Merge task/467 so the sweep tail can reach the three mechanisms (V-528)

attentionq.go, repair.go and internal/router/complaint.go carry the last
hand-written Russian patterns of the V-522 sweep, and they live on task/467.
internal/lexicon, internal/morph and cmd/mavend/topics.go live here. One of
the two had to move.

Four conflicts, and one of them is a real collision rather than a mechanical
one. Both branches wrote the narrative stage 0 rule. This side had
NarrativeQueryGrammars, plural, with the rest-of-day rule beside it and the
verb alternation built from the lexicon; task/467 had NarrativeQueryGrammar,
singular, which extracts the topic into Slots.Text, refuses a bare "расскажи",
and excludes the shapes that are chat ("расскажи о себе", "историю на ночь").
Resolved by keeping this side's container and this side's lexicon-built
pattern, and taking every behaviour only the other side had: the topic slot,
the empty-topic refusal, chatNarrativeTopics, and its wiring position after
TaskCaptureGrammar so "запиши" still beats "расскажи".

The rest: queryFeeds keeps task/467's conditional claim (V-474 supersedes the
unconditional one), rank.go keeps Spoken and drops pluralTasksRU because
say.CountWord is the one copy of Russian count agreement, and vendor/ was
re-vendored — the merged modules.txt claimed replaces for nexus and praxis
that neither go.mod has.

Routing fixture 58/82, unchanged from both sides.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-04 19:00:32 +04:00
62 changed files with 2658 additions and 80 deletions
+79
View File
@@ -0,0 +1,79 @@
package router
import "strings"
// transientStems — the states a thing is in for an afternoon. Compared as
// prefixes because Russian inflects the ending: "медленн" covers "медленная",
// "медленный" and "медленно" without listing them.
var transientStems = []string{
"медленн", "тормоз", "лаг", "завис", "виснет", "глюч", "барахл",
"отвал", "падает", "упал", "сдох", "греется", "перегре",
"slow", "laggy", "stuck", "frozen", "flaky", "broken", "down",
}
// brokenVerbs — what "не ..." is denying when the sentence is a complaint.
// "не работает", "не грузит", "не открывается". Prefixes again.
var brokenVerbs = []string{
"работ", "пашет", "груз", "открыва", "включа", "коннект", "подключ",
"work", "load", "connect", "respond",
}
// selfMarkers — the words that make a sentence about him rather than about a
// thing. Their presence turns the test off, because losing a fact he meant to
// store is worse than keeping a complaint: "я сломал руку" is durable, and
// "интернет не работает" is not.
var selfMarkers = []string{"я", "мне", "меня", "мной", "i", "me", "my"}
// IsTransientComplaint reports whether text observes a passing state of some
// thing rather than recording a fact.
//
// It exists because "сеть какая-то медленная" and "интернет не работает" were
// written to the fact store as `self` rows at confidence 1.00 (Vikunja #481),
// where recall reads them back later as if they were still true. A complaint
// describes a moment; the fact store describes him.
//
// Deterministic, offline, and shaped exactly like IsQuestionShaped: an
// explicit capture verb wins over everything, because "запомни что интернет
// не работает" is an instruction and not a passing remark. A first-person
// marker also turns it off — the test is meant to catch a sentence about a
// thing, and it errs toward storing.
func IsTransientComplaint(text string) bool {
t := strings.TrimSpace(text)
if t == "" {
return false
}
toks := planTokens(strings.ToLower(t))
for _, v := range captureVerbs {
if hasTok(toks, v) {
return false
}
}
for _, m := range selfMarkers {
if hasTok(toks, m) {
return false
}
}
for _, tok := range toks {
for _, stem := range transientStems {
if strings.HasPrefix(tok, stem) {
return true
}
}
}
// "не" plus a verb of working, in either order of the two tokens that
// follow it — "не работает" and "не очень работает" both deny the same
// thing.
for i, tok := range toks {
if tok != "не" && tok != "not" && tok != "isn" {
continue
}
for j := i + 1; j < len(toks) && j <= i+2; j++ {
for _, v := range brokenVerbs {
if strings.HasPrefix(toks[j], v) {
return true
}
}
}
}
return false
}
+35
View File
@@ -0,0 +1,35 @@
package router
import "testing"
func TestIsTransientComplaint(t *testing.T) {
for _, tc := range []struct {
text string
want bool
}{
// The two rows from the QA run that named this bug.
{"сеть какая-то медленная", true},
{"интернет не работает", true},
{"вайфай тормозит", true},
{"сервер завис", true},
{"the wifi is slow", true},
// An instruction wins: he asked for it to be written down.
{"запомни что интернет не работает", false},
{"запиши что сеть медленная", false},
// About him, so it stays a fact even when it sounds like a complaint.
{"я сломал руку", false},
{"мне медленно думается", false},
// Ordinary captures must not be touched.
{"поужинал", false},
{"выпил воды", false},
{"машина на парковке", false},
{"", false},
} {
if got := IsTransientComplaint(tc.text); got != tc.want {
t.Errorf("IsTransientComplaint(%q) = %v, want %v", tc.text, got, tc.want)
}
}
}
+3
View File
@@ -81,6 +81,9 @@ func NewPythonDateParser() *PythonDateParser {
// or dateparser is unavailable, falls back to the stub parser. Returns
// (time, true, nil) on success; (zero, false, nil) when no date is found.
func (p *PythonDateParser) Parse(ctx context.Context, text string, now time.Time) (time.Time, bool, error) {
// Speech says the hour in words, and neither this parser nor the stub
// reads "в семь вечера" (Vikunja #469). Both see the digits instead.
text = SpellOutDigits(text)
t, ok, err := p.parseWithPython(ctx, text, now)
if err != nil {
// python3 missing, dateparser not installed, or process failure —
+8 -1
View File
@@ -236,8 +236,15 @@ func newBaselineRouter(t *testing.T, emb router.Embedder, llmR *router.LLMRouter
// Same order as buildRouter (voicewire.go). The fixture is only worth
// anything while its grammar set is the daemon's grammar set.
grammars = append(grammars, router.AgendaQueryGrammars()...)
grammars = append(grammars, router.NarrativeQueryGrammars()...)
grammars = append(grammars, router.FeedQueryGrammar())
// The list side of the same exposure: a phrasing with no possessive in it
// ("список дел") routed system and never reached queryTasks (Vikunja #467).
grammars = append(grammars, router.TaskListGrammar())
grammars = append(grammars, router.ReminderGrammar())
grammars = append(grammars, router.TaskCaptureGrammar())
// "расскажи про X" is a world question the model called a fact, and the
// rule goes last because it matches on the first word alone (Vikunja #498).
grammars = append(grammars, router.NarrativeQueryGrammars()...)
return router.New(router.Config{
Grammars: grammars,
Classifier: cls,
+2
View File
@@ -25,6 +25,8 @@
{ "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-024", "utterance": "что дальше?", "lang": "ru", "intent": "query", "tags": ["calendar", "no-question-word"], "note": "the rest of the day, with no possessive and no plan word to anchor on; the model called it a fact and the write had to be caught downstream (Vikunja #498)" },
{ "id": "ru-query-025", "utterance": "расскажи про битву при Ватерлоо", "lang": "ru", "intent": "query", "tags": ["world", "no-question-word"], "note": "a narrative request carries no question mark and no interrogative, so it routed fact; contrast ru-chat-003, where the same verb asks for a joke" },
{ "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" },
+55
View File
@@ -0,0 +1,55 @@
package router
import (
"context"
"testing"
)
func feedRouter(t *testing.T) *Router {
t.Helper()
r := newTestRouter(t, 0.0)
r.grammars = append(r.grammars, SystemTimeDateGrammars()...)
r.grammars = append(r.grammars, AgendaQueryGrammars()...)
r.grammars = append(r.grammars, FeedQueryGrammar())
return r
}
// The documented utterance of task 258 step 1 routed system and answered
// "пока не умею отвечать на этот вопрос.", while the same question worded with
// "новостях" worked (Vikunja #474).
func TestFeedQuestionsRouteToQuery(t *testing.T) {
r := feedRouter(t)
for _, u := range []string{
"что нового в лентах?",
"что в лентах?",
"расскажи что в новостных лентах",
"покажи ленту",
} {
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 greeting and the statement keep their intents. "что нового?" is the most
// common opener in the language, and a rule that claimed it would answer hello
// with a configuration status.
