[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.

llama_stack/distribution/utils/dynamic.py

@@ -8,6 +8,7 @@ import importlib
 from typing import Any, Dict
 
 from llama_stack.distribution.datatypes import *  # noqa: F403
+from termcolor import cprint
 
 
 def instantiate_class_type(fully_qualified_name):
@@ -20,7 +21,7 @@ def instantiate_class_type(fully_qualified_name):
 async def instantiate_provider(
     provider_spec: ProviderSpec,
     deps: Dict[str, Any],
-    provider_config: ProviderMapEntry,
+    provider_config: Union[GenericProviderConfig, RoutingTable],
 ):
     module = importlib.import_module(provider_spec.module)
 
@@ -35,13 +36,20 @@ async def instantiate_provider(
         config_type = instantiate_class_type(provider_spec.config_class)
         config = config_type(**provider_config.config)
         args = [config, deps]
-    elif isinstance(provider_spec, RouterProviderSpec):
-        method = "get_router_impl"
+    elif isinstance(provider_spec, AutoRoutedProviderSpec):
+        method = "get_auto_router_impl"
+
+        config = None
+        args = [provider_spec.api, deps[provider_spec.routing_table_api], deps]
+    elif isinstance(provider_spec, RoutingTableProviderSpec):
+        method = "get_routing_table_impl"
+
+        assert isinstance(provider_config, List)
+        routing_table = provider_config
 
-        assert isinstance(provider_config, list)
         inner_specs = {x.provider_id: x for x in provider_spec.inner_specs}
         inner_impls = []
-        for routing_entry in provider_config:
+        for routing_entry in routing_table:
             impl = await instantiate_provider(
                 inner_specs[routing_entry.provider_id],
                 deps,
@@ -50,7 +58,7 @@ async def instantiate_provider(
             inner_impls.append((routing_entry.routing_key, impl))
 
         config = None
-        args = [inner_impls, deps]
+        args = [provider_spec.api, inner_impls, routing_table, deps]
     else:
         method = "get_provider_impl"