In python example a2a_mcp error in agent_executor.py when request to orchestrator agent: TypeError: 'SendStreamingMessageResponse' object is not subscriptable

### What happened?

All agents (planning, travel agents) response successfully without errors.
But when try to request orchestrator agent, then get an error

```
agent_executor.py", line 65, in execute
| is_task_complete = item['is_task_complete']
| ~~~~^^^^^^^^^^^^^^^^^^^^
| TypeError: 'SendStreamingMessageResponse' object is not subscriptable
+------------------------------------
```

request sent

```
{
"jsonrpc": "2.0",
"id": "test-orchestrator-1",
"method": "message/stream",
"params": {
"message": {
"role": "user",
"parts": [
{
"kind": "text",
"text": "I'm planning a business trip to London from New York from August 10-17, 2025. I need comprehensive travel arrangements including:\n\n1. FLIGHT: I need a direct flight from New York JFK to London Heathrow on August 10, 2025, returning on August 17, 2025. Economy class for one adult with morning departure. My flight budget is $1200 maximum for the round trip. I prefer either British Airways or American Airlines.\n\n2. HOTEL: I need a 4-star hotel for 1 adult in Central London near the financial district, checking in August 10, 2025 for 7 nights. My hotel budget is $300 per night. The hotel should include breakfast.\n\n3. CAR RENTAL: I need to rent a mid-size SUV with automatic transmission from August 10, 2025 to August 17, 2025. I want comprehensive insurance coverage. My car rental budget is $70 per day. The car should have GPS. I want pickup and drop-off at London Heathrow Airport Terminal 5. I have a US driver's license.\n\nMy total budget for all bookings is $3000. Can you help me plan this trip?"
}
],
"messageId": "orchestrator-msg-1"
}
}
}
```

installed dependencies in .venv

```
a2a-sdk[sql]>=0.2.16
click>=8.1.8
fastmcp>=1.0
google-adk>=1.0.0
google-cloud-aiplatform>=1.91.0
google-generativeai>=0.8.5
httpx>=0.28.1
langchain-google-genai>=2.0.10
langchain-mcp-adapters>=0.0.9
langgraph>=0.4.1
mcp[cli]>=1.5.0
nest-asyncio>=1.6.0
networkx>=3.4.2
numpy>=2.2.5
pandas>=2.2.3
pydantic>=2.11.4
litellm
```

### Relevant log output

```shell

```

### Code of Conduct

- [x] I agree to follow this project's Code of Conduct