openai-agents 0.0.16__tar.gz → 0.0.17__tar.gz

{openai_agents-0.0.16 → openai_agents-0.0.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openai-agents
-Version: 0.0.16
+Version: 0.0.17
 Summary: OpenAI Agents SDK
 Project-URL: Homepage, https://github.com/openai/openai-agents-python
 Project-URL: Repository, https://github.com/openai/openai-agents-python

{openai_agents-0.0.16 → openai_agents-0.0.17}/docs/ja/mcp.md

@@ -12,12 +12,13 @@ Agents SDK は MCP をサポートしており、これにより幅広い MCP
 
 ## MCP サーバー
 
-現在、MCP 仕様では使用するトランスポート方式に基づき 2 種類のサーバーが定義されています。
+現在、MCP 仕様では使用するトランスポート方式に基づき 3 種類のサーバーが定義されています。
 
-1. **stdio** サーバー: アプリケーションのサブプロセスとして実行されます。ローカルで動かすイメージです。  
+1. **stdio** サーバー: アプリケーションのサブプロセスとして実行されます。ローカルで動かすイメージです。
 2. **HTTP over SSE** サーバー: リモートで動作し、 URL 経由で接続します。
+3. **Streamable HTTP** サーバー: MCP 仕様に定義された Streamable HTTP トランスポートを使用してリモートで動作します。
 
-これらのサーバーへは [`MCPServerStdio`][agents.mcp.server.MCPServerStdio] と [`MCPServerSse`][agents.mcp.server.MCPServerSse] クラスを使用して接続できます。
+これらのサーバーへは [`MCPServerStdio`][agents.mcp.server.MCPServerStdio]、[`MCPServerSse`][agents.mcp.server.MCPServerSse]、[`MCPServerStreamableHttp`][agents.mcp.server.MCPServerStreamableHttp] クラスを使用して接続できます。
 
 たとえば、[公式 MCP filesystem サーバー](https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem)を利用する場合は次のようになります。
 
@@ -46,7 +47,7 @@ agent=Agent(
 
 ## キャッシュ
 
-エージェントが実行されるたびに、MCP サーバーへ `list_tools()` が呼び出されます。サーバーがリモートの場合は特にレイテンシが発生します。ツール一覧を自動でキャッシュしたい場合は、[`MCPServerStdio`][agents.mcp.server.MCPServerStdio] と [`MCPServerSse`][agents.mcp.server.MCPServerSse] の両方に `cache_tools_list=True` を渡してください。ツール一覧が変更されないと確信できる場合のみ使用してください。
+エージェントが実行されるたびに、MCP サーバーへ `list_tools()` が呼び出されます。サーバーがリモートの場合は特にレイテンシが発生します。ツール一覧を自動でキャッシュしたい場合は、[`MCPServerStdio`][agents.mcp.server.MCPServerStdio]、[`MCPServerSse`][agents.mcp.server.MCPServerSse]、[`MCPServerStreamableHttp`][agents.mcp.server.MCPServerStreamableHttp] の各クラスに `cache_tools_list=True` を渡してください。ツール一覧が変更されないと確信できる場合のみ使用してください。
 
