a Russian act reaches a tool, and the seeds stop disagreeing (V-633)

Three tangled defects, fixed together because each one hid the others. DefaultActMatcher matched an exact English prefix and internal/tool.Matcher delegated straight to it, so no Russian utterance could reach a tool: 55 of the 69 lines in models/seeds/act.txt routed to IntentAct and fell to proposeGap. Tools now carry spoken aliases from deploy/mavend.json, matched as exact leading tokens, longest phrase first. Config data, not a stem pattern in code. The comment claiming "the production matcher is fuzzy" was false and is gone. Seven lines were exact duplicates inside models/seeds/query.txt, each one a second identical vector double-weighting its region. "как дела у сервера" carried both a query and a system label. It leaves system.txt, because replySystem's stats arm answers "системная статистика пока не подключена." and always did. The mode inventory records that shape as act.tool.hoststats rather than a system mode. Fixture unchanged at 69/91, and it cannot see any of this: no host-stat case and no Russian act in it. TestActMatcherAliases is the coverage. docs/evals/2026-08-06-russian-acts-reach-tools.md has the numbers. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0117tgnmbgZpHVV3XSNw8Qua
2026-08-06 18:09:11 +04:00
parent 1f8e9f21ce
commit e7ecce2859
9 changed files with 254 additions and 38 deletions
@@ -0,0 +1,72 @@
+package router
+
+import "testing"
+
+// Before V-633 the matcher only ever matched the English tool name, so no
+// Russian utterance could reach a tool: 55 of the 69 lines in models/seeds/act.txt
+// routed to IntentAct and then fell to proposeGap. These are those lines.
+func TestActMatcherAliases(t *testing.T) {
+	m := DefaultActMatcher{
+		Fns: []string{"status", "ps", "uptime", "disk", "memory", "logs",
+			"restart", "stop", "start", "docker-restart", "docker-stop", "reboot"},
+		Aliases: map[string][]string{
+			"status":         {"статус", "покажи статус"},
+			"ps":             {"статус докера", "что запущено"},
+			"uptime":         {"покажи uptime", "как работает сервер"},
+			"disk":           {"сколько места на диске"},
+			"memory":         {"свободная память"},
+			"logs":           {"покажи логи", "логи"},
+			"restart":        {"перезагрузи", "перезапусти"},
+			"docker-restart": {"перезагрузи контейнер"},
+			"reboot":         {"перезагрузи сервер"},
+		},
+	}
+	cases := []struct {
+		utterance string
+		wantFn    string
+		wantArgs  []string
+	}{
+		{"покажи статус nginx", "status", []string{"nginx"}},
+		{"статус sshd", "status", []string{"sshd"}},
+		{"статус докера", "ps", nil},
+		{"что запущено", "ps", nil},
+		{"сколько места на диске", "disk", nil},
+		{"свободная память", "memory", nil},
+		{"покажи uptime", "uptime", nil},
+		{"логи nginx", "logs", []string{"nginx"}},
+		{"перезагрузи nginx", "restart", []string{"nginx"}},
+		// Longest phrase first, so the two-word alias wins over the one word
+		// inside it and the act reaches the right tool.
+		{"перезагрузи контейнер maven", "docker-restart", []string{"maven"}},
+		{"перезагрузи сервер", "reboot", nil},
+		// The English names still match, unchanged.
+		{"restart nginx", "restart", []string{"nginx"}},
+		{"uptime", "uptime", nil},
+	}
+	for _, c := range cases {
+		fn, args, ok := m.Match(c.utterance)
+		if !ok || fn != c.wantFn {
+			t.Errorf("%q: got fn=%q ok=%v, want %q", c.utterance, fn, ok, c.wantFn)
+			continue
+		}
+		if len(args) != len(c.wantArgs) {
+			t.Errorf("%q: got args=%v, want %v", c.utterance, args, c.wantArgs)
+			continue
+		}
+		for i := range args {
+			if args[i] != c.wantArgs[i] {
+				t.Errorf("%q: got args=%v, want %v", c.utterance, args, c.wantArgs)
+				break
+			}
+		}
+	}
+	// Past tense is a fact, not a command, and aliases match exact tokens so it
+	// stays one. This is the trap cmd/mavend/quiet_toggle.go documents.
+	if fn, _, ok := m.Match("перезагрузил роутер"); ok {
+		t.Errorf("past tense reached a tool: fn=%q", fn)
+	}
+	// A phrase nobody configured still refuses, so the router can clarify.
+	if fn, _, ok := m.Match("свари кофе"); ok {
+		t.Errorf("unconfigured phrase reached a tool: fn=%q", fn)
+	}
+}
@@ -90,27 +90,57 @@ func (e Extractor) Extract(ctx context.Context, intent Intent, utterance string,

