fix: rename llama_stack_api dir (#4155)

# What does this PR do?

the directory structure was src/llama-stack-api/llama_stack_api

instead it should just be src/llama_stack_api to match the other
packages.

update the structure and pyproject/linting config

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

src/llama_stack/core/build.py

@@ -6,7 +6,6 @@
 
 import sys
 
-from llama_stack_api import Api
 from pydantic import BaseModel
 from termcolor import cprint
 
@@ -14,6 +13,7 @@ from llama_stack.core.datatypes import BuildConfig
 from llama_stack.core.distribution import get_provider_registry
 from llama_stack.distributions.template import DistributionTemplate
 from llama_stack.log import get_logger
+from llama_stack_api import Api
 
 log = get_logger(name=__name__, category="core")
 

src/llama_stack/core/client.py

@@ -12,10 +12,11 @@ from enum import Enum
 from typing import Any, Union, get_args, get_origin
 
 import httpx
-from llama_stack_api import RemoteProviderConfig
 from pydantic import BaseModel, parse_obj_as
 from termcolor import cprint
 
+from llama_stack_api import RemoteProviderConfig
+
 _CLIENT_CLASSES = {}
 
 

src/llama_stack/core/configure.py

@@ -6,8 +6,6 @@
 import textwrap
 from typing import Any
 
-from llama_stack_api import Api, ProviderSpec
-
 from llama_stack.core.datatypes import (
     LLAMA_STACK_RUN_CONFIG_VERSION,
     DistributionSpec,
@@ -22,6 +20,7 @@ from llama_stack.core.stack import cast_image_name_to_string, replace_env_vars
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.core.utils.prompt_for_config import prompt_for_config
 from llama_stack.log import get_logger
+from llama_stack_api import Api, ProviderSpec
 
 logger = get_logger(name=__name__, category="core")
 

src/llama_stack/core/conversations/conversations.py

@@ -8,6 +8,13 @@ import secrets
 import time
 from typing import Any, Literal
 
+from pydantic import BaseModel, TypeAdapter
+
+from llama_stack.core.datatypes import AccessRule, StackRunConfig
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
+from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
+from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
 from llama_stack_api import (
     Conversation,
     ConversationDeletedResource,
@@ -18,13 +25,6 @@ from llama_stack_api import (
     Conversations,
     Metadata,
 )
-from pydantic import BaseModel, TypeAdapter
-
-from llama_stack.core.datatypes import AccessRule, StackRunConfig
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
-from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
-from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
 
 logger = get_logger(name=__name__, category="openai_conversations")
 

src/llama_stack/core/datatypes.py

@@ -9,6 +9,15 @@ from pathlib import Path
 from typing import Annotated, Any, Literal, Self
 from urllib.parse import urlparse
 
+from pydantic import BaseModel, Field, field_validator, model_validator
+
+from llama_stack.core.access_control.datatypes import AccessRule
+from llama_stack.core.storage.datatypes import (
+    KVStoreReference,
+    StorageBackendType,
+    StorageConfig,
+)
+from llama_stack.log import LoggingConfig
 from llama_stack_api import (
     Api,
     Benchmark,
@@ -35,15 +44,6 @@ from llama_stack_api import (
     VectorStore,
     VectorStoreInput,
 )
-from pydantic import BaseModel, Field, field_validator, model_validator
-
-from llama_stack.core.access_control.datatypes import AccessRule
-from llama_stack.core.storage.datatypes import (
-    KVStoreReference,
-    StorageBackendType,
-    StorageConfig,
-)
-from llama_stack.log import LoggingConfig
 
 LLAMA_STACK_BUILD_CONFIG_VERSION = 2
 LLAMA_STACK_RUN_CONFIG_VERSION = 2

src/llama_stack/core/distribution.py

@@ -10,17 +10,17 @@ import os
 from typing import Any
 
 import yaml
+from pydantic import BaseModel
+
+from llama_stack.core.datatypes import BuildConfig, DistributionSpec
+from llama_stack.core.external import load_external_apis
+from llama_stack.log import get_logger
 from llama_stack_api import (
     Api,
     InlineProviderSpec,
     ProviderSpec,
     RemoteProviderSpec,
 )
-from pydantic import BaseModel
-
-from llama_stack.core.datatypes import BuildConfig, DistributionSpec
-from llama_stack.core.external import load_external_apis
-from llama_stack.log import get_logger
 
 logger = get_logger(name=__name__, category="core")
 

src/llama_stack/core/external.py

@@ -6,10 +6,10 @@
 
 
 import yaml
-from llama_stack_api import Api, ExternalApiSpec
 
 from llama_stack.core.datatypes import BuildConfig, StackRunConfig
 from llama_stack.log import get_logger
+from llama_stack_api import Api, ExternalApiSpec
 
 logger = get_logger(name=__name__, category="core")
 

src/llama_stack/core/inspect.py

@@ -6,6 +6,11 @@
 
 from importlib.metadata import version
 
+from pydantic import BaseModel
+
+from llama_stack.core.datatypes import StackRunConfig
+from llama_stack.core.external import load_external_apis
+from llama_stack.core.server.routes import get_all_api_routes
 from llama_stack_api import (
     HealthInfo,
     HealthStatus,
@@ -14,11 +19,6 @@ from llama_stack_api import (
     RouteInfo,
     VersionInfo,
 )
-from pydantic import BaseModel
-
-from llama_stack.core.datatypes import StackRunConfig
-from llama_stack.core.external import load_external_apis
-from llama_stack.core.server.routes import get_all_api_routes
 
 
 class DistributionInspectConfig(BaseModel):

src/llama_stack/core/library_client.py

@@ -18,6 +18,7 @@ from typing import Any, TypeVar, Union, get_args, get_origin
 import httpx
 import yaml
 from fastapi import Response as FastAPIResponse
+
 from llama_stack_api import is_unwrapped_body_param
 
 try:

src/llama_stack/core/prompts/prompts.py

@@ -7,11 +7,11 @@
 import json
 from typing import Any
 
-from llama_stack_api import ListPromptsResponse, Prompt, Prompts
 from pydantic import BaseModel
 
 from llama_stack.core.datatypes import StackRunConfig
 from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
+from llama_stack_api import ListPromptsResponse, Prompt, Prompts
 
 
 class PromptServiceConfig(BaseModel):

src/llama_stack/core/providers.py

@@ -7,10 +7,10 @@
 import asyncio
 from typing import Any
 
-from llama_stack_api import HealthResponse, HealthStatus, ListProvidersResponse, ProviderInfo, Providers
 from pydantic import BaseModel
 
 from llama_stack.log import get_logger
+from llama_stack_api import HealthResponse, HealthStatus, ListProvidersResponse, ProviderInfo, Providers
 
 from .datatypes import StackRunConfig
 from .utils.config import redact_sensitive_fields

src/llama_stack/core/resolver.py

@@ -8,6 +8,19 @@ import importlib.metadata
 import inspect
 from typing import Any
 
+from llama_stack.core.client import get_client_impl
+from llama_stack.core.datatypes import (
+    AccessRule,
+    AutoRoutedProviderSpec,
+    Provider,
+    RoutingTableProviderSpec,
+    StackRunConfig,
+)
+from llama_stack.core.distribution import builtin_automatically_routed_apis
+from llama_stack.core.external import load_external_apis
+from llama_stack.core.store import DistributionRegistry
+from llama_stack.core.utils.dynamic import instantiate_class_type
+from llama_stack.log import get_logger
 from llama_stack_api import (
     LLAMA_STACK_API_V1ALPHA,
     Agents,
@@ -48,20 +61,6 @@ from llama_stack_api import (
     Providers as ProvidersAPI,
 )
 
-from llama_stack.core.client import get_client_impl
-from llama_stack.core.datatypes import (
-    AccessRule,
-    AutoRoutedProviderSpec,
-    Provider,
-    RoutingTableProviderSpec,
-    StackRunConfig,
-)
-from llama_stack.core.distribution import builtin_automatically_routed_apis
-from llama_stack.core.external import load_external_apis
-from llama_stack.core.store import DistributionRegistry
-from llama_stack.core.utils.dynamic import instantiate_class_type
-from llama_stack.log import get_logger
-
 logger = get_logger(name=__name__, category="core")
 
 

src/llama_stack/core/routers/__init__.py

@@ -6,8 +6,6 @@
 
 from typing import Any
 
-from llama_stack_api import Api, RoutingTable
-
 from llama_stack.core.datatypes import (
     AccessRule,
     RoutedProtocol,
@@ -15,6 +13,7 @@ from llama_stack.core.datatypes import (
 from llama_stack.core.stack import StackRunConfig
 from llama_stack.core.store import DistributionRegistry
 from llama_stack.providers.utils.inference.inference_store import InferenceStore
+from llama_stack_api import Api, RoutingTable
 
 
 async def get_routing_table_impl(

src/llama_stack/core/routers/datasets.py

@@ -6,9 +6,8 @@
 
 from typing import Any
 
-from llama_stack_api import DatasetIO, DatasetPurpose, DataSource, PaginatedResponse, RoutingTable
-
 from llama_stack.log import get_logger
+from llama_stack_api import DatasetIO, DatasetPurpose, DataSource, PaginatedResponse, RoutingTable
 
 logger = get_logger(name=__name__, category="core::routers")
 

src/llama_stack/core/routers/eval_scoring.py

@@ -6,6 +6,7 @@
 
 from typing import Any
 
+from llama_stack.log import get_logger
 from llama_stack_api import (
     BenchmarkConfig,
     Eval,
@@ -18,8 +19,6 @@ from llama_stack_api import (
     ScoringFnParams,
 )
 
-from llama_stack.log import get_logger
-
 logger = get_logger(name=__name__, category="core::routers")
 
 

src/llama_stack/core/routers/inference.py

@@ -11,6 +11,16 @@ from datetime import UTC, datetime
 from typing import Annotated, Any
 
 from fastapi import Body
+from openai.types.chat import ChatCompletionToolChoiceOptionParam as OpenAIChatCompletionToolChoiceOptionParam
+from openai.types.chat import ChatCompletionToolParam as OpenAIChatCompletionToolParam
+from pydantic import TypeAdapter
+
+from llama_stack.core.telemetry.telemetry import MetricEvent
+from llama_stack.core.telemetry.tracing import enqueue_event, get_current_span
+from llama_stack.log import get_logger
+from llama_stack.models.llama.llama3.chat_format import ChatFormat
+from llama_stack.models.llama.llama3.tokenizer import Tokenizer
+from llama_stack.providers.utils.inference.inference_store import InferenceStore
 from llama_stack_api import (
     HealthResponse,
     HealthStatus,
@@ -39,16 +49,6 @@ from llama_stack_api import (
     RerankResponse,
     RoutingTable,
 )
-from openai.types.chat import ChatCompletionToolChoiceOptionParam as OpenAIChatCompletionToolChoiceOptionParam
-from openai.types.chat import ChatCompletionToolParam as OpenAIChatCompletionToolParam
-from pydantic import TypeAdapter
-
-from llama_stack.core.telemetry.telemetry import MetricEvent
-from llama_stack.core.telemetry.tracing import enqueue_event, get_current_span
-from llama_stack.log import get_logger
-from llama_stack.models.llama.llama3.chat_format import ChatFormat
-from llama_stack.models.llama.llama3.tokenizer import Tokenizer
-from llama_stack.providers.utils.inference.inference_store import InferenceStore
 
 logger = get_logger(name=__name__, category="core::routers")
 

src/llama_stack/core/routers/safety.py

@@ -6,10 +6,9 @@
 
 from typing import Any
 
-from llama_stack_api import ModerationObject, OpenAIMessageParam, RoutingTable, RunShieldResponse, Safety, Shield
-
 from llama_stack.core.datatypes import SafetyConfig
 from llama_stack.log import get_logger
+from llama_stack_api import ModerationObject, OpenAIMessageParam, RoutingTable, RunShieldResponse, Safety, Shield
 
 logger = get_logger(name=__name__, category="core::routers")
 

src/llama_stack/core/routers/tool_runtime.py

@@ -6,14 +6,13 @@
 
 from typing import Any
 
+from llama_stack.log import get_logger
 from llama_stack_api import (
     URL,
     ListToolDefsResponse,
     ToolRuntime,
 )
 