 キャッシュを無効化したい場合は、サーバーで `invalidate_tools_cache()` を呼び出します。
 

{openai_agents-0.0.16 → openai_agents-0.0.17}/docs/ja/tools.md

@@ -17,6 +17,10 @@ OpenAI は [`OpenAIResponsesModel`][agents.models.openai_responses.OpenAIRespons
 -   [`WebSearchTool`][agents.tool.WebSearchTool] はエージェントに Web 検索を行わせます。
 -   [`FileSearchTool`][agents.tool.FileSearchTool] は OpenAI ベクトルストアから情報を取得します。
 -   [`ComputerTool`][agents.tool.ComputerTool] はコンピュータ操作タスクを自動化します。
+-   [`CodeInterpreterTool`][agents.tool.CodeInterpreterTool] はサンドボックス環境でコードを実行します。
+-   [`HostedMCPTool`][agents.tool.HostedMCPTool] はリモート MCP サーバーのツールをモデルから直接利用できるようにします。
+-   [`ImageGenerationTool`][agents.tool.ImageGenerationTool] はプロンプトから画像を生成します。
+-   [`LocalShellTool`][agents.tool.LocalShellTool] はローカルマシンでシェルコマンドを実行します。
 
 ```python
 from agents import Agent, FileSearchTool, Runner, WebSearchTool

{openai_agents-0.0.16 → openai_agents-0.0.17}/docs/ja/tracing.md

@@ -119,4 +119,5 @@ async def main():
 -   [Comet Opik](https://www.comet.com/docs/opik/tracing/integrations/openai_agents)
 -   [Langfuse](https://langfuse.com/docs/integrations/openaiagentssdk/openai-agents)
 -   [Langtrace](https://docs.langtrace.ai/supported-integrations/llm-frameworks/openai-agents-sdk)
--   [Okahu‑Monocle](https://github.com/monocle2ai/monocle)
+-   [Okahu‑Monocle](https://github.com/monocle2ai/monocle)
+-   [Portkey AI](https://portkey.ai/docs/integrations/agents/openai-agents)

{openai_agents-0.0.16 → openai_agents-0.0.17}/docs/mcp.md

@@ -8,12 +8,13 @@ The Agents SDK has support for MCP. This enables you to use a wide range of MCP
 
 ## MCP servers
 
-Currently, the MCP spec defines two kinds of servers, based on the transport mechanism they use:
+Currently, the MCP spec defines three kinds of servers, based on the transport mechanism they use:
 
 1. **stdio** servers run as a subprocess of your application. You can think of them as running "locally".
 2. **HTTP over SSE** servers run remotely. You connect to them via a URL.
+3. **Streamable HTTP** servers run remotely using the Streamable HTTP transport defined in the MCP spec.
 
-You can use the [`MCPServerStdio`][agents.mcp.server.MCPServerStdio] and [`MCPServerSse`][agents.mcp.server.MCPServerSse] classes to connect to these servers.
+You can use the [`MCPServerStdio`][agents.mcp.server.MCPServerStdio], [`MCPServerSse`][agents.mcp.server.MCPServerSse], and [`MCPServerStreamableHttp`][agents.mcp.server.MCPServerStreamableHttp] classes to connect to these servers.
 
 For example, this is how you'd use the [official MCP filesystem server](https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem).
 
@@ -42,7 +43,7 @@ agent=Agent(
 
 ## Caching
 
-Every time an Agent runs, it calls `list_tools()` on the MCP server. This can be a latency hit, especially if the server is a remote server. To automatically cache the list of tools, you can pass `cache_tools_list=True` to both [`MCPServerStdio`][agents.mcp.server.MCPServerStdio] and [`MCPServerSse`][agents.mcp.server.MCPServerSse]. You should only do this if you're certain the tool list will not change.
+Every time an Agent runs, it calls `list_tools()` on the MCP server. This can be a latency hit, especially if the server is a remote server. To automatically cache the list of tools, you can pass `cache_tools_list=True` to [`MCPServerStdio`][agents.mcp.server.MCPServerStdio], [`MCPServerSse`][agents.mcp.server.MCPServerSse], and [`MCPServerStreamableHttp`][agents.mcp.server.MCPServerStreamableHttp]. You should only do this if you're certain the tool list will not change.
 
 If you want to invalidate the cache, you can call `invalidate_tools_cache()` on the servers.
 

{openai_agents-0.0.16 → openai_agents-0.0.17}/docs/tools.md

@@ -13,6 +13,10 @@ OpenAI offers a few built-in tools when using the [`OpenAIResponsesModel`][agent
 -   The [`WebSearchTool`][agents.tool.WebSearchTool] lets an agent search the web.
 -   The [`FileSearchTool`][agents.tool.FileSearchTool] allows retrieving information from your OpenAI Vector Stores.
 -   The [`ComputerTool`][agents.tool.ComputerTool] allows automating computer use tasks.
+-   The [`CodeInterpreterTool`][agents.tool.CodeInterpreterTool] lets the LLM execute code in a sandboxed environment.
+-   The [`HostedMCPTool`][agents.tool.HostedMCPTool] exposes a remote MCP server's tools to the model.
+-   The [`ImageGenerationTool`][agents.tool.ImageGenerationTool] generates images from a prompt.
+-   The [`LocalShellTool`][agents.tool.LocalShellTool] runs shell commands on your machine.
 
