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/providers/remote/inference/watsonx/watsonx.py

@@ -9,8 +9,9 @@ from typing import Any
 
 import litellm
 import requests
-
-from llama_stack.apis.inference.inference import (
+from llama_stack_api import (
+    Model,
+    ModelType,
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
     OpenAIChatCompletionRequestWithExtraBody,
@@ -20,8 +21,7 @@ from llama_stack.apis.inference.inference import (
     OpenAIEmbeddingsRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
-from llama_stack.apis.models import Model
-from llama_stack.apis.models.models import ModelType
+
 from llama_stack.core.telemetry.tracing import get_current_span
 from llama_stack.log import get_logger
 from llama_stack.providers.remote.inference.watsonx.config import WatsonXConfig
@@ -238,7 +238,8 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin):
         )
 
         # Convert response to OpenAI format
-        from llama_stack.apis.inference import OpenAIEmbeddingUsage
+        from llama_stack_api import OpenAIEmbeddingUsage
+
         from llama_stack.providers.utils.inference.litellm_openai_mixin import b64_encode_openai_embeddings_response
 
         data = b64_encode_openai_embeddings_response(response.data, params.encoding_format)