add default toolgroups to all providers (#795)

# What does this PR do?

Add toolgroup defs to all the distribution templates

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -105,6 +105,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "memory": [memory_provider],
                 },
                 default_models=[inference_model, embedding_model],
+                default_tool_groups=default_tool_groups,
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -105,4 +105,10 @@ memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
-tool_groups: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter