Compare commits

...

8 Commits

Author SHA1 Message Date
claude 45a5e37963 calendar, mavweb: read the notification clock as his wall clock (V-482)
A phone posts an RFC 3339 instant ending in Z, and the clock inside the
text is a wall clock nobody means in UTC. The wall clock used to be
resolved against Posted's own zone, so on this UTC+4 box a 14:30 standup
was stored at 18:30. The size of the error is the deploy's offset, which
is why the tests never saw it: they ran on a UTC box.

EventFromNotificationIn takes the zone explicitly and EventFromNotification
passes time.Local. The day comes from Posted's local day too, since a
notification posted at 23:30Z saying "завтра" is already tomorrow where he
is standing. Posted itself stays an instant, so the past-grace check still
compares instants.

The two handler fixtures said a bare "10:00" against a 09:40Z post, which
is stale once the clock is read locally. They say "завтра" now, so they
mean a future meeting in every zone. internal/calendar and cmd/mavweb pass
under UTC, Europe/Samara, America/Los_Angeles, Pacific/Kiritimati and
Asia/Kathmandu.
2026-08-04 05:23:11 +04:00
claude 6d8a95095a deploy, docs: turn service_down back on (V-444)
It was disabled because it could not say which service. It can now.
2026-08-04 05:15:02 +04:00
claude 7e21cd06b3 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.
2026-08-04 05:15:01 +04:00
claude 09c648b934 mavpoll: write one kuma fact per monitor (V-444)
The aggregate could not name the service, which is the whole reason the nudge
said 'a service on homesrv is down' and the rule shipped disabled.

A monitor deleted in kuma stops appearing in the gauge and its last fact would
read down forever, so a vanished monitor is marked unknown. Pending and
maintenance are not down: a monitor paused in kuma now silences that monitor
rather than nothing.
2026-08-04 05:15:01 +04:00
claude 4f516657da loop, store: read a fact family by prefix (V-444)
A rule over a key set that only exists at read time cannot declare its keys
at wiring time. Kuma has one monitor per service and the names live in the
gauge, so the rule declares a prefix and the gatherer resolves the family per
tick.

ServiceDownRule now fires on any monitor reading down, names it through
DownServices, and is edge-triggered: a service that stays down is one nudge,
not one per tick with cooldown as the only brake.
2026-08-04 05:14:50 +04:00
claude 990a4a99e9 ecosystem: ask Nexus for the name he actually said (V-476)
Two defects in one logged line, both of which put a working capability out
of reach of every utterance.

The resident model rewrites as it routes, and on the way it transliterates:
"перезапусти muzick indexer" came back as "перезагрузить музик индексер", so
Nexus was asked to resolve a service nobody has ever named. entityReferenceText
takes the longest Latin run out of his own words, but only when the Text slot
has lost every Latin letter the utterance had — an English turn and a Russian
entity name are both left alone, and reversing the transliteration is not
attempted.

The second half: the stage-3 gate thins an act that matched no allowlisted fn,
and that question was the whole turn, so handleHexisAct never ran. Hexis is
where an act with no local fn belongs, so it gets one chance before she asks,
and a "" back still leaves her asking. With no ecosystem wired nothing changes.
Capability matching reads the phrase as the haystack when there is no fn,
because no capability name contains "restart status muzick indexer".

Authority is untouched: ambiguity still stops, a mutating capability still
goes through the spoken confirm.
2026-08-04 03:38:20 +04:00
claude 5b622389c5 dialogue: a restart expires the parked question (V-385)
The decision, not a behaviour change: ClarifyStore stays in memory, and she
does not announce the loss either.

The TTL and the attempt count measure a pause in one conversation. A restart
is a gap of unknown length, so a restored question is either dead already or
lying about its age, and the request behind it is one he has likely given up
on. Announcing it would mean storing a marker that outlives the thing it
describes, to say one sentence in the rare window where he speaks within 90s
of a restart. His next words route fresh, which is right either way.

Written down in docs/design.md, pinned at both ends by a comment, and held by
a test that builds a second handler over the same store.
2026-08-04 03:33:19 +04:00
claude a820a95ebb store: wake the routines accepted before the fire-forever fix (V-377)
Routines accepted before Vikunja #366 carry accepted_ts NULL and a live
reminder row. The tick loop reads accepted_ts to decide when a routine is
next due, so those rows have been silent since the fix landed, while the
reminder they still point at keeps firing on its own schedule.

Migration #19 cancels that reminder first, then dates the acceptance from
created_ts and lets the reminder id go. Order matters: the second update
clears the id the first one needs.
2026-08-04 03:29:51 +04:00
31 changed files with 1033 additions and 119 deletions
+20
View File
@@ -530,3 +530,23 @@ func TestClarifyIsPerConversation(t *testing.T) {
func voiceCtx() context.Context {
return withDialogueID(context.Background(), dialogueIDFor(sourceVoice, ""))
}
// TestARestartExpiresTheParkedQuestion pins the Vikunja #385 decision: the
// question dies with the process, and she does not claim to have let it go —
// the words that follow are routed as a fresh request. Restarting is modelled
// the way the daemon does it, by building a second handler over the same store.
func TestARestartExpiresTheParkedQuestion(t *testing.T) {
h, _, _ := newClarifyHandler(t)
ctx := voiceCtx()
if _, asked := h.askClarify(ctx, clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question before the restart")
}
restarted, _, _ := newClarifyHandler(t)
if _, handled := restarted.resolveClarifyAnswer(ctx, "в 11:00"); handled {
t.Fatal("a question parked before the restart must not eat the next utterance")
}
if notice := restarted.clarifyExpiredNotice(ctx); notice != "" {
t.Fatalf("notice = %q, want silence: nothing survived to expire", notice)
}
}
+45 -5
View File
@@ -514,11 +514,14 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
// Resolve the utterance text as an entity reference through Nexus. An
// ambiguous match must stop and clarify — never guess a mutation target.
// The name comes from entityReferenceText, not straight from the Text slot:
// the model transliterates Latin names as it routes (Vikunja #476).
subject := entityReferenceText(dec)
started := h.now()
entityID, displayName, ambiguous, err := h.ecosystem.resolveEntityReference(ctx, dec.Slots.Text, nil)
entityID, displayName, ambiguous, err := h.ecosystem.resolveEntityReference(ctx, subject, nil)
if err != nil {
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceStatusForError(err), started,
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(dec.Slots.Text)}))
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(subject)}))
if unauthorizedEcosystemError(err) {
return "экосистема отклоняет доступ, проверь токен."
}
@@ -535,7 +538,7 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
}
if entityID == "" {
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceNotFound, started,
map[string]any{"subject": redactSubject(dec.Slots.Text)})
map[string]any{"subject": redactSubject(subject)})
return ""
}
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceOK, started,
@@ -569,10 +572,21 @@ func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decisio
}
verbLower := strings.ToLower(verb)
// With no allowlisted fn the verb is a whole phrase ("restart status muzick
// indexer"), which no capability name ever contains. Read it the other way
// round then: the phrase is the haystack and the capability name is what we
// look for in it (Vikunja #476). Only when the fn slot is empty — a matched
// fn is a single verb and containment already means what it says.
loose := !dec.Slots.HasFn
var matches []*hexisclient.Capability
for i, c := range caps {
if strings.Contains(strings.ToLower(c.Name), verbLower) ||
(c.Description != "" && strings.Contains(strings.ToLower(c.Description), verbLower)) {
name := strings.ToLower(c.Name)
hit := strings.Contains(name, verbLower) ||
(c.Description != "" && strings.Contains(strings.ToLower(c.Description), verbLower))
if loose && name != "" && strings.Contains(verbLower, name) {
hit = true
}
if hit {
matches = append(matches, &caps[i])
}
}
@@ -632,3 +646,29 @@ func (h *reactiveHandler) execHexis(ctx context.Context, capID, capName, entityI
})
return "команда выполнена для " + displayName + "."
}
// hexisBeforeClarify gives an entity-shaped act one chance at Hexis before she
// asks what to do.
//
// The stage-3 gate thins an act that never matched an allowlisted fn, so
// "перезапусти muzick indexer" was answered with "Что сделать?" and the Hexis
// path was never entered — the capability existed and no utterance could reach
// it (Vikunja #476). Hexis is exactly where an act with no local fn belongs:
// the verb is matched against the capabilities Hexis registers for the entity,
// not against the allowlist.
