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/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")