Split safety into (llama-guard, prompt-guard, code-scanner) (#400)

Splits the meta-reference safety implementation into three distinct providers:

- inline::llama-guard
- inline::prompt-guard
- inline::code-scanner

Note that this PR is a backward incompatible change to the llama stack server. I have added deprecation_error field to ProviderSpec -- the server reads it and immediately barfs. This is used to direct the user with a specific message on what action to perform. An automagical "config upgrade" is a bit too much work to implement right now :/

(Note that we will be gradually prefixing all inline providers with inline:: -- I am only doing this for this set of new providers because otherwise existing configuration files will break even more badly.)

llama_stack/distribution/resolver.py

@@ -33,6 +33,10 @@ from llama_stack.distribution.store import DistributionRegistry
 from llama_stack.distribution.utils.dynamic import instantiate_class_type
 
 
+class InvalidProviderError(Exception):
+    pass
+
+
 def api_protocol_map() -> Dict[Api, Any]:
     return {
         Api.agents: Agents,
@@ -102,16 +106,20 @@ async def resolve_impls(
                 )
 
             p = provider_registry[api][provider.provider_type]
-            if p.deprecation_warning:
+            if p.deprecation_error:
+                cprint(p.deprecation_error, "red", attrs=["bold"])
+                raise InvalidProviderError(p.deprecation_error)
+
+            elif p.deprecation_warning:
                 cprint(
                     f"Provider `{provider.provider_type}` for API `{api}` is deprecated and will be removed in a future release: {p.deprecation_warning}",
-                    "red",
+                    "yellow",
                     attrs=["bold"],
                 )
             p.deps__ = [a.value for a in p.api_dependencies]
             spec = ProviderWithSpec(
                 spec=p,
-                **(provider.dict()),
+                **(provider.model_dump()),
             )
             specs[provider.provider_id] = spec
 

llama_stack/distribution/server/server.py

@@ -9,6 +9,7 @@ import functools
 import inspect
 import json
 import signal
+import sys
 import traceback
 
 from contextlib import asynccontextmanager
@@ -41,7 +42,7 @@ from llama_stack.providers.utils.telemetry.tracing import (
 )
 from llama_stack.distribution.datatypes import *  # noqa: F403
 from llama_stack.distribution.request_headers import set_request_provider_data
-from llama_stack.distribution.resolver import resolve_impls
+from llama_stack.distribution.resolver import InvalidProviderError, resolve_impls
 
 from .endpoints import get_all_api_endpoints
 
@@ -282,7 +283,13 @@ def main(
 
     dist_registry, dist_kvstore = asyncio.run(create_dist_registry(config))
 
-    impls = asyncio.run(resolve_impls(config, get_provider_registry(), dist_registry))
+    try:
+        impls = asyncio.run(
+            resolve_impls(config, get_provider_registry(), dist_registry)
+        )
+    except InvalidProviderError:
+        sys.exit(1)
+
     if Api.telemetry in impls:
         setup_logger(impls[Api.telemetry])