//
// Narrow on purpose. Only an act, only when the fn slot is still empty, and
// only when Hexis is wired — a box with no ecosystem asks the question it
// always asked. A "" back means Nexus knew no such entity or Hexis had no
// matching capability, and then she asks after all. Authority is unchanged:
// resolution stops on ambiguity and a mutating capability still goes through
// the spoken confirm in handleHexisAct.
func (h *reactiveHandler) hexisBeforeClarify(ctx context.Context, dec router.Decision) string {
if h.ecosystem == nil || h.ecosystem.hexis == nil {
return ""
}
if dec.Intent != router.IntentAct || dec.Slots.HasFn || dec.Slots.Text == "" {
return ""
}
return h.handleHexisAct(ctx, dec)
}
+59
View File
@@ -0,0 +1,59 @@
package main
import (
"regexp"
"strings"
"unicode"
"github.com/kami/maven/internal/router"
)
// latinRun matches a run of Latin-script words — the shape a service, host or
// project name takes in a Russian sentence. Digits, dot, dash and underscore
// ride along because "muzick-indexer" and "nginx.conf" are one name, not two.
var latinRun = regexp.MustCompile(`[A-Za-z][A-Za-z0-9._-]*(?:\s+[A-Za-z][A-Za-z0-9._-]*)*`)
// hasLatin reports whether s carries a Latin letter.
func hasLatin(s string) bool {
for _, r := range s {
if unicode.In(r, unicode.Latin) {
return true
}
}
return false
}
// entityReferenceText is the name Nexus is asked to resolve.
//
// Normally that is the router's Text slot, which is the verb phrase the model
// wrote. But the resident model rewrites a Russian utterance as it routes, and
// on the way it transliterates: "перезапусти muzick indexer" came back as
// "перезагрузить музик индексер" (Vikunja #476). Nexus is then asked for a
// service nobody has ever named, so the act cannot resolve its target even
// with every gate open.
//
// The recovery is deliberately narrow. Only when the utterance holds a Latin
// run and the model's Text holds none has a name certainly been rewritten —
// then the longest Latin run in his own words is the reference. Anything else
// keeps the Text slot, so an English utterance and a Russian entity name are
// both untouched. Un-transliterating the Cyrillic back is not attempted: the
// surface form he said is right there, and guessing at a reverse mapping would
// invent a second name to be wrong about.
func entityReferenceText(dec router.Decision) string {
text := dec.Slots.Text
if hasLatin(text) || !hasLatin(dec.Utterance) {
return text
}
longest := ""
for _, m := range latinRun.FindAllString(dec.Utterance, -1) {
if len(m) > len(longest) {
longest = m
}
}
longest = strings.TrimSpace(longest)
// A single stray letter is not a name.
if len(longest) < 2 {
return text
}
return longest
}
+133
View File
@@ -0,0 +1,133 @@
package main
import (
"context"
"strings"
"testing"
"github.com/kami/maven/internal/router"
)
// TestEntityReferenceText pins when his own words win over the model's.
func TestEntityReferenceText(t *testing.T) {
for _, tc := range []struct {
name string
utterance string
text string
want string
}{
{
name: "the model transliterated the name",
utterance: "перезапусти muzick indexer",
text: "перезагрузить музик индексер",
want: "muzick indexer",
},
{
name: "it kept the name, so nothing to repair",
utterance: "перезапусти muzick indexer",
text: "перезагрузить muzick indexer",
want: "перезагрузить muzick indexer",
},
{
name: "an all-Russian entity name is not a rewrite",
utterance: "перезапусти домашний сервер",
text: "перезагрузить домашний сервер",
want: "перезагрузить домашний сервер",
},
{
name: "an English turn never enters the recovery",
utterance: "restart muzick indexer",
text: "restart muzick indexer",
want: "restart muzick indexer",
},
{
name: "the longest Latin run is the name",
utterance: "а перезапусти-ка nginx на muzick-indexer, пожалуйста",
text: "перезагрузить нгинкс",
want: "muzick-indexer",
},
{
name: "one stray letter is not a name",
utterance: "перезапусти сервер a",
text: "перезагрузить сервер",
want: "перезагрузить сервер",
},
} {
t.Run(tc.name, func(t *testing.T) {
dec := router.Decision{Utterance: tc.utterance, Slots: router.Slots{Text: tc.text}}
if got := entityReferenceText(dec); got != tc.want {
t.Fatalf("entityReferenceText = %q, want %q", got, tc.want)
}
})
}
}
// TestNexusIsAskedForTheNameHeSaid — the defect end to end (Vikunja #476): the
// router hands over a transliterated Text, and Nexus must still be asked about
// the service that exists.
func TestNexusIsAskedForTheNameHeSaid(t *testing.T) {
ctx := context.Background()
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", "Muzick indexer", "service"))
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
h := ecoHandler(t, nexus, nil, hexis)
dec := router.Decision{
Utterance: "перезапусти muzick indexer",
Intent: router.IntentAct,
Slots: router.Slots{Text: "перезагрузить музик индексер", Fn: "restart", HasFn: true},
}
h.handleHexisAct(ctx, dec)
reqs := nexus.Requests()
if len(reqs) == 0 {
t.Fatal("nexus was never asked")
}
body := string(reqs[0].Body)
if !strings.Contains(body, "muzick indexer") {
t.Fatalf("nexus resolve body = %s, want the name he said", body)
}
}
// TestAnEntityActReachesHexisInsteadOfAsking — the second half of #476. The
// stage-3 gate thins an act with no allowlisted fn, and that question used to
// be the whole turn, so the Hexis path was unreachable from voice or chat.
func TestAnEntityActReachesHexisInsteadOfAsking(t *testing.T) {
ctx := context.Background()
nexus := newFakeNexus(t, fixtureNexusResolved("ent_muzick", "Muzick indexer", "service"))
hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
h := ecoHandler(t, nexus, nil, hexis)
dec := router.Decision{
Utterance: "перезапусти muzick indexer",
Intent: router.IntentAct,
Stage: 3,
Clarify: true,
Slots: router.Slots{Text: "restart status muzick indexer"},
}
reply := h.hexisBeforeClarify(ctx, dec)
if reply == "" {
t.Fatal("a resolvable entity act must reach hexis rather than fall through to the question")
}
if hexis.Count("", "/api/v1") == 0 {
t.Fatal("hexis was never contacted")
}
}
// TestClarifyStillAsksWithoutHexis — the narrowing. No ecosystem, no change:
// she asks exactly what she asked before.
func TestClarifyStillAsksWithoutHexis(t *testing.T) {
h, _, _ := newClarifyHandler(t)
dec := router.Decision{
Utterance: "перезапусти muzick indexer",
Intent: router.IntentAct,
Stage: 3,
Clarify: true,
Slots: router.Slots{Text: "перезагрузить музик индексер"},
}
if reply := h.hexisBeforeClarify(context.Background(), dec); reply != "" {
t.Fatalf("no hexis must mean no reply, got %q", reply)
}
if _, asked := h.askClarify(voiceCtx(), dec); !asked {
t.Fatal("she must still ask what to do")
}
}
+1 -1
View File
@@ -584,7 +584,7 @@ func TestDigestSev4BypassesQueue(t *testing.T) {
ctx := context.Background()
now := refNow()
markPresent(t, st, ctx, now)
if _, err := st.SetValue(ctx, store.KindSelf, "service_down", "poll:uptimekuma", "down", now); err != nil {
if _, err := st.SetValue(ctx, store.KindSelf, "service_down:db", "poll:uptimekuma", "down", now); err != nil {
t.Fatalf("seed service_down: %v", err)
}
sink := &fakeSink{}
+3
View File
@@ -351,6 +351,9 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
// and park the request (clarify.go); otherwise the replier's canned reply
// stands.
if dec.Clarify {
if reply := h.hexisBeforeClarify(ctx, dec); reply != "" {
return withNotice(expiredNotice, reply)
}
if question, asked := h.askClarify(ctx, dec); asked {
return withNotice(expiredNotice, question)
}
+4 -1
View File
@@ -238,7 +238,10 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
// ----- dialogue (multi-turn slot carry-over; 2-min follow-up window) -----
// Store-backed when the daemon passes a store, so a restart mid-conversation
// keeps the thread (Vikunja #363). Sessions past their TTL are dropped on
// load, never revived. Clarify's parked question stays in memory only.
