feat: support ClientTool output metadata (#1426)

# Summary:
Client side change in
https://github.com/meta-llama/llama-stack-client-python/pull/180
Changes the resume_turn API to accept `ToolResponse` instead of
`ToolResponseMessage`:
1. `ToolResponse` contains `metadata`
2. `ToolResponseMessage` is a concept for model inputs. Here we are just
submitting the outputs of tool execution.

# Test Plan:
Ran integration tests with newly added test using client tool with
metadata

LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --record-responses

llama_stack/providers/inline/agents/meta_reference/agents.py

@@ -27,6 +27,7 @@ from llama_stack.apis.agents import (
 from llama_stack.apis.inference import (
     Inference,
     ToolConfig,
+    ToolResponse,
     ToolResponseMessage,
     UserMessage,
 )
@@ -168,7 +169,7 @@ class MetaReferenceAgentsImpl(Agents):
         agent_id: str,
         session_id: str,
         turn_id: str,
-        tool_responses: List[ToolResponseMessage],
+        tool_responses: Union[List[ToolResponse], List[ToolResponseMessage]],
         stream: Optional[bool] = False,
     ) -> AsyncGenerator:
         request = AgentTurnResumeRequest(