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/providers/inline/safety/prompt_guard/config.py

@@ -0,0 +1,25 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from enum import Enum
+
+from pydantic import BaseModel, field_validator
+
+
+class PromptGuardType(Enum):
+    injection = "injection"
+    jailbreak = "jailbreak"
+
+
+class PromptGuardConfig(BaseModel):
+    guard_type: str = PromptGuardType.injection.value
+
+    @classmethod
+    @field_validator("guard_type")
+    def validate_guard_type(cls, v):
+        if v not in [t.value for t in PromptGuardType]:
+            raise ValueError(f"Unknown prompt guard type: {v}")
+        return v