refactor: enforce top-level imports for llama-stack-api

Enforce that all imports from llama-stack-api use the form:

from llama_stack_api import <symbol>

 This prevents external code from accessing internal package structure
 (e.g., llama_stack_api.agents, llama_stack_api.common.*) and establishes
 a clear public API boundary.

 Changes:
 - Export 400+ symbols from llama_stack_api/__init__.py
 - Include all API types, common utilities, and strong_typing helpers
 - Update files across src/llama_stack, docs/, tests/, scripts/
 - Convert all submodule imports to top-level imports
 - ensure docs use the proper importing structure

 Addresses PR review feedback requiring explicit __all__ definition to
 prevent "peeking inside" the API package.

Signed-off-by: Charlie Doern <cdoern@redhat.com>

tests/unit/providers/batches/test_reference.py

@@ -58,8 +58,7 @@ import json
 from unittest.mock import AsyncMock, MagicMock
 
 import pytest
-from llama_stack_api.batches import BatchObject
-from llama_stack_api.common.errors import ConflictError, ResourceNotFoundError
+from llama_stack_api import BatchObject, ConflictError, ResourceNotFoundError
 
 
 class TestReferenceBatchesImpl:

tests/unit/providers/batches/test_reference_idempotency.py

@@ -43,7 +43,7 @@ Key Behaviors Tested:
 import asyncio
 
 import pytest
-from llama_stack_api.common.errors import ConflictError
+from llama_stack_api import ConflictError
 
 
 class TestReferenceBatchesIdempotency:

tests/unit/providers/files/test_s3_files.py

@@ -8,8 +8,7 @@ from unittest.mock import patch
 
 import pytest
 from botocore.exceptions import ClientError
-from llama_stack_api.common.errors import ResourceNotFoundError
-from llama_stack_api.files import OpenAIFilePurpose
+from llama_stack_api import OpenAIFilePurpose, ResourceNotFoundError
 
 
 class TestS3FilesImpl:
@@ -227,7 +226,7 @@ class TestS3FilesImpl:
 
             mock_now.return_value = 0
 
-            from llama_stack_api.files import ExpiresAfter
+            from llama_stack_api import ExpiresAfter
 
             sample_text_file.filename = "test_expired_file"
             uploaded = await s3_provider.openai_upload_file(
@@ -259,7 +258,7 @@ class TestS3FilesImpl:
 
     async def test_unsupported_expires_after_anchor(self, s3_provider, sample_text_file):
         """Unsupported anchor value should raise ValueError."""
-        from llama_stack_api.files import ExpiresAfter
+        from llama_stack_api import ExpiresAfter
 
         sample_text_file.filename = "test_unsupported_expires_after_anchor"
 
@@ -272,7 +271,7 @@ 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_api.files import ExpiresAfter
+        from llama_stack_api import ExpiresAfter
 
         sample_text_file.filename = "test_nonint_expires_after_seconds"
 
@@ -285,7 +284,7 @@ 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_api.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

@@ -7,8 +7,7 @@
 from unittest.mock import patch
 
 import pytest
-from llama_stack_api.common.errors import ResourceNotFoundError
-from llama_stack_api.files import OpenAIFilePurpose
+from llama_stack_api import OpenAIFilePurpose, ResourceNotFoundError
 
 from llama_stack.core.datatypes import User
 from llama_stack.providers.remote.files.s3.files import S3FilesImpl

tests/unit/providers/inference/test_bedrock_adapter.py

@@ -8,7 +8,7 @@ from types import SimpleNamespace
 from unittest.mock import AsyncMock, MagicMock
 
 import pytest
-from llama_stack_api.inference import OpenAIChatCompletionRequestWithExtraBody
+from llama_stack_api import OpenAIChatCompletionRequestWithExtraBody
 from openai import AuthenticationError
 
 from llama_stack.providers.remote.inference.bedrock.bedrock import BedrockInferenceAdapter

tests/unit/providers/inference/test_remote_vllm.py

@@ -9,8 +9,9 @@ import time
 from unittest.mock import AsyncMock, MagicMock, PropertyMock, patch
 
 import pytest
-from llama_stack_api.datatypes import HealthStatus
-from llama_stack_api.inference import (
+from llama_stack_api import (
+    HealthStatus,
+    Model,
     OpenAIAssistantMessageParam,
     OpenAIChatCompletion,
     OpenAIChatCompletionRequestWithExtraBody,
@@ -20,7 +21,6 @@ from llama_stack_api.inference import (
     OpenAICompletionRequestWithExtraBody,
     ToolChoice,
 )
-from llama_stack_api.models import Model
 
 from llama_stack.core.routers.inference import InferenceRouter
 from llama_stack.core.routing_tables.models import ModelsRoutingTable

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

@@ -7,7 +7,7 @@
 from unittest.mock import AsyncMock
 
 import pytest
-from llama_stack_api.tools import ToolDef
+from llama_stack_api import ToolDef
 
 from llama_stack.providers.inline.agents.meta_reference.responses.streaming import (
     convert_tooldef_to_chat_tool,

tests/unit/providers/nvidia/test_datastore.py

@@ -8,8 +8,7 @@ import os
 from unittest.mock import patch
 
 import pytest
-from llama_stack_api.datasets import Dataset, DatasetPurpose, URIDataSource
-from llama_stack_api.resource import ResourceType
+from llama_stack_api import Dataset, DatasetPurpose, ResourceType, URIDataSource
 
 from llama_stack.providers.remote.datasetio.nvidia.config import NvidiaDatasetIOConfig
 from llama_stack.providers.remote.datasetio.nvidia.datasetio import NvidiaDatasetIOAdapter

tests/unit/providers/nvidia/test_eval.py

@@ -8,11 +8,17 @@ import os
 from unittest.mock import MagicMock, patch
 
 import pytest
-from llama_stack_api.benchmarks import Benchmark
-from llama_stack_api.common.job_types import Job, JobStatus
-from llama_stack_api.eval import BenchmarkConfig, EvaluateResponse, ModelCandidate, SamplingParams
-from llama_stack_api.inference import TopPSamplingStrategy
-from llama_stack_api.resource import ResourceType
+from llama_stack_api import (
+    Benchmark,
+    BenchmarkConfig,
+    EvaluateResponse,
+    Job,
+    JobStatus,
+    ModelCandidate,
+    ResourceType,
+    SamplingParams,
+    TopPSamplingStrategy,
+)
 
 from llama_stack.models.llama.sku_types import CoreModelId
 from llama_stack.providers.remote.eval.nvidia.config import NVIDIAEvalConfig

tests/unit/providers/nvidia/test_parameters.py

@@ -9,7 +9,7 @@ import warnings
 from unittest.mock import patch
 
 import pytest
-from llama_stack_api.post_training import (
+from llama_stack_api import (
     DataConfig,
     DatasetFormat,
     EfficiencyConfig,

tests/unit/providers/nvidia/test_rerank_inference.py

@@ -8,7 +8,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import aiohttp
 import pytest
-from llama_stack_api.models import ModelType
+from llama_stack_api import ModelType
 
 from llama_stack.providers.remote.inference.nvidia.config import NVIDIAConfig
 from llama_stack.providers.remote.inference.nvidia.nvidia import NVIDIAInferenceAdapter

tests/unit/providers/nvidia/test_safety.py

@@ -9,13 +9,14 @@ from typing import Any
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
-from llama_stack_api.inference import (
+from llama_stack_api import (
     OpenAIAssistantMessageParam,
     OpenAIUserMessageParam,
+    ResourceType,
+    RunShieldResponse,
+    Shield,
+    ViolationLevel,
 )
-from llama_stack_api.resource import ResourceType
-from llama_stack_api.safety import RunShieldResponse, ViolationLevel
-from llama_stack_api.shields import Shield
 
 from llama_stack.providers.remote.safety.nvidia.config import NVIDIASafetyConfig
 from llama_stack.providers.remote.safety.nvidia.nvidia import NVIDIASafetyAdapter

tests/unit/providers/nvidia/test_supervised_fine_tuning.py

@@ -9,7 +9,7 @@ import warnings
 from unittest.mock import patch
 
 import pytest
-from llama_stack_api.post_training import (
+from llama_stack_api import (
     DataConfig,
     DatasetFormat,
     LoraFinetuningConfig,

tests/unit/providers/test_bedrock.py

@@ -7,7 +7,7 @@
 from types import SimpleNamespace
 from unittest.mock import AsyncMock, PropertyMock, patch
 
