Files
Maven/cmd/mavend/reactive_notes_test.go
T
claude 5b0b29dfad Make locative recall prove identity, not overlap (V-719)
The spare-key note scored 0.832 to 0.867 against a spare passport, a blue
shirt, a blue document box and a car key. Score and margin cannot separate
those: the right note runs 0.817 to 0.892 and the silent cases 0.787 to
0.874, so the ranges overlap and structure has to decide.

RecallAllowed now takes two structural facts from the router. A locative
question must corroborate every identity term against the candidate's
subject, read up to its first dictionary-proven verb, so a location object
in the note cannot answer for the thing being located. A turn that is not
question-shaped needs a named shared topic even when it ends in '?', which
is what "я отменил напоминание про молоко" lacked when it recalled an
unrelated note at 0.825 with no runner-up to fail the margin.

query_min_score moves 0.55 to 0.80 for tokenizer rev 2. The held-out
fixture answers 14/27 real recalls and 0/14 false ones.

LocativeAnswerVerifier is the resident-model second opinion, kept behind
the deterministic gate and wired into nothing. The measurement that says
why is docs/evals/2026-08-15-locative-answerability-verifier.md.

--no-verify: master is the working branch this session by the owner's call.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-15 17:19:01 +04:00

191 lines
6.6 KiB
Go

package main
import (
"context"
"strings"
"testing"
"time"
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/memory"
"github.com/kami/maven/internal/phraser"
"github.com/kami/maven/internal/router"
"github.com/kami/maven/internal/store"
"github.com/kami/maven/internal/tool"
"github.com/kami/maven/internal/voice"
)
func TestReactiveNotesReminders(t *testing.T) {
ctx := context.Background()
st := newTestStore(t)
api := ipc.NewStoreAPI(st)
now := time.Now()
emb := router.NewHashEmbedder(1024)
matcher := tool.NewMatcher(api)
rtr := buildRouter(emb, matcher, 0.55, nil, nil)
h := &reactiveHandler{
api: api,
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
router: rtr,
replier: voice.NewStubReplier(),
now: func() time.Time { return now },
dataStore: st,
}
t.Run("reminder capture", func(t *testing.T) {
fireAt := now.Add(24 * time.Hour).Truncate(time.Millisecond)
dec := router.Decision{
Intent: router.IntentReminder,
Utterance: "напомни завтра позвонить маме",
Slots: router.Slots{
Text: "завтра позвонить маме",
Time: fireAt,
HasTime: true,
},
}
// The confirmation is phrased from the row now (Vikunja #507), so it
// names the stored hour rather than leaving the replier to read one
// out of the sentence.
reply := h.applyAction(ctx, dec)
if want := "хорошо, напомню завтра в " + fireAt.Format("15:04") + "."; reply != want {
t.Errorf("reply = %q, want %q", reply, want)
}
reminders, err := st.ListReminders(ctx, 10)
if err != nil {
t.Fatalf("ListReminders: %v", err)
}
if len(reminders) == 0 {
t.Fatal("expected at least one reminder, got none")
}
last := reminders[0]
if last.FireTs.UnixMilli() != fireAt.UnixMilli() {
t.Errorf("reminder FireTs = %v, want %v", last.FireTs, fireAt)
}
if last.Status != "pending" {
t.Errorf("reminder Status = %q, want pending", last.Status)
}
})
t.Run("note capture", func(t *testing.T) {
dec := router.Decision{
Intent: router.IntentNote,
Utterance: "запомни что кофе закончился",
}
reply := h.applyAction(ctx, dec)
if reply != "" {
t.Errorf("expected empty reply from applyAction, got %q", reply)
}
notes, err := st.RecentNotes(ctx, 10)
if err != nil {
t.Fatalf("RecentNotes: %v", err)
}
if len(notes) == 0 {
t.Fatal("expected at least one note, got none")
}
last := notes[0]
if last.Text != "кофе закончился" {
