nil {
return nil, nil, fmt.Errorf("%s stands on %s: %w", manifest.Module, base.Image, err)
return nil, fmt.Errorf("%s stands on %s: %w", manifest.Module, base.Image, err)
}
args = append(args, "--build-arg", base.Arg+"="+reference)
resolved = append(resolved, reference)
continue
}
if base.Arg == "" || base.Module == "" || base.Artifact == "" {
return nil, nil, fmt.Errorf(
return nil, fmt.Errorf(
"%s says its build stands on something, and does not say all of what: a base "+
"needs the module, the artifact, and the build argument the recipe reads it "+
"from", manifest.Module)
@@ -769,15 +745,14 @@ func standingOn(ctx context.Context, manifest catalogue.Manifest, held map[strin
key := base.Module + "/" + base.Artifact
reference, has := held[key]
if !has {
return nil, nil, fmt.Errorf(
return nil, fmt.Errorf(
"%s builds on %s, and this mesh has not built it. Build %s first — every module "+
"in this toolchain stands on it, so it is the thing to have before anything "+
"else", manifest.Module, key, base.Module)
}
args = append(args, "--build-arg", base.Arg+"="+reference)
resolved = append(resolved, reference)
}
return args, resolved, nil
return args, nil
}
// compile runs a module's own code through its toolchain, and says where the result is.
@@ -1022,31 +997,3 @@ func instructions(recipe string) []string {
flush()
return out
}
// readBy is every repository other than the module's own that this build's recipes read source from,
// each once and in a fixed order, so two builds of one commit report the same thing the same way.
func readBy(manifest catalogue.Manifest) []catalogue.ArtifactContext {
if manifest.Build == nil {
return nil
}
seen := map[string]bool{}
var out []catalogue.ArtifactContext
for _, a := range manifest.Build.Artifacts {
if a.Context == nil || a.Context.Repository == "" {
continue
}
key := a.Context.Repository + "#" + a.Context.Ref
if seen[key] {
continue
}
seen[key] = true
out = append(out, *a.Context)
}
sort.Slice(out, func(i, j int) bool {
if out[i].Repository != out[j].Repository {
return out[i].Repository < out[j].Repository
}
return out[i].Ref < out[j].Ref
})
return out
}
-14
View File
@@ -180,20 +180,6 @@ func (r Registry) MirrorImage(ctx context.Context, from, repository string) (str
if err != nil {
return "", err
}
// **Already held is already mirrored.** A base is named by digest, and a digest this registry
// holds under the module's repository is the same bytes whatever upstream would say — so
// upstream is not asked. Asked every build, the public hub's anonymous pull limit was reached
// on the first merge that rebuilt a whole catalogue (2026-09-28), and every module whose base
// lives there failed on a copy it did not need.
if strings.HasPrefix(where.reference, "sha256:") {
held, err := r.has(ctx, "http://"+r.Address+"/v2/"+repository+"/manifests/"+where.reference, manifestAccept)
if err != nil {
return "", fmt.Errorf("asking %s whether it holds %s: %w", r.Address, from, err)
}
if held {
return r.Address + "/" + repository + "@" + where.reference, nil
}
}
src := &source{client: r.client()}
digest, err := r.copyManifest(ctx, src, where, where.reference, repository)
if err != nil {
-38
View File
@@ -103,20 +103,6 @@ func (m *theMeshsRegistry) handler() http.Handler {
m.mu.Lock()
defer m.mu.Unlock()
switch {
case r.Method == http.MethodHead && strings.Contains(r.URL.Path, "/manifests/"):
// **As strictly as a real registry.** A manifest is answered only in a media type the
// caller named; a request with no Accept is answered as if nothing were there. The fake
// used to answer regardless, which is why it could not catch a check that asked without
// one — and the mesh copied every base again (2026-09-28).
if !strings.Contains(r.Header.Get("Accept"), "manifest") && !strings.Contains(r.Header.Get("Accept"), "index") {
w.WriteHeader(http.StatusNotFound)
return
}
if _, ok := m.manifests[r.URL.Path[strings.LastIndex(r.URL.Path, "/")+1:]]; ok {
w.WriteHeader(http.StatusOK)
} else {
w.WriteHeader(http.StatusNotFound)
}
case r.Method == http.MethodHead && strings.Contains(r.URL.Path, "/blobs/"):
if _, ok := m.blobs[r.URL.Path[strings.LastIndex(r.URL.Path, "/")+1:]]; ok {
w.WriteHeader(http.StatusOK)
@@ -233,27 +219,3 @@ func TestATagBeforeTheDigestIsNotPartOfTheRepository(t *testing.T) {
t.Fatalf("got %+v", got)
}
}
// A base this registry already holds by digest is not asked of upstream at all: the public hub
// limits anonymous pulls, and a catalogue rebuilt on one merge asked it once per module.
func TestABaseAlreadyHeldIsNotAskedOfUpstream(t *testing.T) {
src, indexDigest, _ := anUpstreamRegistry(t)
dst := &theMeshsRegistry{blobs: map[string][]byte{}, manifests: map[string][]byte{}}
dstServer := httptest.NewServer(dst.handler())
defer dstServer.Close()
address := strings.TrimPrefix(dstServer.URL, "http://")
r := Registry{Address: address, HTTP: src.Client()}
host := strings.TrimPrefix(src.URL, "http://")
if _, err := r.MirrorImage(context.Background(), host+"/library/thing:latest", "hello-web/server"); err != nil {
t.Fatal(err)
}
// Upstream gone: the pinned base is answered from what the mesh holds.
src.Close()
reference, err := r.MirrorImage(context.Background(), host+"/library/thing@"+indexDigest, "hello-web/server")
if err != nil {
t.Fatalf("a base the registry holds was asked of an upstream that is gone: %v", err)
}
if reference != address+"/hello-web/server@"+indexDigest {
t.Fatalf("pinned as %q", reference)
}
}
+1 -13
View File
@@ -122,23 +122,11 @@ func (r Registry) PublishArchive(ctx context.Context, repository string, body []
return final, nil
}
// has is whether this registry already holds what is at that URL.
//
// **A manifest HEAD must say what it accepts.** A registry answers a manifest request only in a media
// type the caller named, and a bare HEAD — no Accept at all — is answered 404 for a manifest it holds
// perfectly well. Measured against the mesh's own registry (2026-09-28): the same digest answered 200
// with the manifest media types and 404 without them, so a check written without them concluded the
// registry held nothing, copied every base again, and exhausted the public hub's pull limit. A blob
// needs no Accept, which is why this went unnoticed: the same helper was right for blobs and wrong
// for manifests.
func (r Registry) has(ctx context.Context, url string, accept ...string) (bool, error) {
func (r Registry) has(ctx context.Context, url string) (bool, error) {
request, err := http.NewRequestWithContext(ctx, http.MethodHead, url, nil)
if err != nil {
return false, err
}
for _, media := range accept {
request.Header.Add("Accept", media)
}
response, err := r.client().Do(request)
if err != nil {
return false, fmt.Errorf("cannot reach the registry at %s: %w", r.Address, err)
+6 -55
View File
@@ -22,7 +22,7 @@ func TestABaseTheMeshHasNotBuiltIsRefused(t *testing.T) {
On: []catalogue.BuildsOn{{Arg: "RUNTIME_BASE", Module: "mesh-tools", Artifact: "runtime"}},
},
}
_, _, err := standingOn(context.Background(), manifest, map[string]string{}, noMirror)
_, err := standingOn(context.Background(), manifest, map[string]string{}, noMirror)
if err == nil {
t.Fatal("a base nothing has built was accepted; the build would have failed on its first line")
}
@@ -42,7 +42,7 @@ func TestABaseTheMeshHoldsBecomesABuildArgument(t *testing.T) {
},
}
held := map[string]string{"mesh-tools/runtime": "127.0.0.1:5000/mesh-tools/runtime@sha256:" + strings.Repeat("a", 64)}
args, _, err := standingOn(context.Background(), manifest, held, noMirror)
args, err := standingOn(context.Background(), manifest, held, noMirror)
if err != nil {
t.Fatalf("a base this mesh holds was refused: %v", err)
}
@@ -54,7 +54,7 @@ func TestABaseTheMeshHoldsBecomesABuildArgument(t *testing.T) {
// A module naming no base asks for nothing, which is most modules.
func TestAModuleNamingNoBaseAddsNoArguments(t *testing.T) {
args, _, err := standingOn(context.Background(), catalogue.Manifest{Module: "hello-web", Build: &catalogue.Build{}}, nil, noMirror)
args, err := standingOn(context.Background(), catalogue.Manifest{Module: "hello-web", Build: &catalogue.Build{}}, nil, noMirror)
if err != nil || args != nil {
t.Fatalf("a module naming no base produced %v, %v", args, err)
}
@@ -66,7 +66,7 @@ func TestAnIncompleteBaseIsRefused(t *testing.T) {
Module: "postgres",
Build: &catalogue.Build{On: []catalogue.BuildsOn{{Module: "mesh-tools", Artifact: "runtime"}}},
}
if _, _, err := standingOn(context.Background(), manifest, map[string]string{"mesh-tools/runtime": "x"}, noMirror); err == nil {
if _, err := standingOn(context.Background(), manifest, map[string]string{"mesh-tools/runtime": "x"}, noMirror); err == nil {
t.Fatal("a base with no build argument was accepted; nothing would have read it")
}
}
@@ -86,7 +86,7 @@ func TestADeclaredVendorImageIsCopiedInAndHandedToTheRecipe(t *testing.T) {
},
}
var asked []string
args, _, err := standingOn(context.Background(), manifest, nil, func(_ context.Context, from, repository string) (string, error) {
args, err := standingOn(context.Background(), manifest, nil, func(_ context.Context, from, repository string) (string, error) {
asked = append(asked, from+" -> "+repository)
return "127.0.0.1:5000/" + repository + "@sha256:" + strings.Repeat("d", 64), nil
})
@@ -101,7 +101,7 @@ func TestADeclaredVendorImageIsCopiedInAndHandedToTheRecipe(t *testing.T) {
}
// Unpinned, it is refused: a tag is what somebody else can move.
manifest.Build.On[0].Image = "quay.io/minio/mc:latest"
if _, _, err := standingOn(context.Background(), manifest, nil, noMirror); err == nil || !strings.Contains(err.Error(), "not pinned") {
if _, err := standingOn(context.Background(), manifest, nil, noMirror); err == nil || !strings.Contains(err.Error(), "not pinned") {
t.Fatalf("an unpinned vendor image was accepted: %v", err)
}
}
@@ -151,52 +151,3 @@ func TestARecipeIsReadAsInstructions(t *testing.T) {
t.Fatalf("a heredoc line or a continued stage was read as a base: %v", bases)
}
}
// What a build was handed as its bases is what it stood on — recorded, so a changed base knows what
// to rebuild (novox/hq 04-ISSUES/131). A recipe reads the base from an argument, so nothing else
// could know.
func TestTheBasesABuildWasHandedAreWhatItStoodOn(t *testing.T) {
manifest := catalogue.Manifest{
Module: "gitea",
Build: &catalogue.Build{
On: []catalogue.BuildsOn{
{Arg: "RUNTIME_BASE", Module: "mesh-tools", Artifact: "runtime"},
{Arg: "BUILD_BASE", Module: "mesh-tools", Artifact: "build"},
},
Artifacts: []catalogue.Artifact{{Name: "runtime", Kind: catalogue.ArtifactImage, From: "Dockerfile"}},
},
}
held := map[string]string{
"mesh-tools/runtime": "127.0.0.1:5000/mesh-tools/runtime@sha256:" + strings.Repeat("a", 64),
"mesh-tools/build": "127.0.0.1:5000/mesh-tools/build@sha256:" + strings.Repeat("b", 64),
}
_, resolved, err := standingOn(context.Background(), manifest, held, noMirror)
if err != nil {
t.Fatal(err)
}
got := against(t.TempDir(), manifest, resolved)
if len(got) != 2 || got[0] != held["mesh-tools/build"] || got[1] != held["mesh-tools/runtime"] {
t.Fatalf("the bases the build was handed were not what it stood on: %v", got)
}
}
// What a build read besides its module's own repository is the second repository its recipes name,
// each once: a module that packages source living elsewhere is affected when that source moves.
func TestWhatABuildReadIsTheRepositoriesItsRecipesName(t *testing.T) {
elsewhere := catalogue.ArtifactContext{Repository: "http://forge.internal:20000/novox/mesh-controller.git", Ref: "main"}
manifest := catalogue.Manifest{
Module: "builder",
Build: &catalogue.Build{Artifacts: []catalogue.Artifact{
{Name: "server", Kind: catalogue.ArtifactImage, From: "Dockerfile", Context: &elsewhere},
{Name: "tools", Kind: catalogue.ArtifactImage, From: "Dockerfile", Context: &elsewhere},
{Name: "config", Kind: catalogue.ArtifactArchive, From: "etc"},
}},
}
read := readBy(manifest)
if len(read) != 1 || read[0] != elsewhere {
t.Fatalf("the repositories this build read are %+v", read)
}
if readBy(catalogue.Manifest{Module: "gitea", Build: &catalogue.Build{}}) != nil {
t.Fatal("a module whose recipes name no other repository read one")
}
}
-107
View File
@@ -103,11 +103,6 @@ type Rendering struct {
// **Only the users, never the server's own settings**: those are the module's, in its image and
// its mounts (Manifest.BusUsers).
BusUsers string
// BusMembership is this machine's membership for the bus the mesh is moving to, sealed to it
// (design 28, task 5.2). Empty for a machine not being moved. Written as a file the host reads
// after the declaration has applied, so the bus it names is standing before the machine leaves
// the one it is on.
BusMembership string
// MeshRange is the private network's CIDR (the range node addresses are allocated from), for a
// module that must name the whole mesh rather than one machine — an intrusion filter that must
@@ -243,23 +238,9 @@ func (r Resolution) Compose(with Rendering) (Composed, error) {
if err != nil {
return Composed{}, err
}
if with.BusMembership != "" {
// The machine's own, not any module's: how it reaches the mesh from now on. Sealed like a
// secret and placed where the host looks for exactly this (design 28, task 5.2).
resources = append(resources, map[string]any{
"id": BusMembershipID(), "type": "file", "path": BusMembershipPath,
"sealed": with.BusMembership, "mode": "0600",
})
}
return Composed{Resources: resources, Owner: owner}, nil
}
// BusMembershipID names the resource carrying a machine's membership for the new bus, and
// BusMembershipPath is where the host reads it — the same constant on both sides.
func BusMembershipID() string { return "bus-membership" }
const BusMembershipPath = "/var/lib/mesh/membership-next.json"
func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[string]any, error) {
// Every manifest is placed first (novox/hq ADR 0112): the maps naming where its bindings,
// credentials and contributions land are resolved against this node's directories, so every
@@ -623,9 +604,6 @@ 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 {
@@ -711,18 +689,6 @@ 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)
}
@@ -1625,76 +1591,3 @@ 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
}
// **A hyphen, not a dot.** A resource's id is `<module>.<its own id>`, and a module's name may
// itself contain a dot (`novox.be`), so the module is everything before the *last* dot — which
// only works if what the mesh derives adds no dot of its own.
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
}
-44
View File
@@ -114,47 +114,3 @@ func TestCanHoldJudgesClaimScopeAndWhatTheSeatDelivers(t *testing.T) {
t.Fatalf("with the row saying amqp, an amqp provider was refused: %v", err)
}
}
// A machine being moved is handed its membership for the new bus as a sealed file in its own
// declaration — the machine's, not any module's (design 28, task 5.2).
func TestAMembershipForTheNewBusIsComposedAsASealedFile(t *testing.T) {
r := Resolution{Node: "anchor"}
got, err := r.Compose(Rendering{BusMembership: "sealed-blob"})
if err != nil {
t.Fatal(err)
}
var found map[string]any
for _, res := range got.Resources {
if res["id"] == BusMembershipID() {
found = res
}
}
if found == nil {
t.Fatalf("no membership resource in %v", got.Resources)
}
if found["path"] != BusMembershipPath || found["sealed"] != "sealed-blob" || found["mode"] != "0600" {
t.Fatalf("the membership is not a sealed 0600 file where the host reads it: %v", found)
}
// And a machine not being moved is handed nothing.
got, _ = r.Compose(Rendering{})
for _, res := range got.Resources {
if res["id"] == BusMembershipID() {
t.Fatal("a machine with no membership on record was handed one")
}
}
}
// The store's seat rows have no protocol columns yet; loading them must not drop the protocol the
// bus is derived from, or no role's work queue is ever raised (found live, 2026-09-28).
func TestAStoreRowWithoutAProtocolKeepsTheCompiledOne(t *testing.T) {
was := Seats()
t.Cleanup(func() { UseSeats(was) })
UseSeats([]Seat{{Name: "mesh-build-machine", Scope: ScopeMesh, Decision: "row"}})
got, ok := SeatNamed("mesh-build-machine")
if !ok || len(got.Accepts) == 0 {
t.Fatalf("the build machine's seat lost what it accepts when loaded from the store: %+v", got)
}
if got.Decision != "row" {
t.Fatalf("the store's own columns were not kept: %+v", got)
}
}
-24
View File
@@ -225,19 +225,6 @@ 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
@@ -1289,17 +1276,6 @@ 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
-141
View File
@@ -1,141 +0,0 @@
package catalogue
import (
"encoding/json"
"fmt"
"strings"
"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)
}
// A module's name may contain a dot, so a resource's module is everything before the last one —
// which the derived id must not add to, or a machine reads the wrong owner from it.
if strings.Count("gitea.runtime-prepare", ".") != 1 {
t.Fatal("the derived id adds a dot, so what owns it cannot be read from it")
}
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")
}
}
+5 -1
View File
@@ -13,6 +13,7 @@ func TestASeatPlaceholderAnswersWhereThisMachinePutTheHolder(t *testing.T) {
"type": "container", "id": "server", "name": "mesh-controller",
"env": map[string]any{
"MESH_STORE_INVENTORY_PORT": "${seat:mesh-store:5432}",
"MESH_BROKER_AMQP_PORT": "${seat:mesh-broker:5672}",
"MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}",
"MESH_STORE_INVENTORY_FILE": "/run/secrets/inventory",
},
@@ -26,6 +27,7 @@ func TestASeatPlaceholderAnswersWhereThisMachinePutTheHolder(t *testing.T) {
env := control["env"].(map[string]any)
for key, want := range map[string]string{
"MESH_STORE_INVENTORY_PORT": "6852",
"MESH_BROKER_AMQP_PORT": "5679",
"MESH_BROKER_ADDRESS_PORT": "5671",
"MESH_STORE_INVENTORY_FILE": "/run/secrets/inventory",
} {
@@ -144,6 +146,7 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
"MESH_STORE_INVENTORY_PORT": "6852",
"MESH_STORE_IDENTITY_PORT": "6852",
"MESH_STORE_LICENCES_PORT": "6852",
"MESH_BROKER_AMQP_PORT": "5679",
"MESH_BROKER_MANAGEMENT_PORT": "15673",
"MESH_BROKER_ADDRESS_PORT": "5671",
} {
@@ -161,7 +164,7 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
t.Fatal(err)
}
env, _ = fileNamed(out, "mesh-controller.server")["env"].(map[string]any)
if env["MESH_STORE_INVENTORY_PORT"] != "" {
if env["MESH_STORE_INVENTORY_PORT"] != "" || env["MESH_BROKER_AMQP_PORT"] != "" {
t.Errorf("with no settings, the control plane is told %v", env)
}
}
@@ -172,6 +175,7 @@ var SeatPorts = map[string]string{
"MESH_STORE_INVENTORY_PORT": "${seat:mesh-store:5432}",
"MESH_STORE_IDENTITY_PORT": "${seat:mesh-store:5432}",
"MESH_STORE_LICENCES_PORT": "${seat:mesh-store:5432}",
"MESH_BROKER_AMQP_PORT": "${seat:mesh-broker:5672}",
"MESH_BROKER_MANAGEMENT_PORT": "${seat:mesh-broker:15672}",
"MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}",
}
+2 -23
View File
@@ -109,30 +109,9 @@ func DefaultSeats() []Seat { return append([]Seat(nil), defaultSeats...) }
// than running on the set the binary shipped with. So the store can only ever *replace* the set with
// a non-empty one, never erase it.
func UseSeats(s []Seat) {
if len(s) == 0 {
return
if len(s) > 0 {
seats = s
}
// **The store's rows carry no protocol yet, and the protocol is what the bus is derived
// from.** ADR 0129 gives a seat what it accepts, emits and serves; ADR 0122 moved the set into
// a table that has name, scope, delivers and decision and nothing else, and the columns for
// the rest are not there yet. So a row replacing a compiled entry would silently drop the
// protocol, and the roles' work queues would never be raised — found live as "no response
// from stream" the first time a build was submitted over the new bus (2026-09-28). Until the
// table gains the columns, a row without a protocol keeps the compiled one of the same name.
byName := map[string]Seat{}
for _, d := range defaultSeats {
byName[d.Name] = d
}
merged := make([]Seat, 0, len(s))
for _, row := range s {
if len(row.Accepts)+len(row.Emits)+len(row.Serves) == 0 {
if d, known := byName[row.Name]; known {
row.Accepts, row.Emits, row.Serves = d.Accepts, d.Emits, d.Serves
}
}
merged = append(merged, row)
}
seats = merged
}
// aliases maps a seat's former names to its current canonical name (novox/hq ADR 0122). Loaded from
+3 -89
View File
@@ -36,21 +36,12 @@ type Build struct {
// Against is every artifact this build stood on, as references rather than module names —
// what makes a build edge derived rather than declared (ADR 0009).
Against []string
// Read is every repository this build read source from besides the module's own (novox/hq
// 04-ISSUES/131), at the ref it read.
Read []ReadRepository
// Failed is the builder's own words, empty when it worked.
Failed string
Made []Artifact
At time.Time
}
// ReadRepository is a repository a build read source from besides the module's own.
type ReadRepository struct {
Repository string `json:"repository"`
Ref string `json:"ref,omitempty"`
}
// Artifact is one thing a build published.
type Artifact struct {
Name string `json:"name"`
@@ -75,21 +66,17 @@ func (i *Inventory) RecordBuild(ctx context.Context, b Build) error {
if err != nil {
return err
}
read, err := json.Marshal(b.Read)
if err != nil {
return err
}
var module *string
if b.Module != "" {
module = &b.Module
}
_, 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)
values ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12)
source_path, manifest, built_against)
values ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11)
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)
return err
}
@@ -177,79 +164,6 @@ func (i *Inventory) Held(ctx context.Context) (map[string]string, error) {
return held, rows.Err()
}
// BuiltAgainst is what each module's newest successful build stood on, as recorded — the build
// edges (ADR 0009). A module whose last build recorded no bases is absent, which is also what a
// module standing on nothing looks like: an edge the mesh has not derived is not an edge.
func (i *Inventory) BuiltAgainst(ctx context.Context) (map[string][]string, error) {
rows, err := i.store.Pool().Query(ctx,
`select distinct on (module) module, built_against
from build
where module is not null and module <> '' and failed = ''
order by module, at desc`)
if err != nil {
return nil, err
}
defer rows.Close()
against := map[string][]string{}
for rows.Next() {
var module string
var raw []byte
if err := rows.Scan(&module, &raw); err != nil {
return nil, err
}
if len(raw) == 0 {
continue
}
var refs []string
if err := json.Unmarshal(raw, &refs); err != nil {
continue
}
if len(refs) > 0 {
against[module] = refs
}
}
return against, rows.Err()
}
// ReadRepositories is what each module's newest successful build read source from besides its own
// repository, by module name.
//
// The mirror of BuiltAgainst, and derived the same way and for the same reason: a merge into a
// repository a module only packages is a change to that module, and the manifest the mesh keeps
// carries nothing that would say so (novox/hq 04-ISSUES/131).
func (i *Inventory) ReadRepositories(ctx context.Context) (map[string][]ReadRepository, error) {
rows, err := i.store.Pool().Query(ctx,
`select distinct on (module) module, built_contexts
from build
where module is not null and module <> '' and failed = ''
order by module, at desc`)
if err != nil {
return nil, err
}
defer rows.Close()
read := map[string][]ReadRepository{}
for rows.Next() {
var module string
var raw []byte
if err := rows.Scan(&module, &raw); err != nil {
return nil, err
}
if len(raw) == 0 {
continue
}
var of []ReadRepository
if err := json.Unmarshal(raw, &of); err != nil {
continue
}
if len(of) > 0 {
read[module] = of
}
}
return read, rows.Err()
}
// manifestOrNil keeps the difference between "declared nothing" and "predates this being kept".
//
// A build recorded before the mesh kept manifests has no manifest, and that is not the same as one
-33
View File
@@ -136,36 +136,3 @@ func ids(builds []Build) []string {
}
return out
}
// What a build read besides its module's own repository comes back for the newest build of each
// module, and only for builds that worked. Nothing recorded is absent rather than empty, which is how
// a build made before the mesh kept this is told from one that read nothing (novox/hq 04-ISSUES/131).
func TestWhatABuildReadComesBackForTheNewestBuildOfEachModule(t *testing.T) {
inv := fresh(t)
ctx := context.Background()
older := aBuild("older", "builder", "")
older.Read = []ReadRepository{{Repository: "novox/mesh-controller", Ref: "release"}}
newer := aBuild("newer", "builder", "")
newer.Read = []ReadRepository{{Repository: "novox/mesh-controller", Ref: "main"}}
plain := aBuild("plain", "gitea", "")
failed := aBuild("failed", "route-proxy", "cannot clone")
failed.Read = []ReadRepository{{Repository: "novox/mesh-controller", Ref: "main"}}
for _, b := range []Build{older, newer, plain, failed} {
if err := inv.RecordBuild(ctx, b); err != nil {
t.Fatal(err)
}
}
read, err := inv.ReadRepositories(ctx)
if err != nil {
t.Fatal(err)
}
if len(read["builder"]) != 1 || read["builder"][0].Ref != "main" {
t.Fatalf("the newest build's reading is %+v", read["builder"])
}
if _, has := read["gitea"]; has {
t.Fatalf("a build that read nothing but its own repository reads as %+v", read["gitea"])
}
if _, has := read["route-proxy"]; has {
t.Fatal("a failed build's reading was kept as what that module reads")
}
}
+1 -3
View File
@@ -86,11 +86,9 @@ func TestAnAssignedModuleBecomesAUserWithWhatItDeclared(t *testing.T) {
if err != nil {
t.Fatal(err)
}
// Its tools are every one under its own name — the list in the manifest is a person's
// vocabulary for asking, not the module's permission to answer.
if !granted(perms.Publish, "mesh.mod.shop.event.order.placed") ||
!granted(perms.Publish, "mesh.seat.telegram-sender.accept.send") ||
!granted(perms.Subscribe, "mesh.mod.shop.tool.>") {
!granted(perms.Subscribe, "mesh.mod.shop.tool.price") {
t.Fatalf("one.shop's authority is not what it declared: %+v", perms)
}
}
-32
View File
@@ -230,35 +230,3 @@ func (i *Inventory) ForgetPerson(ctx context.Context, name string) error {
}
return i.ForgetBusUser(ctx, "person."+name)
}
// PutBusMembership records a machine's membership for the new bus, sealed to it (design 28, 5.2).
// Replaces any earlier one: a machine has one membership per bus, and re-minting is re-telling.
func (i *Inventory) PutBusMembership(ctx context.Context, nodeName, sealed string) error {
node, err := i.NodeByName(ctx, nodeName)
if err != nil {
return err
}
_, err = i.store.Pool().Exec(ctx,
`insert into bus_membership (node, sealed) values ($1, $2)
on conflict (node) do update set sealed = excluded.sealed, since = now()`, node.ID, sealed)
return err
}
// BusMemberships is every machine's sealed membership for the new bus, by node name.
func (i *Inventory) BusMemberships(ctx context.Context) (map[string]string, error) {
rows, err := i.store.Pool().Query(ctx,
`select n.name, b.sealed from bus_membership b join node n on n.id = b.node`)
if err != nil {
return nil, err
}
defer rows.Close()
out := map[string]string{}
for rows.Next() {
var name, sealed string
if err := rows.Scan(&name, &sealed); err != nil {
return nil, err
}
out[name] = sealed
}
return out, rows.Err()
}
+2 -10
View File
@@ -8,7 +8,6 @@ import (
"sort"
"strconv"
"strings"
"time"
"github.com/jackc/pgx/v5"
"github.com/novox/mesh-controller/internal/catalogue"
@@ -39,9 +38,6 @@ type Source struct {
BuiltFrom string
// Head is the newest commit the source is known to have.
Head string
// Seen is when the source was last looked at — by a build, by hand, or by the forge saying it
// moved. What a late report of an older move is judged against.
Seen time.Time
}
// Current reports whether what the mesh holds is what the source last had.
