[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/run_openapi_generator.sh

@@ -7,6 +7,7 @@
 # the root directory of this source tree.
 
 PYTHONPATH=${PYTHONPATH:-}
+THIS_DIR="$(cd "$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")" && pwd)"
 
 set -euo pipefail
 
@@ -18,8 +19,6 @@ check_package() {
     fi
 }
 
-check_package json-strong-typing
-
 if [ ${#missing_packages[@]} -ne 0 ]; then
     echo "Error: The following package(s) are not installed:"
     printf " - %s\n" "${missing_packages[@]}"
@@ -28,4 +27,6 @@ if [ ${#missing_packages[@]} -ne 0 ]; then
     exit 1
 fi
 
-PYTHONPATH=$PYTHONPATH:../.. python -m docs.openapi_generator.generate $*
+stack_dir=$(dirname $(dirname $THIS_DIR))
+models_dir=$(dirname $stack_dir)/llama-models
+PYTHONPATH=$PYTHONPATH:$stack_dir:$models_dir python -m docs.openapi_generator.generate $(dirname $THIS_DIR)/resources