t.Errorf("note text = %q, want %q", last.Text, "кофе закончился")
}
})
}
// TestRunTurnExplicitNoteStoresOnlyTheBody pins the live failure end to end:
// a routed text turn reaches actionNote, stores only the dictated body in both
// durable and vector memory, and cannot ask the resident model to choose the
// acknowledgement's grammatical gender (V-721).
func TestRunTurnExplicitNoteStoresOnlyTheBody(t *testing.T) {
ctx := context.Background()
st := newTestStore(t)
api := ipc.NewStoreAPI(st)
now := time.Date(2026, 8, 15, 8, 0, 0, 0, time.FixedZone("+04", 4*60*60))
emb := router.NewHashEmbedder(1024)
mem := memory.NewInMemoryStore()
rtr := router.New(router.Config{
Grammars: []router.Grammar{{
Name: "explicit-note-test",
Decide: func(string) (router.Decision, bool) {
return router.Decision{
Stage: 0, Intent: router.IntentNote, Confidence: 1,
// Deliberately hostile model slot: neither persistence nor
// acknowledgement may use it.
Slots: router.Slots{Text: "ты поедешь на дачу"},
}, true
},
}},
Threshold: 0.55,
})
model := &countingCompleter{out: `{"response":"Хорошо, сохранил.","mood":"neutral"}`}
h := &reactiveHandler{
api: api, router: rtr,
recall: recallWiring{embedder: emb, memStore: mem},
replier: newLLMReplier(model, nil),
now: func() time.Time { return now },
dataStore: st,
}
const utterance = "запомни: запасной ключ лежит в синей коробке"
if reply := h.runTurn(ctx, utterance, sourceText); reply != "сохранила заметку." {
t.Fatalf("reply = %q, want the fixed feminine acknowledgement", reply)
}
if model.calls != 0 {
t.Fatalf("resident model was called %d time(s) for a note acknowledgement", model.calls)
}
notes, err := st.RecentNotes(ctx, 10)
if err != nil {
t.Fatalf("RecentNotes: %v", err)
}
const body = "запасной ключ лежит в синей коробке"
if len(notes) != 1 || notes[0].Text != body || notes[0].Source != "tap:voice" || !notes[0].Ts.Equal(now) {
t.Fatalf("stored notes = %+v, want one exact body at the turn time", notes)
}
records, err := mem.ByPrefix(ctx, "note:")
if err != nil {
t.Fatalf("vector catalog: %v", err)
}
if len(records) != 1 || records[0].Meta["text"] != body {
t.Fatalf("vector records = %+v, want the same extracted body", records)
}
if records[0].Meta["text"] == utterance || records[0].Meta["text"] == "ты поедешь на дачу" {
t.Fatalf("vector metadata used a command or model rewrite: %+v", records[0].Meta)
}
if !phraser.IsAck(phraser.AckNote, nil, "сохранила заметку.") {
t.Fatal("fixed acknowledgement is not registered as the note acknowledgement")
}
}
// TestSpokenTaskCaptureFilesATask — the whole path, from the utterance to the
// task table. It went dead when the router started claiming the marker as an
// act: capture rides the note intent, so nothing below actionNote was ever
// reached and every capture answered "Что сделать?" (Vikunja #467).
func TestSpokenTaskCaptureFilesATask(t *testing.T) {
ctx := context.Background()
st := newTestStore(t)
api := ipc.NewStoreAPI(st)
now := time.Now()
emb := router.NewHashEmbedder(1024)
matcher := tool.NewMatcher(api)
h := &reactiveHandler{
api: api,
recall: recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
router: buildRouter(emb, matcher, 0.55, nil, nil),
replier: voice.NewStubReplier(),
now: func() time.Time { return now },
dataStore: st,
}
reply := h.handleText(ctx, "web", "добавь в задачи купить молоко")
if !strings.Contains(reply, "купить молоко") {
t.Fatalf("capture did not claim the turn: %q", reply)
}
open, err := st.ListTasks(ctx, store.TaskOpen)
if err != nil || len(open) != 1 {
t.Fatalf("task was not filed: tasks=%v err=%v", open, err)
}
// The words he said, not the model's rewrite of them.
if open[0].Text != "купить молоко" {
t.Fatalf("task text was rewritten: %q", open[0].Text)
}
}