-from llama_stack_api.inference import OpenAIChatCompletionRequestWithExtraBody
+from llama_stack_api import OpenAIChatCompletionRequestWithExtraBody
 
 from llama_stack.providers.remote.inference.bedrock.bedrock import BedrockInferenceAdapter
 from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig

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

@@ -10,8 +10,7 @@ from typing import Any
 from unittest.mock import AsyncMock, MagicMock, Mock, PropertyMock, patch
 
 import pytest
-from llama_stack_api.inference import Model, OpenAIChatCompletionRequestWithExtraBody, OpenAIUserMessageParam
-from llama_stack_api.models import ModelType
+from llama_stack_api import Model, ModelType, OpenAIChatCompletionRequestWithExtraBody, OpenAIUserMessageParam
 from pydantic import BaseModel, Field
 
 from llama_stack.core.request_headers import request_provider_data_context

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

@@ -4,10 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack_api.inference import (
-    OpenAIAssistantMessageParam,
-    OpenAIUserMessageParam,
-)
+from llama_stack_api import OpenAIAssistantMessageParam, OpenAIUserMessageParam
 
 from llama_stack.models.llama.datatypes import RawTextItem
 from llama_stack.providers.utils.inference.prompt_adapter import (

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

@@ -7,8 +7,7 @@
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
-from llama_stack_api.common.content_types import URL, TextContentItem
-from llama_stack_api.rag_tool import RAGDocument
+from llama_stack_api import URL, RAGDocument, TextContentItem
 
 from llama_stack.providers.utils.memory.vector_store import content_from_data_and_mime_type, content_from_doc
 

tests/unit/providers/utils/test_model_registry.py

@@ -34,7 +34,7 @@
 #
 
 import pytest
-from llama_stack_api.models import Model
+from llama_stack_api import Model
 
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper, ProviderModelEntry
 

tests/unit/providers/vector_io/conftest.py

@@ -9,8 +9,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import numpy as np
 import pytest
-from llama_stack_api.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
-from llama_stack_api.vector_stores import VectorStore
+from llama_stack_api import Chunk, ChunkMetadata, QueryChunksResponse, VectorStore
 
 from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
 from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig

tests/unit/providers/vector_io/test_faiss.py

@@ -9,10 +9,7 @@ from unittest.mock import MagicMock, patch
 
 import numpy as np
 import pytest
-from llama_stack_api.datatypes import HealthStatus
-from llama_stack_api.files import Files
-from llama_stack_api.vector_io import Chunk, QueryChunksResponse
-from llama_stack_api.vector_stores import VectorStore
+from llama_stack_api import Chunk, Files, HealthStatus, QueryChunksResponse, VectorStore
 
 from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
 from llama_stack.providers.inline.vector_io.faiss.faiss import (

tests/unit/providers/vector_io/test_sqlite_vec.py

@@ -8,7 +8,7 @@ import asyncio
 
 import numpy as np
 import pytest
-from llama_stack_api.vector_io import Chunk, QueryChunksResponse
+from llama_stack_api import Chunk, QueryChunksResponse
 
 from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import (
     SQLiteVecIndex,

tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py

@@ -10,16 +10,16 @@ from unittest.mock import AsyncMock, patch
 
 import numpy as np
 import pytest
-from llama_stack_api.common.errors import VectorStoreNotFoundError
-from llama_stack_api.vector_io import (
+from llama_stack_api import (
     Chunk,
     OpenAICreateVectorStoreFileBatchRequestWithExtraBody,
     OpenAICreateVectorStoreRequestWithExtraBody,
     QueryChunksResponse,
+    VectorStore,
     VectorStoreChunkingStrategyAuto,
     VectorStoreFileObject,
+    VectorStoreNotFoundError,
 )
-from llama_stack_api.vector_stores import VectorStore
 
 from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import VECTOR_DBS_PREFIX
 
@@ -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_api.vector_io import Chunk, ChunkMetadata
+    from llama_stack_api import Chunk, ChunkMetadata
 
     fake_index = AsyncMock()
     vector_io_adapter.cache["db1"] = fake_index
@@ -255,7 +255,7 @@ 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_api.vector_io import Chunk
+    from llama_stack_api import Chunk
 
     # Integer document_id should raise TypeError
     from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id

tests/unit/providers/vector_io/test_vector_utils.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack_api.vector_io import Chunk, ChunkMetadata
+from llama_stack_api import Chunk, ChunkMetadata
 
 from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id