Merge pull request 'safeKey drops Cyrillic, so Russian calendar events on one day collide' (#119) from task/443-safekey-drops-cyrillic-so-russian-calend into master

internal/calendar/calendar.go

@@ -18,6 +18,7 @@ import (
 	"sort"
 	"strings"
 	"time"
+	"unicode"
 )
 
 // Fact sources. A calendar event reaches the store as a
@@ -153,14 +154,20 @@ func Overlapping(events []Event, from, to time.Time) []Event {
 	return out
 }
 
-// safeKey makes a summary safe to use inside a fact key (ASCII alphanumerics
-// and dashes). Non-Latin summaries collapse to their punctuation, which is why
-// the day prefix carries the identity and this only disambiguates within a day.
+// safeKey makes a summary safe to use inside a fact key: letters and digits in
+// any script, plus dashes, with space and underscore folded to a dash.
+//
+// It kept ASCII only until 04-08-2026, and dropped everything else. His
+// calendar is Russian, so "Встреча с Аней" and "Обед с мамой" both reduced to
+// "--" and produced the same key on the same day — the second event of the day
+// silently overwrote the first (Vikunja #443). Letting the letters through is
+// what makes the key identify the event. Migration #18 drops the keys written
+// under the old rule; they are re-derived on the next poll.
 func safeKey(s string) string {
 	var b strings.Builder
 	for _, r := range s {
 		switch {
-		case (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9') || r == '-':
+		case unicode.IsLetter(r) || unicode.IsDigit(r) || r == '-':
 			b.WriteRune(r)
 		case r == ' ' || r == '_':
 			b.WriteRune('-')

internal/calendar/calendar_test.go

@@ -139,6 +139,9 @@ func TestSafeKey(t *testing.T) {
 		{"Hello_World", "Hello-World"},
 		{"special@#$chars!!", "specialchars"},
 		{"ALL_CAPS_123", "ALL-CAPS-123"},
+		// His calendar is Russian. These reduced to "--" and "--" (Vikunja #443).
+		{"Встреча с Аней", "Встреча-с-Аней"},
+		{"Обед с мамой", "Обед-с-мамой"},
 	}
 	for _, tt := range tests {
 		if got := safeKey(tt.in); got != tt.want {
@@ -263,3 +266,19 @@ func TestSourceTrust(t *testing.T) {
 		t.Errorf("Sources() = %v", Sources())
 	}
 }
+
+// Two Russian events on one day must not share a key. They did: safeKey kept
+// ASCII only, so both summaries collapsed to their spaces and the second event
+// overwrote the first in the store (Vikunja #443).
+func TestFactKeyDistinguishesRussianEventsOnOneDay(t *testing.T) {
+	day := time.Date(2026, 8, 4, 0, 0, 0, 0, time.UTC)
+	a := Event{Summary: "Встреча с Аней", Start: day.Add(10 * time.Hour), End: day.Add(11 * time.Hour)}
+	b := Event{Summary: "Обед с мамой", Start: day.Add(13 * time.Hour), End: day.Add(14 * time.Hour)}
+	if FactKeyIn(a, time.UTC) == FactKeyIn(b, time.UTC) {
+		t.Fatalf("both events keyed as %q", FactKeyIn(a, time.UTC))
+	}
+	// The day prefix still has to survive, because the store range-scans on it.
+	if !strings.HasPrefix(FactKeyIn(a, time.UTC), KeyPrefixForDay(day)) {
+		t.Fatalf("key %q lost the day prefix %q", FactKeyIn(a, time.UTC), KeyPrefixForDay(day))
+	}
+}

