A build says what it does on the bus, as it happens (novox/hq ADR 0157)

The build-machine seat emits `started` and `log.<build id>` beside `built`. Every line the builder
speaks — each step, each command with its duration, and on failure the command's own output — goes
to stderr as before and onto the bus under the build's id, one subject per build, kept a week in
EVENTS with every other event. `builds --log <id>` reads it back from the stream with a consumer
that is gone when the reading is done, on the command line and as the controller's seat verb;
`builds` lists each build's id and `build` says the id it asked with.

Lines are core publishes with a sequence number, so a build is not slowed by an ack per line and a
gap is visible; `started` and `built` are awaited into the stream. The seat protocol widens
additively at the controller's next start; the holder's grant follows on the broker node's next
composition.
This commit is contained in:
2026-10-01 00:43:07 +02:00
parent f6685ed22d
commit 17f7cb0d9c
12 changed files with 259 additions and 19 deletions
+22 -10
View File
@@ -148,20 +148,34 @@ func answer(ctx context.Context, publisher builder.Publisher, on, workspace stri
// it either finishes or fails is indistinguishable from one that never arrived — which cost a long
// diagnosis against a running mesh, chasing "the handler never fired" when the truth was only that
// the handler said nothing until the end.
fmt.Fprintf(os.Stderr, "a build request arrived for %s\n", request.Repository)
fmt.Fprintf(os.Stderr, "a build request arrived for %s (%s)\n", request.Repository, request.ID)
// **Everything a build says goes two ways**: to stderr, as always, and onto the bus as the
// role's own events under the build's id (novox/hq ADR 0157) — so whoever asked, and anybody
// watching, reads the same lines this container's log holds, live, and after the fact from the
// stream. Said first, before anything runs, so a build that hangs is one that visibly started.
say := func(step, message string) {
fmt.Fprintf(os.Stderr, " [%s] %s\n", step, message)
work.Say(step, message)
}
builder.Said = say
defer func() { builder.Said = nil }()
if err := work.Began(ctx); err != nil {
fmt.Fprintf(os.Stderr, "cannot say a build started: %v\n", err)
}
result := link.BuildResult{
ID: request.ID, Repository: request.Repository, Path: request.Path,
Ref: request.Ref, On: on,
}
fmt.Fprintf(os.Stderr, "building %s", request.Repository)
what := "building " + request.Repository
if request.Path != "" {
fmt.Fprintf(os.Stderr, " at %s", request.Path)
what += " at " + request.Path
}
if request.Ref != "" {
fmt.Fprintf(os.Stderr, " at %s", request.Ref)
what += " on " + request.Ref
}
fmt.Fprintln(os.Stderr)
say("build", what)
npmrc, err := packagesFrom()
var built builder.Result
@@ -171,15 +185,13 @@ func answer(ctx context.Context, publisher builder.Publisher, on, workspace stri
// after a clone that then fails at npm ci.
built, err = builder.Build(ctx, builder.Command, publisher,
request.Repository, request.Path, request.Ref, workspace, request.Held, npmrc,
forgeFrom(), func(step, message string) {
fmt.Fprintf(os.Stderr, " [%s] %s\n", step, message)
}, request.Seats)
forgeFrom(), say, request.Seats)
}
if err != nil {
// A failure is a result. A build that fails and says nothing is indistinguishable from a
// builder that is not running, and those want completely different responses.
result.Failed = err.Error()
fmt.Fprintf(os.Stderr, " failed: %v\n", err)
say("failed", err.Error())
} else {
manifest, marshalErr := json.Marshal(built.Manifest)
if marshalErr != nil {
@@ -196,7 +208,7 @@ func answer(ctx context.Context, publisher builder.Publisher, on, workspace stri
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))
say("built", built.Manifest.Module+" from "+short(built.Commit))
}
}
+64 -2
View File
@@ -10,6 +10,8 @@ import (
"strings"
"time"
"github.com/nats-io/nats.go"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
@@ -175,10 +177,14 @@ func buildFrom(result link.BuildResult) inventory.Build {
func buildsCommand(ctx context.Context, args []string) error {
set := flag.NewFlagSet("builds", flag.ContinueOnError)
limit := set.Int("n", 20, "how many to show")
logOf := set.String("log", "", "a build's id: print what the build machine said, line by line")
positionals, err := parseAround(set, args)
if err != nil {
return err
}
if *logOf != "" {
return buildLog(ctx, *logOf)
}
module := ""
if len(positionals) == 1 {
module = positionals[0]
@@ -219,8 +225,8 @@ func buildsCommand(ctx context.Context, args []string) error {
if !b.Worked() {
outcome = "failed"
}
fmt.Printf("%-18s %-14s %-10s %s\n",
what, outcome, b.On, b.At.Local().Format("2006-01-02 15:04"))
fmt.Printf("%-18s %-14s %-10s %s %s\n",
what, outcome, b.On, b.At.Local().Format("2006-01-02 15:04"), b.ID)
fmt.Printf(" %s", b.Repository)
if b.Ref != "" {
fmt.Printf(" at %s", b.Ref)
@@ -414,6 +420,8 @@ func buildOne(ctx context.Context, source buildSource, path, ref string, wait ti
if source.Seat != "" {
fmt.Printf(" (%s)", repository)
}
// The id is how a person follows this build while it runs: `builds --log <id>`.
fmt.Printf(" as %s", request.ID)
if path != "" {
fmt.Printf(" at %s", path)
}
@@ -625,3 +633,57 @@ func askOver(_ *link.Server) (link.Builders, error) {
}
return link.BuildsOverNATS(address)
}
// buildLog prints everything a build machine said about one build, read back from the bus.
//
// **From the stream, not from a record** (novox/hq ADR 0157). A build's lines are the role's own
// events under the build's id, retained with every other event; the mesh keeps no second copy. Read
// with a consumer of its own that is gone when this returns, so nothing accumulates in the server
// for the reading, and filtered by subject, so one build's lines are all that travel.
func buildLog(ctx context.Context, id string) error {
address, err := broker.BusAddress()
if err != nil {
return err
}
js, err := broker.Dial(address)
if err != nil {
return fmt.Errorf("cannot reach the bus to read a build's log: %w", err)
}
defer js.Close()
sub, err := js.Context().PullSubscribe(link.BuildLog(id), "",
nats.BindStream(broker.EventsStream), nats.DeliverAll(), nats.AckNone())
if err != nil {
return fmt.Errorf("cannot read %s from the bus: %w", link.BuildLog(id), err)
}
defer func() { _ = sub.Unsubscribe() }()
printed := 0
for {
batch, err := sub.Fetch(200, nats.MaxWait(2*time.Second))
if err != nil && !errors.Is(err, nats.ErrTimeout) && !errors.Is(err, context.DeadlineExceeded) {
return fmt.Errorf("reading a build's log: %w", err)
}
for _, msg := range batch {
var line link.BuildLine
if err := json.Unmarshal(msg.Data, &line); err != nil {
fmt.Printf(" ? %s\n", string(msg.Data))
continue
}
at := line.At
if t, err := time.Parse(time.RFC3339Nano, line.At); err == nil {
at = t.Local().Format("15:04:05")
}
fmt.Printf("%s %4d [%s] %s\n", at, line.Seq, line.Step, line.Message)
printed++
}
if len(batch) < 200 {
break
}
}
if printed == 0 {
fmt.Printf("nothing on the bus for build %s: no build by that id in the last week, or a build "+
"machine older than this that said nothing while building\n", id)
}
return nil
}
+3
View File
@@ -62,6 +62,9 @@ func argvFor(verb string, args map[string]any) ([]string, error) {
case "seats":
return []string{"seats", "--json"}, nil
case "builds":
if id := str("log"); id != "" {
return []string{"builds", "--log", id}, nil
}
if m := str("module"); m != "" {
return []string{"builds", m}, nil
}
+12
View File
@@ -30,6 +30,18 @@ func TestEveryDeclaredVerbHasACommandLine(t *testing.T) {
}
}
// `builds` given a build's id reads that build's log from the bus rather than listing builds
// (novox/hq ADR 0157).
func TestBuildsWithAnIdReadsThatBuildsLog(t *testing.T) {
argv, err := argvFor("builds", map[string]any{"log": "build-17"})
if err != nil {
t.Fatal(err)
}
if strings.Join(argv, " ") != "builds --log build-17" {
t.Fatalf("builds with a log id became %q", strings.Join(argv, " "))
}
}
// A required argument missing is refused in the verb's own words, before anything runs.
func TestAVerbMissingWhatItNeedsIsRefused(t *testing.T) {
if _, err := argvFor("node", map[string]any{}); err == nil || !strings.Contains(err.Error(), `node needs "node"`) {