feat: Add responses and safety impl extra_body (#3781)

# What does this PR do?

Have closed the previous PR due to merge conflicts with multiple PRs
Addressed all comments from
https://github.com/llamastack/llama-stack/pull/3768 (sorry for carrying
over to this one)


## Test Plan
Added UTs and integration tests

tests/unit/providers/inline/agents/meta_reference/responses/test_streaming.py

@@ -4,10 +4,45 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from unittest.mock import AsyncMock
+
+import pytest
+
 from llama_stack.apis.tools import ToolDef
 from llama_stack.providers.inline.agents.meta_reference.responses.streaming import (
     convert_tooldef_to_chat_tool,
 )
+from llama_stack.providers.inline.agents.meta_reference.responses.types import ChatCompletionContext
+
+
+@pytest.fixture
+def mock_safety_api():
+    safety_api = AsyncMock()
+    # Mock the routing table and shields list for guardrails lookup
+    safety_api.routing_table = AsyncMock()
+    shield = AsyncMock()
+    shield.identifier = "llama-guard"
+    shield.provider_resource_id = "llama-guard-model"
+    safety_api.routing_table.list_shields.return_value = AsyncMock(data=[shield])
+    # Mock run_moderation to return non-flagged result by default
+    safety_api.run_moderation.return_value = AsyncMock(flagged=False)
+    return safety_api
+
+
+@pytest.fixture
+def mock_inference_api():
+    inference_api = AsyncMock()
+    return inference_api
+
+
+@pytest.fixture
+def mock_context():
+    context = AsyncMock(spec=ChatCompletionContext)
+    # Add required attributes that StreamingResponseOrchestrator expects
+    context.tool_context = AsyncMock()
+    context.tool_context.previous_tools = {}
+    context.messages = []
+    return context
 
 
 def test_convert_tooldef_to_chat_tool_preserves_items_field():