@@ -940,13 +936,12 @@ func (i *Inventory) Catalogued(ctx context.Context) ([]Entry, error) {
`select m.name, m.manifest,
coalesce(m.source, ''), m.source_path, m.source_seat, coalesce(m.ref, ''),
coalesce(m.built_from, ''), coalesce(m.source_head, ''),
coalesce(m.source_seen, to_timestamp(0)),
coalesce(array_agg(n.name order by n.name) filter (where n.name is not null), '{}')
from module m
left join assignment a on a.module = m.name
left join node n on n.id = a.node
group by m.name, m.manifest, m.source, m.source_path, m.source_seat, m.ref, m.built_from,
m.source_head, m.source_seen
m.source_head
order by m.name`)
if err != nil {
return nil, err
@@ -960,12 +955,9 @@ func (i *Inventory) Catalogued(ctx context.Context) ([]Entry, error) {
var source Source
var on []string
if err := rows.Scan(&name, &raw, &source.Repository, &source.Path, &source.Seat, &source.Ref,
&source.BuiltFrom, &source.Head, &source.Seen, &on); err != nil {
&source.BuiltFrom, &source.Head, &on); err != nil {
return nil, err
}
if source.Seen.Unix() == 0 {
source.Seen = time.Time{}
}
var m catalogue.Manifest
if err := json.Unmarshal(raw, &m); err != nil {
return nil, err
+12 -12
View File
@@ -30,12 +30,12 @@ func TestRefusedAndFailedAreDifferentSituations(t *testing.T) {
refuser := nodeNamed(t, inv, "refuser")
failer := nodeNamed(t, inv, "failer")
if _, err := inv.RecordDoing(ctx, refuser, Doing{
if err := inv.RecordDoing(ctx, refuser, Doing{
Outcome: OutcomeRefused, Refused: "resource \"x\": a file needs a path",
}); err != nil {
t.Fatal(err)
}
if _, err := inv.RecordDoing(ctx, failer, Doing{
if err := inv.RecordDoing(ctx, failer, Doing{
Outcome: OutcomeFailed,
Failed: []FailedResource{{ID: "svc", Error: "unit not found"}},
Applied: 4,
@@ -70,7 +70,7 @@ func TestAMachineDoingWhatItWasToldIsNotOnTheList(t *testing.T) {
inv := fresh(t)
ctx := context.Background()
id := nodeNamed(t, inv, "fine")
if _, err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 6}); err != nil {
if err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 6}); err != nil {
t.Fatal(err)
}
wrong, err := inv.NotDoingWhatTheyWereTold(ctx)
@@ -97,12 +97,12 @@ func TestTheLastReportReplacesTheOneBefore(t *testing.T) {
inv := fresh(t)
ctx := context.Background()
id := nodeNamed(t, inv, "recovered")
if _, err := inv.RecordDoing(ctx, id, Doing{
if err := inv.RecordDoing(ctx, id, Doing{
Outcome: OutcomeFailed, Failed: []FailedResource{{ID: "a", Error: "no"}},
}); err != nil {
t.Fatal(err)
}
if _, err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 3}); err != nil {
if err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 3}); err != nil {
t.Fatal(err)
}
wrong, err := inv.NotDoingWhatTheyWereTold(ctx)
@@ -141,7 +141,7 @@ func TestWhatANodeSaidGoesWhenTheNodeDoes(t *testing.T) {
inv := fresh(t)
ctx := context.Background()
id := nodeNamed(t, inv, "leaving")
if _, err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeFailed}); err != nil {
if err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeFailed}); err != nil {
t.Fatal(err)
}
if _, err := inv.store.Pool().Exec(ctx, `delete from node where name = 'leaving'`); err != nil {
@@ -257,7 +257,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
id := nodeNamed(t, inv, "looping")
same := Doing{Outcome: OutcomeFailed, Failed: []FailedResource{{ID: "img", Error: "no such image"}}}
if _, err := inv.RecordDoing(ctx, id, same); err != nil {
if err := inv.RecordDoing(ctx, id, same); err != nil {
t.Fatal(err)
}
first, _, err := inv.DoingOf(ctx, "looping")
@@ -269,7 +269,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
}
for range StuckAfter - 1 {
if _, err := inv.RecordDoing(ctx, id, same); err != nil {
if err := inv.RecordDoing(ctx, id, same); err != nil {
t.Fatal(err)
}
}
@@ -287,7 +287,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
// The same resource failing with different words — a duration, a counter — is still the same
// failure: it is the resource that loops, not the sentence.
reworded := Doing{Outcome: OutcomeFailed, Failed: []FailedResource{{ID: "img", Error: "no such image (after 31s)"}}}
if _, err := inv.RecordDoing(ctx, id, reworded); err != nil {
if err := inv.RecordDoing(ctx, id, reworded); err != nil {
t.Fatal(err)
}
still, _, err := inv.DoingOf(ctx, "looping")
@@ -300,7 +300,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
// A different failure is a new situation, not a longer one.
other := Doing{Outcome: OutcomeFailed, Failed: []FailedResource{{ID: "svc", Error: "unit not found"}}}
if _, err := inv.RecordDoing(ctx, id, other); err != nil {
if err := inv.RecordDoing(ctx, id, other); err != nil {
t.Fatal(err)
}
changed, _, err := inv.DoingOf(ctx, "looping")
@@ -312,7 +312,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
}
// And a clean apply clears it: the machine is doing what it was told, since nothing.
if _, err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 2}); err != nil {
if err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 2}); err != nil {
t.Fatal(err)
}
fine, _, err := inv.DoingOf(ctx, "looping")
@@ -324,7 +324,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
}
// The list of what is wrong carries the count, so `status` can say it.
if _, err := inv.RecordDoing(ctx, id, same); err != nil {
if err := inv.RecordDoing(ctx, id, same); err != nil {
t.Fatal(err)
}
wrong, err := inv.NotDoingWhatTheyWereTold(ctx)
-17
View File
@@ -80,20 +80,3 @@ func TestUnassigningTheHolderTakesTheHoldingWithIt(t *testing.T) {
t.Fatalf("the holding outlived the assignment it pointed at: %+v", held)
}
}
func TestAMachinesMembershipIsOneRowReplacedAndGoesWithTheMachine(t *testing.T) {
inv, ctx := twoBrokersOnTwoNodes(t)
if err := inv.PutBusMembership(ctx, "anchor", "first"); err != nil {
t.Fatal(err)
}
if err := inv.PutBusMembership(ctx, "anchor", "second"); err != nil {
t.Fatal(err)
}
got, err := inv.BusMemberships(ctx)
if err != nil {
t.Fatal(err)
}
if got["anchor"] != "second" || len(got) != 1 {
t.Fatalf("a re-told membership did not replace the first: %v", got)
}
}
@@ -1,11 +0,0 @@
-- A machine already enrolled is moved to the new bus by being told its membership for it
-- (novox/hq design 28, task 5.2). Until this, a membership — bus address, fingerprint, password,
-- transport — existed only in the enrolment reply, and nothing could hand one to a machine that
-- had already joined. The row is the membership sealed to that machine, composed into its
-- declaration as a file it reads after applying; the plaintext exists once, at minting, and then
-- only on the machine. One per node: the mesh moves to one bus.
create table bus_membership (
node uuid primary key references node(id) on delete cascade,
sealed text not null,
since timestamptz not null default now()
);
@@ -1,13 +0,0 @@
-- A build says which repositories it read, so a merge can find everything it affects.
--
-- A module is built from the one repository the mesh records — where its module.json lives — and some
-- modules' recipes reach into a second for the source they package: the packaging and the source are
-- allowed to live apart (catalogue's ArtifactContext). That second repository is named in the manifest
-- the build read, and the manifest the mesh *keeps* carries no build section, so nothing on the mesh
-- could say that a merge into the other repository is a change to this module at all. Two modules are
-- built from the control plane's own repository, and neither had ever been rebuilt when it moved
-- (novox/hq 04-ISSUES/131).
--
-- Nullable, like the two derived columns beside it: null is a build recorded before the mesh kept
-- this, which is not the same as a build that read nothing but its module's own repository.
alter table build add column built_contexts jsonb;
+18 -29
View File
@@ -670,39 +670,31 @@ func sameFailure(a, b Doing) bool {
// a clean apply clears both (novox/hq 04-ISSUES/065). The previous row is read first and the
// comparison made here, so "the same" is a rule this package states rather than a jsonb equality
// that would restart the count on a changed word in an error.
// **And whether this report was news**, which is what makes a fact about it worth stating (novox/hq
// ADR 0134). A machine reconciles continuously and reports each time; the same outcome about the same
// declaration is the same state said again, and a fact per report would be a fact per minute per
// machine that tells nobody anything. Read here because the previous row is read here anyway.
func (i *Inventory) RecordDoing(ctx context.Context, node string, d Doing) (news bool, err error) {
func (i *Inventory) RecordDoing(ctx context.Context, node string, d Doing) error {
failed, err := json.Marshal(d.Failed)
if err != nil {
return false, err
}
var before Doing
var beforeFailed []byte
found := i.store.Pool().QueryRow(ctx,
`select outcome, refused, failed, failing_since, failures, coalesce(declared,'')
from node_report where node = $1`,
node).Scan(&before.Outcome, &before.Refused, &beforeFailed, &before.Since, &before.Times,
&before.Declared)
switch {
case errors.Is(found, pgx.ErrNoRows):
news = true
case found != nil:
return false, found
default:
if err := json.Unmarshal(beforeFailed, &before.Failed); err != nil {
return false, err
}
news = before.Outcome != d.Outcome || before.Declared != d.Declared || !sameFailure(before, d)
return err
}
var since *time.Time
times := 0
if d.Outcome != OutcomeApplied {
var before Doing
var beforeFailed []byte
err := i.store.Pool().QueryRow(ctx,
`select outcome, refused, failed, failing_since, failures from node_report where node = $1`,
node).Scan(&before.Outcome, &before.Refused, &beforeFailed, &before.Since, &before.Times)
switch {
case errors.Is(err, pgx.ErrNoRows):
case err != nil:
return err
default:
if err := json.Unmarshal(beforeFailed, &before.Failed); err != nil {
return err
}
}
now := time.Now()
since, times = &now, 1
if found == nil && sameFailure(before, d) && before.Since != nil {
if err == nil && sameFailure(before, d) && before.Since != nil {
since, times = before.Since, before.Times+1
}
}
@@ -715,10 +707,7 @@ func (i *Inventory) RecordDoing(ctx context.Context, node string, d Doing) (news
declared = excluded.declared,
failing_since = excluded.failing_since, failures = excluded.failures`,
node, d.Outcome, d.Refused, failed, d.Applied, d.Declared, since, times)
if err != nil {
return false, err
}
return news, nil
return err
}
// NotDoingWhatTheyWereTold is every machine whose last report was not a clean apply.
+62 -24
View File
@@ -3,13 +3,16 @@ package link
import (
"context"
"encoding/json"
"errors"
"fmt"
"time"
"github.com/nats-io/nats.go"
amqp "github.com/rabbitmq/amqp091-go"
)
// RPCExchange is where a module's tools are asked over the broker, keyed `<module>.<tool>`, and
// where the answer comes back, keyed by the asker's reply queue (novox/hq ADR 0047).
const RPCExchange = "mesh.rpc"
// Answer is what a module's tool replies: one of the two, never both.
type Answer struct {
Result json.RawMessage `json:"result,omitempty"`
@@ -24,35 +27,70 @@ type Answer struct {
// grants, and should not. The control plane already holds a connection that may, so a person or
// an agent asks through it, and every question passes one process where an audit belongs.
//
// The answer comes back on the asker's own inbox, which only the asker may read; the serving
// module answers there and nowhere else. The bus refuses a request nothing serves at once, so a
// module that is down or a tool that does not exist is said now rather than after the whole wait.
func Ask(ctx context.Context, bus Bus, module, tool string, args json.RawMessage,
// The reply queue is the caller's own, server-named and exclusive, bound to the RPC exchange under
// its own name: a serving module answers through that exchange and never the default one, whose
// permission is per exchange rather than per queue. The correlation is checked rather than
// assumed, as every RPC here is.
func Ask(ctx context.Context, channel *amqp.Channel, module, tool string, args json.RawMessage,
timeout time.Duration) (Answer, error) {
if len(args) == 0 {
args = json.RawMessage(`{}`)
}
key := module + "." + tool
reply, err := bus.AskTool(ctx, module, tool, args, timeout)
replies, err := channel.QueueDeclare("", false, true, true, false, nil)
if err != nil {
if errors.Is(err, nats.ErrNoResponders) {
return Answer{}, fmt.Errorf(
"nothing serves %s: no runtime has bound %q on the bus. The module is not "+
"assigned, its runtime is not up, or it serves no such tool — `status` says "+
"whether the machine carrying it has applied", module, key)
}
if errors.Is(err, context.DeadlineExceeded) || errors.Is(err, nats.ErrTimeout) {
return Answer{}, fmt.Errorf(
"%s did not answer within %s. Its runtime serves %q when it is up and has bound "+
"the bus — `status` says whether the machine carrying it has applied",
module, timeout, key)
}
return Answer{}, err
}
if err := channel.QueueBind(replies.Name, replies.Name, RPCExchange, false, nil); err != nil {
return Answer{}, fmt.Errorf("cannot bind a reply queue to %s: %w", RPCExchange, err)
}
answers, err := channel.ConsumeWithContext(ctx, replies.Name, "", true, true, false, false, nil)
if err != nil {
return Answer{}, err
}
// Mandatory, so a request nothing consumes comes straight back: a module that is down, or a
// tool that does not exist, is said at once rather than after the whole wait.
returned := channel.NotifyReturn(make(chan amqp.Return, 1))
id := fmt.Sprintf("ask-%d", time.Now().UnixNano())
key := module + "." + tool
if err := channel.PublishWithContext(ctx, RPCExchange, key, true, false, amqp.Publishing{
ContentType: "application/json",
CorrelationId: id,
ReplyTo: replies.Name,
Body: args,
}); err != nil {
return Answer{}, fmt.Errorf("cannot ask %s: %w", key, err)
}
var answer Answer
if err := json.Unmarshal(reply, &answer); err != nil {
return Answer{}, fmt.Errorf("%s answered with something unreadable: %w", key, err)
waiting, cancel := context.WithTimeout(ctx, timeout)
defer cancel()
for {
select {
case back := <-returned:
if back.CorrelationId == id {
return Answer{}, fmt.Errorf(
"nothing serves %s: no runtime has bound %q on the broker. The module is not "+
"assigned, its runtime is not up, or it serves no such tool — `status` "+
"says whether the machine carrying it has applied", module, key)
}
case <-waiting.Done():
return Answer{}, fmt.Errorf(
"%s did not answer within %s. Its runtime serves %q when it is up and has bound "+
"the broker — `status` says whether the machine carrying it has applied",
module, timeout, key)
case delivery, ok := <-answers:
if !ok {
return Answer{}, fmt.Errorf("the connection closed while waiting for %s", key)
}
if delivery.CorrelationId != id {
continue
}
var answer Answer
if err := json.Unmarshal(delivery.Body, &answer); err != nil {
return Answer{}, fmt.Errorf("%s answered with something unreadable: %w", key, err)
}
return answer, nil
}
}
return answer, nil
}
+94 -13
View File
@@ -1,7 +1,12 @@
package link
import (
"context"
"encoding/json"
"fmt"
"time"
amqp "github.com/rabbitmq/amqp091-go"
)
// Asking a machine to build a module, and hearing what came out.
@@ -17,6 +22,21 @@ 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).
// BuildQueue is where build requests wait. One queue, so several build machines can share the
// work and each request is done exactly once — which is what a queue is for and what a
// per-machine routing key would not give.
const BuildQueue = "builds"
// KeyBuilt is what a builder publishes when it has finished, successfully or not.
const KeyBuilt = "built"
// ReplyQueue is where the answer to one request goes.
//
// **Named here rather than left to the broker**, so it can be scoped and reasoned about. A broker
// generates its own name for an unnamed queue, and a builder permitted to write to whatever that
// convention happens to produce works on one broker and silently cannot answer on another.
func ReplyQueue(id string) string { return BuildQueue + ".reply." + id }
// 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
@@ -88,26 +108,87 @@ type BuildResult struct {
// (novox/hq ADR 0009). The catalogue turns these into edges; nothing else need care.
Against []string `json:"against,omitempty"`
// Read is every repository this build read source from besides the module's own. A module whose
// recipe packages source that lives elsewhere is affected when that repository moves, and the
// manifest the mesh keeps says nothing about it (novox/hq 04-ISSUES/131).
Read []ReadRepository `json:"read,omitempty"`
// Failed is why, when it did.
Failed string `json:"failed,omitempty"`
}
// ReadRepository is a repository a build read source from besides the module's own, at the branch,
// tag or commit it read. Spelled here as well as in the catalogue and the inventory, for the reason
// MadeArtifact is: one direction of dependency.
type ReadRepository struct {
Repository string `json:"repository"`
Ref string `json:"ref,omitempty"`
}
// MadeArtifact is one thing a build produced, as a person would want it reported.
type MadeArtifact struct {
Name string `json:"name"`
Kind string `json:"kind"`
Reference string `json:"reference"`
}
// RequestBuild asks for a module to be built and waits for the answer.
//
// Waiting rather than returning immediately, because the thing a person wants after asking for a
// build is to know whether it worked. A build that is dispatched and forgotten needs somewhere to
// look afterwards, and there is nowhere yet.
func RequestBuild(ctx context.Context, channel *amqp.Channel, request BuildRequest,
timeout time.Duration) (BuildResult, error) {
// Its own queue for the answer, declared before the ask. Consuming from the shared exchange
// would mean competing with the control plane's own consumer for a message meant for this
// caller — which is the fault this package's own doc comment records having had.
replies, err := channel.QueueDeclare(ReplyQueue(request.ID), false, true, true, false, nil)
if err != nil {
return BuildResult{}, err
}
// Bound to the exchange, and the answer comes back through it.
//
// **A builder never publishes to the default exchange**, because permission there is per
// exchange and not per queue — a builder allowed to use it could publish into any node's
// queue, which is the privilege a build machine most obviously should not have. Found by
// running it: the builder built, could not answer, and the connection closed saying only
// "not allowed to publish to exchange ''".
//
// The cost is that every asker sees every result, which is why the correlation is checked
// below rather than assumed.
if err := channel.QueueBind(replies.Name, KeyBuilt, Exchange, false, nil); err != nil {
return BuildResult{}, err
}
answers, err := channel.ConsumeWithContext(ctx, replies.Name, "", true, true, false, false, nil)
if err != nil {
return BuildResult{}, err
}
body, err := json.Marshal(request)
if err != nil {
return BuildResult{}, err
}
if err := channel.PublishWithContext(ctx, "", BuildQueue, false, false, amqp.Publishing{
ContentType: "application/json",
DeliveryMode: amqp.Persistent,
CorrelationId: request.ID,
ReplyTo: replies.Name,
Body: body,
}); err != nil {
return BuildResult{}, err
}
waiting, cancel := context.WithTimeout(ctx, timeout)
defer cancel()
for {
select {
case <-waiting.Done():
return BuildResult{}, fmt.Errorf(
"no builder answered within %s. Something must be consuming %q, and nothing is "+
"— or it is building something that takes longer than this",
timeout, BuildQueue)
case delivery, ok := <-answers:
if !ok {
return BuildResult{}, fmt.Errorf("the connection closed while waiting for a build")
}
var result BuildResult
if err := json.Unmarshal(delivery.Body, &result); err != nil {
return BuildResult{}, fmt.Errorf("a builder answered with something unreadable: %w", err)
}
if result.ID != request.ID {
// Somebody else's answer on this queue. Ignored rather than returned, because
// returning it would attribute one build's outcome to another's.
continue
}
return result, nil
}
}
}
+202
View File
@@ -0,0 +1,202 @@
package link
import (
"context"
"encoding/json"
"errors"
"fmt"
"time"
amqp "github.com/rabbitmq/amqp091-go"
)
// The build flow on the bus the mesh runs on today.
//
// Moved behind the seam rather than changed. The queue, the reply binding and the correlation are
// what they were, because the mesh is running on this.
// currentBuilds asks for builds over a channel.
type currentBuilds struct{ channel *amqp.Channel }
// BuildsOverCurrent is the asking side on the bus the mesh has.
func BuildsOverCurrent(channel *amqp.Channel) Builders { return currentBuilds{channel: channel} }
func (b currentBuilds) Close() {}
func (b currentBuilds) Submit(ctx context.Context, request BuildRequest,
wait time.Duration) (BuildResult, error) {
// Its own queue for the answer, declared before the ask. Consuming from the shared exchange
// would mean competing with the controller's own consumer for a message meant for this caller.
replies, err := b.channel.QueueDeclare(ReplyQueue(request.ID), false, true, true, false, nil)
if err != nil {
return BuildResult{}, err
}
// **A builder never publishes to the default exchange**, because permission there is per
// exchange and not per queue — a builder allowed to use it could publish into any node's queue,
// which is the privilege a build machine most obviously should not have. The cost is that every
// asker sees every result, which is why the correlation is checked below rather than assumed.
if err := b.channel.QueueBind(replies.Name, KeyBuilt, Exchange, false, nil); err != nil {
return BuildResult{}, err
}
answers, err := b.channel.ConsumeWithContext(ctx, replies.Name, "", true, true, false, false, nil)
if err != nil {
return BuildResult{}, err
}
body, err := json.Marshal(request)
if err != nil {
return BuildResult{}, err
}
if err := b.channel.PublishWithContext(ctx, "", BuildQueue, false, false, amqp.Publishing{
ContentType: "application/json",
DeliveryMode: amqp.Persistent,
CorrelationId: request.ID,
ReplyTo: replies.Name,
Body: body,
}); err != nil {
return BuildResult{}, err
}
waiting, cancel := context.WithTimeout(ctx, wait)
defer cancel()
for {
select {
case <-waiting.Done():
return BuildResult{}, waitingFor(wait)
case delivery, ok := <-answers:
if !ok {
return BuildResult{}, errors.New("the connection closed while waiting for a build")
}
result, mine, err := theOutcomeOf(delivery.Body, request.ID)
if err != nil {
return BuildResult{}, err
}
if mine {
return result, nil
}
}
}
}
// --- the machine's side ---------------------------------------------------------------------
type currentMachine struct {
conn *amqp.Connection
channel *amqp.Channel
on string
}
// MachineOverCurrent takes build work over a channel.
func MachineOverCurrent(conn *amqp.Connection, channel *amqp.Channel, on string) BuildMachine {
return &currentMachine{conn: conn, channel: channel, on: on}
}
func (m *currentMachine) Close() {}
func (m *currentMachine) Take(ctx context.Context, do func(context.Context, Build)) error {
if _, err := m.channel.QueueDeclare(BuildQueue, true, false, false, false, nil); err != nil {
return err
}
// One at a time. A machine that took five requests at once would run five container builds
// against one runtime and finish all of them slower than it would have finished the first — and
// the queue is what shares work between machines, so nothing is lost by it.
if err := m.channel.Qos(1, 0, false); err != nil {
return err
}
// Not auto-acknowledged: a request acknowledged on arrival is a build that vanishes if this
// process dies mid-way, with nobody waiting on it ever hearing why.
requests, err := m.channel.ConsumeWithContext(ctx, BuildQueue, "mesh-builder",
false, false, false, false, nil)
if err != nil {
return err
}
for {
select {
case <-ctx.Done():
return nil
case delivery, ok := <-requests:
if !ok {
return errors.New("the broker closed the connection")
}
var request BuildRequest
if err := json.Unmarshal(delivery.Body, &request); err != nil {
// Unreadable: rejected rather than retried, because the next attempt reads the same
// bytes. Nobody waiting hears an answer, which is correct — there was no request.
_ = delivery.Reject(false)
continue
}
do(ctx, &currentBuild{request: request, delivery: delivery, on: m.on, channel: m.channel})
}
}
}
type currentBuild struct {
request BuildRequest
delivery amqp.Delivery
on string
channel *amqp.Channel
}
func (b *currentBuild) Request() BuildRequest { return b.request }
// Announce answers and announces, which on this bus are two publishes to two exchanges.
//
// The reply goes to whoever asked, correlated to their request; the announcement says to the whole
// mesh that a module now exists at a commit (novox/hq ADR 0072). Only a successful build is
// announced: a failed one produced no module version, and announcing one would put something in the
// graph that was never made.
func (b *currentBuild) Announce(ctx context.Context, result BuildResult) error {
body, err := json.Marshal(result)
if err != nil {
return err
}
if err := b.channel.PublishWithContext(ctx, Exchange, KeyBuilt, false, false, amqp.Publishing{
ContentType: "application/json",
CorrelationId: result.ID,
Body: body,
}); err != nil {
return fmt.Errorf("cannot answer a build request: %w", err)
}
if result.Failed != "" || result.Commit == "" {
return nil
}
// **Announced under both names on this bus, for exactly as long as this bus lives.**
//
// A build's outcome belongs to the role now (novox/hq ADR 0121), so a catalogue built from the
// current manifests listens for the role's name. A catalogue that is *already running* listens for
// the module's, because that is what it was told when it was installed. A rename on a live bus
// needs the publisher and the subscriber to change together, and a merge cannot promise that: one
// of them is deployed first, and in that window the graph silently stops being updated — which is
// the failure this whole change was cleaning up after.
//
// So both, and the order stops mattering. The module's own name goes with the bus, in step 5's
// retirement list; nothing has ever run on the bus being built, so there is no legacy name there
// and this doubling has no counterpart.
announced := announcementOf(result)
if err := EmitEvent(ctx, OverCurrent{Channel: b.channel}, KeyModuleBuilt, "builder", b.on,
announced); err != nil {
return err
}
return EmitEvent(ctx, OverCurrent{Channel: b.channel}, KeyRoleBuilt, TheBuildMachine, b.on,
announced)
}
func (b *currentBuild) Done() error { return b.delivery.Ack(false) }
func (b *currentBuild) Hold(time.Duration) error {
// No delayed redelivery on this bus: handed back at once, which is what it has always done.
return b.delivery.Nack(false, true)
}
// announcementOf is what the mesh is told about a finished build. One function, so the two
// transports cannot describe the same build differently.
func announcementOf(result BuildResult) map[string]any {
return map[string]any{
"module": ModuleOf(result.Manifest), "commit": result.Commit,
"repository": result.Repository, "path": result.Path, "ref": result.Ref,
"manifest": json.RawMessage(result.Manifest), "against": result.Against,
"made": result.Made,
}
}
+46 -33
View File
@@ -7,6 +7,7 @@ import (
"time"
"github.com/nats-io/nats.go"
amqp "github.com/rabbitmq/amqp091-go"
)
// Bus is what the controller needs of the mesh's bus, **in the mesh's own words rather than a
@@ -30,11 +31,6 @@ type Bus interface {
// (design 29 §4, the *state* shape).
PublishDeclaration(ctx context.Context, node string, body []byte) error
// PublishSeatEvent states a fact under a role's own name, for the holder of that role. A
// module's event is addressed to the module; a role's is addressed to the role, so it keeps
// meaning when the holder changes (novox/hq ADR 0121, ADR 0129).
PublishSeatEvent(ctx context.Context, seat, event string, body []byte) error
// AskTool sends one question to a module's tool and awaits one answer. A tool nobody serves
// must say so **at once** rather than after the whole wait: the difference between "that
// module is down" and "that tool is slow" is the first thing a person asking wants.
@@ -43,6 +39,51 @@ type Bus interface {
// --- The bus the mesh runs on today -----------------------------------------------------
// OverCurrent is the bus the mesh runs on today, until the rollout.
type OverCurrent struct{ Channel *amqp.Channel }
func (b OverCurrent) PublishEvent(ctx context.Context, key, source, node string, body []byte) error {
id, err := eventID()
if err != nil {
return err
}
return b.Channel.PublishWithContext(ctx, EventsExchange, key, false, false, amqp.Publishing{
ContentType: "application/json",
DeliveryMode: amqp.Persistent,
MessageId: id,
Timestamp: time.Now().UTC(),
Body: body,
Headers: amqp.Table{
"x-event-id": id,
"x-source": source,
"x-node": node,
"x-time": time.Now().UTC().Format(time.RFC3339),
"content-type": "application/json",
},
})
}
// AskTool is implemented over the existing reply-queue machinery in ask.go; this seam does not
// change how it works today.
func (b OverCurrent) AskTool(ctx context.Context, module, tool string, args []byte, timeout time.Duration) ([]byte, error) {
answer, err := Ask(ctx, b.Channel, module, tool, args, timeout)
if err != nil {
return nil, err
}
return answer.Result, nil
}
func (b OverCurrent) PublishDeclaration(ctx context.Context, node string, body []byte) error {
// To the queue directly rather than through an exchange: a declaration is for one node, and
// routing it by name through a shared exchange would mean a binding per node that nothing
// removes when a node is retired.
return b.Channel.PublishWithContext(ctx, "", QueueFor(node), false, false, amqp.Publishing{
ContentType: "application/json",
DeliveryMode: amqp.Persistent,
Body: body,
})
}
// --- NATS, the bus being built ----------------------------------------------------------------
// OverNATS is the bus as a JetStream context.
@@ -86,13 +127,6 @@ func EventSubject(source, key string) string {
return "mesh.mod." + source + ".event." + key
}
// SeatEventSubject is where a role's own event lands. Derived from the role, never from its holder:
// a fact about the build machine or about the control plane keeps its address when the module holding
// that role is replaced (novox/hq ADR 0121, ADR 0129).
func SeatEventSubject(seat, event string) string {
return "mesh.seat." + seat + ".event." + event
}
// DeclareSubject is where one node's declaration lands. Last-per-subject on the NODES stream, so
// a node that was away gets exactly the current one and a replayed older one is refused by
// sequence — the wire-level answer to novox/hq issue 107.
@@ -124,27 +158,6 @@ func (b OverNATS) PublishEvent(ctx context.Context, key, source, node string, bo
return nil
}
// PublishSeatEvent states a role's own fact. Same envelope as a module's event and a different
// address: the source header is the role, because that is what the fact is about.
func (b OverNATS) PublishSeatEvent(ctx context.Context, seat, event string, body []byte) error {
id, err := eventID()
if err != nil {
return err
}
h := nats.Header{}
h.Set("x-event-id", id)
h.Set("x-source", seat)
_, err = b.JS.PublishMsg(&nats.Msg{
Subject: SeatEventSubject(seat, event),
Header: h,
Data: body,
}, nats.MsgId(id), nats.Context(ctx))
if err != nil {
return fmt.Errorf("stating %s of the %s seat: %w", event, seat, err)
}
return nil
}
func (b OverNATS) PublishDeclaration(ctx context.Context, node string, body []byte) error {
_, err := b.JS.Publish(DeclareSubject(node), body, nats.Context(ctx))
if err != nil {
-23
View File
@@ -1,23 +0,0 @@
package link
import (
"github.com/novox/mesh-controller/internal/broker"
)
// ConnectNats is Connect for the bus being built: the controller's inbound and outbound over one
// JetStream connection the caller has already raised the streams on. Nothing is declared here —
// the streams and the controller's consumers are asserted by Raise, before anything is served.
func ConnectNats(js *broker.JetStream, enroller Enroller, listener Listener) *Server {
return &Server{
inbound: Nats(js),
bus: OverNATS{JS: js.Context(), Conn: js.Conn()},
js: js,
enroller: enroller,
listener: listener,
log: newLog(),
}
}
// Bus is the controller's outbound, whichever transport it connected over. Callers that send a
// declaration or ask a tool use this rather than the channel, which one transport does not have.
func (s *Server) Bus() Bus { return s.bus }
+31 -19
View File
@@ -24,9 +24,10 @@ import (
// — it holds both grants and asks each for its part, which is what the process running them is
// for.
type Enrolment struct {
Inventory *inventory.Inventory
Identity *identity.Identity
Broker broker.Broker
Inventory *inventory.Inventory
Identity *identity.Identity
Management *broker.Management
Broker broker.Broker
// OnNATS says the mesh's own traffic is on the bus being built, so a node's credential is
// minted into the mesh's records and composed into the bus's user list rather than pushed
@@ -193,6 +194,17 @@ func (e Enrolment) Enrol(ctx context.Context, request EnrolRequest) (reply Enrol
reply.Password = password
}
case e.Management != nil:
password, err := freshPassword()
if err != nil {
return EnrolReply{}, err
}
if err := e.Management.CreateNodeAccount(ctx, node.Name, password); err != nil {
log.Printf("%s is enrolled and its broker password could not be replaced, so it keeps "+
"the token's secret as its password: %v", node.Name, err)
} else {
reply.Password = password
}
}
if profile != nil {
@@ -249,6 +261,9 @@ func freshPassword() (string, error) {
var _ Enroller = Enrolment{}
// ErrNoBrokerManagement is returned when an account cannot be made because nothing was configured.
var ErrNoBrokerManagement = errors.New("no broker management configured")
// Heard records what a node reported about itself.
//
// A node states; the owning context writes (novox/hq ADR 0006). What a node says it applied is
@@ -265,7 +280,7 @@ func (e Enrolment) Outstanding(ctx context.Context, node string) (string, error)
return e.Inventory.Outstanding(ctx, node)
}
func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err error) {
func (e Enrolment) Heard(ctx context.Context, report Report) (err error) {
// A store that could not be asked right now is said as such, so the report is kept for
// another attempt rather than acknowledged and lost (novox/hq issue 082).
defer func() {
@@ -274,11 +289,11 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err err
}
}()
if report.Node == "" {
return false, errors.New("a report named no node")
return errors.New("a report named no node")
}
node, err := e.Inventory.NodeByName(ctx, report.Node)
if err != nil {
return false, err
return err
}
// What an adopted node holds, which firewall it found, and what is reachable on it (novox/hq
@@ -298,7 +313,7 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err err
Port: r.Port, By: r.By, Published: r.Published, ContainerPort: r.ContainerPort})
}
if err := e.Inventory.RecordAdoption(ctx, node.ID, held, report.Firewall, reachable); err != nil {
return false, err
return err
}
}
// What it says about the tunnel it carried (novox/hq ADR 0105), whenever it says it.
@@ -308,7 +323,7 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err err
Peers: report.Tunnel.Peers, State: report.Tunnel.State, Note: report.Tunnel.Note,
Kept: report.Tunnel.Kept,
}); err != nil {
return false, err
return err
}
}
// A node taking a found tunnel's key after enrolment (novox/hq ADR 0105). Verified against the
@@ -317,9 +332,9 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err err
// does not verify or is stale — a refusal, not "not now", so the node hears why.
if report.Rekey != nil {
if err := e.rekey(ctx, node, *report.Rekey); err != nil {
return false, err
return err
}
return false, e.Inventory.Seen(ctx, node.ID)
return e.Inventory.Seen(ctx, node.ID)
}
// A bare word that a node is there is not an account of what the machine did or holds: it
@@ -334,7 +349,7 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err err
if report.Superseded != "" {
log.Printf("%s set aside declaration %s for the newer %s", report.Node, report.Declared, report.Superseded)
}
return false, e.Inventory.Seen(ctx, node.ID)
return e.Inventory.Seen(ctx, node.ID)
}
// What it did is kept whichever way it went. Until this, a refusal or a failure moved
// last_seen and the reason went to a log line, so "which machine is not doing what it was
@@ -361,20 +376,17 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err err
// on top of it (novox/hq ADR 0038). Kept even when the declaration was refused: what the
// machine carries is true regardless of what it thought of the last thing it was sent.
if err := e.Inventory.RecordCarried(ctx, report.Node, report.Carried); err != nil {
return false, err
return err
}
// **Whether this is news** is the store's answer: it holds the previous report, and a machine
// that reconciles every minute says the same thing until something changes (novox/hq ADR 0134).
news, err = e.Inventory.RecordDoing(ctx, node.ID, doing)
if err != nil {
return false, err
if err := e.Inventory.RecordDoing(ctx, node.ID, doing); err != nil {
return err
}
// A refusal, a failure, or a bare word that the node is there — none of them is an account of
// what the machine holds, so each moves last_seen and nothing else. Recording a partial list
// as though it were the whole would tell a rebuilding node to remove what it still has.
if report.Refused != "" || len(report.Failed) > 0 || report.Applied == nil {
return news, e.Inventory.Seen(ctx, node.ID)
return e.Inventory.Seen(ctx, node.ID)
}
return news, e.Inventory.RecordOwned(ctx, node.ID, report.Applied)
return e.Inventory.RecordOwned(ctx, node.ID, report.Applied)
}
-58
View File
@@ -49,39 +49,6 @@ func eventID() (string, error) {
return hex.EncodeToString(raw), nil
}
// MeshControllerSeat is the role the control plane holds, and therefore where its own facts live: a
// role's events belong to the role, not to whichever container is holding it today (novox/hq ADR 0121,
// ADR 0129). It is what makes them addressable while the control plane itself is being replaced.
const MeshControllerSeat = "mesh-controller"
// The facts the mesh states about its own work (novox/hq ADR 0134).
const (
// KeyApplied: a machine now runs what it was sent.
KeyApplied = "applied"
// KeyRefused: a machine did not take what it was sent, and why.
KeyRefused = "refused"
// KeyBuiltBefore: a build the mesh already held, for a catalogue that asked what it missed. Not
// `built` — that is the build machine's, said as it happens, and a replay is neither.
KeyBuiltBefore = "built-before"
)
// Applied is what a machine now runs, as the mesh states it.
type Applied struct {
Node string `json:"node"`
Declared string `json:"declared,omitempty"`
// Resources is how many the machine applied, not which: the list is the machine's own account
// of itself and belongs in the records, not in a fact every listener has to read past.
Resources int `json:"resources"`
}
// Refused is a machine that would not take what it was sent.
type Refused struct {
Node string `json:"node"`
Declared string `json:"declared,omitempty"`
Refused string `json:"refused,omitempty"`
Failed map[string]string `json:"failed,omitempty"`
}
// KeyModuleBuilt is what the builder announces when it has built something. The catalogue places
// it in the module graph; nothing else need care.
const KeyModuleBuilt = "module.builder.built"
@@ -150,31 +117,6 @@ type Announcement struct {
}
// Upgraded is what the catalogue says when a module's current version moves.
// SourceMoved is what the forge announces when a pull request is merged: which repository, into
// which branch, producing which commit. The mesh matches it against every module's recorded
// source and builds what moved, bases first.
type SourceMoved struct {
Owner string `json:"owner"`
Repo string `json:"repo"`
Base string `json:"base"`
Head string `json:"head"`
Commit string `json:"merge_commit_sha"`
CloneURL string `json:"clone_url"`
HTMLURL string `json:"html_url"`
// MergedAt is when the forge merged it, RFC 3339. What decides whether this is news.
MergedAt string `json:"merged_at"`
// Paths are the files the merge changed, from the repository's root. Empty means the forge said
// nothing about them, and every module built from the repository is treated as affected.
Paths []string `json:"paths,omitempty"`
// PathsTruncated says the merge changed more files than the forge was asked to list, so Paths is
// a beginning rather than the whole change — and again, everything is treated as affected. Said
// rather than inferred from a round number, because "this is all of it" and "this is as much as
// I asked for" are the difference between rebuilding a module and leaving it stale.
PathsTruncated bool `json:"paths_truncated,omitempty"`
}
type Upgraded struct {
Module string `json:"module"`
Commit string `json:"commit"`
+6 -6
View File
@@ -22,7 +22,7 @@ func heardFrom(t *testing.T, report link.Report) (*inventory.Inventory, inventor
if _, err := inv.AddNode(ctx, report.Node); err != nil {
t.Fatal(err)
}
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, report); err != nil {
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, report); err != nil {
t.Fatal(err)
}
doing, said, err := inv.DoingOf(ctx, report.Node)
@@ -103,7 +103,7 @@ func TestABareAliveDoesNotWipeTheDeclarationThatSaysANodeIsCurrent(t *testing.T)
if err := inv.RecordSent(ctx, node.ID, digest); err != nil {
t.Fatal(err)
}
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{
Node: "anchor", Applied: []string{"a", "b"}, Declared: digest, Carried: []int{5432},
}); err != nil {
t.Fatal(err)
@@ -126,7 +126,7 @@ func TestABareAliveDoesNotWipeTheDeclarationThatSaysANodeIsCurrent(t *testing.T)
}
// Now the node says only that it is there, as it does every minute.
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor"}); err != nil {
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor"}); err != nil {
t.Fatal(err)
}
if !currentOf("anchor") {
@@ -162,7 +162,7 @@ func TestAFailureDoesNotBecomeTheAccountOfWhatTheMachineHolds(t *testing.T) {
if err := inv.RecordOwned(ctx, node.ID, []string{"one", "two", "three"}); err != nil {
t.Fatal(err)
}
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{
Node: "workstation", Applied: []string{"one"}, Failed: map[string]string{"two": "no"},
}); err != nil {
t.Fatal(err)
@@ -200,13 +200,13 @@ func TestWhatAnAdoptedNodeHoldsIsKeptAndAnAliveWordDoesNotWipeIt(t *testing.T) {
}
check("after the report")
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor"}); err != nil {
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor"}); err != nil {
t.Fatal(err)
}
check("after an alive word")
// A reconcile report carrying only adoption is recorded, though it applied nothing.
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor",
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor",
Firewall: "ufw"}); err != nil {
t.Fatal(err)
}
+13 -3
View File
@@ -30,9 +30,6 @@ const (
KindHeartbeat = "heartbeat"
KindBuilt = "built"
KindModuleMoved = "module-moved"
// KindSourceMoved is the forge announcing a merge: a source moved, and what it produces is
// built without anybody telling the mesh (novox/hq 04-ISSUES/131).
KindSourceMoved = "source-moved"
KindCatchUp = "catch-up"
)
@@ -78,6 +75,19 @@ type Control interface {
// Took settles the message: acted on, or understood and needing no action.
Took() error
// About names what this message is about — a node's report, one module's move, one build's
// outcome — and is said before the store is asked.
//
// A transport that holds messages **in memory** uses it to set aside anything older it is
// holding about the same thing: the older is the past, and letting it come back after the
// newer was acted on would undo the newer.
//
// **This is the one thing holding-in-memory can do that holding-in-the-server cannot**, and
// naming it here rather than hiding it is deliberate. On the bus being built the message
// belongs to the server and comes back whatever happened meanwhile, so this is ignored and the
// digest a report carries answers the same question instead (window.go, design 25 §3).
About(what string)
// Hold keeps the message and asks for it again after the delay — the store window.
Hold(after time.Duration) error
+317
View File
@@ -0,0 +1,317 @@
package link
import (
"context"
"errors"
"fmt"
"time"
amqp "github.com/rabbitmq/amqp091-go"
)
// The consume side on the bus the mesh runs on today.
//
// Everything here was the serving loop's until the seam went in: the queues, the binds, the
// prefetch, and the list of messages the store could not take yet. It moved rather than changed —
// the behaviour this transport has is the behaviour it had, because the mesh is running on it and
// a bus nothing speaks yet is no reason to alter the one every node is on (ADR 0116).
// Prefetch is how many messages the bus hands the controller before it has settled them.
//
// More than one because a message the store could not take is held, unsettled, while the loop
// goes on answering others — an enrolment above all, which a host is waiting on (novox/hq issue
// 083). Bounded, because what is held is also what the bus has not kept on its own disk as
// pending.
const Prefetch = 64
// PrefetchHeadroom is how much of the prefetch is never held, so the loop always has messages to
// answer — an enrolment above all — while others wait for the store.
const PrefetchHeadroom = 8
// TryAgainAfter is how often the held are looked at. A store comes back in seconds, and a report a
// few seconds late is still current.
const TryAgainAfter = 2 * time.Second
// currentInbound consumes what nodes say over the bus the mesh has.
type currentInbound struct {
conn *amqp.Connection
channel *amqp.Channel
// upgrades and catchups are bound only when something is listening (Also).
upgrades bool
catchups bool
// held is every message the store could not take, by the bus's own delivery tag. Kept here
// rather than in the serving loop because holding a delivery unacknowledged is this
// transport's way of keeping it, and the other's is to hand it back to the server.
held map[uint64]*holding
// again is how often the held are looked at; zero means TryAgainAfter. Set by tests.
again time.Duration
}
// holding is one message kept for the store, and when to try it again.
type holding struct {
message *currentControl
due time.Time
about string
}
// Current is the consume side of the bus the mesh runs on today.
func Current(conn *amqp.Connection, channel *amqp.Channel) Inbound {
return &currentInbound{conn: conn, channel: channel, held: map[uint64]*holding{}}
}
// Also binds the queue one more kind arrives on.
//
// The kinds nodes publish all share one queue and are bound at Connect, because a node may
// publish any of them and binding one while forgetting another is a message the bus accepts, finds
// no queue for, and drops — the publisher sees success and the consumer sees nothing. The two that
// are events get their own queue each, and only when something is listening.
func (c *currentInbound) Also(kind string) error {
switch kind {
case KindModuleMoved:
if err := c.bindEvent(UpgradeQueue, KeyModuleUpgraded); err != nil {
return err
}
c.upgrades = true
case KindCatchUp:
if err := c.bindEvent(CatchUpQueue, KeyCatchingUp); err != nil {
return err
}
c.catchups = true
default:
return fmt.Errorf("nothing binds a queue for %s on this bus", kind)
}
return nil
}
func (c *currentInbound) bindEvent(queue, key string) error {
if _, err := c.channel.QueueDeclare(queue, true, false, false, false, nil); err != nil {
return fmt.Errorf("cannot declare the %s queue: %w", queue, err)
}
if err := c.channel.QueueBind(queue, key, EventsExchange, false, nil); err != nil {
return fmt.Errorf("cannot bind %s to %s/%s: %w", queue, EventsExchange, key, err)
}
return nil
}
func (c *currentInbound) Close() {}
// Receive consumes until the context ends.