internal/router/agenda_test.go

@@ -75,3 +75,47 @@ func TestAgendaGrammarSparesStatements(t *testing.T) {
 		}
 	}
 }
+
+// The tomorrow form and the bare event noun. Both were measured answering
+// "пока не умею" on the deployed daemon, 02-08-2026, while the same question
+// about today worked — the first rule set needed "у меня" or a calendar noun
+// and these phrasings carry neither (Vikunja #471).
+func TestAgendaCoversOtherDaysAndNamedEvents(t *testing.T) {
+	r := agendaRouter(t)
+	for _, u := range []string{
+		"какие планы на завтра?",
+		"какие планы на послезавтра",
+		"что по делам в среду",
+		"какие планы на выходные",
+		"когда планёрка?",
+		"во сколько созвон",
+		"когда будет совещание",
+	} {
+		d, err := r.Route(context.Background(), u, refNow())
+		if err != nil {
+			t.Fatalf("route(%q): %v", u, err)
+		}
+		if d.Intent != IntentQuery {
+			t.Errorf("route(%q) = %s, want query", u, d.Intent)
+		}
+	}
+}
+
+// The two new rules are narrow on purpose. A world question that opens with
+// "когда" is not an agenda question, and telling her about a plan is not
+// asking about one.
+func TestAgendaGrammarsLeaveTheWorldAlone(t *testing.T) {
+	r := agendaRouter(t)
+	for _, u := range []string{
+		"когда была битва при ватерлоо",
+		"когда изобрели телефон",
+	} {
+		d, err := r.Route(context.Background(), u, refNow())
+		if err != nil {
+			t.Fatalf("route(%q): %v", u, err)
+		}
+		if d.Stage == 0 {
+			t.Errorf("route(%q) was claimed at stage 0 as %s", u, d.Intent)
+		}
+	}
+}

internal/router/eval/ru_routing_v1.json

@@ -23,6 +23,8 @@
     { "id": "ru-query-012", "utterance": "какие заметки я оставил про полив", "lang": "ru", "intent": "query", "tags": ["recall"] },
     { "id": "ru-query-013", "utterance": "во сколько у меня встреча", "lang": "ru", "intent": "query", "tags": ["calendar"] },
     { "id": "ru-query-019", "utterance": "что у меня стоит в календаре на послезавтра", "lang": "ru", "intent": "query", "tags": ["calendar", "hard"], "note": "agenda, not the clock: the daemon answers this from CalendarEvents inside the query branch, so the clock/date system rule must not swallow it" },
+    { "id": "ru-query-022", "utterance": "какие планы на завтра?", "lang": "ru", "intent": "query", "tags": ["calendar"], "note": "the same agenda question as ru-query-019 aimed at another day; it answered \u043f\u043e\u043a\u0430 \u043d\u0435 \u0443\u043c\u0435\u044e on the deployed daemon while the today form worked (Vikunja #471)" },
+    { "id": "ru-query-023", "utterance": "\u043a\u043e\u0433\u0434\u0430 \u043f\u043b\u0430\u043d\u0451\u0440\u043a\u0430?", "lang": "ru", "intent": "query", "tags": ["calendar", "hard"], "note": "a named event with no calendar word — the noun is the only signal that this is a question about his day" },
     { "id": "ru-query-014", "utterance": "я успеваю до дедлайна", "lang": "ru", "intent": "query", "tags": ["hard", "no-question-word"] },
     { "id": "ru-query-015", "utterance": "сколько я прошёл шагов", "lang": "ru", "intent": "query", "tags": ["aggregate"] },
     { "id": "ru-query-016", "utterance": "покажи давление за неделю", "lang": "ru", "intent": "query", "tags": ["hard", "imperative"], "note": "imperative form but a read — must not route to act" },

internal/router/stage0.go

@@ -182,9 +182,38 @@ func AgendaQueryGrammars() []Grammar {
 			Pattern: regexp.MustCompile(`(?i)^\s*(что|чего|какие|сколько|во\s+сколько|когда)\s+у\s+меня(\s|[?!.]|$)`),
 			Build:   agendaQueryBuild,
 		},
+		{
+			// A plan noun aimed at a named day, with no possessive to anchor
+			// on: "какие планы на завтра", "что по делам в среду". The rule
+			// above wants "у меня" and this phrasing never has it, so
+			// "какие планы на завтра" answered "пока не умею" while "какие
+			// планы на сегодня" worked (Vikunja #471). The day word is what
+			// makes it an agenda question rather than a topic.
+			Name: "plan-day-query",
+			// Only "план" and "дел". A verb stem like "встреч" would take
+			// "встречаемся в среду", which is him telling her something, not
+			// asking.
+			Pattern: regexp.MustCompile(`(?i)(^|\s)(план|дел)[а-я]*\s+(на|в|во|по)\s+` + dayWordPattern + `(\s|[?!.]|$)`),
+			Build:   agendaQueryBuild,
+		},
+		{
+			// A named event with no calendar word at all: "когда планёрка?",
+			// "во сколько созвон". He is asking when something on his calendar
+			// happens, and the noun is the only signal. Closed list, so "когда
+			// битва при Ватерлоо" is still a world question.
+			Name:    "event-time-query",
+			Pattern: regexp.MustCompile(`(?i)^\s*(когда|во\s+сколько|в\s+котором\s+часу)\s+(будет\s+|у\s+нас\s+)?(планёрк|планерк|встреч|созвон|митинг|совещани|звонок|созвон|приём|прием|интервью|собеседовани|тренировк|урок|занятие|пара)[а-я]*(\s|[?!.]|$)`),
+			Build:   agendaQueryBuild,
+		},
 	}
 }
 
