feat: remove special handling of builtin::rag tool (#1015)

Summary:

Lets the model decide which tool it needs to call to respond to a query.

Test Plan:
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/ --safety-shield meta-llama/Llama-Guard-3-8B
```

Also evaluated on a small benchmark with 20 questions from HotpotQA.
With this PR and some prompting, the performance is 77% recall compared
to 50% currently.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1015).
* #1268
* #1239
* __->__ #1015

llama_stack/distribution/routers/routers.py

@@ -441,7 +441,7 @@ class ToolRuntimeRouter(ToolRuntime):
             vector_db_ids: List[str],
             query_config: Optional[RAGQueryConfig] = None,
         ) -> RAGQueryResult:
-            return await self.routing_table.get_provider_impl("query_from_memory").query(
+            return await self.routing_table.get_provider_impl("knowledge_search").query(
                 content, vector_db_ids, query_config
             )