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/providers.py

@@ -0,0 +1,69 @@
+# 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 typing import Any, Protocol, runtime_checkable
+
+from pydantic import BaseModel
+
+from llama_stack_api.datatypes import HealthResponse
+from llama_stack_api.schema_utils import json_schema_type, webmethod
+from llama_stack_api.version import LLAMA_STACK_API_V1
+
+
+@json_schema_type
+class ProviderInfo(BaseModel):
+    """Information about a registered provider including its configuration and health status.
+
+    :param api: The API name this provider implements
+    :param provider_id: Unique identifier for the provider
+    :param provider_type: The type of provider implementation
+    :param config: Configuration parameters for the provider
+    :param health: Current health status of the provider
+    """
+
+    api: str
+    provider_id: str
+    provider_type: str
+    config: dict[str, Any]
+    health: HealthResponse
+
+
+class ListProvidersResponse(BaseModel):
+    """Response containing a list of all available providers.
+
+    :param data: List of provider information objects
+    """
+
+    data: list[ProviderInfo]
+
+
+@runtime_checkable
+class Providers(Protocol):
+    """Providers
+
+    Providers API for inspecting, listing, and modifying providers and their configurations.
+    """
+
+    @webmethod(route="/providers", method="GET", level=LLAMA_STACK_API_V1)
+    async def list_providers(self) -> ListProvidersResponse:
+        """List providers.
+
+        List all available providers.
+
+        :returns: A ListProvidersResponse containing information about all providers.
+        """
+        ...
+
+    @webmethod(route="/providers/{provider_id}", method="GET", level=LLAMA_STACK_API_V1)
+    async def inspect_provider(self, provider_id: str) -> ProviderInfo:
+        """Get provider.
+
+        Get detailed information about a specific provider.
+
+        :param provider_id: The ID of the provider to inspect.
+        :returns: A ProviderInfo object containing the provider's details.
+        """
+        ...