Merge pull request 'Bug: spoken task capture is dead — the router calls the marker an act, and capture only rides the note intent' (#142) from task/467-bug-spoken-task-capture-is-dead-the-rout into master
This commit was merged in pull request #142.
This commit is contained in:
@@ -189,6 +189,18 @@ fixture had said `query` since ru-query-019 was written. Measured: **full accura
|
||||
Go's `\b` is ASCII-only and never fires after a Cyrillic letter; the pattern needs an
|
||||
explicit `(\s|[?!.]|$)`.
|
||||
|
||||
Two more shapes taken off the model, 04-08-2026 (V-498). `rest-of-day-query` inside
|
||||
`AgendaQueryGrammars` claims "что дальше?" / "what's next", and `NarrativeQueryGrammar`
|
||||
(`stage0.go`, wired **last** in `buildRouter`, after the capture marker) claims "расскажи про
|
||||
X", "объясни X", "опиши X". Neither carries a question mark or an interrogative, so the model
|
||||
called both `IntentFact`; the write was caught downstream by `IsQuestionShaped`, so this was a
|
||||
latency and fixture defect, not a correctness one. The narrative rule reads the same
|
||||
`narrativeRequests` lexicon `IsQuestionShaped` reads, and declines `chatNarrativeTopics` — a
|
||||
joke, a bedtime story, herself — because the query chain has no source that answers those.
|
||||
New fixture cases ru-query-024 and ru-query-025. Classifier + ONNX baseline **56/80 (70.0%) →
|
||||
58/82 (70.7%)**, no case regressed, no new false clarify. The LLM arm was not measured (no
|
||||
llama-server in that run), so judge it again before quoting a cascade number.
|
||||
|
||||
## LLM output contract
|
||||
|
||||
All phrasing paths emit `{"response":"...","mood":"..."}` (parsed in `replier_llm.go` and
|
||||
|
||||
@@ -385,12 +385,19 @@ func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64,
|
||||
// Same reason as the agenda rules, for the feeds: "что нового в лентах?"
|
||||
// routed system and answered "пока не умею" (Vikunja #474).
|
||||
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())
|
||||
// Last, and it matches any utterance shape — its Build is the filter. An
|
||||
// explicit capture marker beats the model, which called it an act and
|
||||
// rewrote the task text (Vikunja #467). After the rules above because a
|
||||
// marker never collides with a clock or agenda question.
|
||||
grammars = append(grammars, router.TaskCaptureGrammar())
|
||||
// After the capture marker, so "запиши" still wins over "расскажи", and
|
||||
// last overall because it matches on the first word alone: "расскажи про
|
||||
// X" is a world question the model called a fact (Vikunja #498).
|
||||
grammars = append(grammars, router.NarrativeQueryGrammar())
|
||||
return router.New(router.Config{
|
||||
Grammars: grammars,
|
||||
Classifier: cls,
|
||||
|
||||
@@ -139,7 +139,13 @@ func TestHandleAmbientIgnoresNonMeetings(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestHandleAmbientAuth(t *testing.T) {
|
||||
body := `{"title":"Планёрка 10:00","posted_at":"2026-08-03T09:40:00Z"}`
|
||||
// posted_at carries the local offset, and the clock reading inside the text
|
||||
// sits twenty minutes after it. A bare "Z" here would make the reading
|
||||
// stale by the test machine's own offset and the handler would answer 202
|
||||
// no-meeting, which says nothing about the auth this test is checking
|
||||
// (Vikunja #482).
|
||||
posted := time.Date(2026, 8, 3, 9, 40, 0, 0, time.Local)
|
||||
body := fmt.Sprintf(`{"title":"Планёрка 10:00","posted_at":%q}`, posted.Format(time.RFC3339))
|
||||
|
||||
newReq := func(hdr, val string) *http.Request {
|
||||
r := httptest.NewRequest(http.MethodPost, "/api/ambient", strings.NewReader(body))
|
||||
|
||||
@@ -68,10 +68,19 @@ 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 read in the daemon's zone (Vikunja #482). Posted is an
|
||||
// instant and carries an offset; "созвон в 14:30" is a wall clock and carries
|
||||
// none, so the zone has to come from somewhere else. A relay that posts
|
||||
// "2026-08-02T09:00:00Z" used to make that 14:30 UTC, which stored an 18:30
|
||||
// meeting on a UTC+4 box — wrong by the deploy's own offset, and invisible on a
|
||||
// UTC box. The owner's phone and the box share a zone, so the box's zone is the
|
||||
// honest reading of a bare wall clock.