-from llama_stack.log import get_logger
-
 from ..routing_tables.toolgroups import ToolGroupsRoutingTable
 
 logger = get_logger(name=__name__, category="core::routers")

src/llama_stack/core/routers/vector_io.py

@@ -9,6 +9,9 @@ import uuid
 from typing import Annotated, Any
 
 from fastapi import Body
+
+from llama_stack.core.datatypes import VectorStoresConfig
+from llama_stack.log import get_logger
 from llama_stack_api import (
     Chunk,
     HealthResponse,
@@ -38,9 +41,6 @@ from llama_stack_api import (
     VectorStoreSearchResponsePage,
 )
 
-from llama_stack.core.datatypes import VectorStoresConfig
-from llama_stack.log import get_logger
-
 logger = get_logger(name=__name__, category="core::routers")
 
 

src/llama_stack/core/routing_tables/benchmarks.py

@@ -6,12 +6,11 @@
 
 from typing import Any
 
-from llama_stack_api import Benchmark, Benchmarks, ListBenchmarksResponse
-
 from llama_stack.core.datatypes import (
     BenchmarkWithOwner,
 )
 from llama_stack.log import get_logger
+from llama_stack_api import Benchmark, Benchmarks, ListBenchmarksResponse
 
 from .common import CommonRoutingTableImpl
 

src/llama_stack/core/routing_tables/common.py

@@ -6,8 +6,6 @@
 
 from typing import Any
 
-from llama_stack_api import Api, Model, ModelNotFoundError, ResourceType, RoutingTable
-
 from llama_stack.core.access_control.access_control import AccessDeniedError, is_action_allowed
 from llama_stack.core.access_control.datatypes import Action
 from llama_stack.core.datatypes import (
@@ -20,6 +18,7 @@ from llama_stack.core.datatypes import (
 from llama_stack.core.request_headers import get_authenticated_user
 from llama_stack.core.store import DistributionRegistry
 from llama_stack.log import get_logger
+from llama_stack_api import Api, Model, ModelNotFoundError, ResourceType, RoutingTable
 
 logger = get_logger(name=__name__, category="core::routing_tables")
 

src/llama_stack/core/routing_tables/datasets.py

@@ -7,6 +7,10 @@
 import uuid
 from typing import Any
 
+from llama_stack.core.datatypes import (
+    DatasetWithOwner,
+)
+from llama_stack.log import get_logger
 from llama_stack_api import (
     Dataset,
     DatasetNotFoundError,
@@ -20,11 +24,6 @@ from llama_stack_api import (
     URIDataSource,
 )
 
-from llama_stack.core.datatypes import (
-    DatasetWithOwner,
-)
-from llama_stack.log import get_logger
-
 from .common import CommonRoutingTableImpl
 
 logger = get_logger(name=__name__, category="core::routing_tables")

src/llama_stack/core/routing_tables/models.py

@@ -7,6 +7,13 @@
 import time
 from typing import Any
 
+from llama_stack.core.datatypes import (
+    ModelWithOwner,
+    RegistryEntrySource,
+)
+from llama_stack.core.request_headers import PROVIDER_DATA_VAR, NeedsRequestProviderData
+from llama_stack.core.utils.dynamic import instantiate_class_type
+from llama_stack.log import get_logger
 from llama_stack_api import (
     ListModelsResponse,
     Model,
@@ -17,14 +24,6 @@ from llama_stack_api import (
     OpenAIModel,
 )
 
