Maven/cmd/mavend/factgate_test.go

package main

import (
	"context"
	"testing"
	"time"

	"github.com/kami/maven/internal/ipc"
	"github.com/kami/maven/internal/memory"
	"github.com/kami/maven/internal/router"
	"github.com/kami/maven/internal/tool"
	"github.com/kami/maven/internal/voice"
)

func newFactGateHandler(t *testing.T, now time.Time) (*reactiveHandler, ipc.CoreAPI) {
	t.Helper()
	st := newTestStore(t)
	api := ipc.NewStoreAPI(st)
	emb := router.NewHashEmbedder(1024)
	h := &reactiveHandler{
		api:       api,
		recall:    recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
		router:    buildRouter(emb, tool.NewMatcher(api), 0.55, nil),
		replier:   voice.NewStubReplier(),
		now:       func() time.Time { return now },
		dataStore: st,
	}
	return h, api
}

// The write half of #470: a question routed to IntentFact must not become a
// fact about him, and must not leave a vector behind for recall to serve.
func TestActionFact_QuestionIsNotWritten(t *testing.T) {
	ctx := context.Background()
	h, api := newFactGateHandler(t, time.Now())

	reply := h.actionFact(ctx, router.Decision{
		Intent:    router.IntentFact,
		Utterance: "какая последняя версия языка Go?",
		Slots:     router.Slots{Key: "go_version", HasKey: true, Value: `"1.20"`},
	})

	if _, err := api.LatestFact(ctx, "go_version"); err == nil {
		t.Fatal("a question was stored as a fact about him")
	}
	hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "какая последняя версия языка Go?"), 3)
	if err != nil {
		t.Fatalf("memory search: %v", err)
	}
	if len(hits) != 0 {
		t.Fatalf("the question was indexed for recall: %+v", hits)
	}
	// It went down the query chain instead. Nothing is configured to answer a
	// world question in this harness, so "не знаю." is the honest outcome —
	// what matters is that the turn was answered, not stored.
	if reply == "" {
		t.Fatal("the turn was neither stored nor answered")
	}
}

// The capture that must survive the gate: an explicit instruction to record,
// even though it contains an interrogative.
func TestActionFact_ExplicitCaptureStillWrites(t *testing.T) {
	ctx := context.Background()
	h, api := newFactGateHandler(t, time.Now())

	h.actionFact(ctx, router.Decision{
		Intent:    router.IntentFact,
		Utterance: "запиши что я пил воду",
		Slots:     router.Slots{Key: "water", HasKey: true, Value: `"вода"`},
	})

	f, err := api.LatestFact(ctx, "water")
	if err != nil {
		t.Fatalf("an explicit capture was refused: %v", err)
	}
	if f.Confidence != 1.0 {
		t.Errorf("confidence = %v, want 1.0 for a value he said", f.Confidence)
	}
	// #493: what recall reads back is the fact, not the sentence he said.
	// queryMemory returns a fact's text verbatim, so the utterance sitting here
	// meant "запиши что я пил воду" was the answer to "когда я пил воду?".
	hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "вода"), 3)
	if err != nil {
		t.Fatalf("memory search: %v", err)
	}
	if len(hits) != 1 {
		t.Fatalf("the fact was not indexed once: %+v", hits)
	}
	if got := hits[0].Meta["text"]; got != "water — вода" {
		t.Errorf("indexed text = %q, want the fact", got)
	}
	if got := hits[0].Meta["utterance"]; got != "запиши что я пил воду" {
		t.Errorf("utterance provenance = %q, want it kept alongside", got)
	}
}

func TestFactConfidence(t *testing.T) {
	cases := []struct {
		utterance, value string
		want             float64
	}{
		{"запиши что я пил воду", `"вода"`, 1.0},
		{"я выпил кофе", `"кофе"`, 1.0},
		{"поужинал", "", 1.0},
		{"отметь что я полил кактус", `"полил кактус"`, 1.0},
		{"какая последняя версия языка Go", `"1.20"`, ungroundedConfidence},
		{"кто премьер Японии", `"Тонио Озаки"`, ungroundedConfidence},
	}
	for _, c := range cases {
		if got := factConfidence(c.utterance, c.value); got != c.want {
			t.Errorf("factConfidence(%q, %q) = %v, want %v", c.utterance, c.value, got, c.want)
		}
	}
}

func mustEmbedPassage(t *testing.T, h *reactiveHandler, text string) []float32 {
	t.Helper()
	vec, err := router.EmbedQuery(context.Background(), h.recall.embedder, text)
	if err != nil {
		t.Fatalf("embed %q: %v", text, err)
	}
	return vec
}

// The write half of #481: a complaint about a thing is a state of the
// afternoon, not a fact about him. Stored as a `self` row at confidence 1.00
// it comes back on recall as if the network were still down.
func TestActionFact_ComplaintIsNotWritten(t *testing.T) {
	ctx := context.Background()
	h, api := newFactGateHandler(t, time.Now())

	reply := h.actionFact(ctx, router.Decision{
		Intent:    router.IntentFact,
		Utterance: "сеть какая-то медленная",
		Slots:     router.Slots{Key: "network_speed", HasKey: true, Value: "медленная"},
	})

	if _, err := api.LatestFact(ctx, "network_speed"); err == nil {
		t.Fatal("a passing complaint was stored as a fact about him")
	}
	hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "сеть какая-то медленная"), 3)
	if err != nil {
		t.Fatalf("memory search: %v", err)
	}
	if len(hits) != 0 {
		t.Fatalf("the complaint was indexed for recall: %+v", hits)
	}
	if reply == "" {
		t.Fatal("the turn was neither stored nor answered")
	}
}

// And the complaint he asked her to keep: the capture verb wins, as it does
// over the question gate.
func TestActionFact_AskedToRememberAComplaintStillWrites(t *testing.T) {
	ctx := context.Background()
	h, api := newFactGateHandler(t, time.Now())

	h.actionFact(ctx, router.Decision{
		Intent:    router.IntentFact,
		Utterance: "запомни что интернет не работает",
		Slots:     router.Slots{Key: "internet", HasKey: true, Value: "не работает"},
	})

	if _, err := api.LatestFact(ctx, "internet"); err != nil {
		t.Fatalf("an explicit capture was refused: %v", err)
	}
}

// A second tap of the same key supersedes the first, so recall must hold one
// vector and it must be the new value (Vikunja #493). Before this the id
// carried a timestamp, both rows stayed, and the superseded value went on
// competing for the turn.
func TestActionFact_ARetapSupersedesTheOldVector(t *testing.T) {
	ctx := context.Background()
	h, _ := newFactGateHandler(t, time.Now())

	h.actionFact(ctx, router.Decision{
		Intent:    router.IntentFact,
		Utterance: "запиши что я пил воду",
		Slots:     router.Slots{Key: "water", HasKey: true, Value: `"250мл"`},
	})
	// A later tap of the same key. The clock moves, so the old id and the new
	// one differ — which is exactly what used to leave two rows behind.
	h.now = func() time.Time { return time.Now().Add(time.Hour) }
	h.actionFact(ctx, router.Decision{
		Intent:    router.IntentFact,
		Utterance: "запиши что я пил воду",
		Slots:     router.Slots{Key: "water", HasKey: true, Value: `"500мл"`},
	})

	hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "вода"), 5)
	if err != nil {
		t.Fatalf("memory search: %v", err)
	}
	if len(hits) != 1 {
		t.Fatalf("want one vector for the key, got %d: %+v", len(hits), hits)
	}
	if got := hits[0].Meta["text"]; got != "water — 500мл" {
		t.Errorf("indexed text = %q, want the current value", got)
	}
}

// Another key is not this key. A prefix delete that widened would take the
// whole index with it.
func TestActionFact_ARetapLeavesOtherKeysAlone(t *testing.T) {
	ctx := context.Background()
	h, _ := newFactGateHandler(t, time.Now())

	h.actionFact(ctx, router.Decision{
		Intent:    router.IntentFact,
		Utterance: "запиши что я обедал",
		Slots:     router.Slots{Key: "meal", HasKey: true, Value: `"суп"`},
	})
	h.actionFact(ctx, router.Decision{
		Intent:    router.IntentFact,
		Utterance: "запиши что я пил воду",
		Slots:     router.Slots{Key: "water", HasKey: true, Value: `"250мл"`},
	})

	hits, err := h.recall.memStore.Search(ctx, mustEmbedPassage(t, h, "обед"), 5)
	if err != nil {
		t.Fatalf("memory search: %v", err)
	}
	var found bool
	for _, hit := range hits {
		if hit.Meta["text"] == "meal — суп" {
			found = true
		}
	}
	if !found {
		t.Fatalf("writing water dropped the meal vector: %+v", hits)
	}
}