llama-stack 0.2.21__py3-none-any.whl → 0.2.23__py3-none-any.whl

llama_stack/apis/agents/agents.py

@@ -27,6 +27,7 @@ from llama_stack.apis.inference import (
 )
 from llama_stack.apis.safety import SafetyViolation
 from llama_stack.apis.tools import ToolDef
+from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
 
 from .openai_responses import (
@@ -481,7 +482,7 @@ class Agents(Protocol):
     - Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details.
     """
 
-    @webmethod(route="/agents", method="POST", descriptive_name="create_agent")
+    @webmethod(route="/agents", method="POST", descriptive_name="create_agent", level=LLAMA_STACK_API_V1)
     async def create_agent(
         self,
         agent_config: AgentConfig,
@@ -494,7 +495,10 @@ class Agents(Protocol):
         ...
 
     @webmethod(
-        route="/agents/{agent_id}/session/{session_id}/turn", method="POST", descriptive_name="create_agent_turn"
+        route="/agents/{agent_id}/session/{session_id}/turn",
+        method="POST",
+        descriptive_name="create_agent_turn",
+        level=LLAMA_STACK_API_V1,
     )
     async def create_agent_turn(
         self,
@@ -524,6 +528,7 @@ class Agents(Protocol):
         route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume",
         method="POST",
         descriptive_name="resume_agent_turn",
+        level=LLAMA_STACK_API_V1,
     )
     async def resume_agent_turn(
         self,
@@ -549,6 +554,7 @@ class Agents(Protocol):
     @webmethod(
         route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}",
         method="GET",
+        level=LLAMA_STACK_API_V1,
     )
     async def get_agents_turn(
         self,
@@ -568,6 +574,7 @@ class Agents(Protocol):
     @webmethod(
         route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}",
         method="GET",
+        level=LLAMA_STACK_API_V1,
     )
     async def get_agents_step(
         self,
@@ -586,7 +593,12 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}/session", method="POST", descriptive_name="create_agent_session")
+    @webmethod(
+        route="/agents/{agent_id}/session",
+        method="POST",
+        descriptive_name="create_agent_session",
+        level=LLAMA_STACK_API_V1,
+    )
     async def create_agent_session(
         self,
         agent_id: str,
@@ -600,7 +612,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}/session/{session_id}", method="GET")
+    @webmethod(route="/agents/{agent_id}/session/{session_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_agents_session(
         self,
         session_id: str,
@@ -616,7 +628,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}/session/{session_id}", method="DELETE")
+    @webmethod(route="/agents/{agent_id}/session/{session_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def delete_agents_session(
         self,
         session_id: str,
@@ -629,7 +641,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}", method="DELETE")
+    @webmethod(route="/agents/{agent_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def delete_agent(
         self,
         agent_id: str,
@@ -640,7 +652,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents", method="GET")
+    @webmethod(route="/agents", method="GET", level=LLAMA_STACK_API_V1)
     async def list_agents(self, start_index: int | None = None, limit: int | None = None) -> PaginatedResponse:
         """List all agents.
 
@@ -650,7 +662,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}", method="GET")
+    @webmethod(route="/agents/{agent_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_agent(self, agent_id: str) -> Agent:
         """Describe an agent by its ID.
 
@@ -659,7 +671,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}/sessions", method="GET")
+    @webmethod(route="/agents/{agent_id}/sessions", method="GET", level=LLAMA_STACK_API_V1)
     async def list_agent_sessions(
         self,
         agent_id: str,
@@ -682,7 +694,7 @@ class Agents(Protocol):
     #
     # Both of these APIs are inherently stateful.
 
