feat: split API and provider specs into separate llama-stack-api pkg (#3895)

# What does this PR do?

Extract API definitions and provider specifications into a standalone
llama-stack-api package that can be published to PyPI independently of
the main llama-stack server.


see: https://github.com/llamastack/llama-stack/pull/2978 and
https://github.com/llamastack/llama-stack/pull/2978#issuecomment-3145115942

Motivation

External providers currently import from llama-stack, which overrides
the installed version and causes dependency conflicts. This separation
allows external providers to:

- Install only the type definitions they need without server
dependencies
- Avoid version conflicts with the installed llama-stack package
- Be versioned and released independently

This enables us to re-enable external provider module tests that were
previously blocked by these import conflicts.

Changes

- Created llama-stack-api package with minimal dependencies (pydantic,
jsonschema)
- Moved APIs, providers datatypes, strong_typing, and schema_utils
- Updated all imports from llama_stack.* to llama_stack_api.*
- Configured local editable install for development workflow
- Updated linting and type-checking configuration for both packages

Next Steps

- Publish llama-stack-api to PyPI
- Update external provider dependencies
- Re-enable external provider module tests


Pre-cursor PRs to this one:

- #4093 
- #3954 
- #4064 

These PRs moved key pieces _out_ of the Api pkg, limiting the scope of
change here.


relates to #3237 

## Test Plan

Package builds successfully and can be imported independently. All
pre-commit hooks pass with expected exclusions maintained.

---------

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

src/llama-stack-api/llama_stack_api/models.py

@@ -0,0 +1,172 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from enum import StrEnum
+from typing import Any, Literal, Protocol, runtime_checkable
+
+from pydantic import BaseModel, ConfigDict, Field, field_validator
+
+from llama_stack_api.common.tracing import telemetry_traceable
+from llama_stack_api.resource import Resource, ResourceType
+from llama_stack_api.schema_utils import json_schema_type, webmethod
+from llama_stack_api.version import LLAMA_STACK_API_V1
+
+
+class CommonModelFields(BaseModel):
+    metadata: dict[str, Any] = Field(
+        default_factory=dict,
+        description="Any additional metadata for this model",
+    )
+
+
+@json_schema_type
+class ModelType(StrEnum):
+    """Enumeration of supported model types in Llama Stack.
+    :cvar llm: Large language model for text generation and completion
+    :cvar embedding: Embedding model for converting text to vector representations
+    :cvar rerank: Reranking model for reordering documents based on their relevance to a query
+    """
+
+    llm = "llm"
+    embedding = "embedding"
+    rerank = "rerank"
+
+
+@json_schema_type
+class Model(CommonModelFields, Resource):
+    """A model resource representing an AI model registered in Llama Stack.
+
+    :param type: The resource type, always 'model' for model resources
+    :param model_type: The type of model (LLM or embedding model)
+    :param metadata: Any additional metadata for this model
+    :param identifier: Unique identifier for this resource in llama stack
+    :param provider_resource_id: Unique identifier for this resource in the provider
+    :param provider_id: ID of the provider that owns this resource
+    """
+
+    type: Literal[ResourceType.model] = ResourceType.model
+
+    @property
+    def model_id(self) -> str:
+        return self.identifier
+
+    @property
+    def provider_model_id(self) -> str:
+        assert self.provider_resource_id is not None, "Provider resource ID must be set"
+        return self.provider_resource_id
+
+    model_config = ConfigDict(protected_namespaces=())
+
+    model_type: ModelType = Field(default=ModelType.llm)
+
+    @field_validator("provider_resource_id")
+    @classmethod
+    def validate_provider_resource_id(cls, v):
+        if v is None:
+            raise ValueError("provider_resource_id cannot be None")
+        return v
+
+
+class ModelInput(CommonModelFields):
+    model_id: str
+    provider_id: str | None = None
+    provider_model_id: str | None = None
+    model_type: ModelType | None = ModelType.llm
+    model_config = ConfigDict(protected_namespaces=())
+
+
+class ListModelsResponse(BaseModel):
+    data: list[Model]
+
+
+@json_schema_type
+class OpenAIModel(BaseModel):
+    """A model from OpenAI.
+
+    :id: The ID of the model
+    :object: The object type, which will be "model"
+    :created: The Unix timestamp in seconds when the model was created
+    :owned_by: The owner of the model
+    :custom_metadata: Llama Stack-specific metadata including model_type, provider info, and additional metadata
+    """
+
+    id: str
+    object: Literal["model"] = "model"
+    created: int
+    owned_by: str
+    custom_metadata: dict[str, Any] | None = None
+
+
+class OpenAIListModelsResponse(BaseModel):
+    data: list[OpenAIModel]
+
+
+@runtime_checkable
+@telemetry_traceable
+class Models(Protocol):
+    async def list_models(self) -> ListModelsResponse:
+        """List all models.
+
+        :returns: A ListModelsResponse.
+        """
+        ...
+
+    @webmethod(route="/models", method="GET", level=LLAMA_STACK_API_V1)
+    async def openai_list_models(self) -> OpenAIListModelsResponse:
+        """List models using the OpenAI API.
+
+        :returns: A OpenAIListModelsResponse.
+        """
+        ...
+
+    @webmethod(route="/models/{model_id:path}", method="GET", level=LLAMA_STACK_API_V1)
+    async def get_model(
+        self,
+        model_id: str,
+    ) -> Model:
+        """Get model.
+
+        Get a model by its identifier.
+
+        :param model_id: The identifier of the model to get.
+        :returns: A Model.
+        """
+        ...
+
+    @webmethod(route="/models", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
+    async def register_model(
+        self,
+        model_id: str,
+        provider_model_id: str | None = None,
+        provider_id: str | None = None,
+        metadata: dict[str, Any] | None = None,
+        model_type: ModelType | None = None,
+    ) -> Model:
+        """Register model.
+
+        Register a model.
+
+        :param model_id: The identifier of the model to register.
+        :param provider_model_id: The identifier of the model in the provider.
+        :param provider_id: The identifier of the provider.
+        :param metadata: Any additional metadata for this model.
+        :param model_type: The type of model to register.
+        :returns: A Model.
+        """
+        ...
+
+    @webmethod(route="/models/{model_id:path}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
+    async def unregister_model(
+        self,
+        model_id: str,
+    ) -> None:
+        """Unregister model.
+
+        Unregister a model.
+
+        :param model_id: The identifier of the model to unregister.
+        """
+        ...