mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
feat: Make Safety API an optional dependency for meta-reference agents provider (#4169)
# What does this PR do?
Change Safety API from required to optional dependency, following the
established pattern used for other optional dependencies in Llama Stack.
The provider now starts successfully without Safety API configured.
Requests that explicitly include guardrails will receive a clear error
message when Safety API is unavailable.
This enables local development and testing without Safety API while
maintaining clear error messages when guardrail features are requested.
Closes #4165
Signed-off-by: Anik Bhattacharjee <anbhatta@redhat.com>
## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
1. New unit tests added in
`tests/unit/providers/agents/meta_reference/test_safety_optional.py`
2. Integration tests performed with the files in
https://gist.github.com/anik120/c33cef497ec7085e1fe2164e0705b8d6
(i) test with `test_integration_no_safety_fail.yaml`:
Config WITHOUT Safety API, should fail with helpful error since
`required_safety_api` is `true` by default
```
$ uv run llama stack run test_integration_no_safety_fail.yaml 2>&1 | grep -B 5 -A 15 "ValueError.*Safety\|Safety API is
required"
File "/Users/anbhatta/go/src/github.com/llamastack/llama-stack/src/llama_stack/providers/inline/agents/meta_reference
/__init__.py", line 27, in get_provider_impl
raise ValueError(
...<9 lines>...
)
ValueError: Safety API is required but not configured.
To run without safety checks, explicitly set in your configuration:
providers:
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
require_safety_api: false
Warning: This disables all safety guardrails for this agents provider.
```
(ii) test with `test_integration_no_safety_works.yaml`
Config WITHOUT Safety API, **but** `require_safety_api=false` is
explicitly set, should succeed
```
$ uv run llama stack run test_integration_no_safety_works.yaml
INFO 2025-11-16 09:49:10,044 llama_stack.cli.stack.run:169 cli: Using run configuration:
/Users/anbhatta/go/src/github.com/llamastack/llama-stack/test_integration_no_safety_works.yaml
INFO 2025-11-16 09:49:10,052 llama_stack.cli.stack.run:228 cli: HTTPS enabled with certificates:
Key: None
Cert: None
.
.
.
INFO 2025-11-16 09:49:38,528 llama_stack.core.stack:495 core: starting registry refresh task
INFO 2025-11-16 09:49:38,534 uvicorn.error:62 uncategorized: Application startup complete.
INFO 2025-11-16 09:49:38,535 uvicorn.error:216 uncategorized: Uvicorn running on http://0.0.0.0:8321 (Press CTRL+C
```
Signed-off-by: Anik Bhattacharjee <anbhatta@redhat.com>
Signed-off-by: Anik Bhattacharjee <anbhatta@redhat.com>
This commit is contained in:
Anik
GitHub
parent
d5cd0eea14
commit
4e9633f7c3
7 changed files with 227 additions and 6 deletions
|
|
@ -23,7 +23,7 @@ async def get_provider_impl(
|
|||
config,
|
||||
deps[Api.inference],
|
||||
deps[Api.vector_io],
|
||||
deps[Api.safety],
|
||||
deps.get(Api.safety),
|
||||
deps[Api.tool_runtime],
|
||||
deps[Api.tool_groups],
|
||||
deps[Api.conversations],
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ class MetaReferenceAgentsImpl(Agents):
|
|||
config: MetaReferenceAgentsImplConfig,
|
||||
inference_api: Inference,
|
||||
vector_io_api: VectorIO,
|
||||
safety_api: Safety,
|
||||
safety_api: Safety | None,
|
||||
tool_runtime_api: ToolRuntime,
|
||||
tool_groups_api: ToolGroups,
|
||||
conversations_api: Conversations,
|
||||
|
|
|
|||
|
|
@ -67,7 +67,7 @@ class OpenAIResponsesImpl:
|
|||
tool_runtime_api: ToolRuntime,
|
||||
responses_store: ResponsesStore,
|
||||
vector_io_api: VectorIO, # VectorIO
|
||||
safety_api: Safety,
|
||||
safety_api: Safety | None,
|
||||
conversations_api: Conversations,
|
||||
):
|
||||
self.inference_api = inference_api
|
||||
|
|
@ -273,6 +273,14 @@ class OpenAIResponsesImpl:
|
|||
|
||||
guardrail_ids = extract_guardrail_ids(guardrails) if guardrails else []
|
||||
|
||||
# Validate that Safety API is available if guardrails are requested
|
||||
if guardrail_ids and self.safety_api is None:
|
||||
raise ValueError(
|
||||
"Cannot process guardrails: Safety API is not configured.\n\n"
|
||||
"To use guardrails, ensure the Safety API is configured in your stack, or remove "
|
||||
"the 'guardrails' parameter from your request."
|
||||
)
|
||||
|
||||
if conversation is not None:
|
||||
if previous_response_id is not None:
|
||||
raise ValueError(
|
||||
|
|
|
|||
|
|
@ -66,6 +66,7 @@ from llama_stack_api import (
|
|||
OpenAIResponseUsage,
|
||||
OpenAIResponseUsageInputTokensDetails,
|
||||
OpenAIResponseUsageOutputTokensDetails,
|
||||
Safety,
|
||||
WebSearchToolTypes,
|
||||
)
|
||||
|
||||
|
|
@ -111,7 +112,7 @@ class StreamingResponseOrchestrator:
|
|||
max_infer_iters: int,
|
||||
tool_executor, # Will be the tool execution logic from the main class
|
||||
instructions: str | None,
|
||||
safety_api,
|
||||
safety_api: Safety | None,
|
||||
guardrail_ids: list[str] | None = None,
|
||||
prompt: OpenAIResponsePrompt | None = None,
|
||||
parallel_tool_calls: bool | None = None,
|
||||
|
|
|
|||
|
|
@ -320,11 +320,15 @@ def is_function_tool_call(
|
|||
return False
|
||||
|
||||
|
||||
async def run_guardrails(safety_api: Safety, messages: str, guardrail_ids: list[str]) -> str | None:
|
||||
async def run_guardrails(safety_api: Safety | None, messages: str, guardrail_ids: list[str]) -> str | None:
|
||||
"""Run guardrails against messages and return violation message if blocked."""
|
||||
if not messages:
|
||||
return None
|
||||
|
||||
# If safety API is not available, skip guardrails
|
||||
if safety_api is None:
|
||||
return None
|
||||
|
||||
# Look up shields to get their provider_resource_id (actual model ID)
|
||||
model_ids = []
|
||||
# TODO: list_shields not in Safety interface but available at runtime via API routing
|
||||
|
|
|
|||
|
|
@ -30,12 +30,14 @@ def available_providers() -> list[ProviderSpec]:
|
|||
config_class="llama_stack.providers.inline.agents.meta_reference.MetaReferenceAgentsImplConfig",
|
||||
api_dependencies=[
|
||||
Api.inference,
|
||||
Api.safety,
|
||||
Api.vector_io,
|
||||
Api.tool_runtime,
|
||||
Api.tool_groups,
|
||||
Api.conversations,
|
||||
],
|
||||
optional_api_dependencies=[
|
||||
Api.safety,
|
||||
],
|
||||
description="Meta's reference implementation of an agent system that can use tools, access vector databases, and perform complex reasoning tasks.",
|
||||
),
|
||||
]
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue