feat: integrate OCI agent streaming and web voice client

tests/test_gateway.py

@@ -1698,3 +1698,105 @@ def test_websocket_registration_failure_awaits_task_before_abort():
     assert len(tasks) == 1
     assert tasks[0].done()
     assert abort_checked
+
+
+def test_websocket_streaming_agent_and_tts():
+    """
+    Verify streaming Agent text and TTS audio through WebSocket.
+
+    The first audio segment must be delivered before the
+    Agent's complete response.
+    """
+    created_stt.clear()
+
+    class StreamingTestAgent:
+        async def stream(self, session_id, turn_id, text):
+            yield "Olá, como posso ajudar?"
+            yield " Estou à disposição."
+
+    class StreamingTestTTS:
+        async def synthesize(self, text):
+            yield text.encode("utf-8")
+
+    with patch.object(
+        main,
+        "create_agent_adapter",
+        return_value=StreamingTestAgent(),
+    ):
+        with patch.object(
+            main,
+            "create_tts_adapter",
+            return_value=StreamingTestTTS(),
+        ):
+            with client.websocket_connect("/ws/audio") as websocket:
+                websocket.send_json(
+                    {
+                        "type": "session.start",
+                        "audio": {
+                            "encoding": AUDIO_ENCODING,
+                            "sample_rate": AUDIO_SAMPLE_RATE,
+                            "channels": AUDIO_CHANNELS,
+                        },
+                    }
+                )
+
+                session_ready = websocket.receive_json()
+                assert session_ready["type"] == "session.ready"
+
+                websocket.send_json({"type": "audio.start"})
+
+                turn_started = websocket.receive_json()
+                assert turn_started["type"] == "turn.started"
+
+                turn_id = turn_started["turn_id"]
+                stt = created_stt[0]
+
+                stt.emit_final_now("Olá")
+
+                received_text = []
+                received_audio = []
+                received_complete_response = False
+
+                # The streaming path emits two deltas and
+                # two TTS audio segments.
+                for _ in range(20):
+                    message = websocket.receive()
+
+                    if message.get("bytes") is not None:
+                        received_audio.append(message["bytes"])
+                    else:
+                        import json
+
+                        event = json.loads(message["text"])
+
+                        if event["type"] == "agent.delta":
+                            received_text.append(event["text"])
+
+                        elif event["type"] == "agent.response":
+                            received_complete_response = True
+
+                        elif event["type"] == "error":
+                            raise AssertionError(
+                                f"Gateway returned error: {event}"
+                            )
+
+                    if received_complete_response and len(received_audio) >= 2:
+                        break
+
+                assert "".join(received_text) == (
+                    "Olá, como posso ajudar?"
+                    " Estou à disposição."
+                )
+
+                assert received_audio
+                assert received_complete_response
+
+                websocket.send_json(
+                    {
+                        "type": "audio.stop",
+                        "turn_id": turn_id,
+                    }
+                )
+
+                turn_ended = websocket.receive_json()
+                assert turn_ended["type"] == "turn.ended"