-from llama_stack.core.datatypes import (
-    ModelWithOwner,
-    RegistryEntrySource,
-)
-from llama_stack.core.request_headers import PROVIDER_DATA_VAR, NeedsRequestProviderData
-from llama_stack.core.utils.dynamic import instantiate_class_type
-from llama_stack.log import get_logger
-
 from .common import CommonRoutingTableImpl, lookup_model
 
 logger = get_logger(name=__name__, category="core::routing_tables")

src/llama_stack/core/routing_tables/scoring_functions.py

@@ -4,6 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from llama_stack.core.datatypes import (
+    ScoringFnWithOwner,
+)
+from llama_stack.log import get_logger
 from llama_stack_api import (
     ListScoringFunctionsResponse,
     ParamType,
@@ -13,11 +17,6 @@ from llama_stack_api import (
     ScoringFunctions,
 )
 
-from llama_stack.core.datatypes import (
-    ScoringFnWithOwner,
-)
-from llama_stack.log import get_logger
-
 from .common import CommonRoutingTableImpl
 
 logger = get_logger(name=__name__, category="core::routing_tables")

src/llama_stack/core/routing_tables/shields.py

@@ -6,12 +6,11 @@
 
 from typing import Any
 
-from llama_stack_api import ListShieldsResponse, ResourceType, Shield, Shields
-
 from llama_stack.core.datatypes import (
     ShieldWithOwner,
 )
 from llama_stack.log import get_logger
+from llama_stack_api import ListShieldsResponse, ResourceType, Shield, Shields
 
 from .common import CommonRoutingTableImpl
 

src/llama_stack/core/routing_tables/toolgroups.py

@@ -6,6 +6,8 @@
 
 from typing import Any
 
+from llama_stack.core.datatypes import AuthenticationRequiredError, ToolGroupWithOwner
+from llama_stack.log import get_logger
 from llama_stack_api import (
     URL,
     ListToolDefsResponse,
@@ -16,9 +18,6 @@ from llama_stack_api import (
     ToolGroups,
 )
 
-from llama_stack.core.datatypes import AuthenticationRequiredError, ToolGroupWithOwner
-from llama_stack.log import get_logger
-
 from .common import CommonRoutingTableImpl
 
 logger = get_logger(name=__name__, category="core::routing_tables")

src/llama_stack/core/routing_tables/vector_stores.py

@@ -6,6 +6,11 @@
 
 from typing import Any
 
+from llama_stack.core.datatypes import (
+    VectorStoreWithOwner,
+)
+from llama_stack.log import get_logger
+
 # Removed VectorStores import to avoid exposing public API
 from llama_stack_api import (
     ModelNotFoundError,
@@ -23,11 +28,6 @@ from llama_stack_api import (
     VectorStoreSearchResponsePage,
 )
 
-from llama_stack.core.datatypes import (
-    VectorStoreWithOwner,
-)
-from llama_stack.log import get_logger
-
 from .common import CommonRoutingTableImpl, lookup_model
 
 logger = get_logger(name=__name__, category="core::routing_tables")

src/llama_stack/core/server/auth_providers.py

@@ -11,7 +11,6 @@ from urllib.parse import parse_qs, urljoin, urlparse
 
 import httpx
 import jwt
-from llama_stack_api import TokenValidationError
 from pydantic import BaseModel, Field
 
 from llama_stack.core.datatypes import (
@@ -23,6 +22,7 @@ from llama_stack.core.datatypes import (
     User,
 )
 from llama_stack.log import get_logger
+from llama_stack_api import TokenValidationError
 
 logger = get_logger(name=__name__, category="core::auth")
 

src/llama_stack/core/server/routes.py

@@ -10,10 +10,10 @@ from collections.abc import Callable
 from typing import Any
 
 from aiohttp import hdrs
-from llama_stack_api import Api, ExternalApiSpec, WebMethod
 from starlette.routing import Route
 
 from llama_stack.core.resolver import api_protocol_map
+from llama_stack_api import Api, ExternalApiSpec, WebMethod
 
 EndpointFunc = Callable[..., Any]
 PathParams = dict[str, str]

src/llama_stack/core/server/server.py

@@ -28,7 +28,6 @@ from fastapi import Path as FastapiPath
 from fastapi.exceptions import RequestValidationError
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse, StreamingResponse
-from llama_stack_api import Api, ConflictError, PaginatedResponse, ResourceNotFoundError
 from openai import BadRequestError
 from pydantic import BaseModel, ValidationError
 