//
// One consumer per queue, deliberately: with two on one queue the bus would round-robin between
// them and each would receive half of what it expects — a fault this project has already had,
// between a module's daemon and its capability server.
func (c *currentInbound) Receive(ctx context.Context, act func(context.Context, Control)) error {
// A bounded prefetch rather than one. The loop still takes messages one at a time; what the
// prefetch buys is that a message the store could not take can be held while the loop goes on
// to the next, instead of every enrolment waiting behind it (novox/hq issue 083). Anything
// held goes back to the bus if the controller stops, because nothing held is acknowledged.
if err := c.channel.Qos(Prefetch, 0, false); err != nil {
return err
}
deliveries, err := c.channel.ConsumeWithContext(ctx, ControlQueue, "control-plane",
false, false, false, false, nil)
if err != nil {
return err
}
// Its own queue and its own consumer for each event, for the reason above: two consumers on
// one queue split its messages between them, and an upgrade or a catch-up request going to
// whichever half was not listening is a gap that looks like a working mesh.
var upgrades, catchups <-chan amqp.Delivery
if c.upgrades {
upgrades, err = c.channel.ConsumeWithContext(ctx, UpgradeQueue, "control-plane-upgrades",
false, false, false, false, nil)
if err != nil {
return err
}
}
if c.catchups {
catchups, err = c.channel.ConsumeWithContext(ctx, CatchUpQueue, "control-plane-catchup",
false, false, false, false, nil)
if err != nil {
return err
}
}
closed := c.conn.NotifyClose(make(chan *amqp.Error, 1))
again := c.again
if again == 0 {
again = TryAgainAfter
}
ticker := time.NewTicker(again)
defer ticker.Stop()
for {
select {
case <-ctx.Done():
return nil
case <-ticker.C:
if ctx.Err() != nil {
return nil
}
c.retryHeld(ctx, act)
case delivery, ok := <-catchups:
if !ok {
if catchups != nil {
return errors.New("the bus stopped delivering catch-up requests")
}
continue
}
act(ctx, c.wrap(KindCatchUp, delivery))
case delivery, ok := <-upgrades:
// A nil channel blocks for ever, so this case simply never fires when nothing is
// listening for upgrades. Closed is different, and means the bus stopped.
if !ok {
if upgrades != nil {
return errors.New("the bus stopped delivering upgrades")
}
continue
}
act(ctx, c.wrap(KindModuleMoved, delivery))
case reason := <-closed:
// Said rather than returned quietly. A controller whose bus connection dropped is a
// mesh where nothing can be told anything, and the reason is the first thing anybody
// will want.
return fmt.Errorf("the bus connection closed: %v", reason)
case delivery, ok := <-deliveries:
if !ok {
return errors.New("the bus stopped delivering")
}
kind, known := kindOfKey[delivery.RoutingKey]
if !known {
// Rejected without requeue: a message nothing understands will not be understood
// on the next attempt either, and requeuing it would spin.
_ = delivery.Reject(false)
continue
}
act(ctx, c.wrap(kind, delivery))
}
}
}
// kindOfKey is how this transport's addressing becomes what the mesh calls a message.
var kindOfKey = map[string]string{
KeyEnrol: KindEnrolment,
KeyReport: KindReport,
KeyAlive: KindHeartbeat,
KeyBuilt: KindBuilt,
KeyModuleUpgraded: KindModuleMoved,
KeyCatchingUp: KindCatchUp,
}
func (c *currentInbound) wrap(kind string, delivery amqp.Delivery) *currentControl {
return &currentControl{kind: kind, delivery: delivery, on: c}
}
// retryHeld hands every message whose delay has passed back to the loop. Each handler holds it
// again, settles it, or lets it go past the bound.
func (c *currentInbound) retryHeld(ctx context.Context, act func(context.Context, Control)) {
now := time.Now()
due := make([]*currentControl, 0, len(c.held))
for _, h := range c.held {
if !h.due.After(now) {
due = append(due, h.message)
}
}
for _, m := range due {
if ctx.Err() != nil {
return
}
act(ctx, m)
}
}
// currentControl is one delivery from the bus the mesh has, as the controller reads it.
type currentControl struct {
kind string
delivery amqp.Delivery
on *currentInbound
// about is what this message is about, as the handler named it; empty until it does.
about string
// first is when this message was first held for the store; zero while it has not been.
first time.Time
}
func (m *currentControl) Kind() string { return m.kind }
func (m *currentControl) Body() []byte { return m.delivery.Body }
func (m *currentControl) Redelivered() bool { return m.delivery.Redelivered }
func (m *currentControl) HeldFor() time.Duration {
if m.first.IsZero() {
return 0
}
return time.Since(m.first)
}
// Answer publishes to the reply queue the request named.
func (m *currentControl) Answer(ctx context.Context, body []byte) error {
if m.delivery.ReplyTo == "" {
return errors.New("that request named no reply queue, so nothing can be told the answer")
}
return m.on.channel.PublishWithContext(ctx, "", m.delivery.ReplyTo, false, false,
amqp.Publishing{
ContentType: "application/json",
CorrelationId: m.delivery.CorrelationId,
Body: body,
})
}
func (m *currentControl) Took() error {
m.forget()
return m.delivery.Ack(false)
}
// Drop rejects without requeue: on this bus that is what "understood, and not worth another
// attempt" is spelled as, and it is what feeds a dead-letter queue where one is configured.
func (m *currentControl) Drop() error {
m.forget()
return m.delivery.Reject(false)
}
// About names what this message is about, and lets go of whatever is held about the same thing:
// the held one is the past, and acting on it after this one would undo this one. Acknowledged
// rather than left to come back, because a held message nothing will act on is a place in the
// prefetch nothing gets back.
func (m *currentControl) About(what string) {
m.about = what
if what == "" {
return
}
for tag, h := range m.on.held {
if h.about != what || tag == m.delivery.DeliveryTag {
continue
}
delete(m.on.held, tag)
_ = h.message.delivery.Ack(false)
}
}
// Hold keeps the message unacknowledged and sets it aside to be handed back after the delay.
//
// Held no further than the prefetch leaves room: past that the bus would hand the loop nothing
// new — enrolments included — until something held was let go. A message that cannot be held says
// so, and the handler settles it its own way.
func (m *currentControl) Hold(after time.Duration) error {
if m.on.held == nil {
m.on.held = map[uint64]*holding{}
}
if _, already := m.on.held[m.delivery.DeliveryTag]; !already {
if len(m.on.held) >= Prefetch-PrefetchHeadroom {
return fmt.Errorf("%d messages are already held for the store, and holding more "+
"would stop the queue", len(m.on.held))
}
m.first = time.Now()
}
m.on.held[m.delivery.DeliveryTag] = &holding{
message: m, due: time.Now().Add(after), about: m.about,
}
return nil
}
func (m *currentControl) forget() {
if m.on != nil {
delete(m.on.held, m.delivery.DeliveryTag)
}
}
+71
View File
@@ -0,0 +1,71 @@
package link
import (
"context"
"encoding/json"
"io"
"log"
"testing"
"time"
amqp "github.com/rabbitmq/amqp091-go"
)
// The harness for the consume side on the bus the mesh runs on today.
//
// Messages arrive through the seam, so what these tests exercise is the controller's decision
// about a message and this transport's way of keeping one — which is what the seam separated. A
// fake acknowledger stands in for the bus, because what is asserted is how a message was settled
// and that needs no server.
// settled is how the bus was told to settle one message.
type settled struct{ acked, nacked, requeued, rejected bool }
func (a *settled) Ack(uint64, bool) error { a.acked = true; return nil }
func (a *settled) Nack(_ uint64, _ bool, requeue bool) error {
a.nacked, a.requeued = true, requeue
return nil
}
func (a *settled) Reject(uint64, bool) error { a.rejected = true; return nil }
// unsettled is a message the controller has neither taken nor let go: it is held, and the bus will
// hand it to whatever consumes next if the controller stops.
func (a *settled) unsettled() bool { return !a.acked && !a.nacked && !a.rejected }
var tag uint64
func quiet() *log.Logger { return log.New(io.Discard, "", 0) }
// serving is a controller with nothing but a way of receiving, ready for a listener, a recorder,
// an upgrader or a replayer to be set on it.
func serving() (*Server, *currentInbound) {
in := &currentInbound{held: map[uint64]*holding{}}
return &Server{inbound: in, bus: OverCurrent{}, log: quiet()}, in
}
// sends is one message arriving over this transport, as the controller reads it.
func (c *currentInbound) sends(t *testing.T, to *settled, kind string, v any) Control {
t.Helper()
body, err := json.Marshal(v)
if err != nil {
t.Fatal(err)
}
tag++
return &currentControl{kind: kind, on: c, delivery: amqp.Delivery{
Acknowledger: to, Body: body, DeliveryTag: tag,
}}
}
// dueNow brings every held message forward, so a test need not wait out the backoff a real store
// restart would be given (RedeliverAfter).
func (c *currentInbound) dueNow() {
for _, h := range c.held {
h.due = time.Now().Add(-time.Second)
}
}
// retries hands every held message back to the controller, the way the ticker does.
func (c *currentInbound) retries(ctx context.Context, s *Server) {
c.dueNow()
c.retryHeld(ctx, s.act)
}
-94
View File
@@ -1,94 +0,0 @@
package link
import (
"context"
"encoding/json"
"testing"
"time"
)
// A harness for the controller's decisions about a message, with no bus behind it.
//
// What these tests exercise is the server's verdict — taken, dropped, held for the store, let go
// once the store has been away too long — and the transport's part in that is only to keep a held
// message and hand it back. A fake that does exactly that stands in for the bus, so what is
// asserted is how a message was settled and the decision needs no server.
// settled is how the bus was told to settle one message.
type settled struct{ acked, nacked, requeued, rejected bool }
// unsettled is a message the controller has neither taken nor let go: it is held, and the bus will
// hand it to whatever consumes next if the controller stops.
func (a *settled) unsettled() bool { return !a.acked && !a.nacked && !a.rejected }
// fakeInbound keeps the messages the controller held, the way a stream would.
type fakeInbound struct{ held map[uint64]*fakeControl }
var tag uint64
// serving is a controller with nothing but a way of receiving, ready for a listener, a recorder,
// an upgrader or a replayer to be set on it.
func serving() (*Server, *fakeInbound) {
in := &fakeInbound{held: map[uint64]*fakeControl{}}
return &Server{inbound: in, log: quiet()}, in
}
func (c *fakeInbound) Also(string) error { return nil }
func (c *fakeInbound) Close() {}
func (c *fakeInbound) Receive(context.Context, func(context.Context, Control)) error {
return nil
}
// sends is one message arriving, as the controller reads it.
func (c *fakeInbound) sends(t *testing.T, to *settled, kind string, v any) Control {
t.Helper()
body, err := json.Marshal(v)
if err != nil {
t.Fatal(err)
}
tag++
return &fakeControl{kind: kind, body: body, tag: tag, to: to, on: c}
}
// retries hands every held message back to the controller, the way a stream redelivers.
func (c *fakeInbound) retries(ctx context.Context, s *Server) {
for tag, m := range c.held {
delete(c.held, tag)
m.redelivered = true
s.act(ctx, m)
}
}
type fakeControl struct {
kind string
body []byte
tag uint64
to *settled
on *fakeInbound
redelivered bool
since time.Time
}
func (m *fakeControl) Kind() string { return m.kind }
func (m *fakeControl) Body() []byte { return m.body }
func (m *fakeControl) Redelivered() bool { return m.redelivered }
func (m *fakeControl) About(string) {}
func (m *fakeControl) Answer(context.Context, []byte) error { return nil }
func (m *fakeControl) Took() error { m.to.acked = true; return nil }
func (m *fakeControl) Drop() error { m.to.rejected = true; return nil }
// HeldFor is how long the store has been waited on for this message — zero on a first delivery.
func (m *fakeControl) HeldFor() time.Duration {
if m.since.IsZero() {
return 0
}
return time.Since(m.since)
}
func (m *fakeControl) Hold(time.Duration) error {
if m.since.IsZero() {
m.since = time.Now()
}
m.on.held[m.tag] = m
return nil
}
+9 -44
View File
@@ -23,10 +23,6 @@ import (
// it first could not take it, and a controller that restarts mid-window has nothing to lose.
// natsInbound consumes what nodes and modules say over NATS.
// Prefetch is how many controls the controller holds unacknowledged at once: the store window
// (ADR 0083) is the server's, and this is what it may hand this process ahead of its acting.
const Prefetch = 64
type natsInbound struct {
js *broker.JetStream
// follows is the kinds asked for beyond what nodes say (Also). The events those are are the
@@ -52,7 +48,7 @@ func Nats(js *broker.JetStream) Inbound {
// whatever was asked for — and not at all when nothing was.
func (n *natsInbound) Also(kind string) error {
switch kind {
case KindModuleMoved, KindCatchUp, KindSourceMoved:
case KindModuleMoved, KindCatchUp:
n.follows[kind] = true
return nil
default:
@@ -154,47 +150,10 @@ func (n *natsInbound) deliver(ctx context.Context, act func(context.Context, Con
m.seq = meta.Sequence.Stream
m.delivered = meta.NumDelivered
}
// **Work that outlives the acknowledgement window says so while it runs.**
//
// The bus waits a fixed time to be told a message was taken, and then hands it to whoever
// consumes next — which is right for a consumer that died and wrong for one that is busy.
// Acting on a merge builds every module the merge changed: minutes of work against a
// thirty-second window. So the same merge was handed over again while the first build was
// still running, and again after that — on 2026-09-28 one merge ran the mesh's whole
// catalogue five times over and exhausted a public registry's pull limit.
//
// Here rather than in each handler, because the window belongs to the transport and every
// handler would otherwise have to remember it. It changes nothing about a handler that
// dies: a message is kept alive only while this goroutine is, so a controller that stops
// stops saying so, and the bus redelivers exactly as it should.
working := make(chan struct{})
defer close(working)
go stillWorking(msg, working)
}
act(ctx, m)
}
// heartbeatWhileWorking is how often a handler still running tells the bus so — comfortably inside
// the shortest acknowledgement window the mesh gives any of its consumers.
const heartbeatWhileWorking = 10 * time.Second
// stillWorking keeps one message alive until the work on it returns.
//
// An error is not worth reporting: what the bus does when it is not told is redeliver, which is
// exactly what happens if this fails, and the handler's own outcome is the thing worth logging.
func stillWorking(msg *nats.Msg, done <-chan struct{}) {
tick := time.NewTicker(heartbeatWhileWorking)
defer tick.Stop()
for {
select {
case <-done:
return
case <-tick.C:
_ = msg.InProgress()
}
}
}
// kindOfSubject is how this transport's addressing becomes what the mesh calls a message.
//
// By subject, which is the only thing the server enforces: a body claiming to be a report does not
@@ -221,8 +180,6 @@ func kindOfSubject(subject string) (string, bool) {
return KindModuleMoved, true
case broker.ControllerFollows[1]:
return KindCatchUp, true
case broker.ControllerFollows[3]:
return KindSourceMoved, true
case BuildOutcome():
// A build's outcome is the role's event now, so it arrives on the events stream rather than
// the control branch — and is acted on by the same handler, because what the controller does
@@ -263,6 +220,14 @@ func (m *natsControl) HeldFor() time.Duration {
return time.Since(first)
}
// About is nothing here, and that is the point.
//
// Setting a held message aside when a newer one about the same thing arrives is what a controller
// holding deliveries in memory can do. A naked message belongs to the server and comes back
// whatever happened meanwhile, so the question "is this the past?" is answered by what the message
// says instead — the digest of the declaration a report is about (window.go, design 25 §3).
func (m *natsControl) About(string) {}
// Answer publishes to the reply subject the request carries **in its payload**.
//
// Not `Respond`, and not the message's reply field: a message a JetStream consumer delivers has had
+5 -188
View File
@@ -4,8 +4,6 @@ import (
"context"
"encoding/json"
"errors"
"io"
"log"
"os"
"sync"
"testing"
@@ -86,15 +84,14 @@ type counted struct {
heard []Report
}
func (c *counted) Heard(_ context.Context, r Report) (bool, error) {
func (c *counted) Heard(_ context.Context, r Report) error {
c.mu.Lock()
defer c.mu.Unlock()
if c.err != nil {
return false, c.err
return c.err
}
c.heard = append(c.heard, r)
// News, so what the mesh states about a report is exercised wherever a report is.
return true, nil
return nil
}
func (c *counted) refusing(err error) {
@@ -123,8 +120,6 @@ func eventually(t *testing.T, what string, is func() bool) {
// A report published by a node reaches the controller, is recorded, and is acknowledged — so the
// stream does not hold it. A work queue is the check: what is acknowledged leaves it.
func quiet() *log.Logger { return log.New(io.Discard, "", 0) }
func TestNatsAReportIsHeardAndLeavesTheStream(t *testing.T) {
js := aBus(t)
store := &counted{}
@@ -208,11 +203,11 @@ type sentAndHeardSafely struct {
heard []Report
}
func (s *sentAndHeardSafely) Heard(_ context.Context, r Report) (bool, error) {
func (s *sentAndHeardSafely) Heard(_ context.Context, r Report) error {
s.mu.Lock()
defer s.mu.Unlock()
s.heard = append(s.heard, r)
return true, nil
return nil
}
func (s *sentAndHeardSafely) Outstanding(context.Context, string) (string, error) {
@@ -379,181 +374,3 @@ func TestNatsAReportIsLetGoOnceTheStoreHasBeenGoneTooLong(t *testing.T) {
t.Fatalf("a report was recorded by a store that never came back")
}
}
// A merge announcement is not what these tests are about; taken and forgotten.
func (t *toldAbout) SourceMoved(context.Context, SourceMoved) error { return nil }
// Every subject the controller follows decodes to a kind, and decoding never reaches past the
// list: the day the list was three long and the decoder named a fourth, every message panicked
// the control plane (2026-09-28).
func TestEverySubjectTheControllerFollowsDecodesToAKind(t *testing.T) {
for _, subject := range broker.ControllerFollows {
if _, ok := kindOfSubject(subject); !ok {
t.Errorf("%s is followed and decodes to nothing", subject)
}
}
if _, ok := kindOfSubject("mesh.mod.nobody.event.nothing"); ok {
t.Error("a subject nobody follows decoded to a kind")
}
}
// **A handler slower than the acknowledgement window is not handed its message again.**
//
// The bus waits a fixed time to be told a message was taken and then redelivers, which is right for
// a consumer that died and wrong for one that is busy. Acting on a merge builds modules — minutes
// against a thirty-second window — and the same merge was handed over five times while the first
// build was still running (2026-09-28). Here the window is two seconds and the work takes six.
func TestNatsWorkSlowerThanTheWindowIsNotHandedOverAgain(t *testing.T) {
js := aBus(t)
// The controller's own consumer, with a window short enough to outlive in a test.
if err := js.EnsureConsumer(broker.Consumer{
Name: broker.ControllerName, Stream: "CONTROL", Push: true, AckWaitSeconds: 2,
Why: "a window short enough to outlive in a test",
}); err != nil {
t.Fatal(err)
}
var mu sync.Mutex
handled := 0
slow := make(chan struct{})
s, stop := servingOn(t, js, nil)
defer stop()
s.listener = slowly{func() {
mu.Lock()
handled++
first := handled == 1
mu.Unlock()
if first {
time.Sleep(6 * time.Second)
close(slow)
}
}}
body, err := json.Marshal(Report{Node: "anchor", Declared: "d1", Applied: []string{"store"}})
if err != nil {
t.Fatal(err)
}
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
t.Fatal(err)
}
select {
case <-slow:
case <-time.After(30 * time.Second):
t.Fatal("the slow work never finished")
}
// A moment for a redelivery to arrive, if the bus were going to send one.
time.Sleep(3 * time.Second)
mu.Lock()
defer mu.Unlock()
if handled != 1 {
t.Fatalf("one report was handled %d times, so slow work is run again while it is running", handled)
}
}
// slowly is a listener that runs whatever it was given.
type slowly struct{ work func() }
func (s slowly) Heard(context.Context, Report) (bool, error) { s.work(); return true, nil }
// **The mesh says what it applied** (novox/hq ADR 0134), under the seat the control plane holds — and
// says nothing when a report is the same state said again, which is what a machine reconciling every
// minute sends.
func TestNatsTheMeshSaysWhatAMachineApplied(t *testing.T) {
js := aBus(t)
heard := make(chan *nats.Msg, 4)
sub, err := js.Conn().Subscribe(SeatEventSubject(MeshControllerSeat, ">"), func(m *nats.Msg) {
heard <- m
})
if err != nil {
t.Fatal(err)
}
defer sub.Unsubscribe() //nolint:errcheck // the subscription dies with the connection
_, stop := servingOn(t, js, &counted{})
defer stop()
// A report that changed something: the store says it was news.
body, err := json.Marshal(Report{Node: "anchor", Declared: "d1", Applied: []string{"store", "broker"}})
if err != nil {
t.Fatal(err)
}
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
t.Fatal(err)
}
select {
case m := <-heard:
if m.Subject != SeatEventSubject(MeshControllerSeat, KeyApplied) {
t.Fatalf("the mesh stated %q", m.Subject)
}
var said Applied
if err := json.Unmarshal(m.Data, &said); err != nil {
t.Fatal(err)
}
if said.Node != "anchor" || said.Declared != "d1" || said.Resources != 2 {
t.Fatalf("it said %+v", said)
}
case <-time.After(10 * time.Second):
t.Fatal("the mesh said nothing about a machine that now runs something else")
}
// A refusal is its own fact, with the reason in it rather than only in a log.
refusal, err := json.Marshal(Report{Node: "anchor", Declared: "d2",
Failed: map[string]string{"gitea.server": "no such image"}})
if err != nil {
t.Fatal(err)
}
if _, err := js.Context().Publish(ReportSubject("anchor"), refusal); err != nil {
t.Fatal(err)
}
select {
case m := <-heard:
if m.Subject != SeatEventSubject(MeshControllerSeat, KeyRefused) {
t.Fatalf("a refusal was stated as %q", m.Subject)
}
var said Refused
if err := json.Unmarshal(m.Data, &said); err != nil {
t.Fatal(err)
}
if said.Failed["gitea.server"] == "" {
t.Fatalf("the refusal does not say which resource or why: %+v", said)
}
case <-time.After(10 * time.Second):
t.Fatal("the mesh said nothing about a machine that refused what it was sent")
}
}
// And a report that is not news is not a fact. A machine reconciles every minute; a fact per report
// would be a fact per minute per machine, which is a stream nobody reads.
func TestNatsAReportThatIsNotNewsIsNotStated(t *testing.T) {
js := aBus(t)
heard := make(chan *nats.Msg, 4)
sub, err := js.Conn().Subscribe(SeatEventSubject(MeshControllerSeat, ">"), func(m *nats.Msg) {
heard <- m
})
if err != nil {
t.Fatal(err)
}
defer sub.Unsubscribe() //nolint:errcheck // the subscription dies with the connection
// A store that records the report and says it was nothing new — which is what the mesh's own
// store says about a machine repeating itself.
_, stop := servingOn(t, js, sameAgain{})
defer stop()
body, err := json.Marshal(Report{Node: "anchor", Declared: "d1", Applied: []string{"store"}})
if err != nil {
t.Fatal(err)
}
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
t.Fatal(err)
}
select {
case m := <-heard:
t.Fatalf("the mesh stated %q about a machine that changed nothing", m.Subject)
case <-time.After(3 * time.Second):
}
}
// sameAgain records a report and says it was the same state said again.
type sameAgain struct{}
func (sameAgain) Heard(context.Context, Report) (bool, error) { return false, nil }
+4 -4
View File
@@ -60,7 +60,7 @@ func TestASignedRekeyMovesTheHubOntoItsTunnel(t *testing.T) {
rekey := &link.Rekey{Previous: ownKey, OverlayKey: tunnelKey, Tunnel: theTunnel()}
rekey.Proof = ed25519.Sign(private, link.RekeyProof("anchor", ownKey, tunnelKey, theTunnel()))
if _, err := e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey}); err != nil {
if err := e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey}); err != nil {
t.Fatal(err)
}
placed, err := e.Inventory.Overlays(ctx)
@@ -77,7 +77,7 @@ func TestASignedRekeyMovesTheHubOntoItsTunnel(t *testing.T) {
_ = hub
// Replayed, it is stale: the previous key it names is no longer the node's.
_, err = e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey})
err = e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey})
if err == nil || !strings.Contains(err.Error(), "previous overlay key") {
t.Fatalf("a replayed rekey was accepted: %v", err)
}
@@ -93,7 +93,7 @@ func TestARekeySignedByAnotherKeyIsRefusedAndChangesNothing(t *testing.T) {
rekey := &link.Rekey{Previous: ownKey, OverlayKey: tunnelKey, Tunnel: theTunnel()}
rekey.Proof = ed25519.Sign(stranger, link.RekeyProof("anchor", ownKey, tunnelKey, theTunnel()))
_, err = e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey})
err = e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey})
if err == nil || !strings.Contains(err.Error(), "not signed by anchor's identity key") {
t.Fatalf("a rekey signed by a stranger was accepted: %v", err)
}
@@ -111,7 +111,7 @@ func TestARekeySignedByAnotherKeyIsRefusedAndChangesNothing(t *testing.T) {
other := theTunnel()
other.Port = 51820
moved.Proof = ed25519.Sign(mustPrivate(t, e, "anchor"), link.RekeyProof("anchor", ownKey, tunnelKey, other))
if _, err := e.Heard(ctx, link.Report{Node: "anchor", Rekey: moved}); err == nil {
if err := e.Heard(ctx, link.Report{Node: "anchor", Rekey: moved}); err == nil {
t.Fatal("a proof over another tunnel was accepted")
}
}
+20 -2
View File
@@ -9,12 +9,12 @@ import (
type heardWith struct{ err error }
func (h heardWith) Heard(context.Context, Report) (bool, error) { return h.err == nil, h.err }
func (h heardWith) Heard(context.Context, Report) error { return h.err }
// switchable answers with whatever it is set to — the store away, then back.
type switchable struct{ err error }
func (h *switchable) Heard(context.Context, Report) (bool, error) { return h.err == nil, h.err }
func (h *switchable) Heard(context.Context, Report) error { return h.err }
func aReport(node, declared string) Report {
return Report{Node: node, Declared: declared, Applied: []string{"store"}}
@@ -46,6 +46,24 @@ func TestAReportTheStoreCouldNotTakeIsHeldAndOneItRefusedIsNot(t *testing.T) {
}
}
// A newer report from the same node supersedes one of its reports still held: recorded after the
// newer, the older would overwrite what the node is doing now.
func TestANewerReportSupersedesAHeldOneFromTheSameNode(t *testing.T) {
s, in := serving()
s.listener = heardWith{err: errors.Join(ErrTryAgain, errors.New("starting up"))}
older, newer, other := &settled{}, &settled{}, &settled{}
s.act(context.Background(), in.sends(t, older, KindReport, aReport("anchor", "d1")))
s.act(context.Background(), in.sends(t, other, KindReport, aReport("laptop", "d7")))
s.act(context.Background(), in.sends(t, newer, KindReport, aReport("anchor", "d2")))
if !older.acked {
t.Fatalf("the older report was not set aside by the newer: %+v", older)
}
if !newer.unsettled() || !other.unsettled() || len(in.held) != 2 {
t.Fatalf("the newer report and another node's were not both held: newer %+v other %+v, %d held",
newer, other, len(in.held))
}
}
// A store that has not come back within the bound is not restarting: the report is let go, loudly,
// rather than held for ever.
func TestAReportIsLetGoOnceTheStoreHasBeenGoneTooLong(t *testing.T) {
+85 -98
View File
@@ -7,10 +7,13 @@ import (
"encoding/json"
"errors"
"fmt"
"github.com/novox/mesh-controller/internal/broker"
"log"
"os"
"time"
amqp "github.com/rabbitmq/amqp091-go"
"github.com/novox/mesh-controller/internal/envfile"
)
// AMQPVar is the controller's own connection to the bus the mesh runs on today.
@@ -29,12 +32,7 @@ type Enroller interface {
// Listener is what the controller does with a report. Separate from Enroller so the two can be
// given independently, and so a server that only sends declarations needs neither.
type Listener interface {
// Heard records what a node said, and says whether it was **news** — a machine that now runs
// something else, or refuses something it did not refuse before. A machine reconciles
// continuously and reports each time, so what is news is the store's answer rather than the
// bus's: only this side has the previous report to compare with. What the mesh states about it
// is the server's (novox/hq ADR 0134).
Heard(ctx context.Context, report Report) (news bool, err error)
Heard(ctx context.Context, report Report) error
}
// Recorder keeps what builders say.
@@ -59,8 +57,6 @@ type Upgrader interface {
// stop every upgrade behind it — except the store unreachable for the moment, which is asked
// again for a bounded time (novox/hq issue 083).
Upgraded(ctx context.Context, u Upgraded) error
// SourceMoved is a merge on the forge: build what that source produces, bases first.
SourceMoved(ctx context.Context, m SourceMoved) error
}
// Server acts on what nodes and modules say.
@@ -72,7 +68,8 @@ type Upgrader interface {
type Server struct {
inbound Inbound
bus Bus
js *broker.JetStream
conn *amqp.Connection
channel *amqp.Channel
enroller Enroller
listener Listener
@@ -102,9 +99,6 @@ func (s *Server) Records(r Recorder) { s.recorder = r }
// Follows says what to do about upgrades, and asks for them to be delivered.
func (s *Server) Follows(u Upgrader) error {
if err := s.inbound.Also(KindSourceMoved); err != nil {
return err
}
if err := s.inbound.Also(KindModuleMoved); err != nil {
return err
}
@@ -126,20 +120,82 @@ func (s *Server) Answers(r Replayer) error {
// On the port MESH_BROKER_AMQP_PORT names when the node's settings moved the broker (novox/hq
// 04-ISSUES/102) — the URL is genesis's, sealed, and its port is the one thing in it the node may
// have moved since.
