Merge pull request 'Bug: the router transliterates Latin entity names into Cyrillic before Nexus sees them' (#131) from task/476-bug-the-router-transliterates-latin-enti into master

cmd/mavend/actions.go

@@ -57,9 +57,6 @@ var actionHandlers = map[router.Intent]func(*reactiveHandler, context.Context, r
 func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) string {
 	// Conversational: build history from dialogue session (prior user turns)
 	// and let the LLM respond from general knowledge + context.
-	if h.phraser == nil {
-		return "поговорили."
-	}
 	history := h.chatHistory()
 	reply, err := h.phraser.PhraseChat(ctx, dec.Utterance, history)
 	if err != nil {

cmd/mavend/actions_fact.go

@@ -38,21 +38,6 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
 		q.Slots.Value = ""
 		return h.actionQuery(ctx, q)
 	}
-	// A complaint is not a fact either (#481). "сеть какая-то медленная" and
-	// "интернет не работает" were stored as `self` rows at confidence 1.00, and
-	// recall reads a self row back later as if it were still true — the same
-	// class of row that outranked live search in #470. The sentence describes a
-	// moment, so she answers it and stores nothing. An explicit "запомни ..."
-	// and anything about him are both left alone by the test.
-	if router.IsTransientComplaint(dec.Utterance) {
-		log.Printf("voice: fact write refused, utterance is a passing complaint: %q (key %q) — answering as chat",
-			dec.Utterance, dec.Slots.Key)
-		c := dec
-		c.Intent = router.IntentChat
-		c.Slots.Key, c.Slots.HasKey = "", false
-		c.Slots.Value = ""
-		return h.actionChat(ctx, c)
-	}
 	now := h.now()
 	req := ipc.WriteFactReq{
 		Ts:     now,

cmd/mavend/actions_query.go

@@ -81,11 +81,6 @@ var querySources = []querySource{
 	// matcher requires a task noun or an explicit "что … сделать", so a
 	// date-bearing question still reaches the calendar.
 	{name: "tasks", answer: (*reactiveHandler).queryTasks},
-	// Next to "tasks" and for the same reason: "что требует внимания?" is a
-	// question about the operational state Praxis holds, and it used to fall
-	// through every source to the web search (Vikunja #475). Its matcher needs
-	// an attention marker, and it falls through when Praxis is not configured.
-	{name: "attention", answer: (*reactiveHandler).queryAttention},
 	// Before the recall sources too: "сколько я потратил?" is a question about
 	// the money facts the poller wrote, and the notes pass would otherwise
 	// answer it from whatever he once said about spending. Its matcher needs a

cmd/mavend/attentionq.go

@@ -1,68 +0,0 @@
-package main
-
-import (
-	"context"
-	"strings"
-
-	"github.com/kami/maven/internal/router"
-)
-
-// attentionMarkers — the ways he asks what Praxis is holding. Substrings on a
-// stem, because "внимание", "внимания" and "вниманию" are one word to him.
-//
-// "что нового" is deliberately absent: the feeds source claims it, and it
-// still should — a question about news is a question about the feeds she
-// reads. This list is about the operational state of his things.
-var attentionMarkers = []string{
-	"внимани", "что требует", "что не так", "что важн", "что срочн",
-	"needs attention", "what needs looking",
-}
-
-// isAttentionQuery reports whether the utterance asks what needs looking at.
-func isAttentionQuery(u string) bool {
-	s := strings.ToLower(strings.TrimSpace(u))
-	if s == "" {
-		return false
-	}
-	for _, m := range attentionMarkers {
-		if strings.Contains(s, m) {
-			return true
-		}
-	}
-	return false
-}
-
-// queryAttention answers "что требует внимания?" from Praxis.
-//
-// The capability was already built and already degraded correctly, and no
-// utterance could reach it (Vikunja #475). Its aliases live on the act
-// dispatch, and the question routes to IntentQuery, so it fell through every
-// source to the web search and came back with an encyclopedia article about
-// the concept of attention — worse than silence, because it reads as an
-// answer.
-//
-// Placed above the recall sources and well above the personal boundary: this
-// is operational state about his things, and a notes pass would otherwise
-// answer it from whatever he once wrote about a server. An unconfigured or
-// absent Praxis falls through rather than claiming the turn, the same
-// convention queryHome and queryNetwork follow. A Praxis that is configured
-// and down does claim it, and says it cannot reach the service — that is the
-// degradation the ecosystem contract asks for, and it comes from the same
-// handler the act path uses.
-func (h *reactiveHandler) queryAttention(ctx context.Context, t *queryTurn) (string, bool) {
-	if !isAttentionQuery(t.dec.Utterance) {
-		return "", false
-	}
-	if h.ecosystem == nil || h.ecosystem.praxis == nil {
-		return "", false
-	}
-	reply := h.handlePraxisAct(ctx, router.Decision{
-		Utterance: t.dec.Utterance,
-		Intent:    router.IntentAct,
-		Slots:     router.Slots{Fn: "list_attention", HasFn: true},
-	})
-	if reply == "" {
-		return "", false
-	}
-	return reply, true
-}

