Merge branch 'main' into pr1573

llama_stack/apis/agents/agents.py

@@ -370,7 +370,7 @@ class AgentTurnResumeRequest(BaseModel):
     agent_id: str
     session_id: str
     turn_id: str
-    tool_responses: Union[List[ToolResponse], List[ToolResponseMessage]]
+    tool_responses: List[ToolResponse]
     stream: Optional[bool] = False
 
 
@@ -449,7 +449,7 @@ class Agents(Protocol):
         agent_id: str,
         session_id: str,
         turn_id: str,
-        tool_responses: Union[List[ToolResponse], List[ToolResponseMessage]],
+        tool_responses: List[ToolResponse],
         stream: Optional[bool] = False,
     ) -> Union[Turn, AsyncIterator[AgentTurnResponseStreamChunk]]:
         """Resume an agent turn with executed tool call responses.
@@ -460,7 +460,6 @@ class Agents(Protocol):
         :param session_id: The ID of the session to resume.
         :param turn_id: The ID of the turn to resume.
         :param tool_responses: The tool call responses to resume the turn with.
-            NOTE: ToolResponseMessage will be deprecated. Use ToolResponse.
         :param stream: Whether to stream the response.
         :returns: A Turn object if stream is False, otherwise an AsyncIterator of AgentTurnResponseStreamChunk objects.
         """

llama_stack/apis/telemetry/telemetry.py

@@ -96,6 +96,13 @@ class MetricEvent(EventCommon):
     unit: str
 
 
+@json_schema_type
+class MetricInResponse(BaseModel):
+    metric: str
+    value: Union[int, float]
+    unit: Optional[str] = None
+
+
 # This is a short term solution to allow inference API to return metrics
 # The ideal way to do this is to have a way for all response types to include metrics
 # and all metric events logged to the telemetry API to be inlcuded with the response
@@ -117,7 +124,7 @@ class MetricEvent(EventCommon):
 
 
 class MetricResponseMixin(BaseModel):
-    metrics: Optional[List[MetricEvent]] = None
+    metrics: Optional[List[MetricInResponse]] = None
 
 
 @json_schema_type