Merge remote-tracking branch 'origin/main' into stack-config-default-embed

tests/unit/providers/agent/test_meta_reference_agent.py

@@ -26,6 +26,20 @@ from llama_stack.providers.inline.agents.meta_reference.config import MetaRefere
 from llama_stack.providers.inline.agents.meta_reference.persistence import AgentInfo
 
 
+@pytest.fixture(autouse=True)
+def setup_backends(tmp_path):
+    """Register KV and SQL store backends for testing."""
+    from llama_stack.core.storage.datatypes import SqliteKVStoreConfig, SqliteSqlStoreConfig
+    from llama_stack.providers.utils.kvstore.kvstore import register_kvstore_backends
+    from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
+
+    kv_path = str(tmp_path / "test_kv.db")
+    sql_path = str(tmp_path / "test_sql.db")
+
+    register_kvstore_backends({"kv_default": SqliteKVStoreConfig(db_path=kv_path)})
+    register_sqlstore_backends({"sql_default": SqliteSqlStoreConfig(db_path=sql_path)})
+
+
 @pytest.fixture
 def mock_apis():
     return {
@@ -40,15 +54,20 @@ def mock_apis():
 
 @pytest.fixture
 def config(tmp_path):
+    from llama_stack.core.storage.datatypes import KVStoreReference, ResponsesStoreReference
+    from llama_stack.providers.inline.agents.meta_reference.config import AgentPersistenceConfig
+
     return MetaReferenceAgentsImplConfig(
-        persistence_store={
-            "type": "sqlite",
-            "db_path": str(tmp_path / "test.db"),
-        },
-        responses_store={
-            "type": "sqlite",
-            "db_path": str(tmp_path / "test.db"),
-        },
+        persistence=AgentPersistenceConfig(
+            agent_state=KVStoreReference(
+                backend="kv_default",
+                namespace="agents",
+            ),
+            responses=ResponsesStoreReference(
+                backend="sql_default",
+                table_name="responses",
+            ),
+        )
     )
 
 

tests/unit/providers/agents/meta_reference/test_openai_responses.py

@@ -42,7 +42,7 @@ from llama_stack.apis.inference import (
 )
 from llama_stack.apis.tools.tools import ListToolDefsResponse, ToolDef, ToolGroups, ToolInvocationResult, ToolRuntime
 from llama_stack.core.access_control.access_control import default_policy
-from llama_stack.core.datatypes import ResponsesStoreConfig
+from llama_stack.core.storage.datatypes import ResponsesStoreReference, SqliteSqlStoreConfig
 from llama_stack.providers.inline.agents.meta_reference.responses.openai_responses import (
     OpenAIResponsesImpl,
 )
@@ -50,7 +50,7 @@ from llama_stack.providers.utils.responses.responses_store import (
     ResponsesStore,
     _OpenAIResponseObjectWithInputAndMessages,
 )
-from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
+from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
 from tests.unit.providers.agents.meta_reference.fixtures import load_chat_completion_fixture
 
 
@@ -814,6 +814,69 @@ async def test_create_openai_response_with_instructions_and_previous_response(
     assert sent_messages[3].content == "Which is the largest?"
 
 
+async def test_create_openai_response_with_previous_response_instructions(
+    openai_responses_impl, mock_responses_store, mock_inference_api
+):
+    """Test prepending instructions and previous response with instructions."""
+
+    input_item_message = OpenAIResponseMessage(
+        id="123",
+        content="Name some towns in Ireland",
+        role="user",
+    )
+    response_output_message = OpenAIResponseMessage(
+        id="123",
+        content="Galway, Longford, Sligo",
+        status="completed",
+        role="assistant",
+    )
+    response = _OpenAIResponseObjectWithInputAndMessages(
+        created_at=1,
+        id="resp_123",
+        model="fake_model",
+        output=[response_output_message],
+        status="completed",
+        text=OpenAIResponseText(format=OpenAIResponseTextFormat(type="text")),
+        input=[input_item_message],
+        messages=[
+            OpenAIUserMessageParam(content="Name some towns in Ireland"),
+            OpenAIAssistantMessageParam(content="Galway, Longford, Sligo"),
+        ],
+        instructions="You are a helpful assistant.",
+    )
+    mock_responses_store.get_response_object.return_value = response
+
+    model = "meta-llama/Llama-3.1-8B-Instruct"
+    instructions = "You are a geography expert. Provide concise answers."
+
+    mock_inference_api.openai_chat_completion.return_value = fake_stream()
+
+    # Execute
+    await openai_responses_impl.create_openai_response(
+        input="Which is the largest?", model=model, instructions=instructions, previous_response_id="123"
+    )
+
+    # Verify
+    mock_inference_api.openai_chat_completion.assert_called_once()
+    call_args = mock_inference_api.openai_chat_completion.call_args
+    params = call_args.args[0]
+    sent_messages = params.messages
+
+    # Check that instructions were prepended as a system message
+    # and that the previous response instructions were not carried over
+    assert len(sent_messages) == 4, sent_messages
+    assert sent_messages[0].role == "system"
+    assert sent_messages[0].content == instructions
+
+    # Check the rest of the messages were converted correctly
+    assert sent_messages[1].role == "user"
+    assert sent_messages[1].content == "Name some towns in Ireland"
+    assert sent_messages[2].role == "assistant"
+    assert sent_messages[2].content == "Galway, Longford, Sligo"
+    assert sent_messages[3].role == "user"
+    assert sent_messages[3].content == "Which is the largest?"
+
+
 async def test_list_openai_response_input_items_delegation(openai_responses_impl, mock_responses_store):
     """Test that list_openai_response_input_items properly delegates to responses_store with correct parameters."""
     # Setup
@@ -854,8 +917,10 @@ async def test_responses_store_list_input_items_logic():
 
     # Create mock store and response store
     mock_sql_store = AsyncMock()
+    backend_name = "sql_responses_test"
+    register_sqlstore_backends({backend_name: SqliteSqlStoreConfig(db_path="mock_db_path")})
     responses_store = ResponsesStore(
-        ResponsesStoreConfig(sql_store_config=SqliteSqlStoreConfig(db_path="mock_db_path")), policy=default_policy()
+        ResponsesStoreReference(backend=backend_name, table_name="responses"), policy=default_policy()
     )
     responses_store.sql_store = mock_sql_store
 

tests/unit/providers/batches/conftest.py

@@ -12,10 +12,10 @@ from unittest.mock import AsyncMock
 
 import pytest
 
+from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
 from llama_stack.providers.inline.batches.reference.batches import ReferenceBatchesImpl
 from llama_stack.providers.inline.batches.reference.config import ReferenceBatchesImplConfig
-from llama_stack.providers.utils.kvstore import kvstore_impl
-from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
+from llama_stack.providers.utils.kvstore import kvstore_impl, register_kvstore_backends
 
 
 @pytest.fixture
@@ -23,8 +23,10 @@ async def provider():
     """Create a test provider instance with temporary database."""
     with tempfile.TemporaryDirectory() as tmpdir:
         db_path = Path(tmpdir) / "test_batches.db"
+        backend_name = "kv_batches_test"
         kvstore_config = SqliteKVStoreConfig(db_path=str(db_path))
-        config = ReferenceBatchesImplConfig(kvstore=kvstore_config)
+        register_kvstore_backends({backend_name: kvstore_config})
+        config = ReferenceBatchesImplConfig(kvstore=KVStoreReference(backend=backend_name, namespace="batches"))
 
         # Create kvstore and mock APIs
         kvstore = await kvstore_impl(config.kvstore)

tests/unit/providers/files/conftest.py

@@ -8,8 +8,9 @@ import boto3
 import pytest
 from moto import mock_aws
 
+from llama_stack.core.storage.datatypes import SqliteSqlStoreConfig, SqlStoreReference
 from llama_stack.providers.remote.files.s3 import S3FilesImplConfig, get_adapter_impl
-from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
+from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
 
 
 class MockUploadFile:
@@ -38,11 +39,13 @@ def sample_text_file2():
 def s3_config(tmp_path):
     db_path = tmp_path / "s3_files_metadata.db"
 
+    backend_name = f"sql_s3_{tmp_path.name}"
+    register_sqlstore_backends({backend_name: SqliteSqlStoreConfig(db_path=db_path.as_posix())})
     return S3FilesImplConfig(
         bucket_name=f"test-bucket-{tmp_path.name}",
         region="not-a-region",
         auto_create_bucket=True,
-        metadata_store=SqliteSqlStoreConfig(db_path=db_path.as_posix()),
+        metadata_store=SqlStoreReference(backend=backend_name, table_name="s3_files_metadata"),
     )
 
 

tests/unit/providers/vector_io/conftest.py

@@ -12,13 +12,14 @@ import pytest
 
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
+from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
 from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
 from llama_stack.providers.inline.vector_io.faiss.faiss import FaissIndex, FaissVectorIOAdapter
 from llama_stack.providers.inline.vector_io.sqlite_vec import SQLiteVectorIOConfig
 from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import SQLiteVecIndex, SQLiteVecVectorIOAdapter
 from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVectorIOConfig
 from llama_stack.providers.remote.vector_io.pgvector.pgvector import PGVectorIndex, PGVectorVectorIOAdapter
-from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
+from llama_stack.providers.utils.kvstore import register_kvstore_backends
 
 EMBEDDING_DIMENSION = 768
 COLLECTION_PREFIX = "test_collection"
@@ -112,8 +113,9 @@ async def unique_kvstore_config(tmp_path_factory):
     unique_id = f"test_kv_{np.random.randint(1e6)}"
     temp_dir = tmp_path_factory.getbasetemp()
     db_path = str(temp_dir / f"{unique_id}.db")
-
-    return SqliteKVStoreConfig(db_path=db_path)
+    backend_name = f"kv_vector_{unique_id}"
+    register_kvstore_backends({backend_name: SqliteKVStoreConfig(db_path=db_path)})
+    return KVStoreReference(backend=backend_name, namespace=f"vector_io::{unique_id}")
 
 
 @pytest.fixture(scope="session")
@@ -138,7 +140,7 @@ async def sqlite_vec_vec_index(embedding_dimension, tmp_path_factory):
 async def sqlite_vec_adapter(sqlite_vec_db_path, unique_kvstore_config, mock_inference_api, embedding_dimension):
     config = SQLiteVectorIOConfig(
         db_path=sqlite_vec_db_path,
-        kvstore=unique_kvstore_config,
+        persistence=unique_kvstore_config,
     )
     adapter = SQLiteVecVectorIOAdapter(
         config=config,
@@ -176,7 +178,7 @@ async def faiss_vec_index(embedding_dimension):
 @pytest.fixture
 async def faiss_vec_adapter(unique_kvstore_config, mock_inference_api, embedding_dimension):
     config = FaissVectorIOConfig(
-        kvstore=unique_kvstore_config,
+        persistence=unique_kvstore_config,
     )
     adapter = FaissVectorIOAdapter(
         config=config,
@@ -251,7 +253,7 @@ async def pgvector_vec_adapter(unique_kvstore_config, mock_inference_api, embedd
         db="test_db",
         user="test_user",
         password="test_password",
-        kvstore=unique_kvstore_config,
+        persistence=unique_kvstore_config,
     )
 
     adapter = PGVectorVectorIOAdapter(config, mock_inference_api, None)