feat(multimodal): 视觉分层路由（多模态检测→主/视觉/OCR 工具）+ 语音 STT→TTS 降级链（异步）

internal/runtime/multimodal/voice/cloud_test.go

@@ -0,0 +1,81 @@
+package voice
+
+import (
+	"context"
+	"encoding/base64"
+	"encoding/hex"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+)
+
+func TestHTTPSTT(t *testing.T) {
+	t.Parallel()
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode: %v", err)
+		}
+		if r.Header.Get("Authorization") != "Bearer sk" {
+			t.Errorf("auth = %q, want Bearer sk", r.Header.Get("Authorization"))
+		}
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"text":"hello world"}`))
+	}))
+	defer srv.Close()
+
+	stt := NewHTTPSTT(srv.URL, "sk")
+	text, err := stt.STT(context.Background(), Audio{Format: "wav", Data: []byte("raw")})
+	if err != nil {
+		t.Fatalf("STT error: %v", err)
+	}
+	if text != "hello world" {
+		t.Errorf("text = %q, want hello world", text)
+	}
+}
+
+func TestHTTPSTT_NotConfigured(t *testing.T) {
+	t.Parallel()
+	stt := NewHTTPSTT("", "")
+	if _, err := stt.STT(context.Background(), Audio{}); err != ErrNotConfigured {
+		t.Fatalf("err = %v, want ErrNotConfigured", err)
+	}
+}
+
+func TestHTTPTTS(t *testing.T) {
+	t.Parallel()
+	audioBytes := []byte{1, 2, 3}
+	b64 := base64.StdEncoding.EncodeToString(audioBytes)
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode: %v", err)
+		}
+		if body["text"] != "hi" {
+			t.Errorf("text = %v, want hi", body["text"])
+		}
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"audio":"` + b64 + `","format":"wav"}`))
+	}))
+	defer srv.Close()
+
+	tts := NewHTTPTTS(srv.URL, "")
+	audio, err := tts.TTS(context.Background(), "hi")
+	if err != nil {
+		t.Fatalf("TTS error: %v", err)
+	}
+	if audio.Format != "wav" || hex.EncodeToString(audio.Data) != hex.EncodeToString(audioBytes) {
+		t.Errorf("audio = %+v, want wav/010203", audio)
+	}
+}
+
+func TestHTTPTTS_EmptyText(t *testing.T) {
+	t.Parallel()
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {}))
+	defer srv.Close()
+	tts := NewHTTPTTS(srv.URL, "")
+	if _, err := tts.TTS(context.Background(), "  "); err != ErrEmptyText {
+		t.Fatalf("err = %v, want ErrEmptyText", err)
+	}
+}