 ```python
 from agents import Agent, FileSearchTool, Runner, WebSearchTool
@@ -266,7 +270,7 @@ The `agent.as_tool` function is a convenience method to make it easy to turn an
 ```python
 @function_tool
 async def run_my_agent() -> str:
-  """A tool that runs the agent with custom configs".
+    """A tool that runs the agent with custom configs"""
 
     agent = Agent(name="My agent", instructions="...")
 

{openai_agents-0.0.16 → openai_agents-0.0.17}/docs/tracing.md

@@ -116,3 +116,4 @@ To customize this default setup, to send traces to alternative or additional bac
 -   [Langtrace](https://docs.langtrace.ai/supported-integrations/llm-frameworks/openai-agents-sdk)
 -   [Okahu-Monocle](https://github.com/monocle2ai/monocle)
 -   [Galileo](https://v2docs.galileo.ai/integrations/openai-agent-integration#openai-agent-integration)
+-   [Portkey AI](https://portkey.ai/docs/integrations/agents/openai-agents)

{openai_agents-0.0.16 → openai_agents-0.0.17}/examples/agent_patterns/input_guardrails.py

@@ -20,7 +20,7 @@ This example shows how to use guardrails.
 Guardrails are checks that run in parallel to the agent's execution.
 They can be used to do things like:
 - Check if input messages are off-topic
-- Check that output messages don't violate any policies
+- Check that input messages don't violate any policies
 - Take over control of the agent's execution if an unexpected input is detected
 
 In this example, we'll setup an input guardrail that trips if the user is asking to do math homework.

{openai_agents-0.0.16 → openai_agents-0.0.17}/examples/hosted_mcp/approvals.py

@@ -48,7 +48,7 @@ async def main(verbose: bool, stream: bool):
         print(res.final_output)
 
     if verbose:
-        for item in result.new_items:
+        for item in res.new_items:
             print(item)
 
 

{openai_agents-0.0.16 → openai_agents-0.0.17}/examples/hosted_mcp/simple.py

@@ -34,7 +34,7 @@ async def main(verbose: bool, stream: bool):
         # The repository is primarily written in multiple languages, including Rust and TypeScript...
 
     if verbose:
-        for item in result.new_items:
+        for item in res.new_items:
             print(item)
 
 

{openai_agents-0.0.16 → openai_agents-0.0.17}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "openai-agents"
-version = "0.0.16"
+version = "0.0.17"
 description = "OpenAI Agents SDK"
 readme = "README.md"
 requires-python = ">=3.9"

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/__init__.py

@@ -14,6 +14,7 @@ from .exceptions import (
     MaxTurnsExceeded,
     ModelBehaviorError,
     OutputGuardrailTripwireTriggered,
+    RunErrorDetails,
     UserError,
 )
 from .guardrail import (
@@ -204,6 +205,7 @@ __all__ = [
     "AgentHooks",
     "RunContextWrapper",
     "TContext",
+    "RunErrorDetails",
     "RunResult",
     "RunResultStreaming",
     "RunConfig",

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/_run_impl.py

@@ -33,6 +33,7 @@ from openai.types.responses.response_output_item import (
     ImageGenerationCall,
     LocalShellCall,
     McpApprovalRequest,
+    McpCall,
     McpListTools,
 )
 from openai.types.responses.response_reasoning_item import ResponseReasoningItem
@@ -456,6 +457,9 @@ class RunImpl:
                         )
             elif isinstance(output, McpListTools):
                 items.append(MCPListToolsItem(raw_item=output, agent=agent))
+            elif isinstance(output, McpCall):
+                items.append(ToolCallItem(raw_item=output, agent=agent))
+                tools_used.append("mcp")
             elif isinstance(output, ImageGenerationCall):
                 items.append(ToolCallItem(raw_item=output, agent=agent))
                 tools_used.append("image_generation")

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/agent.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import asyncio
 import dataclasses
 import inspect
 from collections.abc import Awaitable
@@ -17,7 +18,7 @@ from .mcp import MCPUtil
 from .model_settings import ModelSettings
 from .models.interface import Model
 from .run_context import RunContextWrapper, TContext
-from .tool import FunctionToolResult, Tool, function_tool
+from .tool import FunctionTool, FunctionToolResult, Tool, function_tool
 from .util import _transforms
 from .util._types import MaybeAwaitable
 
@@ -246,7 +247,22 @@ class Agent(Generic[TContext]):
         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)
 
-    async def get_all_tools(self) -> list[Tool]:
+    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()
-        return mcp_tools + self.tools
+
