[1/n] Break Agent into AgentBase+Agent (#1068)

This allows base agent stuff to be shared with the realtime agent

Author: rm-openai

src/agents/__init__.py

@@ -5,7 +5,7 @@
 from openai import AsyncOpenAI
 
 from . import _config
-from .agent import Agent, ToolsToFinalOutputFunction, ToolsToFinalOutputResult
+from .agent import Agent, AgentBase, ToolsToFinalOutputFunction, ToolsToFinalOutputResult
 from .agent_output import AgentOutputSchema, AgentOutputSchemaBase
 from .computer import AsyncComputer, Button, Computer, Environment
 from .exceptions import (
@@ -161,6 +161,7 @@ def enable_verbose_stdout_logging():
 
 __all__ = [
     "Agent",
+    "AgentBase",
     "ToolsToFinalOutputFunction",
     "ToolsToFinalOutputResult",
     "Runner",

src/agents/agent.py

@@ -67,7 +67,63 @@ class MCPConfig(TypedDict):
 
 
 @dataclass
-class Agent(Generic[TContext]):
+class AgentBase(Generic[TContext]):
+    """Base class for `Agent` and `RealtimeAgent`."""
+
+    name: str
+    """The name of the agent."""
+
+    handoff_description: str | None = None
+    """A description of the agent. This is used when the agent is used as a handoff, so that an
+    LLM knows what it does and when to invoke it.
+    """
+
+    tools: list[Tool] = field(default_factory=list)
+    """A list of tools that the agent can use."""
+
+    mcp_servers: list[MCPServer] = field(default_factory=list)
+    """A list of [Model Context Protocol](https://modelcontextprotocol.io/) servers that
+    the agent can use. Every time the agent runs, it will include tools from these servers in the
+    list of available tools.
+
+    NOTE: You are expected to manage the lifecycle of these servers. Specifically, you must call
+    `server.connect()` before passing it to the agent, and `server.cleanup()` when the server is no
+    longer needed.
+    """
+
+    mcp_config: MCPConfig = field(default_factory=lambda: MCPConfig())
+    """Configuration for MCP servers."""
+
+    async def get_mcp_tools(self, run_context: RunContextWrapper[TContext]) -> list[Tool]:
+        """Fetches the available tools from the MCP servers."""
+        convert_schemas_to_strict = self.mcp_config.get("convert_schemas_to_strict", False)
+        return await MCPUtil.get_all_function_tools(
+            self.mcp_servers, convert_schemas_to_strict, run_context, self
+        )
+
+    async def get_all_tools(self, run_context: RunContextWrapper[Any]) -> list[Tool]:
+        """All agent tools, including MCP tools and function tools."""
+        mcp_tools = await self.get_mcp_tools(run_context)
+
+        async def _check_tool_enabled(tool: Tool) -> bool:
+            if not isinstance(tool, FunctionTool):
+                return True
+
+            attr = tool.is_enabled
+            if isinstance(attr, bool):
+                return attr
+            res = attr(run_context, self)
+            if inspect.isawaitable(res):
+                return bool(await res)
+            return bool(res)
+
+        results = await asyncio.gather(*(_check_tool_enabled(t) for t in self.tools))
+        enabled: list[Tool] = [t for t, ok in zip(self.tools, results) if ok]
+        return [*mcp_tools, *enabled]
+
+
+@dataclass
+class Agent(AgentBase, Generic[TContext]):
     """An agent is an AI model configured with instructions, tools, guardrails, handoffs and more.
 
     We strongly recommend passing `instructions`, which is the "system prompt" for the agent. In
@@ -76,10 +132,9 @@ class Agent(Generic[TContext]):
 
     Agents are generic on the context type. The context is a (mutable) object you create. It is
     passed to tool functions, handoffs, guardrails, etc.
-    """
 
-    name: str
-    """The name of the agent."""
+    See `AgentBase` for base parameters that are shared with `RealtimeAgent`s.
+    """
 
     instructions: (
         str
@@ -103,11 +158,6 @@ class Agent(Generic[TContext]):
     usable with OpenAI models, using the Responses API.
     """
 
-    handoff_description: str | None = None
-    """A description of the agent. This is used when the agent is used as a handoff, so that an
-    LLM knows what it does and when to invoke it.
-    """
-
     handoffs: list[Agent[Any] | Handoff[TContext]] = 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
@@ -125,22 +175,6 @@ class Agent(Generic[TContext]):
     """Configures model-specific tuning parameters (e.g. temperature, top_p).
     """
 
-    tools: list[Tool] = field(default_factory=list)
-    """A list of tools that the agent can use."""
-
-    mcp_servers: list[MCPServer] = field(default_factory=list)
-    """A list of [Model Context Protocol](https://modelcontextprotocol.io/) servers that
-    the agent can use. Every time the agent runs, it will include tools from these servers in the
-    list of available tools.
-
-    NOTE: You are expected to manage the lifecycle of these servers. Specifically, you must call
-    `server.connect()` before passing it to the agent, and `server.cleanup()` when the server is no
-    longer needed.
-    """
-
-    mcp_config: MCPConfig = field(default_factory=lambda: MCPConfig())
-    """Configuration for MCP servers."""
-
     input_guardrails: list[InputGuardrail[TContext]] = field(default_factory=list)
     """A list of checks that run in parallel to the agent's execution, before generating a
     response. Runs only if the agent is the first agent in the chain.

src/agents/lifecycle.py

@@ -1,25 +1,27 @@
 from typing import Any, Generic
 
-from .agent import Agent
+from typing_extensions import TypeVar
+
+from .agent import Agent, AgentBase
 from .run_context import RunContextWrapper, TContext
 from .tool import Tool
 
+TAgent = TypeVar("TAgent", bound=AgentBase, default=AgentBase)
+
 
-class RunHooks(Generic[TContext]):
+class RunHooksBase(Generic[TContext, TAgent]):
     """A class that receives callbacks on various lifecycle events in an agent run. Subclass and
     override the methods you need.
     """
 
-    async def on_agent_start(
-        self, context: RunContextWrapper[TContext], agent: Agent[TContext]
-    ) -> None:
+    async def on_agent_start(self, context: RunContextWrapper[TContext], agent: TAgent) -> None:
         """Called before the agent is invoked. Called each time the current agent changes."""
         pass
 
     async def on_agent_end(
         self,
         context: RunContextWrapper[TContext],
-        agent: Agent[TContext],
+        agent: TAgent,
         output: Any,
     ) -> None:
         """Called when the agent produces a final output."""
@@ -28,16 +30,16 @@ async def on_agent_end(
     async def on_handoff(
         self,
         context: RunContextWrapper[TContext],
-        from_agent: Agent[TContext],
-        to_agent: Agent[TContext],
+        from_agent: TAgent,
+        to_agent: TAgent,
     ) -> None:
         """Called when a handoff occurs."""
         pass
 
     async def on_tool_start(
         self,
         context: RunContextWrapper[TContext],
-        agent: Agent[TContext],
+        agent: TAgent,
         tool: Tool,
     ) -> None:
         """Called before a tool is invoked."""
@@ -46,30 +48,30 @@ async def on_tool_start(
     async def on_tool_end(
         self,
         context: RunContextWrapper[TContext],
-        agent: Agent[TContext],
+        agent: TAgent,
         tool: Tool,
         result: str,
     ) -> None:
         """Called after a tool is invoked."""
         pass
 
 
-class AgentHooks(Generic[TContext]):
+class AgentHooksBase(Generic[TContext, TAgent]):
     """A class that receives callbacks on various lifecycle events for a specific agent. You can
     set this on `agent.hooks` to receive events for that specific agent.
 
     Subclass and override the methods you need.
     """
 
-    async def on_start(self, context: RunContextWrapper[TContext], agent: Agent[TContext]) -> None:
+    async def on_start(self, context: RunContextWrapper[TContext], agent: TAgent) -> None:
         """Called before the agent is invoked. Called each time the running agent is changed to this
         agent."""
         pass
 
     async def on_end(
         self,
         context: RunContextWrapper[TContext],
-        agent: Agent[TContext],
+        agent: TAgent,
         output: Any,
     ) -> None:
         """Called when the agent produces a final output."""
@@ -78,8 +80,8 @@ async def on_end(
     async def on_handoff(
         self,
         context: RunContextWrapper[TContext],
-        agent: Agent[TContext],
-        source: Agent[TContext],
+        agent: TAgent,
+        source: TAgent,
     ) -> None:
         """Called when the agent is being handed off to. The `source` is the agent that is handing
         off to this agent."""
@@ -88,7 +90,7 @@ async def on_handoff(
     async def on_tool_start(
         self,
         context: RunContextWrapper[TContext],
-        agent: Agent[TContext],
+        agent: TAgent,
         tool: Tool,
     ) -> None:
         """Called before a tool is invoked."""
@@ -97,9 +99,16 @@ async def on_tool_start(
     async def on_tool_end(
         self,
         context: RunContextWrapper[TContext],
-        agent: Agent[TContext],
+        agent: TAgent,
         tool: Tool,
         result: str,
     ) -> None:
         """Called after a tool is invoked."""
         pass
+
+
+RunHooks = RunHooksBase[TContext, Agent]
+"""Run hooks when using `Agent`."""
+
+AgentHooks = AgentHooksBase[TContext, Agent]
+"""Agent hooks for `Agent`s."""

src/agents/mcp/server.py

@@ -22,7 +22,7 @@
 from .util import ToolFilter, ToolFilterCallable, ToolFilterContext, ToolFilterStatic
 
 if TYPE_CHECKING:
-    from ..agent import Agent
+    from ..agent import AgentBase
 
 
 class MCPServer(abc.ABC):
@@ -53,7 +53,7 @@ async def cleanup(self):
     async def list_tools(
         self,
         run_context: RunContextWrapper[Any] | None = None,
-        agent: Agent[Any] | None = None,
+        agent: AgentBase | None = None,
     ) -> list[MCPTool]:
         """List the tools available on the server."""
         pass
@@ -117,7 +117,7 @@ async def _apply_tool_filter(
         self,
         tools: list[MCPTool],
         run_context: RunContextWrapper[Any],
-        agent: Agent[Any],
+        agent: AgentBase,
     ) -> list[MCPTool]:
         """Apply the tool filter to the list of tools."""
         if self.tool_filter is None:
@@ -153,7 +153,7 @@ async def _apply_dynamic_tool_filter(
         self,
         tools: list[MCPTool],
         run_context: RunContextWrapper[Any],
-        agent: Agent[Any],
+        agent: AgentBase,
     ) -> list[MCPTool]:
         """Apply dynamic tool filtering using a callable filter function."""
 
@@ -244,7 +244,7 @@ async def connect(self):
     async def list_tools(
         self,
         run_context: RunContextWrapper[Any] | None = None,
-        agent: Agent[Any] | None = None,
+        agent: AgentBase | None = None,
     ) -> list[MCPTool]:
         """List the tools available on the server."""
         if not self.session:

src/agents/mcp/util.py

@@ -5,20 +5,19 @@
 
 from typing_extensions import NotRequired, TypedDict
 
-from agents.strict_schema import ensure_strict_json_schema
-
 from .. import _debug
 from ..exceptions import AgentsException, ModelBehaviorError, UserError
 from ..logger import logger
 from ..run_context import RunContextWrapper
+from ..strict_schema import ensure_strict_json_schema
 from ..tool import FunctionTool, Tool
 from ..tracing import FunctionSpanData, get_current_span, mcp_tools_span
 from ..util._types import MaybeAwaitable
 
 if TYPE_CHECKING:
     from mcp.types import Tool as MCPTool
 
-    from ..agent import Agent
+    from ..agent import AgentBase
     from .server import MCPServer
 
 
@@ -29,7 +28,7 @@ class ToolFilterContext:
     run_context: RunContextWrapper[Any]
     """The current run context."""
 
-    agent: "Agent[Any]"
+    agent: "AgentBase"
     """The agent that is requesting the tool list."""
 
     server_name: str
@@ -100,7 +99,7 @@ async def get_all_function_tools(
         servers: list["MCPServer"],
         convert_schemas_to_strict: bool,
         run_context: RunContextWrapper[Any],
-        agent: "Agent[Any]",
+        agent: "AgentBase",
     ) -> list[Tool]:
         """Get all function tools from a list of MCP servers."""
         tools = []
@@ -126,7 +125,7 @@ async def get_function_tools(
         server: "MCPServer",
         convert_schemas_to_strict: bool,
         run_context: RunContextWrapper[Any],
-        agent: "Agent[Any]",
+        agent: "AgentBase",
     ) -> list[Tool]:
         """Get all function tools from a single MCP server."""
 

src/agents/tool.py

@@ -30,7 +30,7 @@
 from .util._types import MaybeAwaitable
 
 if TYPE_CHECKING:
-    from .agent import Agent
+    from .agent import Agent, AgentBase
 
 ToolParams = ParamSpec("ToolParams")
 
@@ -87,7 +87,7 @@ class FunctionTool:
     """Whether the JSON schema is in strict mode. We **strongly** recommend setting this to 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], MaybeAwaitable[bool]] = True
     """Whether the tool is enabled. Either a bool or a Callable that takes the run context and agent
     and returns whether the tool is enabled. You can use this to dynamically enable/disable a tool
     based on your context/state."""
@@ -300,7 +300,7 @@ def function_tool(
     use_docstring_info: bool = True,
     failure_error_function: ToolErrorFunction | None = None,
     strict_mode: bool = True,
-    is_enabled: bool | Callable[[RunContextWrapper[Any], Agent[Any]], MaybeAwaitable[bool]] = True,
+    is_enabled: bool | Callable[[RunContextWrapper[Any], AgentBase], MaybeAwaitable[bool]] = True,
 ) -> FunctionTool:
     """Overload for usage as @function_tool (no parentheses)."""
     ...
@@ -315,7 +315,7 @@ def function_tool(
     use_docstring_info: bool = True,
     failure_error_function: ToolErrorFunction | None = None,
     strict_mode: bool = True,
-    is_enabled: bool | Callable[[RunContextWrapper[Any], Agent[Any]], MaybeAwaitable[bool]] = True,
+    is_enabled: bool | Callable[[RunContextWrapper[Any], AgentBase], MaybeAwaitable[bool]] = True,
 ) -> Callable[[ToolFunction[...]], FunctionTool]:
     """Overload for usage as @function_tool(...)."""
     ...
@@ -330,7 +330,7 @@ def function_tool(
     use_docstring_info: bool = True,
     failure_error_function: ToolErrorFunction | None = default_tool_error_function,
     strict_mode: bool = True,
-    is_enabled: bool | Callable[[RunContextWrapper[Any], Agent[Any]], MaybeAwaitable[bool]] = True,
+    is_enabled: bool | Callable[[RunContextWrapper[Any], AgentBase], MaybeAwaitable[bool]] = True,
 ) -> FunctionTool | Callable[[ToolFunction[...]], FunctionTool]:
     """
     Decorator to create a FunctionTool from a function. By default, we will: