chore(package): migrate to src/ layout (#3920)

Migrates package structure to src/ layout following Python packaging
best practices.

All code moved from `llama_stack/` to `src/llama_stack/`. Public API
unchanged - imports remain `import llama_stack.*`.

Updated build configs, pre-commit hooks, scripts, and GitHub workflows
accordingly. All hooks pass, package builds cleanly.

**Developer note**: Reinstall after pulling: `pip install -e .`

src/llama_stack/apis/benchmarks/benchmarks.py

@@ -0,0 +1,108 @@
+# 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, Literal, Protocol, runtime_checkable
+
+from pydantic import BaseModel, Field
+
+from llama_stack.apis.resource import Resource, ResourceType
+from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
+from llama_stack.schema_utils import json_schema_type, webmethod
+
+
+class CommonBenchmarkFields(BaseModel):
+    dataset_id: str
+    scoring_functions: list[str]
+    metadata: dict[str, Any] = Field(
+        default_factory=dict,
+        description="Metadata for this evaluation task",
+    )
+
+
+@json_schema_type
+class Benchmark(CommonBenchmarkFields, Resource):
+    """A benchmark resource for evaluating model performance.
+
+    :param dataset_id: Identifier of the dataset to use for the benchmark evaluation
+    :param scoring_functions: List of scoring function identifiers to apply during evaluation
+    :param metadata: Metadata for this evaluation task
+    :param type: The resource type, always benchmark
+    """
+
+    type: Literal[ResourceType.benchmark] = ResourceType.benchmark
+
+    @property
+    def benchmark_id(self) -> str:
+        return self.identifier
+
+    @property
+    def provider_benchmark_id(self) -> str | None:
+        return self.provider_resource_id
+
+
+class BenchmarkInput(CommonBenchmarkFields, BaseModel):
+    benchmark_id: str
+    provider_id: str | None = None
+    provider_benchmark_id: str | None = None
+
+
+class ListBenchmarksResponse(BaseModel):
+    data: list[Benchmark]
+
+
+@runtime_checkable
+class Benchmarks(Protocol):
+    @webmethod(route="/eval/benchmarks", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
+    @webmethod(route="/eval/benchmarks", method="GET", level=LLAMA_STACK_API_V1ALPHA)
+    async def list_benchmarks(self) -> ListBenchmarksResponse:
+        """List all benchmarks.
+
+        :returns: A ListBenchmarksResponse.
+        """
+        ...
+
+    @webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
+    @webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET", level=LLAMA_STACK_API_V1ALPHA)
+    async def get_benchmark(
+        self,
+        benchmark_id: str,
+    ) -> Benchmark:
+        """Get a benchmark by its ID.
+
+        :param benchmark_id: The ID of the benchmark to get.
+        :returns: A Benchmark.
+        """
+        ...
+
+    @webmethod(route="/eval/benchmarks", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
+    @webmethod(route="/eval/benchmarks", method="POST", level=LLAMA_STACK_API_V1ALPHA)
+    async def register_benchmark(
+        self,
+        benchmark_id: str,
+        dataset_id: str,
+        scoring_functions: list[str],
+        provider_benchmark_id: str | None = None,
+        provider_id: str | None = None,
+        metadata: dict[str, Any] | None = None,
+    ) -> None:
+        """Register a benchmark.
+
+        :param benchmark_id: The ID of the benchmark to register.
+        :param dataset_id: The ID of the dataset to use for the benchmark.
+        :param scoring_functions: The scoring functions to use for the benchmark.
+        :param provider_benchmark_id: The ID of the provider benchmark to use for the benchmark.
+        :param provider_id: The ID of the provider to use for the benchmark.
+        :param metadata: The metadata to use for the benchmark.
+        """
+        ...
+
+    @webmethod(route="/eval/benchmarks/{benchmark_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
+    @webmethod(route="/eval/benchmarks/{benchmark_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
+    async def unregister_benchmark(self, benchmark_id: str) -> None:
+        """Unregister a benchmark.
+
+        :param benchmark_id: The ID of the benchmark to unregister.
+        """
+        ...