Add tts/text output schema

api/tests/test_assistants.py

@@ -23,6 +23,7 @@ class TestAssistantAPI:
         assert data["opener"] == sample_assistant_data["opener"]
         assert data["prompt"] == sample_assistant_data["prompt"]
         assert data["language"] == sample_assistant_data["language"]
+        assert data["voiceOutputEnabled"] is True
         assert "id" in data
         assert data["callCount"] == 0
 
@@ -61,7 +62,8 @@ class TestAssistantAPI:
         update_data = {
             "name": "Updated Assistant",
             "prompt": "You are an updated assistant.",
-            "speed": 1.5
+            "speed": 1.5,
+            "voiceOutputEnabled": False,
         }
         response = client.put(f"/api/assistants/{assistant_id}", json=update_data)
         assert response.status_code == 200
@@ -69,6 +71,7 @@ class TestAssistantAPI:
         assert data["name"] == "Updated Assistant"
         assert data["prompt"] == "You are an updated assistant."
         assert data["speed"] == 1.5
+        assert data["voiceOutputEnabled"] is False
 
     def test_delete_assistant(self, client, sample_assistant_data):
         """Test deleting an assistant"""
@@ -210,3 +213,15 @@ class TestAssistantAPI:
         assert metadata["services"]["llm"]["model"] == sample_llm_model_data["model_name"]
         assert metadata["services"]["asr"]["model"] == sample_asr_model_data["model_name"]
         assert metadata["services"]["tts"]["voice"] == sample_voice_data["voice_key"]
+
+    def test_runtime_config_text_mode_when_voice_output_disabled(self, client, sample_assistant_data):
+        sample_assistant_data["voiceOutputEnabled"] = False
+        assistant_resp = client.post("/api/assistants", json=sample_assistant_data)
+        assert assistant_resp.status_code == 200
+        assistant_id = assistant_resp.json()["id"]
+
+        runtime_resp = client.get(f"/api/assistants/{assistant_id}/runtime-config")
+        assert runtime_resp.status_code == 200
+        metadata = runtime_resp.json()["sessionStartMetadata"]
+        assert metadata["output"]["mode"] == "text"
+        assert metadata["services"]["tts"]["enabled"] is False