Items

TResponse module-attribute

TResponse = Response

A type alias for the Response type from the OpenAI SDK.

TResponseInputItem module-attribute

TResponseInputItem = ResponseInputItemParam

A type alias for the ResponseInputItemParam type from the OpenAI SDK.

TResponseOutputItem module-attribute

TResponseOutputItem = ResponseOutputItem

A type alias for the ResponseOutputItem type from the OpenAI SDK.

TResponseStreamEvent module-attribute

TResponseStreamEvent = ResponseStreamEvent

A type alias for the ResponseStreamEvent type from the OpenAI SDK.

ToolCallItemTypes module-attribute

ToolCallItemTypes: TypeAlias = Union[
    ResponseFunctionToolCall,
    ResponseComputerToolCall,
    ResponseFileSearchToolCall,
    ResponseFunctionWebSearch,
]

A type that represents a tool call item.

RunItem module-attribute

RunItem: TypeAlias = Union[
    MessageOutputItem,
    HandoffCallItem,
    HandoffOutputItem,
    ToolCallItem,
    ToolCallOutputItem,
    ReasoningItem,
]

An item generated by an agent.

RunItemBase dataclass

Bases: Generic[T], ABC

Source code in src/agents/items.py

@dataclass
class RunItemBase(Generic[T], abc.ABC):
    agent: Agent[Any]
    """The agent whose run caused this item to be generated."""

    raw_item: T
    """The raw Responses item from the run. This will always be a either an output item (i.e.
    `openai.types.responses.ResponseOutputItem` or an input item
    (i.e. `openai.types.responses.ResponseInputItemParam`).
    """

    def to_input_item(self) -> TResponseInputItem:
        """Converts this item into an input item suitable for passing to the model."""
        if isinstance(self.raw_item, dict):
            # We know that input items are dicts, so we can ignore the type error
            return self.raw_item  # type: ignore
        elif isinstance(self.raw_item, BaseModel):
            # All output items are Pydantic models that can be converted to input items.
            return self.raw_item.model_dump(exclude_unset=True)  # type: ignore
        else:
            raise AgentsException(f"Unexpected raw item type: {type(self.raw_item)}")

agent instance-attribute

agent: Agent[Any]

The agent whose run caused this item to be generated.

raw_item instance-attribute

raw_item: T

The raw Responses item from the run. This will always be a either an output item (i.e. openai.types.responses.ResponseOutputItem or an input item (i.e. openai.types.responses.ResponseInputItemParam).

to_input_item

to_input_item() -> TResponseInputItem

Converts this item into an input item suitable for passing to the model.

Source code in src/agents/items.py

def to_input_item(self) -> TResponseInputItem:
    """Converts this item into an input item suitable for passing to the model."""
    if isinstance(self.raw_item, dict):
        # We know that input items are dicts, so we can ignore the type error
        return self.raw_item  # type: ignore
    elif isinstance(self.raw_item, BaseModel):
        # All output items are Pydantic models that can be converted to input items.
        return self.raw_item.model_dump(exclude_unset=True)  # type: ignore
    else:
        raise AgentsException(f"Unexpected raw item type: {type(self.raw_item)}")

MessageOutputItem dataclass

Bases: RunItemBase[ResponseOutputMessage]

Represents a message from the LLM.

Source code in src/agents/items.py

@dataclass
class MessageOutputItem(RunItemBase[ResponseOutputMessage]):
    """Represents a message from the LLM."""

    raw_item: ResponseOutputMessage
    """The raw response output message."""

    type: Literal["message_output_item"] = "message_output_item"

raw_item instance-attribute

raw_item: ResponseOutputMessage

The raw response output message.

HandoffCallItem dataclass

Bases: RunItemBase[ResponseFunctionToolCall]

Represents a tool call for a handoff from one agent to another.

Source code in src/agents/items.py

@dataclass
class HandoffCallItem(RunItemBase[ResponseFunctionToolCall]):
    """Represents a tool call for a handoff from one agent to another."""

    raw_item: ResponseFunctionToolCall
    """The raw response function tool call that represents the handoff."""

    type: Literal["handoff_call_item"] = "handoff_call_item"

raw_item instance-attribute

raw_item: ResponseFunctionToolCall

The raw response function tool call that represents the handoff.

HandoffOutputItem dataclass

Bases: RunItemBase[TResponseInputItem]

Represents the output of a handoff.

Source code in src/agents/items.py

@dataclass
class HandoffOutputItem(RunItemBase[TResponseInputItem]):
    """Represents the output of a handoff."""

    raw_item: TResponseInputItem
    """The raw input item that represents the handoff taking place."""

    source_agent: Agent[Any]
    """The agent that made the handoff."""

    target_agent: Agent[Any]
    """The agent that is being handed off to."""

    type: Literal["handoff_output_item"] = "handoff_output_item"

raw_item instance-attribute

raw_item: TResponseInputItem

The raw input item that represents the handoff taking place.

source_agent instance-attribute

source_agent: Agent[Any]

The agent that made the handoff.

target_agent instance-attribute

target_agent: Agent[Any]

The agent that is being handed off to.

ToolCallItem dataclass

Bases: RunItemBase[ToolCallItemTypes]

Represents a tool call e.g. a function call or computer action call.

Source code in src/agents/items.py

@dataclass
class ToolCallItem(RunItemBase[ToolCallItemTypes]):
    """Represents a tool call e.g. a function call or computer action call."""

    raw_item: ToolCallItemTypes
    """The raw tool call item."""

    type: Literal["tool_call_item"] = "tool_call_item"

raw_item instance-attribute

raw_item: ToolCallItemTypes

The raw tool call item.

ToolCallOutputItem dataclass

Bases: RunItemBase[Union[FunctionCallOutput, ComputerCallOutput]]

Represents the output of a tool call.

Source code in src/agents/items.py

@dataclass
class ToolCallOutputItem(RunItemBase[Union[FunctionCallOutput, ComputerCallOutput]]):
    """Represents the output of a tool call."""

    raw_item: FunctionCallOutput | ComputerCallOutput
    """The raw item from the model."""

    output: str
    """The output of the tool call."""

    type: Literal["tool_call_output_item"] = "tool_call_output_item"

raw_item instance-attribute

raw_item: FunctionCallOutput | ComputerCallOutput

The raw item from the model.

output instance-attribute

output: str

The output of the tool call.

ReasoningItem dataclass

Bases: RunItemBase[ResponseReasoningItem]

Represents a reasoning item.

Source code in src/agents/items.py

@dataclass
class ReasoningItem(RunItemBase[ResponseReasoningItem]):
    """Represents a reasoning item."""

    raw_item: ResponseReasoningItem
    """The raw reasoning item."""

    type: Literal["reasoning_item"] = "reasoning_item"

raw_item instance-attribute

raw_item: ResponseReasoningItem

The raw reasoning item.

ModelResponse dataclass

Source code in src/agents/items.py

@dataclass
class ModelResponse:
    output: list[TResponseOutputItem]
    """A list of outputs (messages, tool calls, etc) generated by the model"""

    usage: Usage
    """The usage information for the response."""

    referenceable_id: str | None
    """An ID for the response which can be used to refer to the response in subsequent calls to the
    model. Not supported by all model providers.
    """

    def to_input_items(self) -> list[TResponseInputItem]:
        """Convert the output into a list of input items suitable for passing to the model."""
        # We happen to know that the shape of the Pydantic output items are the same as the
        # equivalent TypedDict input items, so we can just convert each one.
        # This is also tested via unit tests.
        return [it.model_dump(exclude_unset=True) for it in self.output]  # type: ignore

output instance-attribute

output: list[TResponseOutputItem]

A list of outputs (messages, tool calls, etc) generated by the model

usage instance-attribute

usage: Usage

The usage information for the response.

referenceable_id instance-attribute

referenceable_id: str | None

An ID for the response which can be used to refer to the response in subsequent calls to the model. Not supported by all model providers.

to_input_items

to_input_items() -> list[TResponseInputItem]

Convert the output into a list of input items suitable for passing to the model.

Source code in src/agents/items.py

def to_input_items(self) -> list[TResponseInputItem]:
    """Convert the output into a list of input items suitable for passing to the model."""
    # We happen to know that the shape of the Pydantic output items are the same as the
    # equivalent TypedDict input items, so we can just convert each one.
    # This is also tested via unit tests.
    return [it.model_dump(exclude_unset=True) for it in self.output]  # type: ignore

ItemHelpers

Source code in src/agents/items.py

class ItemHelpers:
    @classmethod
    def extract_last_content(cls, message: TResponseOutputItem) -> str:
        """Extracts the last text content or refusal from a message."""
        if not isinstance(message, ResponseOutputMessage):
            return ""

        last_content = message.content[-1]
        if isinstance(last_content, ResponseOutputText):
            return last_content.text
        elif isinstance(last_content, ResponseOutputRefusal):
            return last_content.refusal
        else:
            raise ModelBehaviorError(f"Unexpected content type: {type(last_content)}")

