phraser: name the service that is down (V-444)

Stub and LLM paths both read loop.DownServices, so the message can never name
a service the predicate did not fire on. Two down at once are both named — he
needs the blast radius.

internal/phraser/llmphraser.go

@@ -975,6 +975,9 @@ var fallbackNudges = map[string]string{
 }
 
 func fallbackNudge(c loop.Candidate) string {
+	if down := loop.DownServices(c.State); len(down) > 0 {
+		return "Не отвечает: " + strings.Join(down, ", ") + "."
+	}
 	if s, ok := fallbackNudges[c.Rule.Name]; ok {
 		return s
 	}
@@ -990,6 +993,11 @@ func buildNudgePrompt(c loop.Candidate) string {
 	if f, ok := c.State.Facts[c.Rule.Name]; ok && f.Key != "" && f.Key != c.Rule.Name {
 		ctxParts = append(ctxParts, "Что именно: "+f.Key)
 	}
+	if down := loop.DownServices(c.State); len(down) > 0 {
+		// The names come from the same helper the rule fired on, so the model
+		// is never handed a service that is actually up.
+		ctxParts = append(ctxParts, "Какие сервисы лежат: "+strings.Join(down, ", "))
+	}
 	if d, ok := c.State.Since(c.Rule.Name); ok {
 		ctxParts = append(ctxParts, "Прошло: "+ruDur(d))
 	}

internal/phraser/phraser.go

@@ -142,16 +142,21 @@ func phraseNudge(c loop.Candidate) (body, summary string) {
 		}
 		return body, "take a break"
 	case "service_down":
-		// the fact value is json `"down"`; the key carries the service name.
-		body = "a service on homesrv is down — check journalctl."
-		summary = "service down on homesrv"
-		if f, ok := c.State.Fact("service_down"); ok {
-			if f.Key != "" && f.Key != "service_down" {
-				body = fmt.Sprintf("%s on homesrv is down — check journalctl.", f.Key)
-				summary = fmt.Sprintf("%s down on homesrv", f.Key)
-			}
+		// One fact per kuma monitor, so the nudge names the service. The rule
+		// and this share loop.DownServices, so the message cannot name a
+		// service the predicate did not fire on.
+		down := loop.DownServices(c.State)
+		switch len(down) {
+		case 0:
+			return "a service on homesrv is down — check journalctl.", "service down on homesrv"
+		case 1:
+			return fmt.Sprintf("%s on homesrv is down — check journalctl.", down[0]),
+				fmt.Sprintf("%s down on homesrv", down[0])
+		default:
+			list := strings.Join(down, ", ")
+			return fmt.Sprintf("%s on homesrv are down — check journalctl.", list),
+				fmt.Sprintf("%d services down on homesrv", len(down))
 		}
-		return body, summary
 	default:
 		// generic: name the rule + severity; the LLM impl replaces this with
 		// a prompted phrase. the Stub never editorializes beyond the rule name.

internal/phraser/phraser_test.go

@@ -78,12 +78,14 @@ func TestPhraseNudgeBreakDeskDuration(t *testing.T) {
 }
 
 func TestPhraseNudgeServiceDownNamedService(t *testing.T) {
-	// a service_down fact whose Key is the specific service name → the phrase
-	// names the service, not just "service down".
+	// one fact per kuma monitor → the phrase names the monitor that is down.
 	now := time.Now().UTC()
 	st := loop.State{
-		Now:   now,
-		Facts: map[string]store.Fact{"service_down": {Key: "nginx", Ts: now, Source: "poll:healthcheck", Value: `"down"`}},
+		Now: now,
+		Facts: map[string]store.Fact{
+			"service_down:nginx": {Key: "service_down:nginx", Ts: now, Source: loop.ServiceDownSource, Value: `"down"`},
+			"service_down:db":    {Key: "service_down:db", Ts: now, Source: loop.ServiceDownSource, Value: `"up"`},
+		},
 	}
 	c := loop.Candidate{Rule: loop.ServiceDownRule(), Severity: loop.Sev4, State: st}
 	pn, _ := NewStub().PhraseNudge(context.Background(), c)
@@ -96,12 +98,12 @@ func TestPhraseNudgeServiceDownNamedService(t *testing.T) {
 }
 
 func TestPhraseNudgeServiceDownGenericKey(t *testing.T) {
-	// the rule key itself ("service_down") rather than a specific service →
-	// the generic phrase, not a phantom "service_down down on homesrv".
+	// the old aggregate key, still in the store from before the per-monitor
+	// facts landed → the generic phrase, never a phantom "service_down down".
 	now := time.Now().UTC()
 	st := loop.State{
 		Now:   now,
-		Facts: map[string]store.Fact{"service_down": {Key: "service_down", Ts: now, Source: "poll:healthcheck", Value: `"down"`}},
+		Facts: map[string]store.Fact{"service_down": {Key: "service_down", Ts: now, Source: loop.ServiceDownSource, Value: `"down"`}},
 	}
 	c := loop.Candidate{Rule: loop.ServiceDownRule(), Severity: loop.Sev4, State: st}
 	pn, _ := NewStub().PhraseNudge(context.Background(), c)
@@ -110,6 +112,26 @@ func TestPhraseNudgeServiceDownGenericKey(t *testing.T) {
 	}
 }
 
+// Two monitors down at once must both be named — he needs to know the blast
+// radius, and "a service is down" was the whole defect being fixed here.
+func TestPhraseNudgeServiceDownNamesEveryDownMonitor(t *testing.T) {
+	now := time.Now().UTC()
+	st := loop.State{
+		Now: now,
+		Facts: map[string]store.Fact{
+			"service_down:nginx": {Key: "service_down:nginx", Ts: now, Source: loop.ServiceDownSource, Value: `"down"`},
+			"service_down:db":    {Key: "service_down:db", Ts: now, Source: loop.ServiceDownSource, Value: `"down"`},
+		},
+	}
+	c := loop.Candidate{Rule: loop.ServiceDownRule(), Severity: loop.Sev4, State: st}
+	pn, _ := NewStub().PhraseNudge(context.Background(), c)
+	for _, want := range []string{"nginx", "db"} {
+		if !strings.Contains(pn.Body, want) {
+			t.Fatalf("body should name %q, got %q", want, pn.Body)
+		}
+	}
+}
+
 func TestPhraseNudgeUnknownRuleFallsBack(t *testing.T) {
 	// a rule without a dedicated template — generic fallback names the rule +
 	// severity gist. never empty.