+        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]

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/agent_output.py

@@ -38,7 +38,7 @@ class AgentOutputSchemaBase(abc.ABC):
     @abc.abstractmethod
     def is_strict_json_schema(self) -> bool:
         """Whether the JSON schema is in strict mode. Strict mode constrains the JSON schema
-        features, but guarantees valis JSON. See here for details:
+        features, but guarantees valid JSON. See here for details:
         https://platform.openai.com/docs/guides/structured-outputs#supported-schemas
         """
         pass

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/exceptions.py

@@ -1,12 +1,42 @@
-from typing import TYPE_CHECKING
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Any
 
 if TYPE_CHECKING:
+    from .agent import Agent
     from .guardrail import InputGuardrailResult, OutputGuardrailResult
+    from .items import ModelResponse, RunItem, TResponseInputItem
+    from .run_context import RunContextWrapper
+
+from .util._pretty_print import pretty_print_run_error_details
+
+
+@dataclass
+class RunErrorDetails:
+    """Data collected from an agent run when an exception occurs."""
+
+    input: str | list[TResponseInputItem]
+    new_items: list[RunItem]
+    raw_responses: list[ModelResponse]
+    last_agent: Agent[Any]
+    context_wrapper: RunContextWrapper[Any]
+    input_guardrail_results: list[InputGuardrailResult]
+    output_guardrail_results: list[OutputGuardrailResult]
+
+    def __str__(self) -> str:
+        return pretty_print_run_error_details(self)
 
 
 class AgentsException(Exception):
     """Base class for all exceptions in the Agents SDK."""
 
+    run_data: RunErrorDetails | None
+
+    def __init__(self, *args: object) -> None:
+        super().__init__(*args)
+        self.run_data = None
+
 
 class MaxTurnsExceeded(AgentsException):
     """Exception raised when the maximum number of turns is exceeded."""
@@ -15,6 +45,7 @@ class MaxTurnsExceeded(AgentsException):
 
     def __init__(self, message: str):
         self.message = message
+        super().__init__(message)
 
 
 class ModelBehaviorError(AgentsException):
@@ -26,6 +57,7 @@ class ModelBehaviorError(AgentsException):
 
     def __init__(self, message: str):
         self.message = message
+        super().__init__(message)
 
 
 class UserError(AgentsException):
@@ -35,15 +67,16 @@ class UserError(AgentsException):
 
     def __init__(self, message: str):
         self.message = message
+        super().__init__(message)
 
 
 class InputGuardrailTripwireTriggered(AgentsException):
     """Exception raised when a guardrail tripwire is triggered."""
 
-    guardrail_result: "InputGuardrailResult"
+    guardrail_result: InputGuardrailResult
     """The result data of the guardrail that was triggered."""
 
-    def __init__(self, guardrail_result: "InputGuardrailResult"):
+    def __init__(self, guardrail_result: InputGuardrailResult):
         self.guardrail_result = guardrail_result
         super().__init__(
             f"Guardrail {guardrail_result.guardrail.__class__.__name__} triggered tripwire"
@@ -53,10 +86,10 @@ class InputGuardrailTripwireTriggered(AgentsException):
 class OutputGuardrailTripwireTriggered(AgentsException):
     """Exception raised when a guardrail tripwire is triggered."""
 
-    guardrail_result: "OutputGuardrailResult"
+    guardrail_result: OutputGuardrailResult
     """The result data of the guardrail that was triggered."""
 
-    def __init__(self, guardrail_result: "OutputGuardrailResult"):
+    def __init__(self, guardrail_result: OutputGuardrailResult):
         self.guardrail_result = guardrail_result
         super().__init__(
             f"Guardrail {guardrail_result.guardrail.__class__.__name__} triggered tripwire"

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/extensions/models/litellm_model.py

@@ -5,7 +5,6 @@ import time
 from collections.abc import AsyncIterator
 from typing import Any, Literal, cast, overload
 
-import litellm.types
 from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails
 
 from agents.exceptions import ModelBehaviorError
@@ -112,11 +111,13 @@ class LitellmModel(Model):
                             cached_tokens=getattr(
                                 response_usage.prompt_tokens_details, "cached_tokens", 0
                             )
+                            or 0
                         ),
                         output_tokens_details=OutputTokensDetails(
                             reasoning_tokens=getattr(
                                 response_usage.completion_tokens_details, "reasoning_tokens", 0
                             )
+                            or 0
                         ),
                     )
                     if response.usage

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/extensions/visualization.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from __future__ import annotations
 
 import graphviz  # type: ignore
 
@@ -31,7 +31,9 @@ def get_main_graph(agent: Agent) -> str:
     return "".join(parts)
 
 
-def get_all_nodes(agent: Agent, parent: Optional[Agent] = None) -> str:
+def get_all_nodes(
+    agent: Agent, parent: Agent | None = None, visited: set[str] | None = None
+) -> str:
     """
     Recursively generates the nodes for the given agent and its handoffs in DOT format.
 
@@ -41,17 +43,23 @@ def get_all_nodes(agent: Agent, parent: Optional[Agent] = None) -> str:
     Returns:
         str: The DOT format string representing the nodes.
     """
+    if visited is None:
+        visited = set()
+    if agent.name in visited:
+        return ""
+    visited.add(agent.name)
+
     parts = []
 
     # Start and end the graph
-    parts.append(
-        '"__start__" [label="__start__", shape=ellipse, style=filled, '
-        "fillcolor=lightblue, width=0.5, height=0.3];"
-        '"__end__" [label="__end__", shape=ellipse, style=filled, '
-        "fillcolor=lightblue, width=0.5, height=0.3];"
-    )
-    # Ensure parent agent node is colored
     if not parent:
+        parts.append(
+            '"__start__" [label="__start__", shape=ellipse, style=filled, '
+            "fillcolor=lightblue, width=0.5, height=0.3];"
+            '"__end__" [label="__end__", shape=ellipse, style=filled, '
+            "fillcolor=lightblue, width=0.5, height=0.3];"
+        )
+        # Ensure parent agent node is colored
         parts.append(
             f'"{agent.name}" [label="{agent.name}", shape=box, style=filled, '
             "fillcolor=lightyellow, width=1.5, height=0.8];"
@@ -71,17 +79,20 @@ def get_all_nodes(agent: Agent, parent: Optional[Agent] = None) -> str:
                 f"fillcolor=lightyellow, width=1.5, height=0.8];"
             )
         if isinstance(handoff, Agent):
-            parts.append(
-                f'"{handoff.name}" [label="{handoff.name}", '
-                f"shape=box, style=filled, style=rounded, "
-                f"fillcolor=lightyellow, width=1.5, height=0.8];"
-            )
-            parts.append(get_all_nodes(handoff))
+            if handoff.name not in visited:
+                parts.append(
+                    f'"{handoff.name}" [label="{handoff.name}", '
+                    f"shape=box, style=filled, style=rounded, "
+                    f"fillcolor=lightyellow, width=1.5, height=0.8];"
+                )
+            parts.append(get_all_nodes(handoff, agent, visited))
 
     return "".join(parts)
 
 
-def get_all_edges(agent: Agent, parent: Optional[Agent] = None) -> str:
+def get_all_edges(
+    agent: Agent, parent: Agent | None = None, visited: set[str] | None = None
+) -> str:
     """
     Recursively generates the edges for the given agent and its handoffs in DOT format.
 
@@ -92,6 +103,12 @@ def get_all_edges(agent: Agent, parent: Optional[Agent] = None) -> str:
     Returns:
         str: The DOT format string representing the edges.
     """
+    if visited is None:
+        visited = set()
+    if agent.name in visited:
+        return ""
+    visited.add(agent.name)
+
     parts = []
 
     if not parent:
@@ -109,7 +126,7 @@ def get_all_edges(agent: Agent, parent: Optional[Agent] = None) -> str:
         if isinstance(handoff, Agent):
             parts.append(f"""
             "{agent.name}" -> "{handoff.name}";""")
-            parts.append(get_all_edges(handoff, agent))
+            parts.append(get_all_edges(handoff, agent, visited))
 
     if not agent.handoffs and not isinstance(agent, Tool):  # type: ignore
         parts.append(f'"{agent.name}" -> "__end__";')
@@ -117,7 +134,7 @@ def get_all_edges(agent: Agent, parent: Optional[Agent] = None) -> str:
     return "".join(parts)
 
 
-def draw_graph(agent: Agent, filename: Optional[str] = None) -> graphviz.Source:
+def draw_graph(agent: Agent, filename: str | None = None) -> graphviz.Source:
     """
     Draws the graph for the given agent and optionally saves it as a PNG file.
 

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/handoffs.py

@@ -168,7 +168,7 @@ def handoff(
         input_filter: a function that filters the inputs that are passed to the next agent.
     """
     assert (on_handoff and input_type) or not (on_handoff and input_type), (