// Connect is ConnectNats: the mesh has one bus (novox/hq ADR 0131, design 28 task 5.5). Kept as
// the name callers know; the transport it opened before is gone with the bus it spoke to.
func Connect(js *broker.JetStream, enroller Enroller, listener Listener) *Server {
return ConnectNats(js, enroller, listener)
func Connect(enroller Enroller, listener Listener) (*Server, error) {
url, err := envfile.Placed(AMQPVar)
if err != nil {
return nil, err
}
if url == "" {
return nil, fmt.Errorf(
"this control plane has no %s, so it cannot reach its broker. Nodes talk to it over "+
"the broker and nowhere else, so without this it can hold records and answer "+
"nothing", AMQPVar)
}
conn, err := amqp.Dial(url)
if err != nil {
// Not quoted back: the URL carries the controller's own bus password.
return nil, fmt.Errorf("cannot reach the broker named in %s: %w", AMQPVar, err)
}
channel, err := conn.Channel()
if err != nil {
conn.Close()
return nil, err
}
// Declared here rather than assumed. The controller is the only thing that may create them — a
// node's account can write to this exchange and read its own queue, and configure nothing
// else, so a node arriving before the controller has ever run finds nothing and says so,
// rather than quietly creating a topology nobody designed.
if err := channel.ExchangeDeclare(Exchange, "direct", true, false, false, false, nil); err != nil {
conn.Close()
return nil, fmt.Errorf("cannot declare the %s exchange: %w", Exchange, err)
}
// The events exchange too. The controller is not the only publisher on it — modules announce
// onto it with their own accounts — but it is the only thing permitted to create it, for the
// same reason it is the only thing permitted to create the direct one.
if err := channel.ExchangeDeclare(EventsExchange, "topic", true, false, false, false, nil); err != nil {
conn.Close()
return nil, fmt.Errorf("cannot declare the %s exchange: %w", EventsExchange, err)
}
if _, err := channel.QueueDeclare(ControlQueue, true, false, false, false, nil); err != nil {
conn.Close()
return nil, fmt.Errorf("cannot declare the %s queue: %w", ControlQueue, err)
}
// Every key a node may publish. Binding one and forgetting another is a message the bus
// accepts, finds no queue for, and drops — the publisher sees success and the consumer sees
// nothing. That is exactly what happened to reports: `report` was left unbound while `enrol`
// worked, so nodes announced what they had applied into a void for an afternoon.
for _, key := range []string{KeyEnrol, KeyReport, KeyAlive, KeyBuilt} {
if err := channel.QueueBind(ControlQueue, key, Exchange, false, nil); err != nil {
conn.Close()
return nil, fmt.Errorf("cannot bind %s to %s/%s: %w", ControlQueue, Exchange, key, err)
}
}
return &Server{
inbound: Current(conn, channel),
bus: OverCurrent{Channel: channel},
conn: conn,
channel: channel,
enroller: enroller,
listener: listener,
log: log.New(os.Stdout, "", log.LstdFlags),
}, nil
}
func newLog() *log.Logger { return log.New(os.Stdout, "", log.LstdFlags) }
// Channel is the controller's channel, for the command line's own publishing.
func (s *Server) Channel() *amqp.Channel { return s.channel }
func (s *Server) Close() {
if s.inbound != nil {
s.inbound.Close()
}
if s.js != nil {
s.js.Close()
if s.channel != nil {
_ = s.channel.Close()
}
if s.conn != nil {
_ = s.conn.Close()
}
}
@@ -169,8 +225,6 @@ func (s *Server) act(ctx context.Context, m Control) {
s.wasBuilt(ctx, m)
case KindModuleMoved:
s.moved(ctx, m)
case KindSourceMoved:
s.sourceMoved(ctx, m)
case KindCatchUp:
s.catchingUp(ctx, m)
default:
@@ -262,7 +316,7 @@ func (s *Server) heartbeat(m Control) {
return
}
if s.listener != nil {
if _, err := s.listener.Heard(context.Background(), Report{Node: alive.Node}); err != nil {
if err := s.listener.Heard(context.Background(), Report{Node: alive.Node}); err != nil {
s.log.Printf("could not record that %s is here: %v", alive.Node, err)
}
}
@@ -281,6 +335,7 @@ func (s *Server) reported(ctx context.Context, m Control) {
_ = m.Drop()
return
}
m.About("report " + report.Node)
what := fmt.Sprintf("%s's report of declaration %s", report.Node, report.Declared)
if s.listener != nil {
@@ -296,7 +351,7 @@ func (s *Server) reported(ctx context.Context, m Control) {
return
}
news, err := s.listener.Heard(context.Background(), report)
err := s.listener.Heard(context.Background(), report)
switch s.decide(ctx, m, what, declaredIn, outstanding, err) {
case Hold:
// Held, not settled, while the store cannot take it: the node reports an apply once,
@@ -312,13 +367,6 @@ func (s *Server) reported(ctx context.Context, m Control) {
// node whose recovery copy is silently older than it looks.
s.log.Printf("could not record %s's report: %v", report.Node, err)
}
// **And the mesh says what it did** (novox/hq ADR 0134). Only when the report was news: a
// machine reports every convergence, and a fact per report would be a fact per minute per
// machine saying nothing. Stated after it is recorded, so nothing is announced that the
// mesh does not hold.
if err == nil && news {
s.saysWhatItDid(ctx, report)
}
}
switch {
@@ -420,6 +468,9 @@ func (s *Server) wasBuilt(ctx context.Context, m Control) {
_ = m.Drop()
return
}
// Each build result its own subject: none supersedes another, and recording one twice is
// harmless — the build is kept by its id.
m.About("build " + digest(m.Body()))
err := s.recorder.Built(ctx, result)
switch s.decide(ctx, m, fmt.Sprintf("a build result from %s", result.On), "", "", err) {
case Hold:
@@ -451,6 +502,7 @@ func (s *Server) wasBuilt(ctx context.Context, m Control) {
// the catalogue next restarts (issue 083). One request stands for all: a newer one supersedes one
// still held.
func (s *Server) catchingUp(ctx context.Context, m Control) {
m.About("catch-up")
if s.replayer == nil {
s.log.Printf("a catalogue asked to catch up and this control plane has nothing to replay")
_ = m.Took()
@@ -472,19 +524,7 @@ func (s *Server) catchingUp(ctx context.Context, m Control) {
sent := 0
for _, a := range announcements {
a.Replay = true
// Under the control plane's own seat (novox/hq ADR 0134). It used to be published as a
// module's event from a module called "control-plane", which does not exist — so the
// controller's own account refused it, every catalogue that asked what it missed was
// answered with nothing, and its graph kept the gap (found 2026-09-28).
body, err := json.Marshal(a)
if err != nil {
// A body that cannot be written is this program's fault, not the bus's, and publishing
// an empty one would put a fact on the mesh that says nothing.
s.log.Printf("cannot re-announce %s at %s: %v", a.Module, short(a.Commit), err)
_ = m.Took()
return
}
if err := s.bus.PublishSeatEvent(ctx, MeshControllerSeat, KeyBuiltBefore, body); err != nil {
if err := EmitEvent(ctx, s.bus, KeyModuleBuilt, "control-plane", "", a); err != nil {
// Said and abandoned rather than retried: the catalogue asks again every time it
// starts, and half a graph delivered twice is no better than half delivered once.
s.log.Printf("replaying %s at %s failed, and the rest is abandoned: %v",
@@ -515,6 +555,7 @@ func (s *Server) moved(ctx context.Context, m Control) {
_ = m.Took()
return
}
m.About("upgrade " + u.Module)
if u.Module == "" {
s.log.Printf("an upgrade announcement named no module; ignored")
_ = m.Took()
@@ -555,57 +596,3 @@ func short(commit string) string {
}
return commit
}
// sourceMoved acts on the forge's announcement of a merge. Taken whatever happens: a build that
// fails is reported by the build itself, and re-delivering the merge would only re-fail it.
func (s *Server) sourceMoved(ctx context.Context, m Control) {
var moved SourceMoved
if err := json.Unmarshal(m.Body(), &moved); err != nil {
s.log.Printf("a merge announcement could not be read: %v", err)
_ = m.Took()
return
}
if moved.Commit == "" || moved.Repo == "" {
s.log.Printf("a merge announcement named no repository or no commit; ignored")
_ = m.Took()
return
}
if err := s.upgrader.SourceMoved(ctx, moved); err != nil {
s.log.Printf("%s/%s moved to %.8s and the mesh could not act on it: %v", moved.Owner, moved.Repo, moved.Commit, err)
}
_ = m.Took()
}
// saysWhatItDid states what a machine now runs, or what it would not take, as a fact on the bus
// (novox/hq ADR 0134).
//
// **The control plane speaks, as the holder of its seat.** A node's report is control traffic only
// this process may read, so the chain from a merge to a machine went dark exactly where it touched
// one: nothing said which version a machine runs, or that it refused to. The facts are second-hand
// on purpose — one emitter, one ordering — and a machine that cannot reach the bus produces none, so
// absence is not health.
//
// A failure to state a fact is logged and nothing else: the report is recorded, which is the part
// that must not be lost, and the next change says the same thing again.
func (s *Server) saysWhatItDid(ctx context.Context, report Report) {
if s.bus == nil {
return
}
event, body := KeyApplied, any(Applied{
Node: report.Node, Declared: report.Declared, Resources: len(report.Applied),
})
if report.Refused != "" || len(report.Failed) > 0 {
event, body = KeyRefused, Refused{
Node: report.Node, Declared: report.Declared,
Refused: report.Refused, Failed: report.Failed,
}
}
raw, err := json.Marshal(body)
if err != nil {
s.log.Printf("could not say what %s did: %v", report.Node, err)
return
}
if err := s.bus.PublishSeatEvent(ctx, MeshControllerSeat, event, raw); err != nil {
s.log.Printf("could not say that %s %s: %v", report.Node, event, err)
}
}
+3 -3
View File
@@ -23,12 +23,12 @@ type sentAndHeard struct {
err error
}
func (s *sentAndHeard) Heard(_ context.Context, r Report) (bool, error) {
func (s *sentAndHeard) Heard(_ context.Context, r Report) error {
if s.err != nil {
return false, s.err
return s.err
}
s.heard = append(s.heard, r)
return true, nil
return nil
}
func (s *sentAndHeard) Outstanding(context.Context, string) (string, error) { return s.sent, nil }
+48 -2
View File
@@ -3,6 +3,7 @@ package link
import (
"context"
"errors"
"fmt"
"testing"
"github.com/jackc/pgx/v5/pgconn"
@@ -17,8 +18,7 @@ func (r recordsWith) Built(context.Context, BuildResult) error { return r.err }
type upgradesWith struct{ err error }
func (u upgradesWith) Upgraded(context.Context, Upgraded) error { return u.err }
func (u upgradesWith) SourceMoved(context.Context, SourceMoved) error { return u.err }
func (u upgradesWith) Upgraded(context.Context, Upgraded) error { return u.err }
type replaysWith struct{ err error }
@@ -106,3 +106,49 @@ func TestAMessageHandledDuringShutdownIsLeftForTheBus(t *testing.T) {
t.Fatalf("a build result handled during shutdown was settled, and so lost: %+v", *to)
}
}
// Two identical build results: the newer sets the older aside rather than leaving it unsettled
// for ever, holding a place in the prefetch.
func TestAnIdenticalBuildResultSetsTheHeldOneAside(t *testing.T) {
s, in := serving()
s.recorder = recordsWith{err: restarting}
built := BuildResult{On: "anchor", Repository: "/r", Commit: "abc"}
first, second := &settled{}, &settled{}
s.act(context.Background(), in.sends(t, first, KindBuilt, built))
s.act(context.Background(), in.sends(t, second, KindBuilt, built))
if !first.acked || !second.unsettled() || len(in.held) != 1 {
t.Fatalf("an identical build result did not set the held one aside: first %+v second %+v, %d held",
*first, *second, len(in.held))
}
}
// What is held stops short of the prefetch, so the loop always has room to answer an enrolment.
func TestWhatIsHeldLeavesRoomInThePrefetch(t *testing.T) {
s, in := serving()
s.recorder = recordsWith{err: restarting}
var last *settled
for i := 0; i < Prefetch; i++ {
last = &settled{}
s.act(context.Background(), in.sends(t, last, KindBuilt, BuildResult{On: "anchor", Commit: fmt.Sprint(i)}))
}
if len(in.held) != Prefetch-PrefetchHeadroom {
t.Fatalf("%d messages were held; the ceiling is %d", len(in.held), Prefetch-PrefetchHeadroom)
}
if last.unsettled() {
t.Fatalf("a message past the ceiling was held: %+v", *last)
}
}
// An upgrade handled during shutdown is left for the bus too — the upgrader's error is the
// cancelled context, which is no answer about the announcement.
func TestAnUpgradeHandledDuringShutdownIsLeftForTheBus(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
cancel()
s, in := serving()
s.upgrader = upgradesWith{err: context.Canceled}
to := &settled{}
s.act(ctx, in.sends(t, to, KindModuleMoved, Upgraded{Module: "gitea", Commit: "abcdef0123"}))
if !to.unsettled() {
t.Fatalf("an upgrade was settled during shutdown, and so lost: %+v", *to)
}
}
BIN
View File
Binary file not shown.
+4 -6
View File
@@ -23,11 +23,9 @@
"licences": "/var/lib/mesh/mesh-controller/licences",
"broker": "/var/lib/mesh/mesh-controller/broker",
"broker-management": "/var/lib/mesh/mesh-controller/broker-management",
"broker-address": "/var/lib/mesh/mesh-controller/broker-address",
"bus": "/var/lib/mesh/mesh-controller/bus"
"broker-address": "/var/lib/mesh/mesh-controller/broker-address"
},
"secrets-owner": "65534:65534",
"prepares": true,
"resources": [
{
"id": "mesh-state",
@@ -48,14 +46,15 @@
"MESH_STORE_INVENTORY_FILE": "/run/secrets/inventory",
"MESH_STORE_IDENTITY_FILE": "/run/secrets/identity",
"MESH_STORE_LICENCES_FILE": "/run/secrets/licences",
"MESH_BROKER_AMQP_FILE": "/run/secrets/broker",
"MESH_BROKER_MANAGEMENT_FILE": "/run/secrets/broker-management",
"MESH_BROKER_ADDRESS_FILE": "/run/secrets/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_AMQP_PORT": "${seat:mesh-broker:5672}",
"MESH_BROKER_MANAGEMENT_PORT": "${seat:mesh-broker:15672}",
"MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}",
"MESH_BUS_NATS_FILE": "/run/secrets/bus"
"MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}"
},
"volumes": [
"/var/lib/mesh-broker-tls:/broker-tls:ro",
@@ -63,7 +62,6 @@
"/var/lib/mesh/mesh-controller/identity:/run/secrets/identity:ro",
"/var/lib/mesh/mesh-controller/licences:/run/secrets/licences:ro",
"/var/lib/mesh/mesh-controller/broker:/run/secrets/broker:ro",
"/var/lib/mesh/mesh-controller/bus:/run/secrets/bus:ro",
"/var/lib/mesh/mesh-controller/broker-management:/run/secrets/broker-management:ro",
"/var/lib/mesh/mesh-controller/broker-address:/run/secrets/broker-address:ro"
],