feat: tool outputs metadata (#1155)

Summary:

Allows tools to output metadata. This is useful for evaluating tool
outputs, e.g. RAG tool will output document IDs, which can be used to
score recall.

Will need to make a similar change on the client side to support
ClientTool outputting metadata.

Test Plan:

LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/client-sdk/agents/test_agents.py

llama_stack/apis/inference/inference.py

@@ -165,6 +165,7 @@ class ToolResponse(BaseModel):
     call_id: str
     tool_name: Union[BuiltinTool, str]
     content: InterleavedContent
+    metadata: Optional[Dict[str, Any]] = None
 
     @field_validator("tool_name", mode="before")
     @classmethod

llama_stack/apis/tools/rag_tool.py

@@ -26,6 +26,7 @@ class RAGDocument(BaseModel):
 @json_schema_type
 class RAGQueryResult(BaseModel):
     content: Optional[InterleavedContent] = None
+    metadata: Dict[str, Any] = Field(default_factory=dict)
 
 
 @json_schema_type

llama_stack/apis/tools/tools.py

@@ -72,6 +72,7 @@ class ToolInvocationResult(BaseModel):
     content: InterleavedContent
     error_message: Optional[str] = None
     error_code: Optional[int] = None
+    metadata: Optional[Dict[str, Any]] = None
 
 
 class ToolStore(Protocol):