Merge remote-tracking branch 'origin/main' into resp_branching

llama_stack/apis/agents/agents.py

@@ -472,20 +472,23 @@ class AgentStepResponse(BaseModel):
 
 @runtime_checkable
 class Agents(Protocol):
-    """Agents API for creating and interacting with agentic systems.
+    """Agents
 
-    Main functionalities provided by this API:
-    - Create agents with specific instructions and ability to use tools.
-    - Interactions with agents are grouped into sessions ("threads"), and each interaction is called a "turn".
-    - Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
-    - Agents can be provided with various shields (see the Safety API for more details).
-    - Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details.
-    """
+    APIs for creating and interacting with agentic systems."""
 
     @webmethod(
-        route="/agents", method="POST", descriptive_name="create_agent", deprecated=True, level=LLAMA_STACK_API_V1
+        route="/agents",
+        method="POST",
+        descriptive_name="create_agent",
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
+    @webmethod(
+        route="/agents",
+        method="POST",
+        descriptive_name="create_agent",
+        level=LLAMA_STACK_API_V1ALPHA,
     )
-    @webmethod(route="/agents", method="POST", descriptive_name="create_agent", level=LLAMA_STACK_API_V1ALPHA)
     async def create_agent(
         self,
         agent_config: AgentConfig,
@@ -648,8 +651,17 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}/session/{session_id}", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
-    @webmethod(route="/agents/{agent_id}/session/{session_id}", method="GET", level=LLAMA_STACK_API_V1ALPHA)
+    @webmethod(
+        route="/agents/{agent_id}/session/{session_id}",
+        method="GET",
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
+    @webmethod(
+        route="/agents/{agent_id}/session/{session_id}",
+        method="GET",
+        level=LLAMA_STACK_API_V1ALPHA,
+    )
     async def get_agents_session(
         self,
         session_id: str,
@@ -666,9 +678,16 @@ class Agents(Protocol):
         ...
 
     @webmethod(
-        route="/agents/{agent_id}/session/{session_id}", method="DELETE", deprecated=True, level=LLAMA_STACK_API_V1
+        route="/agents/{agent_id}/session/{session_id}",
+        method="DELETE",
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
+    @webmethod(
+        route="/agents/{agent_id}/session/{session_id}",
+        method="DELETE",
+        level=LLAMA_STACK_API_V1ALPHA,
     )
-    @webmethod(route="/agents/{agent_id}/session/{session_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
     async def delete_agents_session(
         self,
         session_id: str,
@@ -681,7 +700,12 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}", method="DELETE", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(
+        route="/agents/{agent_id}",
+        method="DELETE",
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
     @webmethod(route="/agents/{agent_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
     async def delete_agent(
         self,
@@ -704,7 +728,12 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(
+        route="/agents/{agent_id}",
+        method="GET",
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
     @webmethod(route="/agents/{agent_id}", method="GET", level=LLAMA_STACK_API_V1ALPHA)
     async def get_agent(self, agent_id: str) -> Agent:
         """Describe an agent by its ID.
@@ -714,7 +743,12 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/agents/{agent_id}/sessions", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(
+        route="/agents/{agent_id}/sessions",
+        method="GET",
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
     @webmethod(route="/agents/{agent_id}/sessions", method="GET", level=LLAMA_STACK_API_V1ALPHA)
     async def list_agent_sessions(
         self,
@@ -793,7 +827,11 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(
+        route="/responses/{response_id}/input_items",
+        method="GET",
+        level=LLAMA_STACK_API_V1,
+    )
     async def list_openai_response_input_items(
         self,
         response_id: str,

llama_stack/apis/datasetio/datasetio.py

@@ -8,7 +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.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1BETA
 from llama_stack.schema_utils import webmethod
 
 
@@ -21,7 +21,8 @@ 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", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasetio/iterrows/{dataset_id:path}", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasetio/iterrows/{dataset_id:path}", method="GET", level=LLAMA_STACK_API_V1BETA)
     async def iterrows(
         self,
         dataset_id: str,
@@ -45,7 +46,10 @@ class DatasetIO(Protocol):
         """
         ...
 
-    @webmethod(route="/datasetio/append-rows/{dataset_id:path}", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(
+        route="/datasetio/append-rows/{dataset_id:path}", method="POST", deprecated=True, level=LLAMA_STACK_API_V1
+    )
+    @webmethod(route="/datasetio/append-rows/{dataset_id:path}", method="POST", level=LLAMA_STACK_API_V1BETA)
     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

@@ -10,7 +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.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1BETA
 from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
 
 
@@ -146,7 +146,8 @@ class ListDatasetsResponse(BaseModel):
 
 
 class Datasets(Protocol):
-    @webmethod(route="/datasets", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasets", method="POST", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasets", method="POST", level=LLAMA_STACK_API_V1BETA)
     async def register_dataset(
         self,
         purpose: DatasetPurpose,
@@ -215,7 +216,8 @@ class Datasets(Protocol):
         """
         ...
 
-    @webmethod(route="/datasets/{dataset_id:path}", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasets/{dataset_id:path}", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasets/{dataset_id:path}", method="GET", level=LLAMA_STACK_API_V1BETA)
     async def get_dataset(
         self,
         dataset_id: str,
@@ -227,7 +229,8 @@ class Datasets(Protocol):
         """
         ...
 
-    @webmethod(route="/datasets", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasets", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasets", method="GET", level=LLAMA_STACK_API_V1BETA)
     async def list_datasets(self) -> ListDatasetsResponse:
         """List all datasets.
 
@@ -235,7 +238,8 @@ class Datasets(Protocol):
         """
         ...
 
-    @webmethod(route="/datasets/{dataset_id:path}", method="DELETE", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasets/{dataset_id:path}", method="DELETE", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(route="/datasets/{dataset_id:path}", method="DELETE", level=LLAMA_STACK_API_V1BETA)
     async def unregister_dataset(
         self,
         dataset_id: str,

llama_stack/apis/inference/inference.py

@@ -1006,28 +1006,6 @@ class InferenceProvider(Protocol):
 
     model_store: ModelStore | None = None
 
-    async def completion(
-        self,
-        model_id: str,
-        content: InterleavedContent,
-        sampling_params: SamplingParams | None = None,
-        response_format: ResponseFormat | None = None,
-        stream: bool | None = False,
-        logprobs: LogProbConfig | None = None,
-    ) -> CompletionResponse | AsyncIterator[CompletionResponseStreamChunk]:
-        """Generate a completion for the given content using the specified model.
-
-        :param model_id: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
-        :param content: The content to generate a completion for.
-        :param sampling_params: (Optional) Parameters to control the sampling strategy.
-        :param response_format: (Optional) Grammar specification for guided (structured) decoding.
-        :param stream: (Optional) If True, generate an SSE event stream of the response. Defaults to False.
-        :param logprobs: (Optional) If specified, log probabilities for each token position will be returned.
-        :returns: If stream=False, returns a CompletionResponse with the full completion.
-                 If stream=True, returns an SSE event stream of CompletionResponseStreamChunk.
-        """
-        ...
-
     async def chat_completion(
         self,
         model_id: str,

llama_stack/apis/telemetry/telemetry.py

@@ -16,7 +16,7 @@ from typing import (
 
 from pydantic import BaseModel, Field
 
-from llama_stack.apis.version import LLAMA_STACK_API_V1
+from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
 from llama_stack.models.llama.datatypes import Primitive
 from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
 
@@ -426,7 +426,14 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/traces", method="POST", required_scope=REQUIRED_SCOPE, level=LLAMA_STACK_API_V1)
+    @webmethod(
+        route="/telemetry/traces",
+        method="POST",
+        required_scope=REQUIRED_SCOPE,
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
+    @webmethod(route="/telemetry/traces", method="POST", required_scope=REQUIRED_SCOPE, level=LLAMA_STACK_API_V1ALPHA)
     async def query_traces(
         self,
         attribute_filters: list[QueryCondition] | None = None,
@@ -445,7 +452,17 @@ class Telemetry(Protocol):
         ...
 
     @webmethod(
-        route="/telemetry/traces/{trace_id:path}", method="GET", required_scope=REQUIRED_SCOPE, level=LLAMA_STACK_API_V1
+        route="/telemetry/traces/{trace_id:path}",
+        method="GET",
+        required_scope=REQUIRED_SCOPE,
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
+    @webmethod(
+        route="/telemetry/traces/{trace_id:path}",
+        method="GET",
+        required_scope=REQUIRED_SCOPE,
+        level=LLAMA_STACK_API_V1ALPHA,
     )
     async def get_trace(self, trace_id: str) -> Trace:
         """Get a trace by its ID.
@@ -459,8 +476,15 @@ class Telemetry(Protocol):
         route="/telemetry/traces/{trace_id:path}/spans/{span_id:path}",
         method="GET",
         required_scope=REQUIRED_SCOPE,
+        deprecated=True,
         level=LLAMA_STACK_API_V1,
     )
+    @webmethod(
+        route="/telemetry/traces/{trace_id:path}/spans/{span_id:path}",
+        method="GET",
+        required_scope=REQUIRED_SCOPE,
+        level=LLAMA_STACK_API_V1ALPHA,
+    )
     async def get_span(self, trace_id: str, span_id: str) -> Span:
         """Get a span by its ID.
 
@@ -473,9 +497,16 @@ class Telemetry(Protocol):
     @webmethod(
         route="/telemetry/spans/{span_id:path}/tree",
         method="POST",
+        deprecated=True,
         required_scope=REQUIRED_SCOPE,
         level=LLAMA_STACK_API_V1,
     )
+    @webmethod(
+        route="/telemetry/spans/{span_id:path}/tree",
+        method="POST",
+        required_scope=REQUIRED_SCOPE,
+        level=LLAMA_STACK_API_V1ALPHA,
+    )
     async def get_span_tree(
         self,
         span_id: str,
@@ -491,7 +522,14 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/spans", method="POST", required_scope=REQUIRED_SCOPE, level=LLAMA_STACK_API_V1)
+    @webmethod(
+        route="/telemetry/spans",
+        method="POST",
+        required_scope=REQUIRED_SCOPE,
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
+    @webmethod(route="/telemetry/spans", method="POST", required_scope=REQUIRED_SCOPE, level=LLAMA_STACK_API_V1ALPHA)
     async def query_spans(
         self,
         attribute_filters: list[QueryCondition],
@@ -507,7 +545,8 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/spans/export", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/telemetry/spans/export", method="POST", deprecated=True, level=LLAMA_STACK_API_V1)
+    @webmethod(route="/telemetry/spans/export", method="POST", level=LLAMA_STACK_API_V1ALPHA)
     async def save_spans_to_dataset(
         self,
         attribute_filters: list[QueryCondition],
@@ -525,7 +564,17 @@ class Telemetry(Protocol):
         ...
 
     @webmethod(
-        route="/telemetry/metrics/{metric_name}", method="POST", required_scope=REQUIRED_SCOPE, level=LLAMA_STACK_API_V1
+        route="/telemetry/metrics/{metric_name}",
+        method="POST",
+        required_scope=REQUIRED_SCOPE,
+        deprecated=True,
+        level=LLAMA_STACK_API_V1,
+    )
+    @webmethod(
+        route="/telemetry/metrics/{metric_name}",
+        method="POST",
+        required_scope=REQUIRED_SCOPE,
+        level=LLAMA_STACK_API_V1ALPHA,
     )
     async def query_metrics(
         self,