[memory refactor][3/n] Introduce RAGToolRuntime as a specialized sub-protocol (#832)

See https://github.com/meta-llama/llama-stack/issues/827 for the broader
design.

Third part:
- we need to make `tool_runtime.rag_tool.query_context()` and
`tool_runtime.rag_tool.insert_documents()` methods work smoothly with
complete type safety. To that end, we introduce a sub-resource path
`tool-runtime/rag-tool/` and make changes to the resolver to make things
work.
- the PR updates the agents implementation to directly call these typed
APIs for memory accesses rather than going through the complex, untyped
"invoke_tool" API. the code looks much nicer and simpler (expectedly.)
- there are a number of hacks in the server resolver implementation
still, we will live with some and fix some

Note that we must make sure the client SDKs are able to handle this
subresource complexity also. Stainless has support for subresources, so
this should be possible but beware.

## Test Plan

Our RAG test is sad (doesn't actually test for actual RAG output) but I
verified that the implementation works. I will work on fixing the RAG
test afterwards.

```bash
pytest -s -v tests/agents/test_agents.py -k "rag and together" --safety-shield=meta-llama/Llama-Guard-3-8B
```

llama_stack/providers/tests/vector_io/test_vector_io.py

@@ -8,13 +8,12 @@ import uuid
 
 import pytest
 
+from llama_stack.apis.tools import RAGDocument
+
 from llama_stack.apis.vector_dbs import ListVectorDBsResponse, VectorDB
 from llama_stack.apis.vector_io import QueryChunksResponse
 
-from llama_stack.providers.utils.memory.vector_store import (
-    make_overlapped_chunks,
-    MemoryBankDocument,
-)
+from llama_stack.providers.utils.memory.vector_store import make_overlapped_chunks
 
 # How to run this test:
 #
@@ -26,22 +25,22 @@ from llama_stack.providers.utils.memory.vector_store import (
 @pytest.fixture(scope="session")
 def sample_chunks():
     docs = [
-        MemoryBankDocument(
+        RAGDocument(
             document_id="doc1",
             content="Python is a high-level programming language.",
             metadata={"category": "programming", "difficulty": "beginner"},
         ),
-        MemoryBankDocument(
+        RAGDocument(
             document_id="doc2",
             content="Machine learning is a subset of artificial intelligence.",
             metadata={"category": "AI", "difficulty": "advanced"},
         ),
-        MemoryBankDocument(
+        RAGDocument(
             document_id="doc3",
             content="Data structures are fundamental to computer science.",
             metadata={"category": "computer science", "difficulty": "intermediate"},
         ),
-        MemoryBankDocument(
+        RAGDocument(
             document_id="doc4",
             content="Neural networks are inspired by biological neural networks.",
             metadata={"category": "AI", "difficulty": "advanced"},