chore(rename): move llama_stack.distribution to llama_stack.core (#2975)

We would like to rename the term `template` to `distribution`. To
prepare for that, this is a precursor.

cc @leseb

llama_stack/providers/remote/datasetio/nvidia/README.md

@@ -34,7 +34,7 @@ os.environ["NVIDIA_API_KEY"] = "your-api-key"
 os.environ["NVIDIA_CUSTOMIZER_URL"] = "http://nemo.test"
 os.environ["NVIDIA_DATASET_NAMESPACE"] = "default"
 os.environ["NVIDIA_PROJECT_ID"] = "test-project"
-from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 client = LlamaStackAsLibraryClient("nvidia")
 client.initialize()

llama_stack/providers/remote/eval/nvidia/__init__.py

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 from typing import Any
 
-from llama_stack.distribution.datatypes import Api
+from llama_stack.core.datatypes import Api
 
 from .config import NVIDIAEvalConfig
 

llama_stack/providers/remote/inference/fireworks/fireworks.py

@@ -39,7 +39,7 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,

llama_stack/providers/remote/inference/nvidia/NVIDIA.md

@@ -33,7 +33,7 @@ os.environ["NVIDIA_API_KEY"] = (
 )
 os.environ["NVIDIA_BASE_URL"] = "http://nim.test"  # NIM URL
 
-from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 client = LlamaStackAsLibraryClient("nvidia")
 client.initialize()

llama_stack/providers/remote/inference/passthrough/passthrough.py

@@ -34,7 +34,7 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.apis.models import Model
-from llama_stack.distribution.library_client import convert_pydantic_to_json_value, convert_to_pydantic
+from llama_stack.core.library_client import convert_pydantic_to_json_value, convert_to_pydantic
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
 from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
 

llama_stack/providers/remote/inference/together/together.py

@@ -38,7 +38,7 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
 from llama_stack.providers.utils.inference.openai_compat import (

llama_stack/providers/remote/post_training/nvidia/README.md

@@ -40,7 +40,7 @@ os.environ["NVIDIA_DATASET_NAMESPACE"] = "default"
 os.environ["NVIDIA_PROJECT_ID"] = "test-project"
 os.environ["NVIDIA_OUTPUT_MODEL_DIR"] = "test-example-model@v1"
 
-from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 client = LlamaStackAsLibraryClient("nvidia")
 client.initialize()

llama_stack/providers/remote/safety/nvidia/README.md

@@ -32,7 +32,7 @@ import os
 os.environ["NVIDIA_API_KEY"] = "your-api-key"
 os.environ["NVIDIA_GUARDRAILS_URL"] = "http://guardrails.test"
 
-from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 client = LlamaStackAsLibraryClient("nvidia")
 client.initialize()

llama_stack/providers/remote/safety/sambanova/sambanova.py

@@ -19,7 +19,7 @@ from llama_stack.apis.safety import (
     ViolationLevel,
 )
 from llama_stack.apis.shields import Shield
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.inference.openai_compat import convert_message_to_openai_dict_new
 

llama_stack/providers/remote/tool_runtime/bing_search/bing_search.py

@@ -18,7 +18,7 @@ from llama_stack.apis.tools import (
     ToolParameter,
     ToolRuntime,
 )
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
 
 from .config import BingSearchToolConfig

llama_stack/providers/remote/tool_runtime/brave_search/brave_search.py

@@ -17,7 +17,7 @@ from llama_stack.apis.tools import (
     ToolParameter,
     ToolRuntime,
 )
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.models.llama.datatypes import BuiltinTool
 from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
 

llama_stack/providers/remote/tool_runtime/model_context_protocol/model_context_protocol.py

@@ -15,7 +15,7 @@ from llama_stack.apis.tools import (
     ToolInvocationResult,
     ToolRuntime,
 )
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
 from llama_stack.providers.utils.tools.mcp import invoke_mcp_tool, list_mcp_tools

llama_stack/providers/remote/tool_runtime/tavily_search/tavily_search.py

@@ -18,7 +18,7 @@ from llama_stack.apis.tools import (
     ToolParameter,
     ToolRuntime,
 )
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
 
 from .config import TavilySearchToolConfig

llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py

@@ -18,7 +18,7 @@ from llama_stack.apis.tools import (
     ToolParameter,
     ToolRuntime,
 )
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
 
 from .config import WolframAlphaToolConfig

llama_stack/providers/remote/vector_io/weaviate/weaviate.py

@@ -18,7 +18,7 @@ from llama_stack.apis.common.errors import VectorStoreNotFoundError
 from llama_stack.apis.files.files import Files
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
-from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
 from llama_stack.providers.utils.kvstore import kvstore_impl
 from llama_stack.providers.utils.kvstore.api import KVStore