cmd/mavend/attentionq_test.go

@@ -1,77 +0,0 @@
-package main
-
-import (
-	"context"
-	"strings"
-	"testing"
-	"time"
-
-	"github.com/kami/maven/internal/router"
-)
-
-func TestIsAttentionQuery(t *testing.T) {
-	for _, tc := range []struct {
-		text string
-		want bool
-	}{
-		{"что требует внимания", true},
-		{"на что обратить внимание?", true},
-		{"что не так?", true},
-		{"что важного?", true},
-		// The feeds source owns this one, and should keep owning it.
-		{"что нового?", false},
-		{"какая погода?", false},
-		{"", false},
-	} {
-		if got := isAttentionQuery(tc.text); got != tc.want {
-			t.Errorf("isAttentionQuery(%q) = %v, want %v", tc.text, got, tc.want)
-		}
-	}
-}
-
-// TestAttentionQuestionReachesPraxis — the defect (Vikunja #475). The question
-// routes to IntentQuery, and every source used to pass, so a web search about
-// the concept of attention answered it.
-func TestAttentionQuestionReachesPraxis(t *testing.T) {
-	ctx := context.Background()
-	praxis := newFakePraxis(t, fixturePraxisAttentionItems(map[string]any{
-		"id": "item_1", "title": "disk almost full", "importance": 3.0,
-	}))
-	h := ecoHandler(t, nil, praxis, nil)
-
-	reply, ok := h.queryAttention(ctx, &queryTurn{dec: router.Decision{
-		Intent: router.IntentQuery, Utterance: "что требует внимания",
-	}})
-	if !ok {
-		t.Fatal("the attention question must be claimed before the world sources")
-	}
-	if !strings.Contains(reply, "disk almost full") {
-		t.Fatalf("reply = %q, want the praxis item", reply)
-	}
-}
-
-// A configured Praxis that is down claims the turn and says so. Falling
-// through here would answer an outage with an encyclopedia article.
-func TestAttentionQuestionSaysWhenPraxisIsDown(t *testing.T) {
-	ctx := context.Background()
-	praxis := newFakePraxis(t, fixturePraxisAttentionItems())
-	h := ecoHandler(t, nil, praxis, nil)
-	praxis.SetFault(503)
-
-	reply, ok := h.queryAttention(ctx, &queryTurn{dec: router.Decision{
-		Intent: router.IntentQuery, Utterance: "что требует внимания",
-	}})
-	if !ok || !strings.Contains(reply, "не могу") {
-		t.Fatalf("an outage must name the gap, got ok=%v reply=%q", ok, reply)
-	}
-}
-
-// No Praxis configured means no claim: the rest of the chain still runs.
-func TestAttentionQuestionFallsThroughWithoutPraxis(t *testing.T) {
-	h, _ := newFactGateHandler(t, time.Now())
-	if _, ok := h.queryAttention(context.Background(), &queryTurn{dec: router.Decision{
-		Intent: router.IntentQuery, Utterance: "что требует внимания",
-	}}); ok {
-		t.Fatal("an unconfigured praxis must not claim the turn")
-	}
-}

cmd/mavend/factgate_test.go

@@ -123,48 +123,3 @@ func mustEmbedPassage(t *testing.T, h *reactiveHandler, text string) []float32 {
 	}
 	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.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)
-	}
-}

