The controller asks the build role that has a holder, and hears both roles' outcomes (hq ADR 0190, the handover)

A controller that asked node-build-agent from its first run would queue every build where nothing
pulls, and the build that registers build-agent — the first holder — would be among them. So the
role is chosen at ask time from the catalogue: the current role when any assigned module claims it,
the retired one while only the builder does, the current one when neither. Outcomes are followed on
both seats, the controller may publish to both, and a build's log is read under whichever role did
it; a machine on the retired role is proven on the bus to take that role's asks. The switch order
is written where the role is named, and the retired half is marked for removal with the seat row.
This commit is contained in:
jochen
2026-10-03 02:51:03 +02:00
parent a5d6a1187c
commit ff5ef0ab60
9 changed files with 187 additions and 23 deletions
+24 -6
View File
@@ -25,16 +25,34 @@ import (
type natsBuilds struct {
js *broker.JetStream
owned bool
// seat is the build role asked: the one that has a holder (ADR 0190 handover), chosen by the
// controller from what is assigned, so an ask lands where a machine is pulling.
seat string
}
// BuildsOverNATS is the asking side on the bus being built. It dials, because the command that asks
// for a build is a one-shot and holds nothing else.
// BuildsOverNATS is the asking side on the bus being built, asking the current build role. It dials,
// because the command that asks for a build is a one-shot and holds nothing else.
func BuildsOverNATS(address string) (Builders, error) {
return BuildsOverNATSOn(address, TheBuildMachine)
}
// BuildsOverNATSOn is the asking side for one named build role — during the handover from the one
// build machine to build agents, the role that has a holder (ADR 0190).
func BuildsOverNATSOn(address, seat string) (Builders, error) {
js, err := broker.Dial(address)
if err != nil {
return nil, fmt.Errorf("cannot reach the bus at %s to ask for a build: %w", address, err)
}
return &natsBuilds{js: js, owned: true}, nil
return &natsBuilds{js: js, owned: true, seat: seat}, nil
}
// role is the seat asked: what the asker was made for, or the current build role for one made
// without saying (a test building the struct by hand).
func (b *natsBuilds) role() string {
if b.seat == "" {
return TheBuildMachine
}
return b.seat
}
func (b *natsBuilds) Close() {
@@ -51,7 +69,7 @@ func (b *natsBuilds) Ask(ctx context.Context, request BuildRequest) error {
}
publish, cancel := context.WithTimeout(ctx, 30*time.Second)
defer cancel()
if _, err := b.js.Context().Publish(BuildWork(), body, nats.Context(publish)); err != nil {
if _, err := b.js.Context().Publish(BuildWorkOf(b.role()), body, nats.Context(publish)); err != nil {
return fmt.Errorf("cannot submit a build: %w", err)
}
return nil
@@ -63,7 +81,7 @@ func (b *natsBuilds) Submit(ctx context.Context, request BuildRequest,
// Subscribed before the ask, so an outcome cannot arrive before there is anywhere for it to
// land. Core, not the stream: the asker is waiting now, and the durable copy of this outcome is
// the same event on EVENTS, which the controller records.
outcomes, err := b.js.Conn().SubscribeSync(BuildOutcome())
outcomes, err := b.js.Conn().SubscribeSync(BuildOutcomeOf(b.role()))
if err != nil {
return BuildResult{}, fmt.Errorf("cannot listen for a build's outcome: %w", err)
}
@@ -80,7 +98,7 @@ func (b *natsBuilds) Submit(ctx context.Context, request BuildRequest,
// be assumed, because nothing else will ever say so.
publish, cancel := context.WithTimeout(ctx, 30*time.Second)
defer cancel()
if _, err := b.js.Context().Publish(BuildWork(), body, nats.Context(publish)); err != nil {
if _, err := b.js.Context().Publish(BuildWorkOf(b.role()), body, nats.Context(publish)); err != nil {
return BuildResult{}, fmt.Errorf("cannot submit a build: %w", err)
}