Maven/cmd/mavend/topics_test.go

package main

import (
	"context"
	"os"
	"path/filepath"
	"testing"

	"github.com/kami/maven/internal/router"
)

// TestTopicFloorAnswersWithoutSeeds — a handler with no embedder never loads the
// seeds, and every topic source has to keep working. This is the case that used
// to be the only one, so a regression here is all four recognisers going silent
// on a box with no embedder at all.
func TestTopicFloorAnswersWithoutSeeds(t *testing.T) {
	h := &reactiveHandler{}
	for _, tc := range []struct {
		utterance string
		label     topicLabel
		floor     func(string) bool
		want      bool
	}{
		{"какая сегодня погода", topicWeather, isWeatherQuery, true},
		{"что включено в доме?", topicHome, isHomeQuery, true},
		{"какие устройства в сети?", topicNetwork, isNetworkQuery, true},
		{"что требует внимания?", topicAttend, isAttentionQuery, true},
		{"что нового в лентах?", topicFeed, feedFloor, true},
		{"что в списке покупок?", topicList, listFloor, true},
		{"почему небо синее", topicWeather, isWeatherQuery, false},
		{"я дома", topicHome, isHomeQuery, false},
		{"интернет не работает", topicNetwork, isNetworkQuery, false},
	} {
		turn := &queryTurn{dec: router.Decision{Utterance: tc.utterance}}
		if got := h.turnIsAbout(context.Background(), turn, tc.label, tc.floor); got != tc.want {
			t.Errorf("turnIsAbout(%q, %s) = %v, want %v", tc.utterance, tc.label, got, tc.want)
		}
	}
}

// TestONNXTopics — the number that matters, scored against the embedder homesrv
// actually runs. Opt-in via MAVEN_ONNX_LIB, like TestONNXPersonalBoundary.
//
// Every case is held out: none of these strings is a seed. It asserts what the
// gate does, not what the raw scorer says — a label under topicMargin is handed
// to the keyword floor, and one case turns on exactly that.
//
// The first three rows are the collisions the old regexes needed hand-written
// bail-outs for: the temperature pair that made isHomeQuery exclude weather
// words, and the "посетил" substring that made isNetworkQuery match "сети" as a
// whole token.
func TestONNXTopics(t *testing.T) {
	lib := os.Getenv("MAVEN_ONNX_LIB")
	if lib == "" {
		t.Skip("MAVEN_ONNX_LIB unset — see AGENTS.md § Embedder model for intent routing")
	}
	dir := filepath.Join("../..", "models/embedder/multilingual-e5-small")
	emb, err := router.NewONNXEmbedder(filepath.Join(dir, "model_quantized.onnx"), filepath.Join(dir, "tokenizer.json"), lib)
	if err != nil {
		t.Skipf("onnx embedder unavailable: %v", err)
	}
	defer emb.Close()

