Merge branch 'main' into feat/add-dana-agent-provider-stub

tests/unit/providers/batches/test_reference.py

@@ -59,8 +59,7 @@ from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
-from llama_stack.apis.batches import BatchObject
-from llama_stack.apis.common.errors import ConflictError, ResourceNotFoundError
+from llama_stack_api import BatchObject, ConflictError, ResourceNotFoundError
 
 
 class TestReferenceBatchesImpl:

tests/unit/providers/batches/test_reference_idempotency.py

@@ -44,7 +44,7 @@ import asyncio
 
 import pytest
 
-from llama_stack.apis.common.errors import ConflictError
+from llama_stack_api import ConflictError
 
 
 class TestReferenceBatchesIdempotency:

tests/unit/providers/files/test_s3_files.py

@@ -9,8 +9,7 @@ from unittest.mock import patch
 import pytest
 from botocore.exceptions import ClientError
 
-from llama_stack.apis.common.errors import ResourceNotFoundError
-from llama_stack.apis.files import OpenAIFilePurpose
+from llama_stack_api import OpenAIFilePurpose, ResourceNotFoundError
 
 
 class TestS3FilesImpl:
@@ -228,7 +227,7 @@ class TestS3FilesImpl:
 
             mock_now.return_value = 0
 
-            from llama_stack.apis.files import ExpiresAfter
+            from llama_stack_api import ExpiresAfter
 
             sample_text_file.filename = "test_expired_file"
             uploaded = await s3_provider.openai_upload_file(
@@ -260,7 +259,7 @@ class TestS3FilesImpl:
 
     async def test_unsupported_expires_after_anchor(self, s3_provider, sample_text_file):
         """Unsupported anchor value should raise ValueError."""
-        from llama_stack.apis.files import ExpiresAfter
+        from llama_stack_api import ExpiresAfter
 
         sample_text_file.filename = "test_unsupported_expires_after_anchor"
 
@@ -273,7 +272,7 @@ class TestS3FilesImpl:
 
     async def test_nonint_expires_after_seconds(self, s3_provider, sample_text_file):
         """Non-integer seconds in expires_after should raise ValueError."""
-        from llama_stack.apis.files import ExpiresAfter
+        from llama_stack_api import ExpiresAfter
 
         sample_text_file.filename = "test_nonint_expires_after_seconds"
 
@@ -286,7 +285,7 @@ class TestS3FilesImpl:
 
     async def test_expires_after_seconds_out_of_bounds(self, s3_provider, sample_text_file):
         """Seconds outside allowed range should raise ValueError."""
-        from llama_stack.apis.files import ExpiresAfter
+        from llama_stack_api import ExpiresAfter
 
         with pytest.raises(ValueError, match="greater than or equal to 3600"):
             await s3_provider.openai_upload_file(

tests/unit/providers/files/test_s3_files_auth.py

@@ -8,10 +8,9 @@ from unittest.mock import patch
 
 import pytest
 
-from llama_stack.apis.common.errors import ResourceNotFoundError
-from llama_stack.apis.files import OpenAIFilePurpose
 from llama_stack.core.datatypes import User
 from llama_stack.providers.remote.files.s3.files import S3FilesImpl
+from llama_stack_api import OpenAIFilePurpose, ResourceNotFoundError
 
 
 async def test_listing_hides_other_users_file(s3_provider, sample_text_file):

tests/unit/providers/inference/test_bedrock_adapter.py

@@ -10,9 +10,9 @@ from unittest.mock import AsyncMock, MagicMock
 import pytest
 from openai import AuthenticationError
 
-from llama_stack.apis.inference import OpenAIChatCompletionRequestWithExtraBody
 from llama_stack.providers.remote.inference.bedrock.bedrock import BedrockInferenceAdapter
 from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
+from llama_stack_api import OpenAIChatCompletionRequestWithExtraBody
 
 
 def test_adapter_initialization():

tests/unit/providers/inference/test_remote_vllm.py

@@ -10,7 +10,13 @@ from unittest.mock import AsyncMock, MagicMock, PropertyMock, patch
 
