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.
This commit is contained in:
2026-08-04 05:15:01 +04:00
parent 09c648b934
commit 7e21cd06b3
9 changed files with 192 additions and 45 deletions
+29 -7
View File
@@ -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.