@@ -57,6 +56,7 @@ from llama_stack.core.utils.config import redact_sensitive_fields
 from llama_stack.core.utils.config_resolution import Mode, resolve_config_or_distro
 from llama_stack.core.utils.context import preserve_contexts_async_generator
 from llama_stack.log import LoggingConfig, get_logger, setup_logging
+from llama_stack_api import Api, ConflictError, PaginatedResponse, ResourceNotFoundError
 
 from .auth import AuthenticationMiddleware
 from .quota import QuotaMiddleware

src/llama_stack/core/stack.py

@@ -12,6 +12,28 @@ import tempfile
 from typing import Any
 
 import yaml
+
+from llama_stack.core.conversations.conversations import ConversationServiceConfig, ConversationServiceImpl
+from llama_stack.core.datatypes import Provider, SafetyConfig, StackRunConfig, VectorStoresConfig
+from llama_stack.core.distribution import get_provider_registry
+from llama_stack.core.inspect import DistributionInspectConfig, DistributionInspectImpl
+from llama_stack.core.prompts.prompts import PromptServiceConfig, PromptServiceImpl
+from llama_stack.core.providers import ProviderImpl, ProviderImplConfig
+from llama_stack.core.resolver import ProviderRegistry, resolve_impls
+from llama_stack.core.routing_tables.common import CommonRoutingTableImpl
+from llama_stack.core.storage.datatypes import (
+    InferenceStoreReference,
+    KVStoreReference,
+    ServerStoresConfig,
+    SqliteKVStoreConfig,
+    SqliteSqlStoreConfig,
+    SqlStoreReference,
+    StorageBackendConfig,
+    StorageConfig,
+)
+from llama_stack.core.store.registry import create_dist_registry
+from llama_stack.core.utils.dynamic import instantiate_class_type
+from llama_stack.log import get_logger
 from llama_stack_api import (
     Agents,
     Api,
@@ -37,28 +59,6 @@ from llama_stack_api import (
     VectorIO,
 )
 
-from llama_stack.core.conversations.conversations import ConversationServiceConfig, ConversationServiceImpl
-from llama_stack.core.datatypes import Provider, SafetyConfig, StackRunConfig, VectorStoresConfig
-from llama_stack.core.distribution import get_provider_registry
-from llama_stack.core.inspect import DistributionInspectConfig, DistributionInspectImpl
-from llama_stack.core.prompts.prompts import PromptServiceConfig, PromptServiceImpl
-from llama_stack.core.providers import ProviderImpl, ProviderImplConfig
-from llama_stack.core.resolver import ProviderRegistry, resolve_impls
-from llama_stack.core.routing_tables.common import CommonRoutingTableImpl
-from llama_stack.core.storage.datatypes import (
-    InferenceStoreReference,
-    KVStoreReference,
-    ServerStoresConfig,
-    SqliteKVStoreConfig,
-    SqliteSqlStoreConfig,
-    SqlStoreReference,
-    StorageBackendConfig,
-    StorageConfig,
-)
-from llama_stack.core.store.registry import create_dist_registry
-from llama_stack.core.utils.dynamic import instantiate_class_type
-from llama_stack.log import get_logger
-
 logger = get_logger(name=__name__, category="core")
 
 

src/llama_stack/core/telemetry/telemetry.py

@@ -16,7 +16,6 @@ from typing import (
     cast,
 )
 
-from llama_stack_api import json_schema_type, register_schema
 from opentelemetry import metrics, trace
 from opentelemetry.exporter.otlp.proto.http.metric_exporter import OTLPMetricExporter
 from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
@@ -29,6 +28,7 @@ from pydantic import BaseModel, Field
 
 from llama_stack.log import get_logger
 from llama_stack.models.llama.datatypes import Primitive
+from llama_stack_api import json_schema_type, register_schema
 
 ROOT_SPAN_MARKERS = ["__root__", "__root_span__"]