func TestFeedGrammarLeavesTheGreetingAlone(t *testing.T) {
r := feedRouter(t)
for _, u := range []string{
"что нового?",
"у меня новая лента в инстаграме",
} {
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)
}
}
}
+85
View File
@@ -0,0 +1,85 @@
package router
import (
"context"
"testing"
)
// narrativeRouter wires the grammars in the order the daemon wires them
// (voicewire.go), with the narrative rule last — so a test that passes here is
// a test of the deployed precedence, not of the rule in isolation.
func narrativeRouter(t *testing.T) *Router {
t.Helper()
r := newTestRouter(t, 0.0)
r.grammars = append(r.grammars, SystemTimeDateGrammars()...)
r.grammars = append(r.grammars, AgendaQueryGrammars()...)
r.grammars = append(r.grammars, TaskListGrammar())
r.grammars = append(r.grammars, TaskCaptureGrammar())
r.grammars = append(r.grammars, NarrativeQueryGrammars()[1])
return r
}
// "расскажи про X" and "что дальше?" carried no question mark and no
// interrogative, so nothing at stage 0 claimed them and the model called both
// facts (Vikunja #498, point 1 of #470). The fact write is contained now, but
// the round trip and the wrong fixture score are not.
func TestNarrativeAndRestOfDayRouteToQueryAtStageZero(t *testing.T) {
r := narrativeRouter(t)
for _, u := range []string{
"расскажи про битву при Ватерлоо",
"расскажи мне про Юникод",
"объясни как работает tcp",
"опиши Самару",
"перечисли планеты",
"tell me about the fall of Rome",
"что дальше?",
"и что там дальше",
"что дальше",
"what's next?",
} {
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)
}
if d.Stage != 0 {
t.Errorf("route(%q) decided at stage %d, want 0 — the point is to skip the model", u, d.Stage)
}
}
}
// The narrative rule must not take a turn that belongs to something else. A
// capture marker wins because it is what he said, and asking her for a joke is
// chat: the query chain has no source that answers it.
func TestNarrativeGrammarLeavesOtherTurnsAlone(t *testing.T) {
r := narrativeRouter(t)
for _, u := range []string{
"расскажи анекдот",
"расскажи о себе",
"расскажи шутку",
"расскажи",
} {
d, err := r.Route(context.Background(), u, refNow())
if err != nil {
t.Fatalf("route(%q): %v", u, err)
}
if d.Stage == 0 && d.Intent == IntentQuery {
t.Errorf("route(%q) was claimed as a world question at stage 0", u)
}
}
}
// The topic reaches the query chain without the verb that introduced it: the
// search leg wants "битву при Ватерлоо", not "расскажи про битву при Ватерлоо".
func TestNarrativeGrammarKeepsTheTopic(t *testing.T) {
r := narrativeRouter(t)
d, err := r.Route(context.Background(), "расскажи про битву при Ватерлоо", refNow())
if err != nil {
t.Fatal(err)
}
if got, want := d.Slots.Text, "битву при Ватерлоо"; got != want {
t.Errorf("text = %q, want %q", got, want)
}
}
+97
View File
@@ -0,0 +1,97 @@
package router
import "strings"
// ruNumerals — spoken numbers as digits, for the clock hours and the minutes
// that follow them. Every case ending he might say is listed rather than
// stemmed: "в семь", "к семи", "около семи" are three forms of one hour, and a
// prefix rule short enough to cover them also matches "семья".
//
// Stops at thirty, which is as far as a spoken time goes ("без двадцати
// восемь", "в половине шестого"). Anything larger is said in digits.
var ruNumerals = map[string]string{
"один": "1", "одного": "1", "одну": "1", "час": "1", "часу": "1",
"два": "2", "две": "2", "двух": "2",
"три": "3", "трёх": "3", "трех": "3",
"четыре": "4", "четырёх": "4", "четырех": "4",
"пять": "5", "пяти": "5",
"шесть": "6", "шести": "6",
"семь": "7", "семи": "7",
"восемь": "8", "восьми": "8",
"девять": "9", "девяти": "9",
"десять": "10", "десяти": "10",
"одиннадцать": "11", "одиннадцати": "11",
"двенадцать": "12", "двенадцати": "12",
"тринадцать": "13", "тринадцати": "13",
"четырнадцать": "14", "четырнадцати": "14",
"пятнадцать": "15", "пятнадцати": "15",
"шестнадцать": "16", "шестнадцати": "16",
"семнадцать": "17", "семнадцати": "17",
"восемнадцать": "18", "восемнадцати": "18",
"девятнадцать": "19", "девятнадцати": "19",
"двадцать": "20", "двадцати": "20",
"тридцать": "30", "тридцати": "30",
"сорок": "40", "сорока": "40",
"пятьдесят": "50", "пятидесяти": "50",
}
// numeralContext — the words that make a numeral a time. A numeral is only
// rewritten when one of these sits next to it, so "три яблока" in a note is
// left alone and "в три часа" is not.
var numeralContext = map[string]bool{
"в": true, "во": true, "к": true, "около": true, "на": true,
"часа": true, "часов": true, "час": true, "часу": true,
"утра": true, "вечера": true, "дня": true, "ночи": true,
"минут": true, "минуты": true, "минуту": true,
"at": true, "by": true,
}
// SpellOutDigits rewrites spoken numbers as digits so the date parsers see the
// shape they know.
//
// "напомни мне позвонить маме в семь вечера" parsed to nothing, while "в 19:00"
// parsed fine (Vikunja #469). Speech is where reminders come from, and speech
// says the hour in words, so this is not a long-tail case — it is the ordinary
// one. dateparser reads "в 7 вечера" through the qualifier rewrite the python
// script already does; it does not read "в семь вечера".
//
// Conservative by construction: a numeral is only rewritten when a time word
// stands beside it. "три часа" becomes "3 часа"; "три яблока" stays as it is,
// and a note or a fact carrying a spoken number is untouched.
func SpellOutDigits(text string) string {
toks := strings.Fields(text)
if len(toks) == 0 {
return text
}
out := make([]string, len(toks))
copy(out, toks)
for i, tok := range toks {
key := strings.ToLower(strings.Trim(tok, ".,!?;:«»\"'"))
digit, ok := ruNumerals[key]
if !ok {
continue
}
// "час" and "часу" are the hour noun as often as they are the number
// one, and rewriting "в час дня" to "в 1 дня" is right either way. What
// must not happen is rewriting the noun that gives another numeral its
// context: "в семь часов" must keep "часов".
if !hasTimeNeighbour(toks, i) {
continue
}
out[i] = digit
}
return strings.Join(out, " ")
}
// hasTimeNeighbour reports whether the token before or after i is a time word.
func hasTimeNeighbour(toks []string, i int) bool {
for _, j := range []int{i - 1, i + 1} {
if j < 0 || j >= len(toks) {
continue
}
if numeralContext[strings.ToLower(strings.Trim(toks[j], ".,!?;:«»\"'"))] {
return true
}
}
return false
}
+38
View File
@@ -0,0 +1,38 @@
package router
import (
"context"
"testing"
"time"
)
func TestSpellOutDigits(t *testing.T) {
for _, tc := range []struct{ in, want string }{
{"напомни мне позвонить маме в семь вечера", "напомни мне позвонить маме в 7 вечера"},
{"в три часа дня", "в 3 часа дня"},
{"напомни в половине шестого", "напомни в половине шестого"},
{"через двадцать минут", "через 20 минут"},
// Untouched: no time word stands beside the number.
{"купить три яблока", "купить три яблока"},
{"семь раз отмерь", "семь раз отмерь"},
{"напомни в 19:00", "напомни в 19:00"},
{"", ""},
} {
if got := SpellOutDigits(tc.in); got != tc.want {
t.Errorf("SpellOutDigits(%q) = %q, want %q", tc.in, got, tc.want)
}
}
}
// The utterance from the QA sitting that named this bug: the numeric form
// parsed and the spoken form did not.
func TestStubParsesASpokenHour(t *testing.T) {
now := time.Date(2026, 8, 2, 9, 0, 0, 0, time.Local)
got, ok, err := StubDateTimeParser{}.Parse(context.Background(), "напомни мне позвонить маме в семь вечера", now)
if err != nil || !ok {
t.Fatalf("Parse ok=%v err=%v, want a time", ok, err)
}
if got.Hour() != 19 {
t.Fatalf("hour = %d, want 19", got.Hour())
}
}
+6
View File
@@ -2,6 +2,7 @@ package router
import (
"context"
"errors"
"log"
"time"
)
@@ -201,5 +202,10 @@ func (r *Router) gateLLMDecision(d *Decision) {
// retrain). Same shape as nudges.outcome tuning cooldowns: more reliable over
// time, introspectable, no model surgery.
func (r *Router) CorrectMisroute(ctx context.Context, utterance string, corrected Intent) error {
if r == nil || r.classifier == nil {
// The LLM router can run with no classifier wired. The correction has
// nowhere to land then, and the caller redoes the request anyway.
return errors.New("router: no classifier to correct")
}
return r.classifier.AddExample(ctx, corrected, utterance)
}
+39 -4
View File
@@ -178,7 +178,7 @@ func afterWord(s, w string) string {
type StubDateTimeParser struct{}
func (StubDateTimeParser) Parse(_ context.Context, text string, now time.Time) (time.Time, bool, error) {
s := strings.ToLower(strings.TrimSpace(text))
s := strings.ToLower(strings.TrimSpace(SpellOutDigits(text)))
toks := strings.Fields(s)
// scan for "in <num> <unit>" anywhere — dateparser extracts the datetime
// expression from surrounding text; the stub does the same naively.
@@ -206,14 +206,22 @@ func (StubDateTimeParser) Parse(_ context.Context, text string, now time.Time) (
// --- Russian time expressions (stub floor; dateparser replaces) ---
// "в <clock>" anywhere — mirror of the English "at" scan.
// "в <clock>" anywhere — mirror of the English "at" scan. A qualifier
// after the hour moves it into the afternoon: "в 7 вечера" is 19:00, and
// with SpellOutDigits in front of this that is what "в семь вечера" reads
// as too (Vikunja #469).
for i := 0; i+1 < len(toks); i++ {
if toks[i] != "в" {
continue
}
if t, ok := parseClock(toks[i+1], now); ok {
return t, true, nil
t, ok := parseClock(toks[i+1], now)
if !ok {
continue
}
if i+2 < len(toks) {
t = applyRuQualifier(t, toks[i+2], now)
}
return t, true, nil
}
// "через <N> <unit>" / "через <unit>" (bare = 1) / "через полчаса".
@@ -465,3 +473,30 @@ func midnight(now time.Time, days int) time.Time {
y, m, d := now.AddDate(0, 0, days).Date()
return time.Date(y, m, d, 0, 0, 0, 0, now.Location())
}
// applyRuQualifier moves an hour into the afternoon when he said "вечера" or
// "дня" after it. Noon-crossing only: 7 becomes 19, and 19 stays 19. Morning
// qualifiers need no arithmetic, they only confirm the hour as spoken.
//
// The date is recomputed rather than shifted, so an hour that parseClock
// already pushed to tomorrow does not land two days out.
func applyRuQualifier(t time.Time, qualifier string, now time.Time) time.Time {
h := t.Hour()
switch strings.Trim(strings.ToLower(qualifier), ".,!?;:") {
case "вечера", "дня":
if h < 12 {
h += 12
}
case "утра", "ночи":
if h == 12 {
h = 0
}
default:
return t
}
out := time.Date(now.Year(), now.Month(), now.Day(), h, t.Minute(), 0, 0, now.Location())
if !out.After(now) {
out = out.Add(24 * time.Hour)
}
return out
}
+76 -11
View File
@@ -199,6 +199,20 @@ func AgendaQueryGrammars() []Grammar {
Pattern: regexp.MustCompile(`(?i)(^|\s)(план|дел)[а-я]*\s+(на|в|во|по)\s+` + dayWordPattern + `(\s|[?!.]|$)`),
Build: agendaQueryBuild,
},
{
// "что дальше?" — the rest of the day, with no possessive and no
// plan word for the rules above to anchor on, so neither claimed
// it and the model called it a fact (Vikunja #498). The predicate
// for the same utterance already exists as IsRestOfDayQuery, one
// layer down in the query chain; this is what gets the turn there.
//
// "и что там дальше" and "что потом дальше" are the same question,
// and "what's next" splits into two tokens, hence the optional
// middles rather than plain adjacency.
Name: "rest-of-day-query",
Pattern: regexp.MustCompile(`(?i)^\s*(и\s+)?(что|чего|what'?s?)\s+(там\s+|ещё\s+|еще\s+|потом\s+|у\s+меня\s+)?(дальше|next)(\s|[?!.]|$)`),
Build: agendaQueryBuild,
},
{
// A named event with no calendar word at all: "когда планёрка?",
// "во сколько созвон". He is asking when something on his calendar
@@ -211,6 +225,11 @@ func AgendaQueryGrammars() []Grammar {
}
}
// chatNarrativeTopics — the things "расскажи X" asks for that are not
// questions about the world. She is being asked to entertain or to describe
// herself, and the query chain has no source for either.
var chatNarrativeTopics = regexp.MustCompile(`(?i)(анекдот|шутк|сказк|истори[юи]\s+на\s+ночь|о\s+себе|про\s+себя|о\s+нас|про\s+нас)`)
// NarrativeQueryGrammars — stage-0 grammars for the two question shapes that
// carry no question mark and no interrogative, and so reached the resident
// model with nothing deterministic in front of them (Vikunja #498).
@@ -255,15 +274,27 @@ var entertainmentNouns = []string{
"joke", "jokes", "story",
}
// narrativeQueryBuild — the narrative shape is a query unless he also said one
// of the capture verbs, or asked for entertainment. "расскажи и запиши" is him
// asking for a note, and stage 0 must not take either off the cascade.
// narrativeQueryBuild — the narrative shape is a query carrying its topic,
// unless he also said one of the capture verbs, asked for entertainment, or
// asked about her. "расскажи и запиши" is him asking for a note, and stage 0
// must not take either off the cascade.
//
// The topic goes into Slots.Text rather than the whole utterance: the query
// chain looks things up by it, and "расскажи мне про Ватерлоо" is a question
// about Ватерлоо.
func narrativeQueryBuild(m []string) (Decision, bool) {
rest := ""
if len(m) > 3 {
rest = m[3]
topic := strings.TrimSpace(m[2])
// "расскажи" with nothing after it is a conversational opener, and there is
// no topic to look up.
if topic == "" {
return Decision{}, false
}
for _, t := range planTokens(rest) {
// Against the whole utterance, not the topic: "о себе" has its preposition
// eaten by the pattern, leaving a bare "себе".
if chatNarrativeTopics.MatchString(m[0]) {
return Decision{}, false
}
for _, t := range planTokens(topic) {
for _, v := range captureVerbs {
if t == v {
return Decision{}, false
@@ -275,7 +306,12 @@ func narrativeQueryBuild(m []string) (Decision, bool) {
}
}
}
return agendaQueryBuild(m)
return Decision{
Stage: 0,
Intent: IntentQuery,
Confidence: 1.0,
Slots: Slots{Text: topic},
}, true
}
// narrativeQueryPattern — "расскажи про X", built from the lexicon rather than
@@ -285,9 +321,36 @@ func narrativeQueryBuild(m []string) (Decision, bool) {
//
// Anchored at the start, which was the point of the old literal and still is:
// "запиши что мне рассказали" is a capture, and a narrative verb buried
// mid-utterance is not the shape.
// mid-utterance is not the shape. The dative and the preposition are eaten so
// the topic slot comes out clean: "расскажи мне про Ватерлоо" leaves
// "Ватерлоо".
var narrativeQueryPattern = regexp.MustCompile(
`(?i)^\s*(` + strings.Join(lexicon.NarrativeRequests(), "|") + `)(\s+(.*))?$`)
`(?is)^\s*(` + strings.Join(lexicon.NarrativeRequests(), "|") +
`)(?:\s+(?:мне|нам|us|me))?(?:\s+(?:про|о|об|about))?(\s+.+)$`)
// FeedQueryGrammar — stage-0 rule for "что нового в лентах?", routed to
// IntentQuery so it reaches queryFeeds.