+// dayWordPattern — the day words an agenda question can name. Weekdays appear
+// in the accusative and prepositional forms the questions actually use ("в
+// среду", "на среде"), which is why the stems carry an inflection tail rather
+// than a fixed ending.
+const dayWordPattern = `(сегодня|завтра|послезавтра|выходн[а-я]+|недел[а-я]+|понедельник[а-я]*|вторник[а-я]*|сред[ауые][а-я]*|четверг[а-я]*|пятниц[ауые][а-я]*|суббот[ауые][а-я]*|воскресень[ея][а-я]*)`
+
 // agendaQueryBuild — shared Build for the agenda grammars. Confidence 1.0 on
 // the intent only: the utterance travels intact and the query chain's own
 // matchers decide the rest.

internal/store/migrations.go

@@ -208,6 +208,17 @@ ALTER TABLE reminders ADD COLUMN next_fire_ts INTEGER;`, // #2
 	// list_tasks into something that writes without the row changing by one
 	// byte. The fingerprint is the declared shape at approval time, so a
 	// redefinition is a re-approval instead of a silent upgrade.
+	`DELETE FROM facts
+	  WHERE key LIKE 'calendar_event_%'
+	    AND replace(substr(key, 25), '-', '') = '';`,
+	// #18 — drop the calendar keys written while safeKey dropped Cyrillic
+	// (Vikunja #443). Everything after the date prefix was punctuation, so
+	// every Russian event on one day shared one key and only the last one
+	// survived. Deleting rather than rewriting: a calendar fact is derived
+	// data, the next poll writes the day again under keys that identify the
+	// 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.
 }
 
 // migrate applies every migration with a number greater than the DB's current

internal/store/migrations_test.go

@@ -47,3 +47,36 @@ func TestMigrateAppliesOnceAndIsIdempotent(t *testing.T) {
 		t.Fatalf("after re-migrate user_version = %d, want %d", v, want)
 	}
 }
+
+// Migration #18 clears the calendar keys written while safeKey dropped
+// Cyrillic. Those rows are indistinguishable from real events on read, so
+// leaving them would recite one meeting as several (Vikunja #443).
+func TestCollapsedCalendarKeysAreDropped(t *testing.T) {
+	ctx := context.Background()
+	s := newTestStore(t)
+
+	rows := []string{
+		"calendar_event_20260804_--",             // "Встреча с Аней" under the old rule
+		"calendar_event_20260804_",               // a one-word Russian summary
+		"calendar_event_20260804_Встреча-с-Аней", // the new format
+		"calendar_event_20260804_Standup",        // an ASCII summary, always fine
+	}
+	for _, key := range rows {
+		if _, err := s.db.ExecContext(ctx,
+			`INSERT INTO facts (ts, kind, key, value, source, confidence) VALUES (0, 'env', ?, 'x', 'poll:caldav', 1.0)`,
+			key); err != nil {
+			t.Fatalf("seed %q: %v", key, err)
+		}
+	}
+	if _, err := s.db.ExecContext(ctx, migrations[17]); err != nil {
+		t.Fatalf("migration 18: %v", err)
+	}
+
+	var got int
+	if err := s.db.QueryRowContext(ctx, `SELECT count(*) FROM facts WHERE key LIKE 'calendar_event_%'`).Scan(&got); err != nil {
+		t.Fatal(err)
+	}
+	if got != 2 {
+		t.Fatalf("%d calendar rows left, want the 2 that identify their event", got)
+	}
+}