|
||||
func EventFromNotification(n Notification) (Event, bool) {
|
||||
if n.Posted.IsZero() {
|
||||
return Event{}, false
|
||||
}
|
||||
n.Posted = n.Posted.In(time.Local)
|
||||
line := strings.TrimSpace(n.Title + " " + n.Text)
|
||||
start, end, ok := parseTimeRange(line)
|
||||
if !ok {
|
||||
|
||||
@@ -1,12 +1,22 @@
|
||||
package calendar
|
||||
|
||||
import (
|
||||
"os"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// A bare clock reading in a notification is read in the daemon's zone, so every
|
||||
// test here needs a known one. UTC+4 is the deploy's (Europe/Samara) and it is
|
||||
// the offset the 18:30 bug was measured at, so a regression shows up as four
|
||||
// hours rather than as nothing at all on a UTC runner.
|
||||
func TestMain(m *testing.M) {
|
||||
time.Local = time.FixedZone("+04", 4*3600)
|
||||
os.Exit(m.Run())
|
||||
}
|
||||
|
||||
func TestEventFromNotification(t *testing.T) {
|
||||
posted := time.Date(2026, 8, 3, 9, 40, 0, 0, time.FixedZone("+04", 4*3600))
|
||||
posted := time.Date(2026, 8, 3, 9, 40, 0, 0, time.Local)
|
||||
|
||||
tests := []struct {
|
||||
name string
|
||||
@@ -98,10 +108,10 @@ 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.
|
||||
if ev.Start.Location() != posted.Location() {
|
||||
t.Errorf("location = %v, want %v", ev.Start.Location(), posted.Location())
|
||||
// The event lands on the day the phone showed it, in the daemon's
|
||||
// zone — the clock reading is a wall clock, not an instant.
|
||||
if ev.Start.Location() != time.Local {
|
||||
t.Errorf("location = %v, want %v", ev.Start.Location(), time.Local)
|
||||
}
|
||||
if y, m, d := ev.Start.Date(); y != 2026 || m != time.August || d != 3 {
|
||||
t.Errorf("date = %d-%02d-%02d, want 2026-08-03", y, m, d)
|
||||
@@ -115,8 +125,7 @@ func TestEventFromNotification(t *testing.T) {
|
||||
// the meeting twelve hours in the past and filed it under today in FactKey. A
|
||||
// wrong meeting stored is worse than nothing stored.
|
||||
func TestEventFromNotificationDayWords(t *testing.T) {
|
||||
loc := time.FixedZone("+04", 4*3600)
|
||||
evening := time.Date(2026, 8, 3, 21, 0, 0, 0, loc)
|
||||
evening := time.Date(2026, 8, 3, 21, 0, 0, 0, time.Local)
|
||||
|
||||
tests := []struct {
|
||||
name string
|
||||
@@ -191,7 +200,7 @@ func TestEventFromNotificationDayWords(t *testing.T) {
|
||||
func TestEventFromNotificationDropsDayWordFromSummary(t *testing.T) {
|
||||
ev, ok := EventFromNotification(Notification{
|
||||
Title: "Завтра Планёрка 09:00",
|
||||
Posted: time.Date(2026, 8, 3, 21, 0, 0, 0, time.UTC),
|
||||
Posted: time.Date(2026, 8, 3, 21, 0, 0, 0, time.Local),
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("expected an event")
|
||||
@@ -201,6 +210,31 @@ func TestEventFromNotificationDropsDayWordFromSummary(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// Vikunja #482. A relay that posts its instant as UTC used to hand the wall
|
||||
// clock inside the text the same zone, so "созвон в 14:30" was stored as 14:30Z
|
||||
// and read back as 18:30 on a UTC+4 box — late by exactly the deploy's offset,
|
||||
// and correct-looking on a UTC one. Nobody writes a notification meaning 14:30Z.
|
||||
func TestEventFromNotificationReadsTheClockAsLocalTime(t *testing.T) {
|
||||
ev, ok := EventFromNotification(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
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("expected an event")
|
||||
}
|
||||
if got := ev.Start.Format("15:04"); got != "14:30" {
|
||||
t.Errorf("start = %s, want 14:30 local", got)
|
||||
}
|
||||
if ev.Start.Location() != time.Local {
|
||||
t.Errorf("location = %v, want %v", ev.Start.Location(), time.Local)
|
||||
}
|
||||
if got, want := FactKey(ev), "calendar_event_20260802_Standup"; got != want {
|
||||
t.Errorf("fact key = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
func TestEventFromNotificationNeedsPostedAt(t *testing.T) {
|
||||
if _, ok := EventFromNotification(Notification{Title: "Планёрка 10:00"}); ok {
|
||||
t.Error("a notification with no posted_at has no date to sit on")
|
||||
@@ -211,7 +245,7 @@ func TestEventFromNotificationNeedsPostedAt(t *testing.T) {
|
||||
func TestAmbientEventsAreStoredAtReducedConfidence(t *testing.T) {
|
||||
ev, ok := EventFromNotification(Notification{
|
||||
Title: "Планёрка 10:00-10:30",
|
||||
Posted: time.Date(2026, 8, 3, 9, 0, 0, 0, time.UTC),
|
||||
Posted: time.Date(2026, 8, 3, 9, 0, 0, 0, time.Local),
|
||||
})
|
||||
if !ok {
|
||||
t.Fatal("expected an event")
|
||||
|
||||
@@ -85,6 +85,15 @@ type Config struct {
|
||||
NCtx int
|
||||
Timeout time.Duration
|
||||
|
||||
// StartupTimeout bounds the wait for llama-server to print the address it
|
||||
// listens on. A config field and not a constant because the box may
|
||||
// legitimately need longer: a cold 1.7B loading off a spinning disk can
|
||||
// outrun a minute, and until this existed that returned "server did not
|
||||
// start within 60s" with no way to raise it.
|
||||
//
|
||||
// 0 ⇒ defaultStartupTimeout.
|
||||
StartupTimeout time.Duration
|
||||
|
||||
// CacheRAMMiB bounds llama-server's prompt cache, which is what actually ate
|
||||
// this box. Measured on homesrv 2026-08-03: the server's own default limit is
|
||||
// 8192 MiB, it stores the full KV state of every idle slot it evicts (112 kiB
|
||||
@@ -134,6 +143,8 @@ func DefaultConfig(modelPath string) Config {
|
||||
// 512 MiB caps total RSS near 1 GB and still holds several recent prompts.
|
||||
CacheRAMMiB: 512,
|
||||
Timeout: 30 * time.Second,
|
||||
|
||||
StartupTimeout: defaultStartupTimeout,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -260,7 +271,15 @@ func llamaArgs(cfg Config) []string {
|
||||
return args
|
||||
}
|
||||
|
||||
// defaultStartupTimeout — the wait for llama-server's listen line when Config
|
||||
// does not set one. A cold model load off disk is the slow part.
|
||||
const defaultStartupTimeout = 60 * time.Second
|
||||
|
||||
func startLlamaProc(ctx context.Context, cfg Config) (*llamaProc, error) {
|
||||
startupTimeout := cfg.StartupTimeout
|
||||
if startupTimeout <= 0 {
|
||||
startupTimeout = defaultStartupTimeout
|
||||
}
|
||||
p := &llamaProc{}
|
||||
cmd := exec.CommandContext(ctx, cfg.BinPath, llamaArgs(cfg)...)
|
||||
// Pdeathsig: the kernel SIGKILLs llama-server the moment mavend dies — by
|
||||
@@ -338,8 +357,8 @@ func startLlamaProc(ctx context.Context, cfg Config) (*llamaProc, error) {
|
||||
return fail(fmt.Errorf("llm: server output: %w; last output: %s", err, tail.String()))
|
||||
case <-ctx.Done():
|
||||
return fail(ctx.Err())
|
||||
case <-time.After(60 * time.Second):
|
||||
return fail(fmt.Errorf("llm: server did not start within 60s; last output: %s", tail.String()))
|
||||
case <-time.After(startupTimeout):
|
||||
return fail(fmt.Errorf("llm: server did not start within %s; last output: %s", startupTimeout, tail.String()))
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -181,6 +181,37 @@ exit 1`)
|
||||
t.Fatalf("err = %v, want context.Canceled", err)
|
||||
}
|
||||
})
|
||||
|
||||
// The last arm of the startup race, and the one most likely to leak: a
|
||||
// llama-server still loading a model is alive, so giving up on it without
|
||||
// killing and reaping it orphans a process holding the GPU. Testable at all
|
||||
// because Config.StartupTimeout replaced a hardcoded 60s (Vikunja #323).
|
||||
t.Run("startup timeout", func(t *testing.T) {
|
||||
pidPath := filepath.Join(t.TempDir(), "pid")
|
||||
bin := fakeLlama(t, fmt.Sprintf(`echo $$ > %s
|
||||
while : ; do sleep 1 ; done`, pidPath))
|
||||
cfg := testCfg(bin)
|
||||
cfg.StartupTimeout = 200 * time.Millisecond
|
||||
|
||||
_, err := startLlamaProc(context.Background(), cfg)
|
||||
if err == nil || !strings.Contains(err.Error(), "did not start within 200ms") {
|
||||
t.Fatalf("err = %v, want the startup-timeout arm naming the timeout", err)
|
||||
}
|
||||
|
||||
raw, readErr := os.ReadFile(pidPath)
|
||||
if readErr != nil {
|
||||
t.Fatalf("fake server never recorded its pid: %v", readErr)
|
||||
}
|
||||
pid, convErr := strconv.Atoi(strings.TrimSpace(string(raw)))
|
||||
if convErr != nil {
|
||||
t.Fatalf("pid file = %q: %v", raw, convErr)
|
||||
}
|
||||
// Killed, and reaped: a zombie still answers signal 0, so this asserts
|
||||
// the Wait ran too.
|
||||
if err := syscall.Kill(pid, 0); err == nil {
|
||||
t.Errorf("llama-server %d survived the startup timeout", pid)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
func TestNewLLMPhraserSpawns(t *testing.T) {
|
||||
|
||||
@@ -237,7 +237,14 @@ func newBaselineRouter(t *testing.T, emb router.Embedder, llmR *router.LLMRouter
|
||||
// anything while its grammar set is the daemon's grammar set.
|
||||
grammars = append(grammars, router.AgendaQueryGrammars()...)
|
||||
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.NarrativeQueryGrammar())
|
||||
return router.New(router.Config{
|
||||
Grammars: grammars,
|
||||
Classifier: cls,
|
||||
|
||||
@@ -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" },
|
||||
|
||||
@@ -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, NarrativeQueryGrammar())
|
||||
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)
|
||||
}
|
||||
}
|
||||
@@ -196,6 +196,20 @@ 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
|
||||
@@ -208,6 +222,55 @@ 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)`)
|
||||
|
||||
// NarrativeQueryGrammar — stage-0 rule for "расскажи про X", "объясни X",
|
||||
// "опиши X", routed to IntentQuery.
|
||||
//
|
||||
// It carries no question mark and no interrogative, so the model called
|
||||
// "расскажи про битву при Ватерлоо" a fact and tried to store the answer it
|
||||
// invented (Vikunja #470, point 1). The write is contained now — actions_fact
|
||||
// refuses a question-shaped write and re-runs the turn as a query — but every
|
||||
// such utterance still paid a model round trip to reach a decision one regex
|
||||
// can make, and the fixture still scored the routing as wrong (Vikunja #498).
|
||||
//
|
||||
// The lexicon is narrativeRequests in question.go, which IsQuestionShaped
|
||||
// already uses. One list, two callers: a word that marks an utterance as
|
||||
// asking must not mark it here and not there.
|
||||
//
|
||||
// Routing, not answering. Which source claims the turn is still the query
|
||||
// chain's decision, and the personal boundary still sits where it sat.
|
||||
func NarrativeQueryGrammar() Grammar {
|
||||
return Grammar{
|
||||
Name: "narrative-query",
|
||||
// (\s|[?!.]|$) rather than \b: Go's \b is ASCII-only and never fires
|
||||
// after a Cyrillic letter, so the pattern would silently never match.
|
||||
Pattern: regexp.MustCompile(`(?is)^\s*(` + strings.Join(narrativeRequests, "|") + `)(?:\s+(?:мне|нам|us|me))?(?:\s+(?:про|о|об|about))?(\s+.+)$`),
|
||||
Build: func(m []string) (Decision, bool) {
|
||||
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
|
||||
}
|
||||
// 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
|
||||
}
|
||||
return Decision{
|
||||
Stage: 0,
|
||||
Intent: IntentQuery,
|
||||
Confidence: 1.0,
|
||||
Slots: Slots{Text: topic},
|
||||
}, true
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// FeedQueryGrammar — stage-0 rule for "что нового в лентах?", routed to
|
||||
// IntentQuery so it reaches queryFeeds.
|
||||
//
|
||||
|
||||
@@ -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
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user