Realtime: handoffs

Author: rm-openai

src/agents/agent.py

@@ -158,7 +158,7 @@ class Agent(AgentBase, Generic[TContext]):
     usable with OpenAI models, using the Responses API.
     """
 
-    handoffs: list[Agent[Any] | Handoff[TContext]] = field(default_factory=list)
+    handoffs: list[Agent[Any] | Handoff[TContext, Any]] = field(default_factory=list)
     """Handoffs are sub-agents that the agent can delegate to. You can provide a list of handoffs,
     and the agent can choose to delegate to them if relevant. Allows for separation of concerns and
     modularity.

src/agents/guardrail.py

@@ -244,7 +244,7 @@ def decorator(
         return InputGuardrail(
             guardrail_function=f,
             # If not set, guardrail name uses the function’s name by default.
-            name=name if name else f.__name__
+            name=name if name else f.__name__,
         )
 
     if func is not None:

src/agents/handoffs.py

@@ -18,12 +18,15 @@
 from .util._types import MaybeAwaitable
 
 if TYPE_CHECKING:
-    from .agent import Agent
+    from .agent import Agent, AgentBase
 
 
 # The handoff input type is the type of data passed when the agent is called via a handoff.
 THandoffInput = TypeVar("THandoffInput", default=Any)
 
+# The agent type that the handoff returns
+TAgent = TypeVar("TAgent", bound="AgentBase[Any]", default="Agent[Any]")
+
 OnHandoffWithInput = Callable[[RunContextWrapper[Any], THandoffInput], Any]
 OnHandoffWithoutInput = Callable[[RunContextWrapper[Any]], Any]
 
@@ -52,7 +55,7 @@ class HandoffInputData:
 
 
 @dataclass
-class Handoff(Generic[TContext]):
+class Handoff(Generic[TContext, TAgent]):
     """A handoff is when an agent delegates a task to another agent.
     For example, in a customer support scenario you might have a "triage agent" that determines
     which agent should handle the user's request, and sub-agents that specialize in different
@@ -69,7 +72,7 @@ class Handoff(Generic[TContext]):
     """The JSON schema for the handoff input. Can be empty if the handoff does not take an input.
     """
 
-    on_invoke_handoff: Callable[[RunContextWrapper[Any], str], Awaitable[Agent[TContext]]]
+    on_invoke_handoff: Callable[[RunContextWrapper[Any], str], Awaitable[TAgent]]
     """The function that invokes the handoff. The parameters passed are:
     1. The handoff run context
     2. The arguments from the LLM, as a JSON string. Empty string if input_json_schema is empty.
@@ -100,20 +103,22 @@ class Handoff(Generic[TContext]):
     True, as it increases the likelihood of correct JSON input.
     """
 
-    is_enabled: bool | Callable[[RunContextWrapper[Any], Agent[Any]], MaybeAwaitable[bool]] = True
+    is_enabled: bool | Callable[[RunContextWrapper[Any], AgentBase[Any]], MaybeAwaitable[bool]] = (
+        True
+    )
     """Whether the handoff is enabled. Either a bool or a Callable that takes the run context and
     agent and returns whether the handoff is enabled. You can use this to dynamically enable/disable
     a handoff based on your context/state."""
 
-    def get_transfer_message(self, agent: Agent[Any]) -> str:
+    def get_transfer_message(self, agent: AgentBase[Any]) -> str:
         return json.dumps({"assistant": agent.name})
 
     @classmethod
-    def default_tool_name(cls, agent: Agent[Any]) -> str:
+    def default_tool_name(cls, agent: AgentBase[Any]) -> str:
         return _transforms.transform_string_function_style(f"transfer_to_{agent.name}")
 
     @classmethod
-    def default_tool_description(cls, agent: Agent[Any]) -> str:
+    def default_tool_description(cls, agent: AgentBase[Any]) -> str:
         return (
             f"Handoff to the {agent.name} agent to handle the request. "
             f"{agent.handoff_description or ''}"
@@ -128,7 +133,7 @@ def handoff(
     tool_description_override: str | None = None,
     input_filter: Callable[[HandoffInputData], HandoffInputData] | None = None,
     is_enabled: bool | Callable[[RunContextWrapper[Any], Agent[Any]], MaybeAwaitable[bool]] = True,
-) -> Handoff[TContext]: ...
+) -> Handoff[TContext, Agent[TContext]]: ...
 
 
 @overload
@@ -141,7 +146,7 @@ def handoff(
     tool_name_override: str | None = None,
     input_filter: Callable[[HandoffInputData], HandoffInputData] | None = None,
     is_enabled: bool | Callable[[RunContextWrapper[Any], Agent[Any]], MaybeAwaitable[bool]] = True,
-) -> Handoff[TContext]: ...
+) -> Handoff[TContext, Agent[TContext]]: ...
 
 
 @overload
@@ -153,7 +158,7 @@ def handoff(
     tool_name_override: str | None = None,
     input_filter: Callable[[HandoffInputData], HandoffInputData] | None = None,
     is_enabled: bool | Callable[[RunContextWrapper[Any], Agent[Any]], MaybeAwaitable[bool]] = True,
-) -> Handoff[TContext]: ...
+) -> Handoff[TContext, Agent[TContext]]: ...
 
 
 def handoff(
@@ -163,8 +168,9 @@ def handoff(
     on_handoff: OnHandoffWithInput[THandoffInput] | OnHandoffWithoutInput | None = None,
     input_type: type[THandoffInput] | None = None,
     input_filter: Callable[[HandoffInputData], HandoffInputData] | None = None,
-    is_enabled: bool | Callable[[RunContextWrapper[Any], Agent[Any]], MaybeAwaitable[bool]] = True,
-) -> Handoff[TContext]:
+    is_enabled: bool
+    | Callable[[RunContextWrapper[Any], Agent[TContext]], MaybeAwaitable[bool]] = True,
+) -> Handoff[TContext, Agent[TContext]]:
     """Create a handoff from an agent.
 
     Args:
@@ -202,7 +208,7 @@ def handoff(
 
     async def _invoke_handoff(
         ctx: RunContextWrapper[Any], input_json: str | None = None
-    ) -> Agent[Any]:
+    ) -> Agent[TContext]:
         if input_type is not None and type_adapter is not None:
             if input_json is None:
                 _error_tracing.attach_error_to_current_span(
@@ -239,12 +245,24 @@ async def _invoke_handoff(
     # If there is a need, we can make this configurable in the future
     input_json_schema = ensure_strict_json_schema(input_json_schema)
 
+    async def _is_enabled(ctx: RunContextWrapper[Any], agent_base: AgentBase[Any]) -> bool:
+        from .agent import Agent
+
+        assert callable(is_enabled), "is_enabled must be non-null here"
+        assert isinstance(agent_base, Agent), "Can't handoff to a non-Agent"
+        result = is_enabled(ctx, agent_base)
+
+        if inspect.isawaitable(result):
+            return await result
+
+        return result
+
     return Handoff(
         tool_name=tool_name,
         tool_description=tool_description,
         input_json_schema=input_json_schema,
         on_invoke_handoff=_invoke_handoff,
         input_filter=input_filter,
         agent_name=agent.name,
-        is_enabled=is_enabled,
+        is_enabled=_is_enabled if callable(is_enabled) else is_enabled,
     )

src/agents/models/chatcmpl_converter.py

@@ -484,7 +484,7 @@ def tool_to_openai(cls, tool: Tool) -> ChatCompletionToolParam:
         )
 
