Files
Maven/cmd/mavend/clarify_test.go
T
kami b9a24334ea Say it the way she'd actually say it
Wording fixes from the review of the clarify + phrasing PRs.

- "На когда напомнить?" → "Когда?". After she has just been asked something,
  the long form is the phrasing of a form field, not of a person.
- A reminder now wants a subject as well as a time. "напомни в 11" had a time
  and nothing to say at 11, and she asked nothing at all — she now asks
  "О чём напомнить?". Subject first, since a reminder with no subject is not
  worth setting.
- The expiry notice is five phrasings picked at random instead of one fixed
  sentence. It is the line he hears every time he walks off mid-request, so it
  is the line that repeats most.
- The nudge prompt's ban on "обращения" is now "ласковые обращения". It was
  meant to forbid "милый"/"дорогой", not his name — "Ками, ноутбук на трёх
  процентах" is how she talks, and the eval's cringe check already only flags
  pet names.
- The nudge example no longer claims she plugged the laptop in. She has no
  hands and no smart plug; an example where she acts teaches the model to
  invent actions Maven never took.
- replySystem: "тепло" → "спокойно и без официальных формулировок". A one-word
  mood instruction a 1.7B can't act on, replaced with the behaviour meant.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 21:52:12 +04:00

333 lines
14 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package main
import (
"context"
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/kami/maven/internal/dialogue"
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/router"
"github.com/kami/maven/internal/store"
"github.com/kami/maven/internal/tool"
"github.com/kami/maven/internal/voice"
)
// newClarifyHandler builds a handler with the clarify path wired and no model:
// stub date parser, the real fact parser, and a matcher over whatever tools the
// test enabled. `now` is fixed so TTL behaviour is testable.
func newClarifyHandler(t *testing.T) (*reactiveHandler, *store.Store, *time.Time) {
t.Helper()
st := newTestStore(t)
api := ipc.NewStoreAPI(st)
now := time.Date(2026, 7, 31, 9, 0, 0, 0, time.UTC)
matcher := tool.NewMatcher(api)
h := &reactiveHandler{
api: api,
dataStore: st,
tools: tool.NewExecutor(api, 2*time.Second),
matcher: matcher,
replier: voice.NewStubReplier(),
now: func() time.Time { return now },
dialogueSessions: dialogue.NewSessionStore(2 * time.Minute),
clarifyStore: dialogue.NewClarifyStore(clarifyTTL),
extractor: router.Extractor{
Time: router.StubDateTimeParser{},
Acts: matcher,
Facts: router.DefaultFactParser{},
},
}
return h, st, &now
}
func clarifyDec(intent router.Intent, slots router.Slots, utterance string) router.Decision {
return router.Decision{Utterance: utterance, Stage: 3, Intent: intent, Slots: slots, Clarify: true}
}
// TestClarifyQuestionForMissingSlot pins which question goes with which gap, and
// which intents get no question at all.
func TestClarifyQuestionForMissingSlot(t *testing.T) {
cases := []struct {
name string
dec router.Decision
want string
asked bool
}{
{"reminder without a time", clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"), "Когда?", true},
{"fact without a key", clarifyDec(router.IntentFact, router.Slots{Text: "запиши"}, "запиши"), "Что записать?", true},
{"act without a fn", clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это"), "Что сделать?", true},
// A time with nothing to say at that time is still half a reminder, so
// the subject is what she asks about — not silence.
{"reminder that has a time but no subject", clarifyDec(router.IntentReminder, router.Slots{HasTime: true}, "напомни в 11"), "О чём напомнить?", true},
{"reminder that has both", clarifyDec(router.IntentReminder, router.Slots{Text: "позвонить маме", HasTime: true}, "напомни в 11 позвонить маме"), "", false},
{"chat is never worth a question", clarifyDec(router.IntentChat, router.Slots{Text: "мгм"}, "мгм"), "", false},
{"query is never worth a question", clarifyDec(router.IntentQuery, router.Slots{Text: "а"}, "а"), "", false},
}
for _, tc := range cases {
_, got, asked := clarifyQuestion(tc.dec)
if asked != tc.asked || got != tc.want {
t.Errorf("%s: got (%q, %v), want (%q, %v)", tc.name, got, asked, tc.want, tc.asked)
}
}
}
// TestClarifyReminderCompletesOnAnswer is the whole point of the feature: she
// asks for the missing time and the answer creates the reminder.
func TestClarifyReminderCompletesOnAnswer(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
question, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме"))
if !asked || question != "Когда?" {
t.Fatalf("expected the time question, got %q asked=%v", question, asked)
}
reply, handled := h.resolveClarifyAnswer(ctx, "в 11:00")
if !handled {
t.Fatal("the answer to an open question must be consumed as an answer")
}
if reply == clarifyGaveUp {
t.Fatalf("a good answer must not drop the request: %q", reply)
}
reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour))
if err != nil || len(reminders) != 1 {
t.Fatalf("clarified reminder was not created: reminders=%v err=%v", reminders, err)
}
if !strings.Contains(reminders[0].Payload, "маме") {
t.Fatalf("the reminder lost the original request: %q", reminders[0].Payload)
}
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("the question must be cleared once answered")
}
}
// TestClarifyFactCompletesOnAnswer — the fact path, where the answer carries
// both the key and the value.
func TestClarifyFactCompletesOnAnswer(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
if _, asked := h.askClarify(clarifyDec(router.IntentFact, router.Slots{Text: "запиши"}, "запиши")); !asked {
t.Fatal("a fact with no key should be asked about")
}
if reply, handled := h.resolveClarifyAnswer(ctx, "пил воду"); !handled || reply == clarifyGaveUp {
t.Fatalf("answer should complete the fact, handled=%v reply=%q", handled, reply)
}
if fact, err := st.LatestFact(ctx, "water"); err != nil || fact.Key != "water" {
t.Fatalf("clarified fact was not written: fact=%+v err=%v", fact, err)
}
}
// TestClarifyAnswerAfterTTLIsANewRequest — a late answer is not an answer.
func TestClarifyAnswerAfterTTLIsANewRequest(t *testing.T) {
ctx := context.Background()
h, st, now := newClarifyHandler(t)
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
*now = now.Add(clarifyTTL + time.Second)
if reply, handled := h.resolveClarifyAnswer(ctx, "в 11:00"); handled {
t.Fatalf("an answer past the TTL must fall through to normal routing, got %q", reply)
}
if reminders, err := st.DueReminders(ctx, now.Add(48*time.Hour)); err != nil || len(reminders) != 0 {
t.Fatalf("expired question must not create anything: reminders=%v err=%v", reminders, err)
}
}
// TestClarifyAsksThreeTimesThenSaysSo — three questions are allowed, the fourth
// is not, and running out is SPOKEN. Silence would read as "handled".
func TestClarifyAsksThreeTimesThenSaysSo(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a first question")
}
// Two more unclear answers ⇒ two more questions (3 asks in total).
for i := 2; i <= 3; i++ {
reply, handled := h.resolveClarifyAnswer(ctx, "ну не знаю")
if !handled {
t.Fatalf("answer %d must be consumed as an answer", i)
}
if reply != "Когда?" {
t.Fatalf("attempt %d should ask again, got %q", i, reply)
}
if h.clarifyStore.Get(voiceDialogueID, h.now()) == nil {
t.Fatalf("attempt %d must leave the question armed", i)
}
}
reply, handled := h.resolveClarifyAnswer(ctx, "ну не знаю")
if !handled || reply != clarifyGaveUp {
t.Fatalf("the fourth try must give up out loud, handled=%v reply=%q", handled, reply)
}
if reply == "" || strings.Contains(reply, "?") {
t.Fatalf("giving up must be spoken and must not be another question: %q", reply)
}
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("a given-up request must leave no armed question")
}
if reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour)); err != nil || len(reminders) != 0 {
t.Fatalf("a given-up request must not create anything: reminders=%v err=%v", reminders, err)
}
}
// TestClarifyMaxAttemptsIsConfigurable — one question when the config says one.
func TestClarifyMaxAttemptsIsConfigurable(t *testing.T) {
ctx := context.Background()
h, _, _ := newClarifyHandler(t)
h.clarifyMaxAttempts = 1
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
if reply, handled := h.resolveClarifyAnswer(ctx, "ну не знаю"); !handled || reply != clarifyGaveUp {
t.Fatalf("with max 1 she must give up at once, handled=%v reply=%q", handled, reply)
}
}
// TestClarifyRestatedAnswerWins — «в 11:00», then «нет, в 15:00». The second
// value is the one that lands.
func TestClarifyRestatedAnswerWins(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни позвонить маме"}, "напомни позвонить маме")); !asked {
t.Fatal("expected a question")
}
// First answer parses, but re-park it by hand as if she had asked again:
// what matters here is that Answer prefers the newer value over the parked
// one, which is the case the daemon hits on a re-ask.
q := h.clarifyStore.Get(voiceDialogueID, h.now())
if q == nil {
t.Fatal("expected an armed question")
}
first := h.extractor.Extract(ctx, router.IntentReminder, "в 11:00", h.now())
q.Slots = q.Answer("в 11:00", toDialogueSlots(first))
if reply, handled := h.resolveClarifyAnswer(ctx, "нет, в 15:00"); !handled || reply == clarifyGaveUp {
t.Fatalf("the restated answer should complete the request, handled=%v reply=%q", handled, reply)
}
reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour))
if err != nil || len(reminders) != 1 {
t.Fatalf("expected one reminder: %v err=%v", reminders, err)
}
want := h.extractor.Extract(ctx, router.IntentReminder, "в 15:00", h.now())
if !reminders[0].FireTs.Equal(want.Time) {
t.Fatalf("reminder at %v, want the restated %v", reminders[0].FireTs, want.Time)
}
}
// TestClarifiedActOffAllowlistIsStillRefused — clarification fills in an
// argument, it never grants authority.
func TestClarifiedActOffAllowlistIsStillRefused(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
marker := filepath.Join(t.TempDir(), "not-allowed-ran")
if _, asked := h.askClarify(clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
t.Fatal("an act with no fn should be asked about")
}
reply, handled := h.resolveClarifyAnswer(ctx, "rm "+marker)
if !handled {
t.Fatal("the answer should be consumed")
}
if strings.Contains(reply, "готово") {
t.Fatalf("an act that is not on the allowlist must not report success: %q", reply)
}
if _, err := os.Stat(marker); !os.IsNotExist(err) {
t.Fatalf("a clarified act off the allowlist ran anyway: %v", err)
}
if tools, err := st.ListTools(ctx, "enabled"); err != nil || len(tools) != 0 {
t.Fatalf("clarify must not enable a tool: tools=%+v err=%v", tools, err)
}
}
// TestClarifiedDestructiveActStillNeedsConfirm — the confirm gate survives the
// clarify path.
func TestClarifiedDestructiveActStillNeedsConfirm(t *testing.T) {
ctx := context.Background()
h, st, _ := newClarifyHandler(t)
marker := filepath.Join(t.TempDir(), "destructive-ran")
if err := st.EnableTool(ctx, "delete_backups", []string{"touch", marker}, true, "test", h.now()); err != nil {
t.Fatal(err)
}
if _, asked := h.askClarify(clarifyDec(router.IntentAct, router.Slots{Text: "сделай это"}, "сделай это")); !asked {
t.Fatal("expected a question")
}
reply, handled := h.resolveClarifyAnswer(ctx, "delete_backups")
if !handled {
t.Fatal("the answer should be consumed")
}
if !strings.Contains(reply, "да") || h.pending == nil {
t.Fatalf("a clarified destructive act must still park a confirm: reply=%q pending=%+v", reply, h.pending)
}
if _, err := os.Stat(marker); !os.IsNotExist(err) {
t.Fatalf("a clarified destructive act ran before confirmation: %v", err)
}
}
// TestNoQuestionWhenNothingIsMissing — noise keeps the canned reply, so she
// never invents a question for nothing.
func TestNoQuestionWhenNothingIsMissing(t *testing.T) {
h, _, _ := newClarifyHandler(t)
for _, dec := range []router.Decision{
clarifyDec(router.IntentChat, router.Slots{Text: "эм"}, "эм"),
clarifyDec(router.IntentQuery, router.Slots{Text: "ммм"}, "ммм"),
clarifyDec(router.IntentNote, router.Slots{Text: "..."}, "..."),
} {
if question, asked := h.askClarify(dec); asked {
t.Fatalf("intent %s should keep the canned reply, got %q", dec.Intent, question)
}
}
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("noise must not park a question")
}
}
// TestClarifyExpiryIsAnnouncedAndWordsStillRoute — his answer lands after the
// TTL: she must say the old request is gone AND still answer the new words.
func TestClarifyExpiryIsAnnouncedAndWordsStillRoute(t *testing.T) {
ctx := context.Background()
h, _, now := newClarifyHandler(t)
emb := router.NewHashEmbedder(1024)
h.embedder = emb
h.router = buildRouter(emb, h.matcher, 0.55, nil)
if _, asked := h.askClarify(clarifyDec(router.IntentReminder, router.Slots{Text: "напомни"}, "напомни")); !asked {
t.Fatal("expected a question")
}
*now = now.Add(clarifyTTL + time.Second)
reply := h.handleText(ctx, "как дела")
if !isClarifyExpired(reply) {
t.Fatalf("expired question must be announced first, got %q", reply)
}
if trimClarifyExpired(reply) == "" {
t.Fatalf("the new words must still be answered, got only the notice: %q", reply)
}
if h.clarifyStore.Get(voiceDialogueID, h.now()) != nil {
t.Fatal("the expired question must be gone")
}
// The notice is said once, not on every later utterance.
if reply := h.handleText(ctx, "как дела"); isClarifyExpired(reply) {
t.Fatalf("notice repeated on a later turn: %q", reply)
}
}
// TestNoPendingQuestionFallsThrough — with nothing parked, an utterance routes
// normally.
func TestNoPendingQuestionFallsThrough(t *testing.T) {
h, _, _ := newClarifyHandler(t)
if reply, handled := h.resolveClarifyAnswer(context.Background(), "напомни в 11:00"); handled {
t.Fatalf("no open question ⇒ must not be treated as an answer, got %q", reply)
}
}