internal/router/complaint.go

@@ -1,79 +0,0 @@
-package router
-
-import "strings"
-
-// transientStems — the states a thing is in for an afternoon. Compared as
-// prefixes because Russian inflects the ending: "медленн" covers "медленная",
-// "медленный" and "медленно" without listing them.
-var transientStems = []string{
-	"медленн", "тормоз", "лаг", "завис", "виснет", "глюч", "барахл",
-	"отвал", "падает", "упал", "сдох", "греется", "перегре",
-	"slow", "laggy", "stuck", "frozen", "flaky", "broken", "down",
-}
-
-// brokenVerbs — what "не ..." is denying when the sentence is a complaint.
-// "не работает", "не грузит", "не открывается". Prefixes again.
-var brokenVerbs = []string{
-	"работ", "пашет", "груз", "открыва", "включа", "коннект", "подключ",
-	"work", "load", "connect", "respond",
-}
-
-// selfMarkers — the words that make a sentence about him rather than about a
-// thing. Their presence turns the test off, because losing a fact he meant to
-// store is worse than keeping a complaint: "я сломал руку" is durable, and
-// "интернет не работает" is not.
-var selfMarkers = []string{"я", "мне", "меня", "мной", "i", "me", "my"}
-
-// IsTransientComplaint reports whether text observes a passing state of some
-// thing rather than recording a fact.
-//
-// It exists because "сеть какая-то медленная" and "интернет не работает" were
-// written to the fact store as `self` rows at confidence 1.00 (Vikunja #481),
-// where recall reads them back later as if they were still true. A complaint
-// describes a moment; the fact store describes him.
-//
-// Deterministic, offline, and shaped exactly like IsQuestionShaped: an
-// explicit capture verb wins over everything, because "запомни что интернет
-// не работает" is an instruction and not a passing remark. A first-person
-// marker also turns it off — the test is meant to catch a sentence about a
-// thing, and it errs toward storing.
-func IsTransientComplaint(text string) bool {
-	t := strings.TrimSpace(text)
-	if t == "" {
-		return false
-	}
-	toks := planTokens(strings.ToLower(t))
-	for _, v := range captureVerbs {
-		if hasTok(toks, v) {
-			return false
-		}
-	}
-	for _, m := range selfMarkers {
-		if hasTok(toks, m) {
-			return false
-		}
-	}
-	for _, tok := range toks {
-		for _, stem := range transientStems {
-			if strings.HasPrefix(tok, stem) {
-				return true
-			}
-		}
-	}
-	// "не" plus a verb of working, in either order of the two tokens that
-	// follow it — "не работает" and "не очень работает" both deny the same
-	// thing.
-	for i, tok := range toks {
-		if tok != "не" && tok != "not" && tok != "isn" {
-			continue
-		}
-		for j := i + 1; j < len(toks) && j <= i+2; j++ {
-			for _, v := range brokenVerbs {
-				if strings.HasPrefix(toks[j], v) {
-					return true
-				}
-			}
-		}
-	}
-	return false
-}

internal/router/complaint_test.go

@@ -1,35 +0,0 @@
-package router
-
-import "testing"
-
-func TestIsTransientComplaint(t *testing.T) {
-	for _, tc := range []struct {
-		text string
-		want bool
-	}{
-		// The two rows from the QA run that named this bug.
-		{"сеть какая-то медленная", true},
-		{"интернет не работает", true},
-		{"вайфай тормозит", true},
-		{"сервер завис", true},
-		{"the wifi is slow", true},
-
-		// An instruction wins: he asked for it to be written down.
-		{"запомни что интернет не работает", false},
-		{"запиши что сеть медленная", false},
-
-		// About him, so it stays a fact even when it sounds like a complaint.
-		{"я сломал руку", false},
-		{"мне медленно думается", false},
-
-		// Ordinary captures must not be touched.
-		{"поужинал", false},
-		{"выпил воды", false},
-		{"машина на парковке", false},
-		{"", false},
-	} {
-		if got := IsTransientComplaint(tc.text); got != tc.want {
-			t.Errorf("IsTransientComplaint(%q) = %v, want %v", tc.text, got, tc.want)
-		}
-	}
-}