     @classmethod
-    def convert_handoff_tool(cls, handoff: Handoff[Any]) -> ChatCompletionToolParam:
+    def convert_handoff_tool(cls, handoff: Handoff[Any, Any]) -> ChatCompletionToolParam:
         return {
             "type": "function",
             "function": {

src/agents/models/openai_responses.py

@@ -370,7 +370,7 @@ def get_response_format(
     def convert_tools(
         cls,
         tools: list[Tool],
-        handoffs: list[Handoff[Any]],
+        handoffs: list[Handoff[Any, Any]],
     ) -> ConvertedTools:
         converted_tools: list[ToolParam] = []
         includes: list[ResponseIncludable] = []

src/agents/realtime/__init__.py

@@ -30,6 +30,7 @@
     RealtimeToolEnd,
     RealtimeToolStart,
 )
+from .handoffs import realtime_handoff
 from .items import (
     AssistantMessageItem,
     AssistantText,
@@ -92,6 +93,8 @@
     "RealtimeAgentHooks",
     "RealtimeRunHooks",
     "RealtimeRunner",
+    # Handoffs
+    "realtime_handoff",
     # Config
     "RealtimeAudioFormat",
     "RealtimeClientMessage",

src/agents/realtime/agent.py

@@ -3,10 +3,11 @@
 import dataclasses
 import inspect
 from collections.abc import Awaitable
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from typing import Any, Callable, Generic, cast
 
 from ..agent import AgentBase
+from ..handoffs import Handoff
 from ..lifecycle import AgentHooksBase, RunHooksBase
 from ..logger import logger
 from ..run_context import RunContextWrapper, TContext
@@ -53,6 +54,14 @@ class RealtimeAgent(AgentBase, Generic[TContext]):
     return a string.
     """
 
+    handoffs: list[RealtimeAgent[Any] | Handoff[TContext, RealtimeAgent[Any]]] = field(
+        default_factory=list
+    )
+    """Handoffs are sub-agents that the agent can delegate to. You can provide a list of handoffs,
+    and the agent can choose to delegate to them if relevant. Allows for separation of concerns and
+    modularity.
+    """
+
     hooks: RealtimeAgentHooks | None = None
     """A class that receives callbacks on various lifecycle events for this agent.
     """

src/agents/realtime/config.py

@@ -9,6 +9,7 @@
 from typing_extensions import NotRequired, TypeAlias, TypedDict
 
 from ..guardrail import OutputGuardrail
+from ..handoffs import Handoff
 from ..model_settings import ToolChoice
 from ..tool import Tool
 
@@ -71,6 +72,7 @@ class RealtimeSessionModelSettings(TypedDict):
 
     tool_choice: NotRequired[ToolChoice]
     tools: NotRequired[list[Tool]]
+    handoffs: NotRequired[list[Handoff]]
 
     tracing: NotRequired[RealtimeModelTracingConfig | None]
 

src/agents/realtime/openai_realtime.py

@@ -56,6 +56,7 @@
 from typing_extensions import assert_never
 from websockets.asyncio.client import ClientConnection
 
+from agents.handoffs import Handoff
 from agents.tool import FunctionTool, Tool
 from agents.util._types import MaybeAwaitable
 
@@ -519,10 +520,14 @@ def _get_session_config(
                 "tool_choice",
                 DEFAULT_MODEL_SETTINGS.get("tool_choice"),  # type: ignore
             ),
-            tools=self._tools_to_session_tools(model_settings.get("tools", [])),
+            tools=self._tools_to_session_tools(
+                tools=model_settings.get("tools", []), handoffs=model_settings.get("handoffs", [])
+            ),
         )
 
-    def _tools_to_session_tools(self, tools: list[Tool]) -> list[OpenAISessionTool]:
+    def _tools_to_session_tools(
+        self, tools: list[Tool], handoffs: list[Handoff]
+    ) -> list[OpenAISessionTool]:
         converted_tools: list[OpenAISessionTool] = []
         for tool in tools:
             if not isinstance(tool, FunctionTool):
@@ -535,6 +540,17 @@ def _tools_to_session_tools(self, tools: list[Tool]) -> list[OpenAISessionTool]:
                     type="function",
                 )
             )
+
+        for handoff in handoffs:
+            converted_tools.append(
+                OpenAISessionTool(
+                    name=handoff.tool_name,
+                    description=handoff.tool_description,
+                    parameters=handoff.input_json_schema,
+                    type="function",
+                )
+            )
+
         return converted_tools
 