-    @webmethod(route="/openai/v1/responses/{response_id}", method="GET")
+    @webmethod(route="/openai/v1/responses/{response_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_openai_response(
         self,
         response_id: str,
@@ -694,7 +706,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses", method="POST")
+    @webmethod(route="/openai/v1/responses", method="POST", level=LLAMA_STACK_API_V1)
     async def create_openai_response(
         self,
         input: str | list[OpenAIResponseInput],
@@ -719,7 +731,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses", method="GET")
+    @webmethod(route="/openai/v1/responses", method="GET", level=LLAMA_STACK_API_V1)
     async def list_openai_responses(
         self,
         after: str | None = None,
@@ -737,7 +749,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses/{response_id}/input_items", method="GET")
+    @webmethod(route="/openai/v1/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1)
     async def list_openai_response_input_items(
         self,
         response_id: str,
@@ -759,7 +771,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses/{response_id}", method="DELETE")
+    @webmethod(route="/openai/v1/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def delete_openai_response(self, response_id: str) -> OpenAIDeleteResponseObject:
         """Delete an OpenAI response by its ID.
 

llama_stack/apis/batch_inference/batch_inference.py

@@ -17,6 +17,7 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
+from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.schema_utils import webmethod
 
 
@@ -30,7 +31,7 @@ class BatchInference(Protocol):
     including (post-training, evals, etc).
     """
 
-    @webmethod(route="/batch-inference/completion", method="POST")
+    @webmethod(route="/batch-inference/completion", method="POST", level=LLAMA_STACK_API_V1)
     async def completion(
         self,
         model: str,
@@ -50,7 +51,7 @@ class BatchInference(Protocol):
         """
         ...
 
-    @webmethod(route="/batch-inference/chat-completion", method="POST")
+    @webmethod(route="/batch-inference/chat-completion", method="POST", level=LLAMA_STACK_API_V1)
     async def chat_completion(
         self,
         model: str,

llama_stack/apis/batches/batches.py

@@ -8,6 +8,7 @@ from typing import Literal, Protocol, runtime_checkable
 
 from pydantic import BaseModel, Field
 
+from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.schema_utils import json_schema_type, webmethod
 
 try:
@@ -42,7 +43,7 @@ class Batches(Protocol):
     Note: This API is currently under active development and may undergo changes.
     """
 
-    @webmethod(route="/openai/v1/batches", method="POST")
+    @webmethod(route="/openai/v1/batches", method="POST", level=LLAMA_STACK_API_V1)
     async def create_batch(
         self,
         input_file_id: str,
@@ -62,7 +63,7 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches/{batch_id}", method="GET")
+    @webmethod(route="/openai/v1/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def retrieve_batch(self, batch_id: str) -> BatchObject:
         """Retrieve information about a specific batch.
 
@@ -71,7 +72,7 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST")
+    @webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1)
     async def cancel_batch(self, batch_id: str) -> BatchObject:
         """Cancel a batch that is in progress.
 
@@ -80,7 +81,7 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches", method="GET")
+    @webmethod(route="/openai/v1/batches", method="GET", level=LLAMA_STACK_API_V1)
     async def list_batches(
         self,
         after: str | None = None,

llama_stack/apis/benchmarks/benchmarks.py

@@ -8,6 +8,7 @@ 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
 
 
@@ -53,7 +54,8 @@ class ListBenchmarksResponse(BaseModel):
 
 @runtime_checkable
 class Benchmarks(Protocol):
-    @webmethod(route="/eval/benchmarks", method="GET")
+    @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.
 
@@ -61,7 +63,8 @@ class Benchmarks(Protocol):
         """
         ...
 
-    @webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET")
+    @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,
@@ -73,7 +76,8 @@ class Benchmarks(Protocol):
         """
         ...
 
-    @webmethod(route="/eval/benchmarks", method="POST")
+    @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,
@@ -93,3 +97,12 @@ class Benchmarks(Protocol):
         :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.
+        """
+        ...

llama_stack/apis/datasetio/datasetio.py

@@ -8,6 +8,7 @@ from typing import Any, Protocol, runtime_checkable
 
 from llama_stack.apis.common.responses import PaginatedResponse
 from llama_stack.apis.datasets import Dataset
+from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.schema_utils import webmethod
 
 
@@ -20,7 +21,7 @@ class DatasetIO(Protocol):
     # keeping for aligning with inference/safety, but this is not used
     dataset_store: DatasetStore
 
-    @webmethod(route="/datasetio/iterrows/{dataset_id:path}", method="GET")
+    @webmethod(route="/datasetio/iterrows/{dataset_id:path}", method="GET", level=LLAMA_STACK_API_V1)
     async def iterrows(
         self,
         dataset_id: str,
@@ -44,7 +45,7 @@ class DatasetIO(Protocol):
         """
         ...
 
-    @webmethod(route="/datasetio/append-rows/{dataset_id:path}", method="POST")
+    @webmethod(route="/datasetio/append-rows/{dataset_id:path}", method="POST", level=LLAMA_STACK_API_V1)
     async def append_rows(self, dataset_id: str, rows: list[dict[str, Any]]) -> None:
         """Append rows to a dataset.
 

llama_stack/apis/datasets/datasets.py

@@ -10,6 +10,7 @@ from typing import Annotated, Any, Literal, Protocol
 from pydantic import BaseModel, Field
 
 from llama_stack.apis.resource import Resource, ResourceType
+from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
 
 
@@ -145,7 +146,7 @@ class ListDatasetsResponse(BaseModel):
 
 
 class Datasets(Protocol):
-    @webmethod(route="/datasets", method="POST")
+    @webmethod(route="/datasets", method="POST", level=LLAMA_STACK_API_V1)
     async def register_dataset(
         self,
         purpose: DatasetPurpose,
@@ -214,7 +215,7 @@ class Datasets(Protocol):
         """
         ...
 
-    @webmethod(route="/datasets/{dataset_id:path}", method="GET")
+    @webmethod(route="/datasets/{dataset_id:path}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_dataset(
         self,
         dataset_id: str,
@@ -226,7 +227,7 @@ class Datasets(Protocol):
         """
         ...
 
-    @webmethod(route="/datasets", method="GET")
+    @webmethod(route="/datasets", method="GET", level=LLAMA_STACK_API_V1)
     async def list_datasets(self) -> ListDatasetsResponse:
         """List all datasets.
 
@@ -234,7 +235,7 @@ class Datasets(Protocol):
         """
         ...
 
-    @webmethod(route="/datasets/{dataset_id:path}", method="DELETE")
+    @webmethod(route="/datasets/{dataset_id:path}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def unregister_dataset(
         self,
         dataset_id: str,

llama_stack/apis/eval/eval.py

@@ -13,6 +13,7 @@ from llama_stack.apis.common.job_types import Job
 from llama_stack.apis.inference import SamplingParams, SystemMessage
 from llama_stack.apis.scoring import ScoringResult
 from llama_stack.apis.scoring_functions import ScoringFnParams
+from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
 from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
 
 
@@ -83,7 +84,8 @@ class EvaluateResponse(BaseModel):
 class Eval(Protocol):
     """Llama Stack Evaluation API for running evaluations on model and agent candidates."""
 
-    @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs", method="POST")
+    @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
+    @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs", method="POST", level=LLAMA_STACK_API_V1ALPHA)
     async def run_eval(
         self,
         benchmark_id: str,
@@ -97,7 +99,10 @@ class Eval(Protocol):
         """
         ...
 
-    @webmethod(route="/eval/benchmarks/{benchmark_id}/evaluations", method="POST")
+    @webmethod(
+        route="/eval/benchmarks/{benchmark_id}/evaluations", method="POST", level=LLAMA_STACK_API_V1, deprecated=True
+    )
+    @webmethod(route="/eval/benchmarks/{benchmark_id}/evaluations", method="POST", level=LLAMA_STACK_API_V1ALPHA)
     async def evaluate_rows(
         self,
         benchmark_id: str,
@@ -115,7 +120,10 @@ class Eval(Protocol):
         """
         ...
 
-    @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="GET")
+    @webmethod(
+        route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
+    )
+    @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="GET", level=LLAMA_STACK_API_V1ALPHA)
     async def job_status(self, benchmark_id: str, job_id: str) -> Job:
         """Get the status of a job.
 
@@ -125,7 +133,13 @@ class Eval(Protocol):
         """
         ...
 
