Merge branch 'main' into add-batches

llama_stack/apis/agents/agents.py

@@ -706,6 +706,7 @@ class Agents(Protocol):
         temperature: float | None = None,
         text: OpenAIResponseText | None = None,
         tools: list[OpenAIResponseInputTool] | None = None,
+        include: list[str] | None = None,
         max_infer_iters: int | None = 10,  # this is an extension to the OpenAI API
     ) -> OpenAIResponseObject | AsyncIterator[OpenAIResponseObjectStream]:
         """Create a new OpenAI response.
@@ -713,6 +714,7 @@ class Agents(Protocol):
         :param input: Input message(s) to create the response.
         :param model: The underlying LLM used for completions.
         :param previous_response_id: (Optional) if specified, the new response will be a continuation of the previous response. This can be used to easily fork-off new responses from existing responses.
+        :param include: (Optional) Additional fields to include in the response.
         :returns: An OpenAIResponseObject.
         """
         ...

llama_stack/apis/agents/openai_responses.py

@@ -170,6 +170,23 @@ class OpenAIResponseOutputMessageWebSearchToolCall(BaseModel):
     type: Literal["web_search_call"] = "web_search_call"
 
 
+class OpenAIResponseOutputMessageFileSearchToolCallResults(BaseModel):
+    """Search results returned by the file search operation.
+
+    :param attributes: (Optional) Key-value attributes associated with the file
+    :param file_id: Unique identifier of the file containing the result
+    :param filename: Name of the file containing the result
+    :param score: Relevance score for this search result (between 0 and 1)
+    :param text: Text content of the search result
+    """
+
+    attributes: dict[str, Any]
+    file_id: str
+    filename: str
+    score: float
+    text: str
+
+
 @json_schema_type
 class OpenAIResponseOutputMessageFileSearchToolCall(BaseModel):
     """File search tool call output message for OpenAI responses.
@@ -185,7 +202,7 @@ class OpenAIResponseOutputMessageFileSearchToolCall(BaseModel):
     queries: list[str]
     status: str
     type: Literal["file_search_call"] = "file_search_call"
-    results: list[dict[str, Any]] | None = None
+    results: list[OpenAIResponseOutputMessageFileSearchToolCallResults] | None = None
 
 
 @json_schema_type

llama_stack/apis/common/errors.py

@@ -67,5 +67,14 @@ class SessionNotFoundError(ValueError):
 class ConflictError(ValueError):
     """raised when an operation cannot be performed due to a conflict with the current state"""
 
-    def __init__(self, message: str) -> None:
+    pass
+
+
+class ModelTypeError(TypeError):
+    """raised when a model is present but not the correct type"""
+
+    def __init__(self, model_name: str, model_type: str, expected_model_type: str) -> None:
+        message = (
+            f"Model '{model_name}' is of type '{model_type}' rather than the expected type '{expected_model_type}'"
+        )
         super().__init__(message)