 // --- default implementations (scaffold floors; production swaps wholesale) ---

-// DefaultActMatcher — exact verb prefix + remainder-as-args. The production
-// matcher is fuzzy; this is the scaffold floor. "restart nginx" → fn=restart,
-// args=[nginx]. Not on the list → ok=false → the router refuses the act.
+// DefaultActMatcher — exact phrase prefix + remainder-as-args. This is the only
+// matcher there is: internal/tool.Matcher delegates here over the live enabled
+// names, so a phrase that does not match exactly cannot reach a tool.
+// "restart nginx" → fn=restart, args=[nginx]. Not on the list → ok=false → the
+// router refuses the act.
+//
+// Aliases map a tool name to spoken phrases, so a Russian utterance reaches an
+// English tool name. They come from the deployment config as data, never from a
+// stem pattern in code, and they match as exact leading tokens: "перезагрузи
+// роутер" is a command and "перезагрузил роутер" is a fact, and lemma matching
+// cannot tell the two apart (the trap cmd/mavend/quiet_toggle.go documents).
 type DefaultActMatcher struct {
-	Fns []string
+	Fns     []string
+	Aliases map[string][]string
 }

 func (m DefaultActMatcher) Allowlist() []string { return m.Fns }

 func (m DefaultActMatcher) Match(utterance string) (string, []string, bool) {
-	u := strings.TrimSpace(utterance)
-	// longest-verb-first so "restart" can't be shadowed by a shorter prefix.
-	sorted := append([]string(nil), m.Fns...)
-	sortDescByLen(sorted)
-	for _, fn := range sorted {
-		if u == fn {
-			return fn, nil, true
+	u := strings.TrimSpace(strings.ToLower(utterance))
+	u = strings.TrimRight(u, "?!.")
+	// One table of phrase → fn, so an alias and a name compete on length rather
+	// than on which loop ran first. Longest-first, so "docker-restart" cannot be
+	// shadowed by "restart" and a two-word alias beats the one-word one inside it.
+	phrases := make([]string, 0, len(m.Fns))
+	fnOf := make(map[string]string, len(m.Fns))
+	add := func(phrase, fn string) {
+		phrase = strings.TrimSpace(strings.ToLower(phrase))
+		if phrase == "" {
+			return
 		}
-		if strings.HasPrefix(u, fn+" ") {
-			rest := strings.TrimSpace(strings.TrimPrefix(u, fn+" "))
-			return fn, splitArgs(rest), true
+		if _, seen := fnOf[phrase]; seen {
+			return
+		}
+		fnOf[phrase] = fn
+		phrases = append(phrases, phrase)
+	}
+	for _, fn := range m.Fns {
+		add(fn, fn)
+		for _, a := range m.Aliases[fn] {
+			add(a, fn)
+		}
+	}
+	sortDescByLen(phrases)
+	for _, p := range phrases {
+		if u == p {
+			return fnOf[p], nil, true
+		}
+		if strings.HasPrefix(u, p+" ") {
+			rest := strings.TrimSpace(strings.TrimPrefix(u, p+" "))
+			return fnOf[p], splitArgs(rest), true
 		}
 	}
 	return "", nil, false