// load, never revived. Clarify's parked question stays in memory only, and
// that is a decision rather than an omission (Vikunja #385, docs/design.md):
// a restart expires it, so the thread comes back and the open question does
// not.
var dialogueSessions *dialogue.SessionStore
if dataStore != nil {
dialogueSessions = dialogue.NewPersistentSessionStore(2*time.Minute, dataStore)
+71 -21
View File
@@ -140,6 +140,10 @@ type poller struct {
wgIface string
wgCmd string
// kumaSeen — monitor name → state as of the last poll, so a monitor that
// disappears from the gauge can be marked unknown instead of staying down.
kumaSeen map[string]string
// zen is nil unless a token file was configured — money tracking is a
// capability, off by default like weather and telegram.
zen *zenmoney.Client
@@ -333,50 +337,96 @@ func maxSeverity(a netdataAlarms) string {
return sev
}
// ---- kuma: monitor_status gauge → aggregate service_down -------------------
// ---- kuma: monitor_status gauge → one fact per monitor ---------------------
// Kuma exposes Prometheus text: `monitor_status{...,monitor_name="X"} V` where
// V is 1=up 0=down 2=pending 3=maintenance. We reduce to one aggregate the
// existing ServiceDownRule consumes: "down" if ANY monitor reads 0, else "up".
// Per-service granularity is a later add (a fact per monitor) — the MVP nudge
// only needs "something is down".
var kumaLine = regexp.MustCompile(`^monitor_status\{([^}]*)\}\s+([0-9.eE+-]+)`)
// V is 1=up 0=down 2=pending 3=maintenance. We write one fact per monitor,
// keyed `service_down:<monitor name>`, because the nudge has to say WHICH
// service is down. The aggregate this used to write could not, which is why
// the rule shipped disabled.
var (
kumaLine = regexp.MustCompile(`^monitor_status\{([^}]*)\}\s+([0-9.eE+-]+)`)
kumaName = regexp.MustCompile(`monitor_name="([^"]*)"`)
)
func (p *poller) pollKuma(ctx context.Context, now time.Time) error {
body, err := p.get(ctx, p.kumaURL, p.kumaKey)
if err != nil {
return err
}
down, seen := kumaAnyDown(body)
if !seen {
states := kumaMonitors(body)
if len(states) == 0 {
return fmt.Errorf("no monitor_status metrics (auth/endpoint wrong?)")
}
val := "up"
if down {
val = "down"
var firstErr error
for name, val := range states {
if err := p.writeIfChanged(ctx, kumaFactKey(name), kumaSource, val, now); err != nil && firstErr == nil {
firstErr = err // one bad monitor must not blind the rest
}
}
return p.writeIfChanged(ctx, "service_down", "poll:uptimekuma", val, now)
// A monitor deleted in kuma stops appearing in the gauge, and its last fact
// would otherwise read "down" forever. Mark it unknown, which no rule fires
// on. The seen-set is in memory, so a restart forgets it — harmless, since
// the next poll that still lacks the monitor says nothing new either.
for name := range p.kumaSeen {
if _, still := states[name]; !still {
if err := p.writeIfChanged(ctx, kumaFactKey(name), kumaSource, "unknown", now); err != nil && firstErr == nil {
firstErr = err
}
}
}
p.kumaSeen = states
return firstErr
}
// kumaAnyDown parses kuma's Prometheus text: down=true if any monitor reads 0
// (pending=2/maintenance=3 are not "down"). seen=false ⇒ no monitor_status
// lines matched at all (wrong endpoint or auth rejected before the body).
func kumaAnyDown(body []byte) (down, seen bool) {
// kumaSource — the provenance the loop rule requires. Written here, checked in
// loop.ServiceDownRule; a poller under any other source cannot fire it.
const kumaSource = "poll:uptimekuma"
// kumaFactKey — the fact key for one monitor. The suffix is the name he hears,
// so it stays as kuma spells it rather than being slugged into something else.
func kumaFactKey(name string) string { return "service_down:" + name }
// kumaMonitors parses kuma's Prometheus text into monitor name → state
// ("up"/"down"/"pending"/"maintenance"). An empty map means no monitor_status
// line matched at all (wrong endpoint, or auth rejected before the body).
// A line with no monitor_name label is skipped: a fact nobody can name is
// exactly the thing this replaced.
func kumaMonitors(body []byte) map[string]string {
out := make(map[string]string)
for _, line := range strings.Split(string(body), "\n") {
m := kumaLine.FindStringSubmatch(strings.TrimSpace(line))
if m == nil {
continue
}
seen = true
nm := kumaName.FindStringSubmatch(m[1])
if nm == nil || strings.TrimSpace(nm[1]) == "" {
continue
}
v, err := strconv.ParseFloat(m[2], 64)
if err != nil {
continue
}
if v == 0 {
down = true
}
out[strings.TrimSpace(nm[1])] = kumaState(v)
}
return out
}
// kumaState — the gauge's four values. pending and maintenance are not "down":
// a monitor paused in kuma should silence that monitor, not page him.
func kumaState(v float64) string {
switch v {
case 0:
return "down"
case 1:
return "up"
case 2:
return "pending"
case 3:
return "maintenance"
default:
return "unknown"
}
return down, seen
}
// ---- helpers ---------------------------------------------------------------
+36 -12
View File
@@ -35,22 +35,46 @@ func TestMaxSeverity(t *testing.T) {
}
}
func TestKumaAnyDown(t *testing.T) {
func TestKumaMonitorsNamesEveryOne(t *testing.T) {
cases := []struct {
body string
down, seen bool
name string
body string
want map[string]string
}{
{"", false, false},
{`monitor_status{monitor_name="web"} 1`, false, true},
{`monitor_status{monitor_name="web"} 1` + "\n" + `monitor_status{monitor_name="db"} 0`, true, true},
{`monitor_status{monitor_name="mnt"} 3`, false, true}, // maintenance ≠ down
{`# HELP monitor_status ...`, false, false},
{"empty body", "", map[string]string{}},
{"help line only", `# HELP monitor_status ...`, map[string]string{}},
{
"one up one down",
`monitor_status{monitor_name="web"} 1` + "\n" + `monitor_status{monitor_name="db"} 0`,
map[string]string{"web": "up", "db": "down"},
},
{"maintenance is not down", `monitor_status{monitor_name="mnt"} 3`, map[string]string{"mnt": "maintenance"}},
{"pending is not down", `monitor_status{monitor_name="p"} 2`, map[string]string{"p": "pending"}},
{
"other labels do not hide the name",
`monitor_status{monitor_type="http",monitor_name="ci",monitor_url="x"} 0`,
map[string]string{"ci": "down"},
},
{"a nameless line is skipped", `monitor_status{monitor_type="http"} 0`, map[string]string{}},
}
for _, c := range cases {
down, seen := kumaAnyDown([]byte(c.body))
if down != c.down || seen != c.seen {
t.Errorf("kumaAnyDown(%q) = (%v,%v), want (%v,%v)", c.body, down, seen, c.down, c.seen)
}
t.Run(c.name, func(t *testing.T) {
got := kumaMonitors([]byte(c.body))
if len(got) != len(c.want) {
t.Fatalf("kumaMonitors = %v, want %v", got, c.want)
}
for k, v := range c.want {
if got[k] != v {
t.Errorf("monitor %q = %q, want %q", k, got[k], v)
}
}
})
}
}
func TestKumaFactKeyCarriesTheName(t *testing.T) {
if got := kumaFactKey("nexus db"); got != "service_down:nexus db" {
t.Errorf("kumaFactKey = %q", got)
}
}
+32 -1
View File
@@ -139,7 +139,10 @@ func TestHandleAmbientIgnoresNonMeetings(t *testing.T) {
}
func TestHandleAmbientAuth(t *testing.T) {
body := `{"title":"Планёрка 10:00","posted_at":"2026-08-03T09:40:00Z"}`
// "завтра" so the meeting is in the future in every zone: the clock in the
// text is a local wall clock and posted_at is a Z instant, so a bare "10:00"
// is already stale on a box east of UTC and stores nothing.
body := `{"title":"Планёрка завтра 10:00","posted_at":"2026-08-03T09:40:00Z"}`
newReq := func(hdr, val string) *http.Request {
r := httptest.NewRequest(http.MethodPost, "/api/ambient", strings.NewReader(body))
@@ -245,3 +248,31 @@ func TestHandleAmbientBadInput(t *testing.T) {
}
})
}
// The Z-instant defect end to end: a phone posts an RFC 3339 instant in UTC and
// the clock inside the text is his wall clock. On a UTC+4 box a 14:30 standup
// used to be stored at 18:30, and the size of the error was the deploy's offset.
func TestHandleAmbientStoresTheWallClockHeRead(t *testing.T) {
// No zone juggling: the assertion is that the stored wall clock is the one
// he read, whatever zone the box is in. That is false under the old code
// on every box except a UTC one.
core := &ambientCore{}
rr, resp := postAmbient(t, core, ambientTestToken, calendar.Notification{
Package: "com.slack",
Title: "Standup",
Text: "созвон завтра в 14:30",
Posted: time.Date(2026, 8, 2, 9, 0, 0, 0, time.UTC),
})
if rr.Code != http.StatusCreated {
t.Fatalf("status = %d, want 201: %s", rr.Code, rr.Body)
}
if !strings.HasSuffix(resp.Key, "_Standup") {
t.Errorf("key = %q, want a key naming the meeting", resp.Key)
}
if len(core.writeLog) != 1 {
t.Fatalf("expected 1 fact write, got %d", len(core.writeLog))
}
if got := core.writeLog[0].Value; got != "Standup @ 14:30-15:00" {
t.Errorf("value = %q, want %q", got, "Standup @ 14:30-15:00")
}
}
+5 -5
View File
@@ -8,12 +8,12 @@
"//disabled_rules": [
"Nudge rules that are not wired at all. Names come from loop.DefaultRules:",
"water, meal, break, service_down, netdata_critical.",
"service_down is off because it cannot say WHICH service — mavpoll folds the",
"whole kuma gauge into one boolean, so the nudge is always the generic 'a",
"service on homesrv is down'. Nothing to act on, every fifteen minutes.",
"Turn it back on once Vikunja #444 lands a fact per monitor."
"service_down is back on: mavpoll now writes one fact per kuma monitor",
"(service_down:<name>), so the nudge names the service and pausing a monitor",
"in kuma silences that monitor. It is also edge-triggered, so a service that",
"stays down is one nudge, not one every fifteen minutes."
],
"disabled_rules": ["service_down"],
"disabled_rules": [],
"phraser": {
"model_path": "/opt/maven/models/llm/qwen3/Qwen3-1.7B-UD-Q4_K_XL.gguf",
+47
View File
@@ -223,6 +223,30 @@ Not alternatives — layers:
Router contract: `[{"intent":<enum>, key?, value?, text?, verb?}, ...]` over
7 intents (`fact, reminder, note, query, act, chat, system`).
#### A restart expires a parked question
Decided 2026-08-04 (Vikunja #385). The follow-up dialogue session survives a
restart; the clarify question parked behind it does not, and neither do the
three yes/no confirms in `voice.go`. `ClarifyStore` stays in memory.
Three reasons, in the order they settle it:
- The clock stops meaning anything. A parked question carries a 90s TTL and an
attempt count. A restart is a gap of unknown length, so a restored question is
either already dead or pretending to be young.
- Restoring the question restores the request behind it. He asked for something,
she asked back, and then the daemon went away. Acting on that minutes later,
against words he has probably given up on, is the misroute the stage 3 gate
exists to avoid.
- She does not announce it either. The expiry notice needs to know a question
was parked, and knowing that across a restart means storing it. One sentence,
in the rare window where he speaks within 90s of a restart, does not pay for a
marker that outlives the thing it describes. His next words route fresh, which
is the correct answer with or without the notice.
So the notice stays what it is: the in-process TTL case, where she really did
wait and really did let go.
### save-where — the two-memory routing axis
One discriminator: **does the loop evaluate a predicate against it?**
@@ -365,6 +389,29 @@ lives in `source`; rules trust provenance.
`source=poll:healthcheck`. A compromised poller must not be able to forge a
trigger.
#### A fact per monitor, not an aggregate
mavpoll writes one fact per kuma monitor, keyed `service_down:<monitor name>`.
It used to fold the whole gauge into a single boolean, and the nudge could then
only say that something on homesrv was down. That is not something he can act
on, so the rule shipped disabled.
Three things follow from the split:
- The key set is no longer known at wiring time. A rule declares
`WantPrefixes` and the gatherer resolves the family per tick, which is the
only prefix read in the loop.
- Pausing a monitor in kuma silences that monitor. Under the aggregate it
silenced nothing, because some other monitor kept the boolean at "down".
- A monitor deleted in kuma would keep its last fact reading "down" forever, so
mavpoll marks a vanished monitor "unknown". No rule fires on "unknown".
The rule is also edge-triggered: it fires on a transition it has not already
nudged about (`State.NudgedSince`). A polled fact is written only when the
value changes, but the predicate reads the current value, so without the edge
check a service that stays down qualifies on every tick and cooldown is the
only brake.
### Presence — concrete scoring
**Combiner — noisy-OR, not weighted sum.** These are independent-ish positive
+24 -2
View File
@@ -68,7 +68,28 @@ var dayWords = map[string]int{
// word ("завтра", "tomorrow") when the notification carries one, and the result
// is refused if it lands more than ambientPastGrace in the past. A bare start
// time gets DefaultReminderDuration.
//
// The clock reading is a wall clock in the daemon's local zone. See
// EventFromNotificationIn.
func EventFromNotification(n Notification) (Event, bool) {
return EventFromNotificationIn(n, time.Local)
}
// EventFromNotificationIn is EventFromNotification against an explicit zone.
//
// "созвон в 14:30" carries no zone, and nobody writing a phone notification
// means 14:30Z. The wall clock used to be resolved against Posted's own zone,
// and a phone posts an RFC 3339 instant ending in Z, so every ambient meeting
// on this box landed four hours late. The size of the error is the deploy's UTC
// offset, which is why it is invisible on a UTC box and wrong everywhere else.
//
// Posted stays an instant in its own zone: it says when the phone showed the
// notification, and the past-grace check compares instants. Only the day and
// the wall clock are read in loc.
func EventFromNotificationIn(n Notification, loc *time.Location) (Event, bool) {
if loc == nil {
loc = time.Local
}
if n.Posted.IsZero() {
return Event{}, false
}
@@ -82,8 +103,9 @@ func EventFromNotification(n Notification) (Event, bool) {
return Event{}, false
}
y, m, d := n.Posted.AddDate(0, 0, dayOffset(line)).Date()
loc := n.Posted.Location()
// The day is Posted's LOCAL day: a notification posted at 23:30Z saying
// "завтра в 09:00" is already tomorrow where he is standing.
y, m, d := n.Posted.In(loc).AddDate(0, 0, dayOffset(line)).Date()
s := time.Date(y, m, d, start.hour, start.min, 0, 0, loc)
// Too far in the past to be the meeting this notification is about. The day
// was inferred, so the honest reading is that the inference was wrong.
+59 -10
View File
@@ -74,12 +74,12 @@ func TestEventFromNotification(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
ev, ok := EventFromNotification(Notification{
ev, ok := EventFromNotificationIn(Notification{
Package: "com.google.android.gm",
Title: tt.title,
Text: tt.text,
Posted: posted,
})
}, posted.Location())
if ok != tt.wantOK {
t.Fatalf("ok = %v, want %v (event %+v)", ok, tt.wantOK, ev)
}
@@ -98,8 +98,8 @@ func TestEventFromNotification(t *testing.T) {
if !ev.End.After(ev.Start) {
t.Errorf("end %v must be after start %v", ev.End, ev.Start)
}
// The event lands on the day the phone showed it, in the phone's
// location — not shifted into UTC.