-        "You must provide either both on_input and input_type, or neither"
+        "You must provide either both on_handoff and input_type, or neither"
     )
     type_adapter: TypeAdapter[Any] | None
     if input_type is not None:

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/mcp/server.py

@@ -88,7 +88,7 @@ class _MCPServerWithClientSession(MCPServer, abc.ABC):
         tuple[
             MemoryObjectReceiveStream[SessionMessage | Exception],
             MemoryObjectSendStream[SessionMessage],
-            GetSessionIdCallback | None
+            GetSessionIdCallback | None,
         ]
     ]:
         """Create the streams for the server."""
@@ -243,7 +243,7 @@ class MCPServerStdio(_MCPServerWithClientSession):
         tuple[
             MemoryObjectReceiveStream[SessionMessage | Exception],
             MemoryObjectSendStream[SessionMessage],
-            GetSessionIdCallback | None
+            GetSessionIdCallback | None,
         ]
     ]:
         """Create the streams for the server."""
@@ -314,7 +314,7 @@ class MCPServerSse(_MCPServerWithClientSession):
         tuple[
             MemoryObjectReceiveStream[SessionMessage | Exception],
             MemoryObjectSendStream[SessionMessage],
-            GetSessionIdCallback | None
+            GetSessionIdCallback | None,
         ]
     ]:
         """Create the streams for the server."""
@@ -394,7 +394,7 @@ class MCPServerStreamableHttp(_MCPServerWithClientSession):
         tuple[
             MemoryObjectReceiveStream[SessionMessage | Exception],
             MemoryObjectSendStream[SessionMessage],
-            GetSessionIdCallback | None
+            GetSessionIdCallback | None,
         ]
     ]:
         """Create the streams for the server."""
@@ -403,7 +403,7 @@ class MCPServerStreamableHttp(_MCPServerWithClientSession):
             headers=self.params.get("headers", None),
             timeout=self.params.get("timeout", timedelta(seconds=30)),
             sse_read_timeout=self.params.get("sse_read_timeout", timedelta(seconds=60 * 5)),
-            terminate_on_close=self.params.get("terminate_on_close", True)
+            terminate_on_close=self.params.get("terminate_on_close", True),
         )
 
     @property

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/mcp/util.py

@@ -116,7 +116,7 @@ class MCPUtil:
         if len(result.content) == 1:
             tool_output = result.content[0].model_dump_json()
         elif len(result.content) > 1:
-            tool_output = json.dumps([item.model_dump() for item in result.content])
+            tool_output = json.dumps([item.model_dump(mode="json") for item in result.content])
         else:
             logger.error(f"Errored MCP tool result: {result}")
             tool_output = "Error running tool."

{openai_agents-0.0.16 → openai_agents-0.0.17}/src/agents/models/openai_chatcompletions.py

@@ -71,12 +71,22 @@ class OpenAIChatCompletionsModel(Model):
                 stream=False,
             )
 
+            first_choice = response.choices[0]
+            message = first_choice.message
+
             if _debug.DONT_LOG_MODEL_DATA:
                 logger.debug("Received model response")
             else:
-                logger.debug(
-                    f"LLM resp:\n{json.dumps(response.choices[0].message.model_dump(), indent=2)}\n"
-                )
+                if message is not None:
+                    logger.debug(
+                        "LLM resp:\n%s\n",
+                        json.dumps(message.model_dump(), indent=2),
+                    )
+                else:
+                    logger.debug(
+                        "LLM resp had no message. finish_reason: %s",
+                        first_choice.finish_reason,
+                    )
 
             usage = (
                 Usage(
@@ -101,13 +111,15 @@ class OpenAIChatCompletionsModel(Model):
                 else Usage()
             )
             if tracing.include_data():
-                span_generation.span_data.output = [response.choices[0].message.model_dump()]
+                span_generation.span_data.output = (
+                    [message.model_dump()] if message is not None else []
+                )
             span_generation.span_data.usage = {
                 "input_tokens": usage.input_tokens,
                 "output_tokens": usage.output_tokens,
             }
 
-            items = Converter.message_to_output_items(response.choices[0].message)
+            items = Converter.message_to_output_items(message) if message is not None else []
 
             return ModelResponse(
                 output=items,