Further generalize Xi's changes

- introduce a slightly more general notion of an AutoRouted provider
- the AutoRouted provider is associated with a RoutingTable provider
- e.g. inference -> models
- Introduced safety -> shields and memory -> memory_banks
  correspondences

llama_stack/apis/models/models.py

@@ -4,14 +4,15 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Any, Dict, List, Optional, Protocol
+from typing import List, Optional, Protocol
 
 from llama_models.llama3.api.datatypes import Model
 
 from llama_models.schema_utils import json_schema_type, webmethod
-from llama_stack.distribution.datatypes import GenericProviderConfig
 from pydantic import BaseModel, Field
 
+from llama_stack.distribution.datatypes import GenericProviderConfig
+
 
 @json_schema_type
 class ModelServingSpec(BaseModel):
@@ -21,25 +22,11 @@ class ModelServingSpec(BaseModel):
     provider_config: GenericProviderConfig = Field(
         description="Provider config for the model, including provider_id, and corresponding config. ",
     )
-    api: str = Field(
-        description="The API that this model is serving (e.g. inference / safety).",
-        default="inference",
-    )
-
-
-@json_schema_type
-class ModelsListResponse(BaseModel):
-    models_list: List[ModelServingSpec]
-
-
-@json_schema_type
-class ModelsGetResponse(BaseModel):
-    core_model_spec: Optional[ModelServingSpec] = None
 
 
 class Models(Protocol):
     @webmethod(route="/models/list", method="GET")
-    async def list_models(self) -> ModelsListResponse: ...
+    async def list_models(self) -> List[ModelServingSpec]: ...
 
-    @webmethod(route="/models/get", method="POST")
-    async def get_model(self, core_model_id: str) -> ModelsGetResponse: ...
+    @webmethod(route="/models/get", method="GET")
+    async def get_model(self, core_model_id: str) -> Optional[ModelsGetResponse]: ...