// The event lands on the day the phone showed it, in the zone it
// was resolved against — never shifted into UTC.
if ev.Start.Location() != posted.Location() {
t.Errorf("location = %v, want %v", ev.Start.Location(), posted.Location())
}
@@ -162,10 +162,10 @@ func TestEventFromNotificationDayWords(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
ev, ok := EventFromNotification(Notification{
ev, ok := EventFromNotificationIn(Notification{
Package: "com.google.android.calendar",
Title: tt.title, Text: tt.text, Posted: tt.posted,
})
}, tt.posted.Location())
if ok != tt.wantOK {
t.Fatalf("ok = %v, want %v (event %+v)", ok, tt.wantOK, ev)
}
@@ -189,10 +189,10 @@ func TestEventFromNotificationDayWords(t *testing.T) {
// summary makes "Завтра Планёрка" the name of the meeting, and FactKey folds
// that into the key.
func TestEventFromNotificationDropsDayWordFromSummary(t *testing.T) {
ev, ok := EventFromNotification(Notification{
ev, ok := EventFromNotificationIn(Notification{
Title: "Завтра Планёрка 09:00",
Posted: time.Date(2026, 8, 3, 21, 0, 0, 0, time.UTC),
})
}, time.UTC)
if !ok {
t.Fatal("expected an event")
}
@@ -209,10 +209,10 @@ func TestEventFromNotificationNeedsPostedAt(t *testing.T) {
// An ambient event must never be indistinguishable from a calendar read.
func TestAmbientEventsAreStoredAtReducedConfidence(t *testing.T) {
ev, ok := EventFromNotification(Notification{
ev, ok := EventFromNotificationIn(Notification{
Title: "Планёрка 10:00-10:30",
Posted: time.Date(2026, 8, 3, 9, 0, 0, 0, time.UTC),
})
}, time.UTC)
if !ok {
t.Fatal("expected an event")
}
@@ -237,3 +237,52 @@ func TestStripClock(t *testing.T) {
}
}
}
// The defect this file's zone handling exists for: a phone posts an RFC 3339
// instant ending in Z, and "созвон в 14:30" used to be resolved against that
// Z, so on a UTC+4 box the meeting was stored at 18:30. A wall clock in a
// notification is local by construction.
func TestNotificationClockIsLocalNotUTC(t *testing.T) {
samara := time.FixedZone("+04", 4*3600)
n := Notification{
Package: "com.slack",
Title: "Standup",
Text: "созвон в 14:30",
Posted: time.Date(2026, 8, 2, 9, 0, 0, 0, time.UTC), // 13:00 local
}
ev, ok := EventFromNotificationIn(n, samara)
if !ok {
t.Fatal("expected an event")
}
if got := ev.Start.Format("15:04"); got != "14:30" {
t.Errorf("start = %s local, want 14:30", got)
}
if got := ev.Start.UTC().Format("15:04"); got != "10:30" {
t.Errorf("start = %sZ, want 10:30Z (14:30 at UTC+4)", got)
}
if ev.Start.Location() != samara {
t.Errorf("location = %v, want %v", ev.Start.Location(), samara)
}
// The stored key is the local day, so it files under the day he lived.
if want, got := "calendar_event_20260802_Standup", FactKeyIn(ev, samara); got != want {
t.Errorf("FactKey = %q, want %q", got, want)
}
}
// A notification posted late in the UTC evening is already the next day where
// he is standing. The day must come from the local clock, not from Posted's.
func TestNotificationDayIsTheLocalDay(t *testing.T) {
samara := time.FixedZone("+04", 4*3600)
n := Notification{
Title: "Планёрка 09:00",
Text: "завтра",
Posted: time.Date(2026, 8, 2, 21, 0, 0, 0, time.UTC), // 03-08 01:00 local
}
ev, ok := EventFromNotificationIn(n, samara)
if !ok {
t.Fatal("expected an event")
}
if y, m, d := ev.Start.Date(); y != 2026 || m != time.August || d != 4 {
t.Errorf("date = %d-%02d-%02d, want 2026-08-04 (tomorrow, locally)", y, m, d)
}
}
+5 -4
View File
@@ -149,10 +149,11 @@ type Config struct {
//
// Rules are code, not config (see loop.DefaultRules), and that stays true:
// this only subtracts. It exists because a rule can be right in principle
// and useless in practice — kuma's service_down cannot name the service it
// is nudging about (Vikunja #444), so being told "a service on homesrv is
// down" every fifteen minutes is noise with no action attached. Turning it
// off beats learning to ignore her.
// and useless in practice. service_down was the case that forced it: it
// could not name the service it was nudging about, so being told "a service
// on homesrv is down" every fifteen minutes was noise with no action
// attached. That is fixed — one fact per kuma monitor — and the rule ships
// enabled again. The escape hatch stays.
//
// A disabled rule is never gathered for, never evaluated, and never
// delivered on any channel. Unknown names are ignored, so removing a rule
+8
View File
@@ -57,6 +57,14 @@ func (q *PendingQuestion) CanAsk() bool {
// ClarifyStore holds the parked questions. Same shape and locking as
// SessionStore: keyed by dialogue id, expired entries dropped on read.
//
// Memory only, deliberately, unlike SessionStore — a restart expires every
// parked question and she does not announce that it happened (Vikunja #385,
// written down in docs/design.md). The 90s TTL and the attempt count measure a
// pause in one conversation, and a restart is a gap of unknown length, so a
// restored question would either be dead already or lying about its age. His
// next words route fresh, which is the right answer with or without a notice.
// Do not give this store a persister without re-arguing that.
type ClarifyStore struct {
mu sync.RWMutex
questions map[string]*PendingQuestion
+3 -3
View File
@@ -103,7 +103,7 @@ func TestExplainGate_PresenceAway(t *testing.T) {
func TestExplainGate_PresenceAwayOpsBypass(t *testing.T) {
now := refTime()
s := State{Now: now, Presence: store.Away,
Facts: map[string]store.Fact{"service_down": factAt("service_down", "poll:uptimekuma", `"down"`, now.Add(-1*time.Minute))},
Facts: map[string]store.Fact{"service_down:db": factAt("service_down:db", "poll:uptimekuma", `"down"`, now.Add(-1*time.Minute))},
}
r := ServiceDownRule() // Sev4 ops
passed, blocked, d := ExplainGate(s, r)
@@ -259,8 +259,8 @@ func TestExplainTick_WinnerRecorded(t *testing.T) {
Now: now,
Presence: store.Present,
Facts: map[string]store.Fact{
"water": factAt("water", "tap:water", `"250ml"`, now.Add(-4*time.Hour)),
"service_down": factAt("service_down", "poll:uptimekuma", `"down"`, now.Add(-1*time.Minute)),
"water": factAt("water", "tap:water", `"250ml"`, now.Add(-4*time.Hour)),
"service_down:db": factAt("service_down:db", "poll:uptimekuma", `"down"`, now.Add(-1*time.Minute)),
},
}
cand, trace := ExplainTick(s, DefaultRules())
+6 -6
View File
@@ -198,12 +198,12 @@ func TestTickNeverDogpilesAndPicksLoudest(t *testing.T) {
Now: now,
Presence: store.Present,
Facts: map[string]store.Fact{
"water": ago("water", "tap:water", `"250ml"`, 5*time.Hour),
"meal": ago("meal", "voice", `"lunch"`, 8*time.Hour),
"desk_active": ago("desk_active", "infer:hyprland", "1", 30*time.Second),
"break": ago("break", "voice", `"walk"`, 3*time.Hour),
"service_down": ago("service_down", "poll:uptimekuma", `"down"`, time.Minute),
"netdata_alarm": ago("netdata_alarm", "poll:netdata", `"critical"`, time.Minute),
"water": ago("water", "tap:water", `"250ml"`, 5*time.Hour),
"meal": ago("meal", "voice", `"lunch"`, 8*time.Hour),
"desk_active": ago("desk_active", "infer:hyprland", "1", 30*time.Second),
"break": ago("break", "voice", `"walk"`, 3*time.Hour),
"service_down:db": ago("service_down:db", "poll:uptimekuma", `"down"`, time.Minute),
"netdata_alarm": ago("netdata_alarm", "poll:netdata", `"critical"`, time.Minute),
},
}
// sanity: every rule really does want to fire, so the pick is a real choice.
+14
View File
@@ -91,6 +91,20 @@ func (g *Gatherer) GatherState(ctx context.Context, now time.Time) (State, []sto
return State{}, nil, err
}
// prefix families — the keys a rule cannot name at wiring time (one fact
// per kuma monitor). Loaded into the same map; State.FactsUnder reads them.
for _, r := range g.rules {
for _, p := range r.WantPrefixes {
fam, err := g.store.LatestFactsByPrefix(ctx, p)
if err != nil {
return State{}, nil, err
}
for _, f := range fam {
facts[f.Key] = f
}
}
}
// last nudge per rule + cooldown-until derived from the active cooldown.