//
// Same shape of defect as the agenda grammars: the model calls it system, and
// replySystem has no feeds arm, so the documented utterance of task 258 step 1
// answered "пока не умею отвечать на этот вопрос." while the same question
// worded with "новостях" worked (Vikunja #474).
//
// An ask word at the front and a feed noun after it are both required, which
// is the same pair ParseFeedQuery wants. "что нового?" on its own is a greeting
// — the most common opener in the language — and vagueNouns in feeds.go exists
// to keep it out of the feed reader; routing it to query here would put it
// back. "у меня новая лента в инстаграме" carries the noun without the ask and
// stays the statement it is.
func FeedQueryGrammar() Grammar {
return Grammar{
Name: "feed-query",
// (\s|[?!.]|$) rather than \b, which is ASCII-only and never fires next
// to a Cyrillic letter.
Pattern: regexp.MustCompile(`(?i)^\s*(что|какие|расскажи|покажи|почитай|прочитай)\s+.*(лент|новостн)[а-я]*(\s|[?!.]|$)`),
Build: agendaQueryBuild,
}
}
// dayWordPattern — the day words an agenda question can name. Weekdays appear
// in the accusative and prepositional forms the questions actually use ("в
@@ -345,7 +408,9 @@ func isCyrillic(s string) bool {
return s != ""
}
// agendaQueryBuild — shared Build for the agenda grammars. Confidence 1.0 on
// agendaQueryBuild — shared Build for the agenda grammars and the feed one,
// which all do the same single thing: keep the utterance out of IntentSystem
// and let the query chain decide who answers it. Confidence 1.0 on
// the intent only: the utterance travels intact and the query chain's own
// matchers decide the rest.
func agendaQueryBuild(m []string) (Decision, bool) {
+29
View File
@@ -248,3 +248,32 @@ func TaskCaptureGrammar() Grammar {
},
}
}
// TaskListGrammar — stage 0 for "какие у меня задачи", "список дел", "что мне
// нужно сделать" (Vikunja #467).
//
// The same exposure the capture marker had, pointed the other way. IsTaskListQuery
// is a deterministic lookup that lives inside a query source, so it is only
// consulted once the turn is already IntentQuery. A phrasing the model calls
// system or note never reaches it, and "пока не умею" is what he hears — the
// failure the agenda and feed rules were written for.
//
// Placed after the agenda rules, which already send "какие у меня задачи" to
// query. What this adds is the phrasings with no possessive in them.
func TaskListGrammar() Grammar {
return Grammar{
Name: "task-list-query",
Pattern: regexp.MustCompile(`(?s)^\s*(.+)$`),
Build: func(m []string) (Decision, bool) {
if !IsTaskListQuery(m[1]) {
return Decision{}, false
}
return Decision{
Stage: 0,
Intent: IntentQuery,
Confidence: 1.0,
Slots: Slots{Text: strings.TrimSpace(m[1])},
}, true
},
}
}
+24
View File
@@ -119,3 +119,27 @@ func TestTaskCaptureGrammarClaimsTheMarker(t *testing.T) {
}
}
}
// TestTaskListGrammarClaimsTheAsk — a list question answered before the model,
// including the phrasings with no possessive that used to route elsewhere.
func TestTaskListGrammarClaimsTheAsk(t *testing.T) {
g := TaskListGrammar()
claimed := []string{"какие у меня задачи", "список дел", "что мне нужно сделать"}
for _, u := range claimed {
m := g.Pattern.FindStringSubmatch(u)
if m == nil {
t.Fatalf("%q did not match the grammar pattern", u)
}
d, ok := g.Build(m)
if !ok || d.Intent != IntentQuery {
t.Errorf("%q built %+v ok=%v; want a query", u, d, ok)
}
}
passed := []string{"как дела", "напомни купить хлеб", "что docker делает"}
for _, u := range passed {
m := g.Pattern.FindStringSubmatch(u)
if _, ok := g.Build(m); ok {
t.Errorf("%q was claimed as a task list", u)
}
}
}