    @classmethod
    def extract_last_text(cls, message: TResponseOutputItem) -> str | None:
        """Extracts the last text content from a message, if any. Ignores refusals."""
        if isinstance(message, ResponseOutputMessage):
            last_content = message.content[-1]
            if isinstance(last_content, ResponseOutputText):
                return last_content.text

        return None

    @classmethod
    def input_to_new_input_list(
        cls, input: str | list[TResponseInputItem]
    ) -> list[TResponseInputItem]:
        """Converts a string or list of input items into a list of input items."""
        if isinstance(input, str):
            return [
                {
                    "content": input,
                    "role": "user",
                }
            ]
        return copy.deepcopy(input)

    @classmethod
    def text_message_outputs(cls, items: list[RunItem]) -> str:
        """Concatenates all the text content from a list of message output items."""
        text = ""
        for item in items:
            if isinstance(item, MessageOutputItem):
                text += cls.text_message_output(item)
        return text

    @classmethod
    def text_message_output(cls, message: MessageOutputItem) -> str:
        """Extracts all the text content from a single message output item."""
        text = ""
        for item in message.raw_item.content:
            if isinstance(item, ResponseOutputText):
                text += item.text
        return text

    @classmethod
    def tool_call_output_item(
        cls, tool_call: ResponseFunctionToolCall, output: str
    ) -> FunctionCallOutput:
        """Creates a tool call output item from a tool call and its output."""
        return {
            "call_id": tool_call.call_id,
            "output": output,
            "type": "function_call_output",
        }

extract_last_content classmethod

extract_last_content(message: TResponseOutputItem) -> str

Extracts the last text content or refusal from a message.

Source code in src/agents/items.py

@classmethod
def extract_last_content(cls, message: TResponseOutputItem) -> str:
    """Extracts the last text content or refusal from a message."""
    if not isinstance(message, ResponseOutputMessage):
        return ""

    last_content = message.content[-1]
    if isinstance(last_content, ResponseOutputText):
        return last_content.text
    elif isinstance(last_content, ResponseOutputRefusal):
        return last_content.refusal
    else:
        raise ModelBehaviorError(f"Unexpected content type: {type(last_content)}")

extract_last_text classmethod

extract_last_text(
    message: TResponseOutputItem,
) -> str | None

Extracts the last text content from a message, if any. Ignores refusals.

Source code in src/agents/items.py

@classmethod
def extract_last_text(cls, message: TResponseOutputItem) -> str | None:
    """Extracts the last text content from a message, if any. Ignores refusals."""
    if isinstance(message, ResponseOutputMessage):
        last_content = message.content[-1]
        if isinstance(last_content, ResponseOutputText):
            return last_content.text

    return None

input_to_new_input_list classmethod

input_to_new_input_list(
    input: str | list[TResponseInputItem],
) -> list[TResponseInputItem]

Converts a string or list of input items into a list of input items.

Source code in src/agents/items.py

@classmethod
def input_to_new_input_list(
    cls, input: str | list[TResponseInputItem]
) -> list[TResponseInputItem]:
    """Converts a string or list of input items into a list of input items."""
    if isinstance(input, str):
        return [
            {
                "content": input,
                "role": "user",
            }
        ]
    return copy.deepcopy(input)

text_message_outputs classmethod

text_message_outputs(items: list[RunItem]) -> str

Concatenates all the text content from a list of message output items.

Source code in src/agents/items.py

@classmethod
def text_message_outputs(cls, items: list[RunItem]) -> str:
    """Concatenates all the text content from a list of message output items."""
    text = ""
    for item in items:
        if isinstance(item, MessageOutputItem):
            text += cls.text_message_output(item)
    return text

text_message_output classmethod

text_message_output(message: MessageOutputItem) -> str

Extracts all the text content from a single message output item.

Source code in src/agents/items.py

@classmethod
def text_message_output(cls, message: MessageOutputItem) -> str:
    """Extracts all the text content from a single message output item."""
    text = ""
    for item in message.raw_item.content:
        if isinstance(item, ResponseOutputText):
            text += item.text
    return text

tool_call_output_item classmethod

tool_call_output_item(
    tool_call: ResponseFunctionToolCall, output: str
) -> FunctionCallOutput

Creates a tool call output item from a tool call and its output.

Source code in src/agents/items.py

@classmethod
def tool_call_output_item(
    cls, tool_call: ResponseFunctionToolCall, output: str
) -> FunctionCallOutput:
    """Creates a tool call output item from a tool call and its output."""
    return {
        "call_id": tool_call.call_id,
        "output": output,
        "type": "function_call_output",
    }