// "active" = the feedback tuner's persisted base if one exists, else the
// rule's static Base. LatestFactBySource is the trust-by-provenance read
+47
View File
@@ -0,0 +1,47 @@
package loop
import (
"context"
"path/filepath"
"testing"
"time"
"github.com/kami/maven/internal/store"
)
// The gatherer is the only impure piece, and a rule over a prefix has no keys
// to declare at wiring time. This is the end of that path: mavpoll's per-monitor
// facts reach the snapshot, and the rule fires on the one that is down.
func TestGatherStateLoadsPrefixFamilies(t *testing.T) {
ctx := context.Background()
s, err := store.Open(ctx, filepath.Join(t.TempDir(), "loop_test.db"))
if err != nil {
t.Fatalf("Open: %v", err)
}
t.Cleanup(func() { _ = s.Close() })
now := time.Now().UTC().Truncate(time.Millisecond)
for key, val := range map[string]string{
"service_down:db": "down",
"service_down:web": "up",
} {
if _, err := s.SetValue(ctx, store.KindEnv, key, ServiceDownSource, val, now.Add(-time.Minute)); err != nil {
t.Fatalf("SetValue %s: %v", key, err)
}
}
rules := []Rule{ServiceDownRule()}
st, _, err := NewGatherer(s, rules).GatherState(ctx, now)
if err != nil {
t.Fatalf("GatherState: %v", err)
}
if _, ok := st.Facts["service_down:db"]; !ok {
t.Fatalf("prefix family not gathered: %v", st.Facts)
}
if got := DownServices(st); len(got) != 1 || got[0] != "db" {
t.Fatalf("DownServices = %v, want [db]", got)
}
if !rules[0].Predicate(st) {
t.Fatal("the rule must fire on a gathered per-monitor fact")
}
}
+4 -4
View File
@@ -82,7 +82,7 @@ func TestTickOpsHardSurvivesAwayAndQuiet(t *testing.T) {
Presence: store.Away,
QuietHours: true,
Facts: map[string]store.Fact{
"service_down": factAt("service_down", "poll:uptimekuma", `"down"`, now.Add(-1*time.Minute)),
"service_down:db": factAt("service_down:db", "poll:uptimekuma", `"down"`, now.Add(-1*time.Minute)),
},
}
got := Tick(s, DefaultRules())
@@ -99,7 +99,7 @@ func TestTickServiceSourceTrustRefusesForgedTrigger(t *testing.T) {
Now: now,
Presence: store.Present,
Facts: map[string]store.Fact{
"service_down": factAt("service_down", "ambient", `"down"`, now.Add(-1*time.Minute)),
"service_down:db": factAt("service_down:db", "ambient", `"down"`, now.Add(-1*time.Minute)),
},
}
if got := Tick(s, DefaultRules()); got != nil {
@@ -115,8 +115,8 @@ func TestTickOneNudgePerTickMaxSeverityWins(t *testing.T) {
Now: now,
Presence: store.Present,
Facts: map[string]store.Fact{
"water": factAt("water", "tap:water", `"250ml"`, now.Add(-4*time.Hour)),
"service_down": factAt("service_down", "poll:uptimekuma", `"down"`, now.Add(-1*time.Minute)),
"water": factAt("water", "tap:water", `"250ml"`, now.Add(-4*time.Hour)),
"service_down:db": factAt("service_down:db", "poll:uptimekuma", `"down"`, now.Add(-1*time.Minute)),
},
}
got := Tick(s, DefaultRules())
+55 -13
View File
@@ -28,6 +28,13 @@ type Rule struct {
// that check itself, leave this empty. Otherwise set to the key(s) the rule
// needs and the gate will skip the rule when any are missing.
InertWhenNoData []string
// WantPrefixes — key prefixes whose whole family the gatherer must load.
// InertWhenNoData names keys that exist at wiring time; a rule over a key
// set that is only known at read time (one fact per kuma monitor) declares
// the prefix here instead. Prefixes never make a rule inert: an empty
// family is the predicate's own "no data" case.
WantPrefixes []string
}
// Cooldown — tunable bounded by the envelope so a weird week (auto-tuned) can't
@@ -98,23 +105,58 @@ func BreakRule() Rule {
}
}
// ServiceDownRule — sev4 ops hard: the `service_down` aggregate fact reads
// "down". Source must be poll:uptimekuma — kuma is the source of truth for
// service up/down (mavpoll writes this key). The predicate is provenance-scoped:
// a compromised poller writing under a different source can't forge the trigger.
// ServiceDownPrefix — mavpoll writes one fact per kuma monitor under this
// prefix, `service_down:<monitor name>`. The suffix is the name he hears.
const ServiceDownPrefix = "service_down:"
// ServiceDownSource — kuma is the source of truth for service up/down. The
// rule is provenance-scoped: a poller writing under a different source cannot
// forge the trigger.
const ServiceDownSource = "poll:uptimekuma"
// DownServices — the monitors currently reading "down", by name, in key order.
//
// Pure, and the rule and the phraser both call it, so the message can never
// name a service the predicate did not fire on.
func DownServices(s State) []string {
var out []string
for _, f := range s.FactsUnder(ServiceDownPrefix) {
if f.Source == ServiceDownSource && f.Value == `"down"` {
out = append(out, strings.TrimPrefix(f.Key, ServiceDownPrefix))
}
}
return out
}
// ServiceDownRule — sev4 ops hard: at least one kuma monitor reads "down".
//
// It used to read one aggregate `service_down` fact, which is why it was
// disabled in deploy: the nudge could say that something on homesrv was down
// but never which thing. Per-monitor facts fix that, and pausing a monitor in
// kuma now silences that monitor rather than nothing.
//
// Edge-triggered — see State.NudgedSince. Without it a service that stays down
// for a day qualifies on every tick and cooldown alone is the only brake.
func ServiceDownRule() Rule {
return Rule{
Name: "service_down",
Severity: Sev4,
Cooldown: Cooldown{Base: 15 * time.Minute, Min: 5 * time.Minute, Max: 1 * time.Hour},
InertWhenNoData: []string{"service_down"},
Name: "service_down",
Severity: Sev4,
Cooldown: Cooldown{Base: 15 * time.Minute, Min: 5 * time.Minute, Max: 1 * time.Hour},
WantPrefixes: []string{ServiceDownPrefix},
Predicate: func(s State) bool {
f, ok := s.Fact("service_down")
if !ok || f.Ts.IsZero() {
return false
var newest time.Time
for _, f := range s.FactsUnder(ServiceDownPrefix) {
if f.Source != ServiceDownSource || f.Value != `"down"` {
continue
}
if f.Ts.After(newest) {
newest = f.Ts
}
}
// value is json `"down"`; trivial check keyed off source provenance.
return f.Source == "poll:uptimekuma" && f.Value == `"down"`
if newest.IsZero() {
return false // nothing down, or no data at all → shut up
}
return !s.NudgedSince("service_down", newest)
},
}
}
+80 -15
View File
@@ -193,13 +193,13 @@ func TestOpsRulePredicates(t *testing.T) {
{
name: "service_down fires on a kuma down fact",
rule: ServiceDownRule(),
facts: map[string]store.Fact{"service_down": ago("service_down", "poll:uptimekuma", `"down"`, time.Minute)},
facts: map[string]store.Fact{"service_down:db": ago("service_down:db", "poll:uptimekuma", `"down"`, time.Minute)},
want: true,
},
{
name: "service_down quiet when kuma says up",
rule: ServiceDownRule(),
facts: map[string]store.Fact{"service_down": ago("service_down", "poll:uptimekuma", `"up"`, time.Minute)},
facts: map[string]store.Fact{"service_down:db": ago("service_down:db", "poll:uptimekuma", `"up"`, time.Minute)},
want: false,
},
{
@@ -211,38 +211,38 @@ func TestOpsRulePredicates(t *testing.T) {
{
name: "service_down quiet on a zero-timestamp fact",
rule: ServiceDownRule(),
facts: map[string]store.Fact{"service_down": {Key: "service_down", Source: "poll:uptimekuma", Value: `"down"`}},
facts: map[string]store.Fact{"service_down:db": {Key: "service_down:db", Source: "poll:uptimekuma", Value: `"down"`}},
want: false,
},
// forgery attempts — right value, wrong writer.