 import pytest
 
-from llama_stack.apis.inference import (
+from llama_stack.core.routers.inference import InferenceRouter
+from llama_stack.core.routing_tables.models import ModelsRoutingTable
+from llama_stack.providers.remote.inference.vllm.config import VLLMInferenceAdapterConfig
+from llama_stack.providers.remote.inference.vllm.vllm import VLLMInferenceAdapter
+from llama_stack_api import (
+    HealthStatus,
+    Model,
     OpenAIAssistantMessageParam,
     OpenAIChatCompletion,
     OpenAIChatCompletionRequestWithExtraBody,
@@ -20,12 +26,6 @@ from llama_stack.apis.inference import (
     OpenAICompletionRequestWithExtraBody,
     ToolChoice,
 )
-from llama_stack.apis.models import Model
-from llama_stack.core.routers.inference import InferenceRouter
-from llama_stack.core.routing_tables.models import ModelsRoutingTable
-from llama_stack.providers.datatypes import HealthStatus
-from llama_stack.providers.remote.inference.vllm.config import VLLMInferenceAdapterConfig
-from llama_stack.providers.remote.inference.vllm.vllm import VLLMInferenceAdapter
 
 # These are unit test for the remote vllm provider
 # implementation. This should only contain tests which are specific to

tests/unit/providers/inline/agents/meta_reference/responses/test_streaming.py

@@ -8,11 +8,11 @@ from unittest.mock import AsyncMock
 
 import pytest
 
-from llama_stack.apis.tools import ToolDef
 from llama_stack.providers.inline.agents.meta_reference.responses.streaming import (
     convert_tooldef_to_chat_tool,
 )
 from llama_stack.providers.inline.agents.meta_reference.responses.types import ChatCompletionContext
+from llama_stack_api import ToolDef
 
 
 @pytest.fixture

tests/unit/providers/nvidia/test_datastore.py

@@ -9,10 +9,9 @@ from unittest.mock import patch
 
 import pytest
 
-from llama_stack.apis.datasets import Dataset, DatasetPurpose, URIDataSource
-from llama_stack.apis.resource import ResourceType
 from llama_stack.providers.remote.datasetio.nvidia.config import NvidiaDatasetIOConfig
 from llama_stack.providers.remote.datasetio.nvidia.datasetio import NvidiaDatasetIOAdapter
+from llama_stack_api import Dataset, DatasetPurpose, ResourceType, URIDataSource
 
 
 @pytest.fixture

tests/unit/providers/nvidia/test_eval.py

@@ -9,14 +9,20 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 
-from llama_stack.apis.benchmarks import Benchmark
-from llama_stack.apis.common.job_types import Job, JobStatus
-from llama_stack.apis.eval.eval import BenchmarkConfig, EvaluateResponse, ModelCandidate, SamplingParams
-from llama_stack.apis.inference.inference import TopPSamplingStrategy
-from llama_stack.apis.resource import ResourceType
 from llama_stack.models.llama.sku_types import CoreModelId
 from llama_stack.providers.remote.eval.nvidia.config import NVIDIAEvalConfig
 from llama_stack.providers.remote.eval.nvidia.eval import NVIDIAEvalImpl
+from llama_stack_api import (
+    Benchmark,
+    BenchmarkConfig,
+    EvaluateResponse,
+    Job,
+    JobStatus,
+    ModelCandidate,
+    ResourceType,
+    SamplingParams,
+    TopPSamplingStrategy,
+)
 
 MOCK_DATASET_ID = "default/test-dataset"
 MOCK_BENCHMARK_ID = "test-benchmark"

tests/unit/providers/nvidia/test_parameters.py

@@ -10,7 +10,12 @@ from unittest.mock import patch
 
 import pytest
 
-from llama_stack.apis.post_training.post_training import (
+from llama_stack.core.library_client import convert_pydantic_to_json_value
+from llama_stack.providers.remote.post_training.nvidia.post_training import (
+    NvidiaPostTrainingAdapter,
+    NvidiaPostTrainingConfig,
+)
+from llama_stack_api import (
     DataConfig,
     DatasetFormat,
     EfficiencyConfig,
@@ -19,11 +24,6 @@ from llama_stack.apis.post_training.post_training import (
     OptimizerType,
     TrainingConfig,
 )
-from llama_stack.core.library_client import convert_pydantic_to_json_value
-from llama_stack.providers.remote.post_training.nvidia.post_training import (
-    NvidiaPostTrainingAdapter,
-    NvidiaPostTrainingConfig,
-)
 
 
 class TestNvidiaParameters:

tests/unit/providers/nvidia/test_rerank_inference.py

@@ -9,10 +9,10 @@ from unittest.mock import AsyncMock, MagicMock, patch
 import aiohttp
 import pytest
 
-from llama_stack.apis.models import ModelType
 from llama_stack.providers.remote.inference.nvidia.config import NVIDIAConfig
 from llama_stack.providers.remote.inference.nvidia.nvidia import NVIDIAInferenceAdapter
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import ModelType
 
 
 class MockResponse:

tests/unit/providers/nvidia/test_safety.py

@@ -10,15 +10,16 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from llama_stack.apis.inference import (
-    OpenAIAssistantMessageParam,
-    OpenAIUserMessageParam,
-)
-from llama_stack.apis.resource import ResourceType
-from llama_stack.apis.safety import RunShieldResponse, ViolationLevel
-from llama_stack.apis.shields import Shield
 from llama_stack.providers.remote.safety.nvidia.config import NVIDIASafetyConfig
 from llama_stack.providers.remote.safety.nvidia.nvidia import NVIDIASafetyAdapter
+from llama_stack_api import (
+    OpenAIAssistantMessageParam,
+    OpenAIUserMessageParam,
+    ResourceType,
+    RunShieldResponse,
+    Shield,
+    ViolationLevel,
+)
 
 
 class FakeNVIDIASafetyAdapter(NVIDIASafetyAdapter):

tests/unit/providers/nvidia/test_supervised_fine_tuning.py

@@ -10,15 +10,6 @@ from unittest.mock import patch
 
 import pytest
 
-from llama_stack.apis.post_training.post_training import (
-    DataConfig,
-    DatasetFormat,
-    LoraFinetuningConfig,
-    OptimizerConfig,
-    OptimizerType,
-    QATFinetuningConfig,
-    TrainingConfig,
-)
 from llama_stack.core.library_client import convert_pydantic_to_json_value
 from llama_stack.providers.remote.post_training.nvidia.post_training import (
     ListNvidiaPostTrainingJobs,
@@ -27,6 +18,15 @@ from llama_stack.providers.remote.post_training.nvidia.post_training import (
     NvidiaPostTrainingJob,
     NvidiaPostTrainingJobStatusResponse,
 )
+from llama_stack_api import (
+    DataConfig,
+    DatasetFormat,
+    LoraFinetuningConfig,
+    OptimizerConfig,
+    OptimizerType,
+    QATFinetuningConfig,
+    TrainingConfig,
+)
 
 
 @pytest.fixture

tests/unit/providers/test_bedrock.py

@@ -7,9 +7,9 @@
 from types import SimpleNamespace
 from unittest.mock import AsyncMock, PropertyMock, patch
 
-from llama_stack.apis.inference import OpenAIChatCompletionRequestWithExtraBody
 from llama_stack.providers.remote.inference.bedrock.bedrock import BedrockInferenceAdapter
 from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
+from llama_stack_api import OpenAIChatCompletionRequestWithExtraBody
 
 
 def test_can_create_adapter():

tests/unit/providers/utils/inference/test_openai_mixin.py

@@ -12,11 +12,10 @@ from unittest.mock import AsyncMock, MagicMock, Mock, PropertyMock, patch
 import pytest
 from pydantic import BaseModel, Field
 
-from llama_stack.apis.inference import Model, OpenAIChatCompletionRequestWithExtraBody, OpenAIUserMessageParam
-from llama_stack.apis.models import ModelType
 from llama_stack.core.request_headers import request_provider_data_context
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import Model, ModelType, OpenAIChatCompletionRequestWithExtraBody, OpenAIUserMessageParam
 
 
 class OpenAIMixinImpl(OpenAIMixin):

tests/unit/providers/utils/inference/test_prompt_adapter.py

@@ -4,14 +4,11 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.inference import (
-    OpenAIAssistantMessageParam,
-    OpenAIUserMessageParam,
-)
 from llama_stack.models.llama.datatypes import RawTextItem
 from llama_stack.providers.utils.inference.prompt_adapter import (
     convert_openai_message_to_raw_message,
 )
+from llama_stack_api import OpenAIAssistantMessageParam, OpenAIUserMessageParam
 
 
 class TestConvertOpenAIMessageToRawMessage:

tests/unit/providers/utils/memory/test_vector_store.py

@@ -8,9 +8,8 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from llama_stack.apis.common.content_types import URL, TextContentItem
-from llama_stack.apis.tools import RAGDocument
 from llama_stack.providers.utils.memory.vector_store import content_from_data_and_mime_type, content_from_doc
+from llama_stack_api import URL, RAGDocument, TextContentItem
 
 
 async def test_content_from_doc_with_url():

tests/unit/providers/utils/test_model_registry.py

@@ -35,8 +35,8 @@
 
 import pytest
 
-from llama_stack.apis.models import Model
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper, ProviderModelEntry
+from llama_stack_api import Model
 
 
 @pytest.fixture

tests/unit/providers/vector_io/conftest.py

@@ -10,8 +10,6 @@ from unittest.mock import AsyncMock, MagicMock, patch
 import numpy as np
 import pytest
 
-from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
-from llama_stack.apis.vector_stores import VectorStore
 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
@@ -20,6 +18,7 @@ from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import SQLiteV
 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 import register_kvstore_backends
+from llama_stack_api import Chunk, ChunkMetadata, QueryChunksResponse, VectorStore
 
 EMBEDDING_DIMENSION = 768
 COLLECTION_PREFIX = "test_collection"

tests/unit/providers/vector_io/test_faiss.py

@@ -10,15 +10,12 @@ from unittest.mock import MagicMock, patch
 import numpy as np
 import pytest
 
-from llama_stack.apis.files import Files
-from llama_stack.apis.vector_io import Chunk, QueryChunksResponse
-from llama_stack.apis.vector_stores import VectorStore
-from llama_stack.providers.datatypes import HealthStatus
 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_api import Chunk, Files, HealthStatus, QueryChunksResponse, VectorStore
 
 # This test is a unit test for the FaissVectorIOAdapter class. This should only contain
 # tests which are specific to this class. More general (API-level) tests should be placed in

tests/unit/providers/vector_io/test_sqlite_vec.py

@@ -9,12 +9,12 @@ import asyncio
 import numpy as np
 import pytest
 
-from llama_stack.apis.vector_io import Chunk, QueryChunksResponse
 from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import (
     SQLiteVecIndex,
     SQLiteVecVectorIOAdapter,
     _create_sqlite_connection,
 )
+from llama_stack_api import Chunk, QueryChunksResponse
 
 # This test is a unit test for the SQLiteVecVectorIOAdapter class. This should only contain
 # tests which are specific to this class. More general (API-level) tests should be placed in

tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py

@@ -11,17 +11,17 @@ from unittest.mock import AsyncMock, patch
 import numpy as np
 import pytest
 
-from llama_stack.apis.common.errors import VectorStoreNotFoundError
-from llama_stack.apis.vector_io import (
+from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import VECTOR_DBS_PREFIX
+from llama_stack_api import (
     Chunk,
     OpenAICreateVectorStoreFileBatchRequestWithExtraBody,
     OpenAICreateVectorStoreRequestWithExtraBody,
     QueryChunksResponse,
+    VectorStore,
     VectorStoreChunkingStrategyAuto,
     VectorStoreFileObject,
+    VectorStoreNotFoundError,
 )
-from llama_stack.apis.vector_stores import VectorStore
-from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import VECTOR_DBS_PREFIX
 
 # This test is a unit test for the inline VectorIO providers. This should only contain
 # tests which are specific to this class. More general (API-level) tests should be placed in
@@ -222,7 +222,7 @@ async def test_insert_chunks_missing_db_raises(vector_io_adapter):
 
 async def test_insert_chunks_with_missing_document_id(vector_io_adapter):
     """Ensure no KeyError when document_id is missing or in different places."""
-    from llama_stack.apis.vector_io import Chunk, ChunkMetadata
+    from llama_stack_api import Chunk, ChunkMetadata
 
     fake_index = AsyncMock()
     vector_io_adapter.cache["db1"] = fake_index
@@ -255,10 +255,9 @@ async def test_insert_chunks_with_missing_document_id(vector_io_adapter):
 
 async def test_document_id_with_invalid_type_raises_error():
     """Ensure TypeError is raised when document_id is not a string."""
-    from llama_stack.apis.vector_io import Chunk
-
     # Integer document_id should raise TypeError
     from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id
+    from llama_stack_api import Chunk
 
     chunk = Chunk(content="test", chunk_id=generate_chunk_id("test", "test"), metadata={"document_id": 12345})
     with pytest.raises(TypeError) as exc_info:

tests/unit/providers/vector_io/test_vector_utils.py

@@ -4,8 +4,8 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.vector_io import Chunk, ChunkMetadata
 from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id
+from llama_stack_api import Chunk, ChunkMetadata
 
 # This test is a unit test for the chunk_utils.py helpers. This should only contain
 # tests which are specific to this file. More general (API-level) tests should be placed in