Merge pull request 'A seat's work is shared by its holders: node-build-agent, pulled one ask at a time (hq ADR 0190)' (#228) from feat/a-seats-work-is-shared-by-its-holders into main

cmd/mesh-controller/build.go

@@ -430,11 +430,13 @@ func buildOne(ctx context.Context, source buildSource, path, ref string, wait ti
 	}
 	fmt.Println()
 
-	ask, err := askOver(server)
+	seat := buildSeatHeld(ctx)
+	ask, err := askOverOn(seat)
 	if err != nil {
 		return err
 	}
 	defer ask.Close()
+	fmt.Printf("  of %s\n", seat)
 
 	if wait == 0 {
 		// Asked and not waited for (novox/hq issue 176): the outcome is the role's event, and the
@@ -555,7 +557,7 @@ func buildAndShow(ctx context.Context, source buildSource, path, ref string, wai
 	}
 	defer server.Close()
 
-	ask, err := askOver(server)
+	ask, err := askOverOn(buildSeatHeld(ctx))
 	if err != nil {
 		return err
 	}
@@ -668,12 +670,56 @@ 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) {
+func askOverOn(seat string) (link.Builders, error) {
 	address, err := broker.BusAddress()
 	if err != nil {
 		return nil, err
 	}
-	return link.BuildsOverNATS(address)
+	return link.BuildsOverNATSOn(address, seat)
+}
+
+// buildSeatHeld is the build role to ask: the one some assigned module claims (novox/hq ADR 0190,
+// the handover). Read from the catalogue at ask time, because the answer changes exactly once, the
+// moment the first build-agent is assigned — and a controller that asked the new role before then
+// would queue work nothing takes, while the outcome that registers build-agent itself has to come
+// from the old builder. When the catalogue cannot be read the current role is asked, said aloud.
+func buildSeatHeld(ctx context.Context) string {
+	open, err := openStores(ctx)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "could not read what is assigned, so the build is asked of %s: %v\n",
+			link.TheBuildMachine, err)
+		return link.TheBuildMachine
+	}
+	defer open.Close()
+	entries, err := open.inventory.Catalogued(ctx)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "could not read the catalogue, so the build is asked of %s: %v\n",
+			link.TheBuildMachine, err)
+		return link.TheBuildMachine
+	}
+	return buildSeatAmong(entries)
+}
+
+// buildSeatAmong is the rule, over what the catalogue holds: the current build role when any
+// assigned module claims it; else the retired role while an assigned module still claims that; else
+// the current role, which is where every ask goes once the handover is done.
+func buildSeatAmong(entries []inventory.Entry) string {
+	heldBefore := false
+	for _, e := range entries {
+		if len(e.On) == 0 {
+			continue
+		}
+		if e.Manifest.ClaimsSeat(link.TheBuildMachine) {
+			return link.TheBuildMachine
+		}
+		if e.Manifest.ClaimsSeat(link.TheBuildMachineBefore) {
+			heldBefore = true
+		}
+	}
+	if heldBefore {
+		return link.TheBuildMachineBefore
+	}
+	return link.TheBuildMachine
 }
 
 // buildLog prints everything a build machine said about one build, read back from the bus.
@@ -693,10 +739,13 @@ func buildLog(ctx context.Context, id string) error {
 	}
 	defer js.Close()
 
-	sub, err := js.Context().PullSubscribe(link.BuildLog(id), "",
+	// Under whichever build role did it: a build asked of the retired role during the handover
+	// (ADR 0190) said its lines as that role's events, and a reader should not have to know which.
+	lines := link.BuildLogOf("*", id)
+	sub, err := js.Context().PullSubscribe(lines, "",
 		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)
+		return fmt.Errorf("cannot read %s from the bus: %w", lines, err)
 	}
 	defer func() { _ = sub.Unsubscribe() }()
 

cmd/mesh-controller/build_seat_test.go

@@ -0,0 +1,43 @@
+package main
+
+import (
+	"testing"
+
+	"github.com/novox/mesh-controller/internal/catalogue"
+	"github.com/novox/mesh-controller/internal/inventory"
+	"github.com/novox/mesh-controller/internal/link"
+)
+
+func claiming(module, seat string, on ...string) inventory.Entry {
+	return inventory.Entry{
+		Manifest: catalogue.Manifest{Module: module, Claims: []catalogue.Claim{{Name: seat}}},
+		On:       on,
+	}
+}
+
+// The controller asks the build role that has a holder (novox/hq ADR 0190 handover): the retired
+// one while only the builder is assigned, the current one from the first build-agent on, and the
+// current one when nothing holds either — where every ask goes once the handover is done.
+func TestTheControllerAsksTheBuildRoleThatHasAHolder(t *testing.T) {
+	onlyTheBuilder := []inventory.Entry{
+		claiming("builder", link.TheBuildMachineBefore, "anchor"),
+		claiming("build-agent", link.TheBuildMachine), // registered, assigned nowhere yet
+	}
+	if got := buildSeatAmong(onlyTheBuilder); got != link.TheBuildMachineBefore {
+		t.Errorf("with only the builder assigned, asked %q", got)
+	}
+	bothHeld := []inventory.Entry{
+		claiming("builder", link.TheBuildMachineBefore, "anchor"),
+		claiming("build-agent", link.TheBuildMachine, "home-server"),
+	}
+	if got := buildSeatAmong(bothHeld); got != link.TheBuildMachine {
+		t.Errorf("with a build-agent assigned anywhere, asked %q", got)
+	}
+	neither := []inventory.Entry{claiming("builder", link.TheBuildMachineBefore)}
+	if got := buildSeatAmong(neither); got != link.TheBuildMachine {
+		t.Errorf("with no holder of either, asked %q, want the current role", got)
+	}
+	if got := buildSeatAmong(nil); got != link.TheBuildMachine {
+		t.Errorf("an empty catalogue asks %q", got)
+	}
+}