{
name: "service_down refuses a forgery from the netdata poller",
rule: ServiceDownRule(),
facts: map[string]store.Fact{"service_down": ago("service_down", "poll:netdata", `"down"`, time.Minute)},
facts: map[string]store.Fact{"service_down:db": ago("service_down:db", "poll:netdata", `"down"`, time.Minute)},
want: false,
},
{
name: "service_down refuses a forgery from ambient audio",
rule: ServiceDownRule(),
facts: map[string]store.Fact{"service_down": ago("service_down", "ambient:other", `"down"`, time.Minute)},
facts: map[string]store.Fact{"service_down:db": ago("service_down:db", "ambient:other", `"down"`, time.Minute)},
want: false,
},
{
name: "service_down refuses a forgery from the user's own voice",
rule: ServiceDownRule(),
facts: map[string]store.Fact{"service_down": ago("service_down", "voice", `"down"`, time.Minute)},
facts: map[string]store.Fact{"service_down:db": ago("service_down:db", "voice", `"down"`, time.Minute)},
want: false,
},
{
name: "service_down refuses a source that only looks like kuma",
rule: ServiceDownRule(),
facts: map[string]store.Fact{"service_down": ago("service_down", "poll:uptimekuma-staging", `"down"`, time.Minute)},
facts: map[string]store.Fact{"service_down:db": ago("service_down:db", "poll:uptimekuma-staging", `"down"`, time.Minute)},
want: false,
},
{
name: "service_down refuses an unquoted down value",
rule: ServiceDownRule(),
facts: map[string]store.Fact{"service_down": ago("service_down", "poll:uptimekuma", `down`, time.Minute)},
facts: map[string]store.Fact{"service_down:db": ago("service_down:db", "poll:uptimekuma", `down`, time.Minute)},
want: false,
},
@@ -312,9 +312,11 @@ func TestOpsRulePredicates(t *testing.T) {
// a second no-data backstop, so a rule that forgets it loses the safety net
// even if its predicate happens to check.
func TestDefaultRulesDeclareInertKeys(t *testing.T) {
// A rule over a key set that only exists at read time declares a prefix
// instead — the gatherer still needs to be told what to load.
for _, r := range DefaultRules() {
if len(r.InertWhenNoData) == 0 {
t.Errorf("rule %q declares no InertWhenNoData keys", r.Name)
if len(r.InertWhenNoData) == 0 && len(r.WantPrefixes) == 0 {
t.Errorf("rule %q declares neither InertWhenNoData keys nor WantPrefixes", r.Name)
}
}
}
@@ -377,11 +379,11 @@ func TestDefaultRuleCooldownsAreBounded(t *testing.T) {
// hidden state, no clock reads.
func TestPredicatesArePure(t *testing.T) {
s := stateWith(map[string]store.Fact{
"water": ago("water", "tap:water", `"250ml"`, 4*time.Hour),
"meal": ago("meal", "voice", `"lunch"`, 7*time.Hour),
"desk_active": ago("desk_active", "infer:hyprland", "1", 30*time.Second),
"break": ago("break", "voice", `"walk"`, 2*time.Hour),
"service_down": ago("service_down", "poll:uptimekuma", `"down"`, time.Minute),
"water": ago("water", "tap:water", `"250ml"`, 4*time.Hour),
"meal": ago("meal", "voice", `"lunch"`, 7*time.Hour),
"desk_active": ago("desk_active", "infer:hyprland", "1", 30*time.Second),
"break": ago("break", "voice", `"walk"`, 2*time.Hour),
"service_down:db": ago("service_down:db", "poll:uptimekuma", `"down"`, time.Minute),
})
for _, r := range DefaultRules() {
first := r.Predicate(s)
@@ -434,3 +436,66 @@ func TestRulesExceptEmptyKeepsEverything(t *testing.T) {
t.Errorf("rules = %v, dropped = %v", ruleNames(rules), dropped)
}
}
// ---------------------------- per-monitor service_down -----------------------
// The rule must name what fired on it, and the phraser reads the same helper,
// so a service that is up can never be spoken as down.
func TestDownServicesNamesOnlyTheDownOnes(t *testing.T) {
s := State{
Now: refTime(),
Facts: map[string]store.Fact{
"service_down:web": ago("service_down:web", ServiceDownSource, `"up"`, time.Minute),
"service_down:db": ago("service_down:db", ServiceDownSource, `"down"`, time.Minute),
"service_down:vault": ago("service_down:vault", ServiceDownSource, `"down"`, time.Minute),
"service_down:paused": ago("service_down:paused", ServiceDownSource, `"maintenance"`, time.Minute),
"service_down:forged": ago("service_down:forged", "voice", `"down"`, time.Minute),
"service_down:missing": ago("service_down:missing", ServiceDownSource, `"unknown"`, time.Minute),
},
}
got := DownServices(s)
want := []string{"db", "vault"} // key order, so speech is stable
if len(got) != len(want) {
t.Fatalf("DownServices = %v, want %v", got, want)
}
for i := range want {
if got[i] != want[i] {
t.Fatalf("DownServices = %v, want %v", got, want)
}
}
}
// A monitor paused in kuma must silence that monitor. Before per-monitor facts
// the aggregate stayed "down" and pausing achieved nothing.
func TestPausedMonitorSilencesOnlyItself(t *testing.T) {
base := map[string]store.Fact{
"service_down:db": ago("service_down:db", ServiceDownSource, `"maintenance"`, time.Minute),
"service_down:web": ago("service_down:web", ServiceDownSource, `"down"`, time.Minute),
}
if !ServiceDownRule().Predicate(State{Now: refTime(), Facts: base}) {
t.Fatal("web is still down, the rule must fire")
}
delete(base, "service_down:web")
if ServiceDownRule().Predicate(State{Now: refTime(), Facts: base}) {
t.Fatal("only a paused monitor is left, the rule must be quiet")
}
}
// Edge-triggered: he is told once per transition. A service that stays down
// for a day used to qualify on every tick, with cooldown as the only brake.
func TestServiceDownFiresOncePerTransition(t *testing.T) {
down := ago("service_down:db", ServiceDownSource, `"down"`, time.Hour)
s := State{Now: refTime(), Facts: map[string]store.Fact{"service_down:db": down}}
if !ServiceDownRule().Predicate(s) {
t.Fatal("first sight of the transition must fire")
}
s.LastNudge = map[string]store.Nudge{"service_down": {Ts: down.Ts.Add(time.Minute)}}
if ServiceDownRule().Predicate(s) {
t.Fatal("already told about this transition, must be quiet")
}
// A second service goes down after that nudge — a new edge, so it fires.
s.Facts["service_down:web"] = ago("service_down:web", ServiceDownSource, `"down"`, time.Minute)
if !ServiceDownRule().Predicate(s) {
t.Fatal("a later transition must fire again")
}
}
+28
View File
@@ -23,6 +23,8 @@
package loop
import (
"sort"
"strings"
"time"
"github.com/kami/maven/internal/store"
@@ -95,6 +97,32 @@ func (s State) Fact(key string) (store.Fact, bool) {
return f, true
}
// FactsUnder returns every gathered fact whose key starts with prefix, ordered
// by key so a caller that names them speaks them in a stable order. Facts with
// a zero Ts are skipped, the same "no data" rule Fact applies.
func (s State) FactsUnder(prefix string) []store.Fact {
var out []store.Fact
for k, f := range s.Facts {
if strings.HasPrefix(k, prefix) && !f.Ts.IsZero() {
out = append(out, f)
}
}
sort.Slice(out, func(i, j int) bool { return out[i].Key < out[j].Key })
return out
}
// NudgedSince reports whether rule already sent a nudge at or after ts.
//
// It is what makes a rule edge-triggered. A polled fact is written only when
// the value changes, so its Ts is the moment the service went down — but the
// predicate reads the current value, so a service that stays down keeps
// qualifying forever and cooldown alone only slows the repetition. Asking
// whether he was already told about THIS transition stops it.
func (s State) NudgedSince(rule string, ts time.Time) bool {
n, ok := s.LastNudge[rule]
return ok && !n.Ts.Before(ts)
}
// Since returns the duration since the latest fact for key, or (0,false).
// "false" ⇒ no data ⇒ shuts up when uncertain.
func (s State) Since(key string) (time.Duration, bool) {
+8
View File
@@ -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))
}
+14 -9
View File
@@ -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.
+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.
+35
View File
@@ -254,6 +254,41 @@ func (s *Store) LatestFactBySource(ctx context.Context, key, source string) (Fac
return scanFact(row)
}
// LatestFactsByPrefix — the latest non-voided fact for every key that starts
// with prefix, newest-per-key, ordered by key.
