[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/providers/impls/meta_reference/safety/shields/base.py

@@ -8,11 +8,26 @@ from abc import ABC, abstractmethod
 from typing import List
 
 from llama_models.llama3.api.datatypes import interleaved_text_media_as_str, Message
+from pydantic import BaseModel
 from llama_stack.apis.safety import *  # noqa: F403
 
 CANNED_RESPONSE_TEXT = "I can't answer that. Can I help with something else?"
 
 
+# TODO: clean this up; just remove this type completely
+class ShieldResponse(BaseModel):
+    is_violation: bool
+    violation_type: Optional[str] = None
+    violation_return_message: Optional[str] = None
+
+
+# TODO: this is a caller / agent concern
+class OnViolationAction(Enum):
+    IGNORE = 0
+    WARN = 1
+    RAISE = 2
+
+
 class ShieldBase(ABC):
     def __init__(
         self,
@@ -20,10 +35,6 @@ class ShieldBase(ABC):
     ):
         self.on_violation_action = on_violation_action
 
-    @abstractmethod
-    def get_shield_type(self) -> ShieldType:
-        raise NotImplementedError()
-
     @abstractmethod
     async def run(self, messages: List[Message]) -> ShieldResponse:
         raise NotImplementedError()
@@ -48,11 +59,6 @@ class TextShield(ShieldBase):
 
 
 class DummyShield(TextShield):
-    def get_shield_type(self) -> ShieldType:
-        return "dummy"
-
     async def run_impl(self, text: str) -> ShieldResponse:
         # Dummy return LOW to test e2e
-        return ShieldResponse(
-            shield_type=BuiltinShield.third_party_shield, is_violation=False
-        )
+        return ShieldResponse(is_violation=False)