feat(responses)!: improve responses + conversations implementations

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.)

docs/static/deprecated-llama-stack-spec.html

@@ -8523,6 +8523,12 @@
                     {
                         "$ref": "#/components/schemas/OpenAIResponseMCPApprovalResponse"
                     },
+                    {
+                        "$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPCall"
+                    },
+                    {
+                        "$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPListTools"
+                    },
                     {
                         "$ref": "#/components/schemas/OpenAIResponseMessage"
                     }