-    @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="DELETE")
+    @webmethod(
+        route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}",
+        method="DELETE",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
+    @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
     async def job_cancel(self, benchmark_id: str, job_id: str) -> None:
         """Cancel a job.
 
@@ -134,7 +148,15 @@ class Eval(Protocol):
         """
         ...
 
-    @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result", method="GET")
+    @webmethod(
+        route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result",
+        method="GET",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
+    @webmethod(
+        route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result", method="GET", level=LLAMA_STACK_API_V1ALPHA
+    )
     async def job_result(self, benchmark_id: str, job_id: str) -> EvaluateResponse:
         """Get the result of a job.
 

llama_stack/apis/files/files.py

@@ -11,6 +11,7 @@ from fastapi import File, Form, Response, UploadFile
 from pydantic import BaseModel, Field
 
 from llama_stack.apis.common.responses import Order
+from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
 from llama_stack.schema_utils import json_schema_type, webmethod
 
@@ -104,7 +105,7 @@ class OpenAIFileDeleteResponse(BaseModel):
 @trace_protocol
 class Files(Protocol):
     # OpenAI Files API Endpoints
-    @webmethod(route="/openai/v1/files", method="POST")
+    @webmethod(route="/openai/v1/files", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_upload_file(
         self,
         file: Annotated[UploadFile, File()],
@@ -119,7 +120,7 @@ class Files(Protocol):
         The file upload should be a multipart form request with:
         - file: The File object (not file name) to be uploaded.
         - purpose: The intended purpose of the uploaded file.
-        - expires_after: Optional form values describing expiration for the file. Expected expires_after[anchor] = "created_at", expires_after[seconds] = <int>. Seconds must be between 3600 and 2592000 (1 hour to 30 days).
+        - expires_after: Optional form values describing expiration for the file. Expected expires_after[anchor] = "created_at", expires_after[seconds] = {integer}. Seconds must be between 3600 and 2592000 (1 hour to 30 days).
 
         :param file: The uploaded file object containing content and metadata (filename, content_type, etc.).
         :param purpose: The intended purpose of the uploaded file (e.g., "assistants", "fine-tune").
@@ -127,7 +128,7 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files", method="GET")
+    @webmethod(route="/openai/v1/files", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_files(
         self,
         after: str | None = None,
@@ -146,7 +147,7 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}", method="GET")
+    @webmethod(route="/openai/v1/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_file(
         self,
         file_id: str,
@@ -159,7 +160,7 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}", method="DELETE")
+    @webmethod(route="/openai/v1/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def openai_delete_file(
         self,
         file_id: str,
@@ -172,7 +173,7 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}/content", method="GET")
+    @webmethod(route="/openai/v1/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_file_content(
         self,
         file_id: str,

llama_stack/apis/inference/inference.py

@@ -21,6 +21,7 @@ from llama_stack.apis.common.content_types import ContentDelta, InterleavedConte
 from llama_stack.apis.common.responses import Order
 from llama_stack.apis.models import Model
 from llama_stack.apis.telemetry import MetricResponseMixin
+from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.models.llama.datatypes import (
     BuiltinTool,
     StopReason,
@@ -913,6 +914,7 @@ class OpenAIEmbeddingData(BaseModel):
     """
 
     object: Literal["embedding"] = "embedding"
+    # TODO: consider dropping str and using openai.types.embeddings.Embedding instead of OpenAIEmbeddingData
     embedding: list[float] | str
     index: int
 
@@ -1026,7 +1028,7 @@ class InferenceProvider(Protocol):
 
     model_store: ModelStore | None = None
 
-    @webmethod(route="/inference/completion", method="POST")
+    @webmethod(route="/inference/completion", method="POST", level=LLAMA_STACK_API_V1)
     async def completion(
         self,
         model_id: str,
@@ -1049,7 +1051,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/inference/batch-completion", method="POST", experimental=True)
+    @webmethod(route="/inference/batch-completion", method="POST", experimental=True, level=LLAMA_STACK_API_V1)
     async def batch_completion(
         self,
         model_id: str,
@@ -1070,7 +1072,7 @@ class InferenceProvider(Protocol):
         raise NotImplementedError("Batch completion is not implemented")
         return  # this is so mypy's safe-super rule will consider the method concrete
 
-    @webmethod(route="/inference/chat-completion", method="POST")
+    @webmethod(route="/inference/chat-completion", method="POST", level=LLAMA_STACK_API_V1)
     async def chat_completion(
         self,
         model_id: str,
@@ -1110,7 +1112,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/inference/batch-chat-completion", method="POST", experimental=True)
+    @webmethod(route="/inference/batch-chat-completion", method="POST", experimental=True, level=LLAMA_STACK_API_V1)
     async def batch_chat_completion(
         self,
         model_id: str,
@@ -1135,7 +1137,7 @@ class InferenceProvider(Protocol):
         raise NotImplementedError("Batch chat completion is not implemented")
         return  # this is so mypy's safe-super rule will consider the method concrete
 
-    @webmethod(route="/inference/embeddings", method="POST")
+    @webmethod(route="/inference/embeddings", method="POST", level=LLAMA_STACK_API_V1)
     async def embeddings(
         self,
         model_id: str,
@@ -1155,7 +1157,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/inference/rerank", method="POST", experimental=True)
+    @webmethod(route="/inference/rerank", method="POST", experimental=True, level=LLAMA_STACK_API_V1)
     async def rerank(
         self,
         model: str,
@@ -1174,7 +1176,7 @@ class InferenceProvider(Protocol):
         raise NotImplementedError("Reranking is not implemented")
         return  # this is so mypy's safe-super rule will consider the method concrete
 
-    @webmethod(route="/openai/v1/completions", method="POST")
+    @webmethod(route="/openai/v1/completions", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_completion(
         self,
         # Standard OpenAI completion parameters
@@ -1225,7 +1227,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/chat/completions", method="POST")
+    @webmethod(route="/openai/v1/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_chat_completion(
         self,
         model: str,
@@ -1281,7 +1283,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/embeddings", method="POST")
+    @webmethod(route="/openai/v1/embeddings", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_embeddings(
         self,
         model: str,
@@ -1310,7 +1312,7 @@ class Inference(InferenceProvider):
     - Embedding models: these models generate embeddings to be used for semantic search.
     """
 
-    @webmethod(route="/openai/v1/chat/completions", method="GET")
+    @webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1)
     async def list_chat_completions(
         self,
         after: str | None = None,
@@ -1328,7 +1330,7 @@ class Inference(InferenceProvider):
         """
         raise NotImplementedError("List chat completions is not implemented")
 
-    @webmethod(route="/openai/v1/chat/completions/{completion_id}", method="GET")
+    @webmethod(route="/openai/v1/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
         """Describe a chat completion by its ID.
 

llama_stack/apis/inspect/inspect.py

@@ -8,6 +8,7 @@ from typing import Protocol, runtime_checkable
 
 from pydantic import BaseModel
 
+from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.providers.datatypes import HealthStatus
 from llama_stack.schema_utils import json_schema_type, webmethod
 
@@ -57,7 +58,7 @@ class ListRoutesResponse(BaseModel):
 
 @runtime_checkable
 class Inspect(Protocol):
-    @webmethod(route="/inspect/routes", method="GET")
+    @webmethod(route="/inspect/routes", method="GET", level=LLAMA_STACK_API_V1)
     async def list_routes(self) -> ListRoutesResponse:
         """List all available API routes with their methods and implementing providers.
 
@@ -65,7 +66,7 @@ class Inspect(Protocol):
         """
         ...
 
-    @webmethod(route="/health", method="GET")
+    @webmethod(route="/health", method="GET", level=LLAMA_STACK_API_V1)
     async def health(self) -> HealthInfo:
         """Get the current health status of the service.
 
@@ -73,7 +74,7 @@ class Inspect(Protocol):
         """
         ...
 
-    @webmethod(route="/version", method="GET")
+    @webmethod(route="/version", method="GET", level=LLAMA_STACK_API_V1)
     async def version(self) -> VersionInfo:
         """Get the version of the service.