 

src/agents/realtime/session.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import inspect
 from collections.abc import AsyncIterator
 from typing import Any, cast
 
@@ -31,6 +32,7 @@
     RealtimeToolEnd,
     RealtimeToolStart,
 )
+from .handoffs import realtime_handoff
 from .items import InputAudio, InputText, RealtimeItem
 from .model import RealtimeModel, RealtimeModelConfig, RealtimeModelListener
 from .model_events import (
@@ -255,9 +257,12 @@ async def _put_event(self, event: RealtimeSessionEvent) -> None:
 
     async def _handle_tool_call(self, event: RealtimeModelToolCallEvent) -> None:
         """Handle a tool call event."""
-        all_tools = await self._current_agent.get_all_tools(self._context_wrapper)
-        function_map = {tool.name: tool for tool in all_tools if isinstance(tool, FunctionTool)}
-        handoff_map = {tool.name: tool for tool in all_tools if isinstance(tool, Handoff)}
+        tools, handoffs = await asyncio.gather(
+            self._current_agent.get_all_tools(self._context_wrapper),
+            self._get_handoffs(self._current_agent, self._context_wrapper),
+        )
+        function_map = {tool.name: tool for tool in tools if isinstance(tool, FunctionTool)}
+        handoff_map = {handoff.tool_name: handoff for handoff in handoffs}
 
         if event.name in function_map:
             await self._put_event(
@@ -303,7 +308,9 @@ async def _handle_tool_call(self, event: RealtimeModelToolCallEvent) -> None:
             # Execute the handoff to get the new agent
             result = await handoff.on_invoke_handoff(self._context_wrapper, event.arguments)
             if not isinstance(result, RealtimeAgent):
-                raise UserError(f"Handoff {handoff.name} returned invalid result: {type(result)}")
+                raise UserError(
+                    f"Handoff {handoff.tool_name} returned invalid result: {type(result)}"
+                )
 
             # Store previous agent for event
             previous_agent = self._current_agent
@@ -492,11 +499,37 @@ async def _get__updated_model_settings(
         self, new_agent: RealtimeAgent
     ) -> RealtimeSessionModelSettings:
         updated_settings: RealtimeSessionModelSettings = {}
-        instructions, tools = await asyncio.gather(
+        instructions, tools, handoffs = await asyncio.gather(
             new_agent.get_system_prompt(self._context_wrapper),
             new_agent.get_all_tools(self._context_wrapper),
+            self._get_handoffs(new_agent, self._context_wrapper),
         )
         updated_settings["instructions"] = instructions or ""
         updated_settings["tools"] = tools or []
+        updated_settings["handoffs"] = handoffs or []
 
         return updated_settings
+
+    @classmethod
+    async def _get_handoffs(
+        cls, agent: RealtimeAgent[Any], context_wrapper: RunContextWrapper[Any]
+    ) -> list[Handoff[Any, RealtimeAgent[Any]]]:
+        handoffs: list[Handoff[Any, RealtimeAgent[Any]]] = []
+        for handoff_item in agent.handoffs:
+            if isinstance(handoff_item, Handoff):
+                handoffs.append(handoff_item)
+            elif isinstance(handoff_item, RealtimeAgent):
+                handoffs.append(realtime_handoff(handoff_item))
+
+        async def _check_handoff_enabled(handoff_obj: Handoff[Any, RealtimeAgent[Any]]) -> bool:
+            attr = handoff_obj.is_enabled
+            if isinstance(attr, bool):
+                return attr
+            res = attr(context_wrapper, agent)
+            if inspect.isawaitable(res):
+                return await res
+            return res
+
+        results = await asyncio.gather(*(_check_handoff_enabled(h) for h in handoffs))
+        enabled = [h for h, ok in zip(handoffs, results) if ok]
+        return enabled