Give a consumer's max-deliveries key one watcher, counting what was given up (issue 440)
mesh/merge-gate pass: builds build-agent, mesh-controller → ace, g14, novox, shanks; no bus step; every machine composes with the change as it did without …
mesh/repo-check pass: its merge-check.sh passed
mesh/delivery superseded: a newer head of the same pull request

The dead-letter row and a max-deliveries advisory without a token both said
bus.<stream>.<consumer>.max-deliveries: each look added an observation and a
line of evidence through the row, and the two overwrote each other's words.
The row owns the key since issue 330, so the advisory watcher leaves it, and
the row now says when the newest held message was given up, so a letter held
for a day no longer reads as observed every 30 seconds. Times without Happened
is refused, since the raise ignored it and an update counted it.
This commit is contained in:
2026-10-11 02:30:09 +02:00
parent f8d08b0637
commit f83fcdc15f
8 changed files with 176 additions and 6 deletions
@@ -93,3 +93,76 @@ func TestAConditionOfThePresentCountsItsLooks(t *testing.T) {
t.Fatalf("observed %d time(s), %d evidence lines, last %s", c.Observations, len(c.Evidence), c.LastObserved)
}
}
// **One key, one watcher** (novox/hq issue 440). A consumer's max-deliveries condition is said from
// DEAD_LETTERS while it holds a message the consumer gave up on (issue 330). A max-deliveries advisory
// without a token names the same key; read beside it, each look added an observation and a line of
// evidence through the dead-letter half, and the two summaries overwrote each other on every look. The
// dead-letter row alone says that key, and counts the messages given up on, never the looks.
func TestAHeldDeadLetterIsCountedByWhatWasGivenUpNotByTheLooks(t *testing.T) {
gaveUp := time.Date(2026, 10, 10, 21, 4, 0, 0, time.UTC)
now := gaveUp.Add(20 * time.Second)
store := conditions.NewInMemory()
k := conditions.NewKeeper(t.Context(), conditions.Options{Store: store, History: store,
Teller: &conditions.Told{}, Now: func() time.Time { return now }})
t.Cleanup(func() { k.Close(t.Context()) })
const key = "bus.EVENTS.media_sonarr.max-deliveries"
held := map[string]int{"EVENTS.media_sonarr": 1}
newest := map[string]time.Time{"EVENTS.media_sonarr": gaveUp}
advisory := link.Advisory{Kind: link.AdvisoryMaxDeliveries, ID: "EVENTS.media_sonarr", Stream: "EVENTS",
Consumer: "media_sonarr", Said: "sonarr on media handed message 7 over 5 times and gave up on it",
First: gaveUp, Last: gaveUp, Count: 1}
look := func() conditions.Condition {
t.Helper()
f := &signalFacts{now: now, host: "novox", advisories: []link.Advisory{advisory},
deadLetters: held, deadLettersNewest: newest}
if err := k.Reconcile(t.Context(), "S9", watchAdvisories(f)); err != nil {
t.Fatal(err)
}
c, found, err := conditions.ReadOne(t.Context(), store, key)
if err != nil || !found {
t.Fatalf("%s: found %v, %v", key, found, err)
}
if !strings.Contains(c.Summary, "dead-letters verb") {
t.Fatalf("the summary is not the dead-letter row's: %q", c.Summary)
}
return c
}
var c conditions.Condition
for range 5 {
c = look()
now = now.Add(30 * time.Second)
}
if c.Observations != 1 || len(c.Evidence) != 1 || !c.LastObserved.Equal(gaveUp) {
t.Fatalf("one message given up on, looked at five times, reads as observed %d time(s), last %s, "+
"with %d evidence lines: %+v", c.Observations, c.LastObserved, len(c.Evidence), c.Evidence)
}
// The consumer gives up on a second message between two looks: two given up on, one more line.
again := now.Add(-10 * time.Second)
held["EVENTS.media_sonarr"], newest["EVENTS.media_sonarr"] = 2, again
c = look()
if c.Observations != 2 || len(c.Evidence) != 2 || !c.LastObserved.Equal(again) {
t.Fatalf("two given up on read as observed %d time(s), last %s, evidence %+v", c.Observations,
c.LastObserved, c.Evidence)
}
now = now.Add(30 * time.Second)
if c = look(); c.Observations != 2 || len(c.Evidence) != 2 {
t.Fatalf("a look with nothing new counted: observed %d time(s), evidence %+v", c.Observations, c.Evidence)
}
}
// The advisory still says the max-deliveries it alone knows: a message given up on that could not be
// kept, under a key of its own (issue 330), which issue 440's change leaves as it was.
