internal/router/llmrouter.go

@@ -23,14 +23,16 @@ func NewLLMRouter(c Completer) *LLMRouter { return &LLMRouter{c: c} }
 
 // routeGrammar — GBNF constraining the model to a JSON ARRAY of fixed-shape
 // action objects (one per ask; compound utterances → multiple). Enum + key set
-// prevent free-form drift from a sub-1B model.
+// prevent free-form drift from a sub-1B model. The string rule is length-bounded
+// so a repetition loop cannot fill the whole token budget with one field and
+// truncate the JSON.
 const routeGrammar = `
 root   ::= "[" ws action ("," ws action)* ws "]"
 action ::= "{" ws "\"intent\"" ws ":" ws intent ("," ws field)* ws "}"
 intent ::= "\"fact\"" | "\"reminder\"" | "\"note\"" | "\"query\"" | "\"act\"" | "\"chat\"" | "\"system\""
 field  ::= key ws ":" ws string
 key    ::= "\"key\"" | "\"value\"" | "\"text\"" | "\"verb\""
-string ::= "\"" ([^"\\] | "\\" .)* "\""
+string ::= "\"" ([^"\\] | "\\" .){0,120} "\""
 ws     ::= [ \t\n]*
 `
 
@@ -77,6 +79,11 @@ const routeSystem = `Классифицируй ровно одно сообще
 
 Ответ — JSON-массив: по одному объекту на каждую просьбу. Обычно один. Если в реплике несколько просьб — по объекту на каждую. "напомни купить молоко, и запиши что кофе кончился" → [{"intent":"reminder","text":"купить молоко"},{"intent":"note","text":"кофе кончился"}]. Только JSON, без пояснений.`
 
+// routeRepeatPenalty — the sub-1B model loops one sentence inside the text field
+// until it runs out of tokens, which truncates the JSON. 1.15 is enough to break
+// the loop without hurting short slot values.
+const routeRepeatPenalty = 1.15
+
 type routeAction struct {
 	Intent string `json:"intent"`
 	Key    string `json:"key"`
@@ -86,7 +93,13 @@ type routeAction struct {
 }
 
 func (lr *LLMRouter) Route(ctx context.Context, utterance string, now time.Time) (Decision, bool, error) {
-	raw, err := lr.c.Complete(ctx, llm.Req{System: routeSystem, User: utterance, Grammar: routeGrammar, MaxTokens: 128})
+	raw, err := lr.c.Complete(ctx, llm.Req{
+		System:        routeSystem,
+		User:          utterance,
+		Grammar:       routeGrammar,
+		MaxTokens:     128,
+		RepeatPenalty: routeRepeatPenalty,
+	})
 	if err != nil {
 		return Decision{}, false, err
 	}

internal/router/llmrouter_test.go

@@ -13,9 +13,35 @@ import (
 type mockLLM struct {
 	out string
 	err error
+	got *llm.Req // last request, when the test wants to inspect it
 }
 
-func (m mockLLM) Complete(_ context.Context, _ llm.Req) (string, error) { return m.out, m.err }
+func (m mockLLM) Complete(_ context.Context, r llm.Req) (string, error) {
+	if m.got != nil {
+		*m.got = r
+	}
+	return m.out, m.err
+}
+
+// Without a repeat penalty the model loops inside the text field until MaxTokens
+// and the truncated JSON fails to parse.
+func TestLLMRouterSetsRepeatPenalty(t *testing.T) {
+	var got llm.Req
+	lr := NewLLMRouter(mockLLM{out: `{"intent":"chat","text":"привет"}`, got: &got})
+	if _, _, err := lr.Route(context.Background(), "привет", time.Now()); err != nil {
+		t.Fatalf("route: %v", err)
+	}
+	if got.RepeatPenalty <= 1 {
+		t.Fatalf("want repeat penalty above 1, got %v", got.RepeatPenalty)
+	}
+}
+
+// An unbounded string rule lets one field eat the whole token budget.
+func TestRouteGrammarBoundsStrings(t *testing.T) {
+	if !strings.Contains(routeGrammar, `string ::= "\"" ([^"\\] | "\\" .){0,120} "\""`) {
+		t.Fatal("grammar string rule lost its length bound")
+	}
+}
 
 // A question naming a fact key used to be stored as a fact because the fact rule
 // was tested first. Keep the query rule above it.