Announce the build agent's verbs, let a waiting build hear its cancel, and retry a stopped rollout (hq ADR 0219)

The holder's verbs were served and found by nothing; it now answers discovery with its machine's four, as a runtime announces a seat's verb, so the console finds <node>/node-build-agent.kill. A cancel publishes no outcome, so a build waited for also looks at the cancelled set. A plan that stopped at its first machine is retried by sending that machine the module again, unless a newer plan holds it.
2026-10-05 19:26:40 +02:00
parent 106507b1d3
commit 541603c15c
7 changed files with 273 additions and 7 deletions
@@ -580,3 +580,67 @@ func TestKillAndPauseAskTheHolderOnTheMachine(t *testing.T) {
 		t.Error("a machine nothing answers on was resumed")
 	}
 }
+
+// A plan that stopped at its first machine is retried: the module sent to that machine again, the
+// send recorded as the first anew, and the plan goes on — unless a newer plan holds the module.
+func TestAPlanStoppedAtItsFirstMachineIsRetried(t *testing.T) {
+	open := aMesh(t)
+	ctx := t.Context()
+	asked := asksRecorded(t)
+	twoTiers(t, open)
+	var sentTo [][]string
+	was := sendRollout
+	sendRollout = func(_ context.Context, _ *stores, names []string) ([]string, error) {
+		sentTo = append(sentTo, names)
+		return names, nil
+	}
+	t.Cleanup(func() { sendRollout = was })
+
+	long := time.Now().UTC().Add(-2 * time.Hour)
+	stopped := inventory.Plan{ID: "plan-rollout", Repository: "novox/a", Branch: "main", Commit: "c0ffee",
+		Created: long, State: inventory.PlanFailed, Tiers: [][]string{{"a"}, {"b"}},
+		Note: "a stopped at its first machine in tier 0: laptop refused what it was sent",
+		Modules: map[string]*inventory.PlanModule{"a": {State: "built", BuiltAt: &long, Commit: "c0ffee",
+			First: []string{"laptop"}, FirstAt: &long, Why: "laptop refused what it was sent"}}}
+	if err := open.inventory.SavePlan(ctx, stopped); err != nil {
+		t.Fatal(err)
+	}
+
+	// A newer plan holding a refuses it: sending the older build would put it back.
+	newer := inventory.Plan{ID: "plan-newer", Repository: "novox/other", Commit: "d00d", Created: long.Add(time.Hour),
+		State: inventory.PlanDone, Tiers: [][]string{{"a"}}, Modules: map[string]*inventory.PlanModule{}}
+	if err := open.inventory.SavePlan(ctx, newer); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := retryPlan(ctx, open, stopped.ID); err == nil || !strings.Contains(err.Error(), "plan-newer") {
+		t.Fatalf("retried under a newer plan: %v", err)
+	}
+	newer.State = inventory.PlanSuperseded
+	if err := open.inventory.SavePlan(ctx, newer); err != nil {
+		t.Fatal(err)
+	}
+
+	said, err := retryPlan(ctx, open, stopped.ID)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(sentTo) != 1 || !reflect.DeepEqual(sentTo[0], []string{"laptop"}) || !strings.Contains(said, "laptop") {
+		t.Fatalf("sent %v; said %q", sentTo, said)
+	}
+	p, err := open.inventory.PlanByID(ctx, stopped.ID)
+	if err != nil {
+		t.Fatal(err)
+	}
+	a := p.Modules["a"]
+	if p.State != inventory.PlanRolling || a.FirstAt == nil || !a.FirstAt.After(long) || a.Why != "" {
+		t.Fatalf("after retry the plan is %s, a %+v", p.State, a)
+	}
+	// And it goes on: a records (its policy sends nothing more), so the next tier is asked.
+	advancePlans(ctx, open)
+	if p, _ = open.inventory.PlanByID(ctx, stopped.ID); p.Tier != 1 || p.Modules["b"] == nil || p.Modules["b"].State != "asked" {
+		t.Fatalf("the retried plan did not go on: tier %d %s %+v", p.Tier, p.State, p.Modules["b"])
+	}
+	if len(*asked) != 1 {
+		t.Fatalf("asked %v", *asked)
+	}
+}