func TestAMessageThatCouldNotBeKeptIsStillSaidFromTheAdvisory(t *testing.T) {
at := time.Date(2026, 10, 10, 21, 4, 0, 0, time.UTC)
f := &signalFacts{now: at, host: "novox", advisories: []link.Advisory{{Kind: link.AdvisoryMaxDeliveries,
ID: "EVENTS.media_sonarr", Stream: "EVENTS", Consumer: "media_sonarr", Token: link.AdvisoryNotKept,
Said: "sonarr on media gave up on message 7, and it could not be kept", First: at, Last: at, Count: 1}}}
said := watchAdvisories(f)
if len(said) != 1 || said[0].Key() != "bus.EVENTS.media_sonarr.not-kept" {
t.Fatalf("%+v", said)
}
}
+16
View File
@@ -523,6 +523,14 @@ func watchAdvisories(f *signalFacts) []conditions.Observation {
if a.Kind == link.AdvisoryConsumerLost && !f.lostConsumers[a.Stream+"."+a.Consumer] {
continue // it exists again, or the mesh no longer expects it: a removal, not a loss
}
if a.Kind == link.AdvisoryMaxDeliveries && a.Token == "" {
// A consumer's max-deliveries key is the dead-letter row's (novox/hq issue 330): said while
// DEAD_LETTERS holds what it gave up on, cleared when that is delivered again or dropped. The
// listener records no such advisory today; one read here as well added a look to the count and
// overwrote the row's words on every look (novox/hq issue 440). Only one that could not be kept
// (AdvisoryNotKept), which DEAD_LETTERS cannot say, is said from here.
continue
}
severity := conditions.Warning
times := ""
if a.Count > 1 {
@@ -568,7 +576,15 @@ func watchDeadLetters(f *signalFacts) []conditions.Observation {
messages, them = fmt.Sprintf("%d messages", n), "them"
}
who := consumerWho(stream, consumer)
// DEAD_LETTERS is a record of what was given up on: the condition counts the messages and says when
// the newest was given up, never how often the controller looked (novox/hq issues 402 and 440).
// Without that time it counts its looks, as a source of the present does.
happened, times := f.deadLettersNewest[key], 0
if !happened.IsZero() {
times = n
}
out = append(out, conditions.Observation{Scope: conditions.ScopeBus, ID: key, Kind: link.AdvisoryMaxDeliveries,
Happened: happened, Times: times,
Machine: consumerMachine(stream, consumer), Severity: conditions.Warning,
Summary: fmt.Sprintf("%s gave up on %s; %s kept in %s until delivered again or dropped, with why, "+
"through the controller's dead-letters verb", link.ConsumerInWords(stream, consumer), messages,
+5 -4
View File
@@ -100,14 +100,15 @@ var suppressions = map[string]suppression{
inside: func(f *signalFacts) { f.standings = []conditions.Condition{standingSaid(f.now.Add(-29 * time.Minute))} },
past: func(f *signalFacts) { f.standings = []conditions.Condition{standingSaid(f.now.Add(-31 * time.Minute))} },
},
// A message given up on and not kept: the one max-deliveries advisory S9 says itself (issue 440).
"S9": {
inside: func(f *signalFacts) {
f.advisories = []link.Advisory{{Kind: link.AdvisoryMaxDeliveries, ID: "EVENTS.anchor_shop", Said: "gave up",
First: f.now.Add(-2 * time.Hour), Last: f.now.Add(-61 * time.Minute), Count: 1}}
f.advisories = []link.Advisory{{Kind: link.AdvisoryMaxDeliveries, ID: "EVENTS.anchor_shop",
Token: link.AdvisoryNotKept, Said: "gave up, not kept", First: f.now.Add(-2 * time.Hour), Last: f.now.Add(-61 * time.Minute), Count: 1}}
},
past: func(f *signalFacts) {
f.advisories = []link.Advisory{{Kind: link.AdvisoryMaxDeliveries, ID: "EVENTS.anchor_shop", Said: "gave up",
First: f.now.Add(-2 * time.Hour), Last: f.now.Add(-59 * time.Minute), Count: 1}}
f.advisories = []link.Advisory{{Kind: link.AdvisoryMaxDeliveries, ID: "EVENTS.anchor_shop",
Token: link.AdvisoryNotKept, Said: "gave up, not kept", First: f.now.Add(-2 * time.Hour), Last: f.now.Add(-59 * time.Minute), Count: 1}}
},
},
"S10": {
+8 -2
View File
@@ -79,8 +79,11 @@ type signalFacts struct {
lostConsumers map[string]bool
// deadLetters are how many messages DEAD_LETTERS holds per consumer, by `<stream>.<consumer>`
// (novox/hq issue 330): each consumer's max-deliveries condition is open while it holds any.
deadLetters map[string]int
advisoriesErr error
deadLetters map[string]int
// deadLettersNewest is when each of those consumers last gave up on a message DEAD_LETTERS still
// holds: the condition counts the messages given up on, not the looks (novox/hq issue 440).
deadLettersNewest map[string]time.Time
advisoriesErr error
selfCheck selfCheckFacts
@@ -350,6 +353,9 @@ func (w *watchdogs) gather(ctx context.Context) *signalFacts {
if f.advisoriesErr == nil && w.js != nil {
f.deadLetters, f.advisoriesErr = link.HeldDeadLetters(w.js.Context())
}
if f.advisoriesErr == nil && len(f.deadLetters) > 0 {
f.deadLettersNewest, f.advisoriesErr = link.NewestDeadLetters(w.js.Context(), f.deadLetters)
}
f.handActs, f.handActsErr = w.gatherHandActs(ctx, now)
f.facts.taken, _, f.facts.began, f.facts.err = exportedFacts.last()
return f