	cases := []struct {
		utterance string
		want      topicLabel
		floor     func(string) bool
	}{
		{"какая температура на улице?", topicWeather, isWeatherQuery},
		{"какая температура в доме?", topicHome, isHomeQuery},
		{"сколько машин я посетил?", topicOther, nil},
		{"сколько сейчас градусов", topicWeather, isWeatherQuery},
		{"дождь будет вечером?", topicWeather, isWeatherQuery},
		{"тепло сегодня на улице?", topicWeather, isWeatherQuery},
		{"свет на кухне включен?", topicHome, isHomeQuery},
		{"что сейчас включено дома", topicHome, isHomeQuery},
		{"датчики в квартире что показывают", topicHome, isHomeQuery},
		{"просканируй сеть", topicNetwork, isNetworkQuery},
		{"сколько устройств в локальной сети", topicNetwork, isNetworkQuery},
		{"кто сейчас в сетке", topicNetwork, isNetworkQuery},
		// The case the margin exists for. It reads as network by 0.0055, and
		// isNetworkQuery says no, so it stays the complaint it is — a scan she
		// runs unasked is the behaviour the bounds prevent.
		{"вайфай опять отвалился", topicOther, isNetworkQuery},
		{"я уже приехал домой", topicOther, nil},
		{"что я говорил про погоду в москве", topicOther, nil},
		{"напомни полить цветы", topicOther, nil},
		{"что требует моего внимания сейчас", topicAttend, isAttentionQuery},
		{"что не так с базой данных", topicAttend, isAttentionQuery},
		{"есть что-то срочное на сегодня", topicAttend, isAttentionQuery},
		{"что нового в ленте за сегодня", topicFeed, feedFloor},
		{"какие сегодня заголовки", topicFeed, feedFloor},
		{"что нового про искусственный интеллект", topicFeed, feedFloor},
		// The greeting. It has to lose to topicOther, or fall thin enough that
		// ParseFeedQuery — which declines a vague noun with no topic — answers.
		{"что нового?", topicOther, feedFloor},
		{"что мне надо купить в магазине", topicList, listFloor},
		{"прочитай мне список", topicList, listFloor},
		{"что там в аптеке нужно взять", topicList, listFloor},
		// A task read-back is not a list read-back, and the two collide on
		// "что у меня".
		{"какие у меня сейчас задачи", topicOther, listFloor},
		// World questions that name a day (Vikunja #553). Weather was the only
		// topic carrying day words, so all of these read as weather and two of
		// them cleared the margin: the gate asked "для какого города?" about
		// the dollar. The last two are far from any seed on purpose — the
		// first three are close enough to the new topicOther seeds that they
		// would pass on similarity alone.
		{"какой сегодня курс доллара", topicOther, isWeatherQuery},
		{"какой сегодня праздник", topicOther, isWeatherQuery},
		{"что интересного произошло сегодня в мире", topicOther, isWeatherQuery},
		{"во сколько завтра открывается музей", topicOther, isWeatherQuery},
		{"кто сегодня играет в лиге чемпионов", topicOther, isWeatherQuery},
		// The control the seeds above must not cost: real weather still reads
		// as weather, including the two that lean on the keyword floor.
		{"будет ли завтра дождь в москве", topicWeather, isWeatherQuery},
		{"какая температура завтра утром", topicWeather, isWeatherQuery},
		// The same shape one topic over, seen on the box (Vikunja #554): a
		// device has a history, and asking about it is not asking what is
		// plugged in. "кто изобрёл телефон" answered "нашла 3 устройства".
		// Held out from the seeds, which name the telephone and the computer.
		{"кто придумал радио", topicOther, isNetworkQuery},
		{"когда изобрели телевизор", topicOther, isNetworkQuery},
		{"как устроен телефон внутри", topicOther, isNetworkQuery},
		// The control: a real scan is still a scan.
		{"какие устройства подключены к вайфаю", topicNetwork, isNetworkQuery},
	}

	h := &reactiveHandler{recall: recallWiring{embedder: emb}}
	ctx := context.Background()
	h.recall.topics.load(ctx, emb)
	if !h.recall.topics.loaded {
		t.Fatal("topic seeds did not load")
	}
	right := 0
	for _, tc := range cases {
		vec, err := router.EmbedQuery(ctx, emb, tc.utterance)
		if err != nil {
			t.Fatalf("embed %q: %v", tc.utterance, err)
		}
		label, margin, ok := h.recall.topics.best(vec)
		if !ok {
			t.Fatalf("best(%q) not ok", tc.utterance)
		}
		// What the gate would do, which is the thing under test: a label that
		// does not clear the margin is handed to that source's keyword floor.
		got := label
		if margin < topicMargin {
			got = topicOther
			if tc.floor != nil && tc.floor(tc.utterance) {
				got = label
			}
		}
		if got == tc.want {
			right++
		} else {
			t.Errorf("%q: %s by %.4f, want %s", tc.utterance, label, margin, tc.want)
		}
		t.Logf("  %-40s -> %-8s margin %.4f", tc.utterance, label, margin)
	}
	t.Logf("topics: %d/%d", right, len(cases))
}