feat(responses)!: improve responses + conversations implementations (#3810)

This PR updates the Conversation item related types and improves a
couple critical parts of the implemenation:

- it creates a streaming output item for the final assistant message
output by
  the model. until now we only added content parts and included that
  message in the final response.

- rewrites the conversation update code completely to account for items
  other than messages (tool calls, outputs, etc.)

## Test Plan

Used the test script from
https://github.com/llamastack/llama-stack-client-python/pull/281 for
this

```
TEST_API_BASE_URL=http://localhost:8321/v1 \
  pytest tests/integration/test_agent_turn_step_events.py::test_client_side_function_tool -xvs
```

llama_stack/apis/agents/openai_responses.py

@@ -1258,9 +1258,9 @@ OpenAIResponseInput = Annotated[
     | OpenAIResponseInputFunctionToolCallOutput
     | OpenAIResponseMCPApprovalRequest
     | OpenAIResponseMCPApprovalResponse
-    |
-    # Fallback to the generic message type as a last resort
-    OpenAIResponseMessage,
+    | OpenAIResponseOutputMessageMCPCall
+    | OpenAIResponseOutputMessageMCPListTools
+    | OpenAIResponseMessage,
     Field(union_mode="left_to_right"),
 ]
 register_schema(OpenAIResponseInput, name="OpenAIResponseInput")