//
// The loop's gatherer loads the keys its rules declare, which works while the
// key set is static. Kuma's monitors are not: one fact per monitor means the
// keys are only known once the gauge is read, so the rule declares the prefix
// and this read resolves it per tick. `_` and `%` are escaped — a monitor name
// is user text and must not act as a LIKE wildcard.
func (s *Store) LatestFactsByPrefix(ctx context.Context, prefix string) ([]Fact, error) {
esc := strings.NewReplacer(`\`, `\\`, `%`, `\%`, `_`, `\_`).Replace(prefix)
rows, err := s.db.QueryContext(ctx, `
SELECT id, ts, kind, key, value, source, confidence, voids_id
FROM facts f
WHERE key LIKE ? ESCAPE '\'
AND id NOT IN (SELECT voids_id FROM facts WHERE voids_id IS NOT NULL)
AND id = (SELECT id FROM facts g
WHERE g.key = f.key
AND g.id NOT IN (SELECT voids_id FROM facts WHERE voids_id IS NOT NULL)
ORDER BY g.ts DESC, g.id DESC LIMIT 1)
ORDER BY key`, esc+"%")
if err != nil {
return nil, fmt.Errorf("facts by prefix %q: %w", prefix, err)
}
defer rows.Close()
var out []Fact
for rows.Next() {
f, err := scanFact(rows)
if err != nil {
return nil, err
}
out = append(out, f)
}
return out, rows.Err()
}
// Since returns how long ago the latest non-voided fact for key landed, or
// (0, ErrNoFact). Implements the `since(key)==null → don't fire` guard from
// the spec — silence on no-data is "shuts up when uncertain".
+62
View File
@@ -0,0 +1,62 @@
package store
import (
"context"
"testing"
"time"
)
// One fact per kuma monitor means the loop cannot name its keys at wiring time,
// so it asks for the family by prefix. The read must return the newest row per
// key and stop at the prefix boundary.
func TestLatestFactsByPrefix(t *testing.T) {
s := newTestStore(t)
ctx := context.Background()
now := time.Now().UTC().Truncate(time.Millisecond)
write := func(key, val string, at time.Time) int64 {
id, err := s.SetValue(ctx, KindEnv, key, "poll:uptimekuma", val, at)
if err != nil {
t.Fatalf("SetValue %s: %v", key, err)
}
return id
}
write("service_down:db", "up", now.Add(-2*time.Hour))
write("service_down:db", "down", now.Add(-time.Hour)) // newer wins
write("service_down:web", "up", now.Add(-time.Hour))
write("service_downtime", "irrelevant", now) // no colon, not in the family
write("water", "250ml", now)
got, err := s.LatestFactsByPrefix(ctx, "service_down:")
if err != nil {
t.Fatalf("LatestFactsByPrefix: %v", err)
}
if len(got) != 2 {
t.Fatalf("got %d facts, want 2: %+v", len(got), got)
}
if got[0].Key != "service_down:db" || got[0].Value != `"down"` {
t.Errorf("first = %s=%s, want the newest db row", got[0].Key, got[0].Value)
}
if got[1].Key != "service_down:web" {
t.Errorf("second = %s, want service_down:web", got[1].Key)
}
}
// A monitor name is user text. An underscore in it must match itself, not act
// as a LIKE wildcard and drag in every other monitor.
func TestLatestFactsByPrefixEscapesWildcards(t *testing.T) {
s := newTestStore(t)
ctx := context.Background()
now := time.Now().UTC().Truncate(time.Millisecond)
for _, k := range []string{"a_b:one", "axb:two"} {
if _, err := s.SetValue(ctx, KindEnv, k, "poll:uptimekuma", "down", now); err != nil {
t.Fatalf("SetValue %s: %v", k, err)
}
}
got, err := s.LatestFactsByPrefix(ctx, "a_b:")
if err != nil {
t.Fatalf("LatestFactsByPrefix: %v", err)
}
if len(got) != 1 || got[0].Key != "a_b:one" {
t.Fatalf("got %+v, want only a_b:one", got)
}
}
+29
View File
@@ -219,6 +219,35 @@ ALTER TABLE reminders ADD COLUMN next_fire_ts INTEGER;`, // #2
// event, and the old rows would otherwise be recited as extra meetings.
// The filter is exact — it keeps any key whose summary part still has a
// letter or a digit in it.
// #19 — unstick the routines accepted before the fire-forever fix
// (Vikunja #377, follow-up to #366). Accepting used to leave accepted_ts
// NULL and a live one-shot reminder behind, and the tick loop skips a row
// with no accepted_ts, so every non-weekly routine accepted before that fix
// has been silent ever since.
//
// Three statements, in this order, per stuck row: adopt created_ts as the
// acceptance time, cancel the reminder that is still holding the schedule,
// then let go of it. Cancelling before clearing matters — clearing first
// loses the only pointer to the reminder and leaves it to fire on its own.
//
// created_ts rather than a fresh timestamp because a migration has no
// clock, and because the first interval should be measured from when he
// said yes. A routine whose interval has already elapsed nudges on the next
// tick, which is what being unstuck looks like.
//
// Weekly rows are included deliberately. Theirs was the case that kept
// working, because the cron reminder reschedules itself — so leaving them
// alone would give them both a cron reminder and a tick-loop schedule for
// one habit, and he would hear it twice.
`UPDATE reminders
SET status = 'cancelled'
WHERE status = 'pending'
AND id IN (SELECT reminder_id FROM proposed_routines
WHERE status = 'accepted' AND accepted_ts IS NULL AND reminder_id IS NOT NULL);
UPDATE proposed_routines
SET accepted_ts = created_ts, reminder_id = NULL
WHERE status = 'accepted' AND accepted_ts IS NULL;`,
}
// migrate applies every migration with a number greater than the DB's current
+67
View File
@@ -3,6 +3,7 @@ package store
import (
"context"
"testing"
"time"
)
func userVersion(t *testing.T, s *Store) int {
@@ -80,3 +81,69 @@ func TestCollapsedCalendarKeysAreDropped(t *testing.T) {
t.Fatalf("%d calendar rows left, want the 2 that identify their event", got)
}
}
// TestStuckRoutinesAreBackfilled — routines accepted before the fire-forever
// fix have accepted_ts NULL and a live reminder, so the tick loop skips them
// and they have been silent ever since (Vikunja #377). The migration touches
// live reminders, which is why it is tested against a real store.
func TestStuckRoutinesAreBackfilled(t *testing.T) {
ctx := context.Background()
s := newTestStore(t)
created := time.Date(2026, 7, 1, 9, 0, 0, 0, time.UTC)
rem, err := s.CreateReminder(ctx, created.Add(time.Hour), "полить цветы", "")
if err != nil {
t.Fatal(err)
}
healthy, err := s.CreateReminder(ctx, created.Add(2*time.Hour), "не трогать", "")
if err != nil {
t.Fatal(err)
}
if _, err := s.db.ExecContext(ctx,
`INSERT INTO proposed_routines (action, object, interval_days, status, created_ts, reminder_id, accepted_ts)
VALUES ('water', 'plants', 7, 'accepted', ?, ?, NULL)`,
created.UnixMilli(), rem); err != nil {
t.Fatal(err)
}
// An already-healthy accepted row, and a still-open proposal: neither is
// this migration's business.
if _, err := s.db.ExecContext(ctx,
`INSERT INTO proposed_routines (action, object, interval_days, status, created_ts, accepted_ts)
VALUES ('feed', 'cat', 1, 'accepted', ?, ?)`,
created.UnixMilli(), created.UnixMilli()); err != nil {
t.Fatal(err)
}
if _, err := s.db.ExecContext(ctx, migrations[18]); err != nil {
t.Fatalf("migration 19: %v", err)
}
accepted, err := s.ListAcceptedRoutines(ctx)
if err != nil || len(accepted) != 2 {
t.Fatalf("ListAcceptedRoutines = %d rows, err=%v, want 2", len(accepted), err)
}
stuck := accepted[0]
if stuck.Object != "plants" {
stuck = accepted[1]
}
if stuck.AcceptedTs == nil || !stuck.AcceptedTs.Equal(created) {
t.Fatalf("accepted_ts = %v, want the creation time", stuck.AcceptedTs)
}
if stuck.ReminderID != nil {
t.Fatalf("reminder_id = %v, want it let go", stuck.ReminderID)
}
// The reminder it was holding is cancelled, and nothing else is.
var status string
if err := s.db.QueryRowContext(ctx, `SELECT status FROM reminders WHERE id = ?`, rem).Scan(&status); err != nil {
t.Fatal(err)
}
if status != ReminderCancelled {
t.Fatalf("linked reminder status = %q, want cancelled", status)
}
if err := s.db.QueryRowContext(ctx, `SELECT status FROM reminders WHERE id = ?`, healthy).Scan(&status); err != nil {
t.Fatal(err)
}
if status != "pending" {
t.Fatalf("unrelated reminder status = %q, want it untouched", status)
}
}