[API Updates] Model / shield / memory-bank routing + agent persistence + support for private headers (#92)

This is yet another of those large PRs (hopefully we will have less and less of them as things mature fast). This one introduces substantial improvements and some simplifications to the stack.

Most important bits:

* Agents reference implementation now has support for session / turn persistence. The default implementation uses sqlite but there's also support for using Redis.

* We have re-architected the structure of the Stack APIs to allow for more flexible routing. The motivating use cases are:
  - routing model A to ollama and model B to a remote provider like Together
  - routing shield A to local impl while shield B to a remote provider like Bedrock
  - routing a vector memory bank to Weaviate while routing a keyvalue memory bank to Redis

* Support for provider specific parameters to be passed from the clients. A client can pass data using `x_llamastack_provider_data` parameter which can be type-checked and provided to the Adapter implementations.

docs/openapi_generator/pyopenapi/generator.py

@@ -9,9 +9,9 @@ import ipaddress
 import typing
 from typing import Any, Dict, Set, Union
 
-from strong_typing.core import JsonType
-from strong_typing.docstring import Docstring, parse_type
-from strong_typing.inspection import (
+from ..strong_typing.core import JsonType
+from ..strong_typing.docstring import Docstring, parse_type
+from ..strong_typing.inspection import (
     is_generic_list,
     is_type_optional,
     is_type_union,
@@ -19,15 +19,15 @@ from strong_typing.inspection import (
     unwrap_optional_type,
     unwrap_union_types,
 )
-from strong_typing.name import python_type_to_name
-from strong_typing.schema import (
+from ..strong_typing.name import python_type_to_name
+from ..strong_typing.schema import (
     get_schema_identifier,
     JsonSchemaGenerator,
     register_schema,
     Schema,
     SchemaOptions,
 )
-from strong_typing.serialization import json_dump_string, object_to_json
+from ..strong_typing.serialization import json_dump_string, object_to_json
 
 from .operations import (
     EndpointOperation,
@@ -462,6 +462,15 @@ class Generator:
 
         # parameters passed anywhere
         parameters = path_parameters + query_parameters
+        parameters += [
+            Parameter(
+                name="X-LlamaStack-ProviderData",
+                in_=ParameterLocation.Header,
+                description="JSON-encoded provider data which will be made available to the adapter servicing the API",
+                required=False,
+                schema=self.schema_builder.classdef_to_ref(str),
+            )
+        ]
 
         # data passed in payload
         if op.request_params: