openai-agents 0.0.14__tar.gz → 0.0.15__tar.gz

{openai_agents-0.0.14 → openai_agents-0.0.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openai-agents
-Version: 0.0.14
+Version: 0.0.15
 Summary: OpenAI Agents SDK
 Project-URL: Homepage, https://github.com/openai/openai-agents-python
 Project-URL: Repository, https://github.com/openai/openai-agents-python
@@ -19,7 +19,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
 Requires-Python: >=3.9
 Requires-Dist: griffe<2,>=1.5.6
-Requires-Dist: mcp<2,>=1.6.0; python_version >= '3.10'
+Requires-Dist: mcp<2,>=1.8.0; python_version >= '3.10'
 Requires-Dist: openai>=1.76.0
 Requires-Dist: pydantic<3,>=2.10
 Requires-Dist: requests<3,>=2.0

openai_agents-0.0.15/examples/mcp/streamablehttp_example/README.md

@@ -0,0 +1,13 @@
+# MCP Streamable HTTP Example
+
+This example uses a local Streamable HTTP server in [server.py](server.py).
+
+Run the example via:
+
+```
+uv run python examples/mcp/streamablehttp_example/main.py
+```
+
+## Details
+
+The example uses the `MCPServerStreamableHttp` class from `agents.mcp`. The server runs in a sub-process at `https://localhost:8000/mcp`.

openai_agents-0.0.15/examples/mcp/streamablehttp_example/main.py

@@ -0,0 +1,83 @@
+import asyncio
+import os
+import shutil
+import subprocess
+import time
+from typing import Any
+
+from agents import Agent, Runner, gen_trace_id, trace
+from agents.mcp import MCPServer, MCPServerStreamableHttp
+from agents.model_settings import ModelSettings
+
+
+async def run(mcp_server: MCPServer):
+    agent = Agent(
+        name="Assistant",
+        instructions="Use the tools to answer the questions.",
+        mcp_servers=[mcp_server],
+        model_settings=ModelSettings(tool_choice="required"),
+    )
+
+    # Use the `add` tool to add two numbers
+    message = "Add these numbers: 7 and 22."
+    print(f"Running: {message}")
+    result = await Runner.run(starting_agent=agent, input=message)
+    print(result.final_output)
+
+    # Run the `get_weather` tool
+    message = "What's the weather in Tokyo?"
+    print(f"\n\nRunning: {message}")
+    result = await Runner.run(starting_agent=agent, input=message)
+    print(result.final_output)
+
+    # Run the `get_secret_word` tool
+    message = "What's the secret word?"
+    print(f"\n\nRunning: {message}")
+    result = await Runner.run(starting_agent=agent, input=message)
+    print(result.final_output)
+
+
+async def main():
+    async with MCPServerStreamableHttp(
+        name="Streamable HTTP Python Server",
+        params={
+            "url": "http://localhost:8000/mcp",
+        },
+    ) as server:
+        trace_id = gen_trace_id()
+        with trace(workflow_name="Streamable HTTP Example", trace_id=trace_id):
+            print(f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}\n")
+            await run(server)
+
+
+if __name__ == "__main__":
+    # Let's make sure the user has uv installed
+    if not shutil.which("uv"):
+        raise RuntimeError(
+            "uv is not installed. Please install it: https://docs.astral.sh/uv/getting-started/installation/"
+        )
+
+    # We'll run the Streamable HTTP server in a subprocess. Usually this would be a remote server, but for this
+    # demo, we'll run it locally at http://localhost:8000/mcp
+    process: subprocess.Popen[Any] | None = None
+    try:
+        this_dir = os.path.dirname(os.path.abspath(__file__))
+        server_file = os.path.join(this_dir, "server.py")
+
+        print("Starting Streamable HTTP server at http://localhost:8000/mcp ...")
+
+        # Run `uv run server.py` to start the Streamable HTTP server
+        process = subprocess.Popen(["uv", "run", server_file])
+        # Give it 3 seconds to start
+        time.sleep(3)
+
+        print("Streamable HTTP server started. Running example...\n\n")
+    except Exception as e:
+        print(f"Error starting Streamable HTTP server: {e}")
+        exit(1)
+
+    try:
+        asyncio.run(main())
+    finally:
+        if process:
+            process.terminate()

openai_agents-0.0.15/examples/mcp/streamablehttp_example/server.py

@@ -0,0 +1,33 @@
+import random
+
+import requests
+from mcp.server.fastmcp import FastMCP
+
+# Create server
+mcp = FastMCP("Echo Server")
+
+
+@mcp.tool()
+def add(a: int, b: int) -> int:
+    """Add two numbers"""
+    print(f"[debug-server] add({a}, {b})")
+    return a + b
+
+
+@mcp.tool()
+def get_secret_word() -> str:
+    print("[debug-server] get_secret_word()")
+    return random.choice(["apple", "banana", "cherry"])
+
+
+@mcp.tool()
+def get_current_weather(city: str) -> str:
+    print(f"[debug-server] get_current_weather({city})")
+
+    endpoint = "https://wttr.in"
+    response = requests.get(f"{endpoint}/{city}")
+    return response.text
+
+
+if __name__ == "__main__":
+    mcp.run(transport="streamable-http")

{openai_agents-0.0.14 → openai_agents-0.0.15}/examples/research_bot/agents/search_agent.py

@@ -3,7 +3,7 @@ from agents.model_settings import ModelSettings
 
 INSTRUCTIONS = (
     "You are a research assistant. Given a search term, you search the web for that term and "
-    "produce a concise summary of the results. The summary must 2-3 paragraphs and less than 300 "
+    "produce a concise summary of the results. The summary must be 2-3 paragraphs and less than 300 "
     "words. Capture the main points. Write succinctly, no need to have complete sentences or good "
     "grammar. This will be consumed by someone synthesizing a report, so its vital you capture the "
     "essence and ignore any fluff. Do not include any additional commentary other than the summary "

{openai_agents-0.0.14 → openai_agents-0.0.15}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "openai-agents"
-version = "0.0.14"
+version = "0.0.15"
 description = "OpenAI Agents SDK"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -13,7 +13,7 @@ dependencies = [
     "typing-extensions>=4.12.2, <5",
     "requests>=2.0, <3",
     "types-requests>=2.0, <3",
-    "mcp>=1.6.0, <2; python_version >= '3.10'",
+    "mcp>=1.8.0, <2; python_version >= '3.10'",
 ]
 classifiers = [
     "Typing :: Typed",

{openai_agents-0.0.14 → openai_agents-0.0.15}/src/agents/extensions/models/litellm_model.py

@@ -269,6 +269,8 @@ class LitellmModel(Model):
             extra_kwargs["extra_query"] = model_settings.extra_query
         if model_settings.metadata:
             extra_kwargs["metadata"] = model_settings.metadata
+        if model_settings.extra_body and isinstance(model_settings.extra_body, dict):
+            extra_kwargs.update(model_settings.extra_body)
 
         ret = await litellm.acompletion(
             model=self.model,

{openai_agents-0.0.14 → openai_agents-0.0.15}/src/agents/mcp/__init__.py

@@ -5,6 +5,8 @@ try:
         MCPServerSseParams,
         MCPServerStdio,
         MCPServerStdioParams,
+        MCPServerStreamableHttp,
+        MCPServerStreamableHttpParams,
     )
 except ImportError:
     pass
@@ -17,5 +19,7 @@ __all__ = [
     "MCPServerSseParams",
     "MCPServerStdio",
     "MCPServerStdioParams",
+    "MCPServerStreamableHttp",
+    "MCPServerStreamableHttpParams",
     "MCPUtil",
 ]

{openai_agents-0.0.14 → openai_agents-0.0.15}/src/agents/mcp/server.py

@@ -10,7 +10,9 @@ from typing import Any, Literal
 from anyio.streams.memory import MemoryObjectReceiveStream, MemoryObjectSendStream
 from mcp import ClientSession, StdioServerParameters, Tool as MCPTool, stdio_client
 from mcp.client.sse import sse_client
-from mcp.types import CallToolResult, JSONRPCMessage
+from mcp.client.streamable_http import GetSessionIdCallback, streamablehttp_client
+from mcp.shared.message import SessionMessage
+from mcp.types import CallToolResult
 from typing_extensions import NotRequired, TypedDict
 
 from ..exceptions import UserError
@@ -83,8 +85,9 @@ class _MCPServerWithClientSession(MCPServer, abc.ABC):
         self,
     ) -> AbstractAsyncContextManager[
         tuple[
-            MemoryObjectReceiveStream[JSONRPCMessage | Exception],
-            MemoryObjectSendStream[JSONRPCMessage],
+            MemoryObjectReceiveStream[SessionMessage | Exception],
+            MemoryObjectSendStream[SessionMessage],
+            GetSessionIdCallback | None
         ]
     ]:
         """Create the streams for the server."""
@@ -105,7 +108,11 @@ class _MCPServerWithClientSession(MCPServer, abc.ABC):
         """Connect to the server."""
         try:
             transport = await self.exit_stack.enter_async_context(self.create_streams())
-            read, write = transport
+            # streamablehttp_client returns (read, write, get_session_id)
+            # sse_client returns (read, write)
+
+            read, write, *_ = transport
+
             session = await self.exit_stack.enter_async_context(
                 ClientSession(
                     read,
@@ -232,8 +239,9 @@ class MCPServerStdio(_MCPServerWithClientSession):
         self,
     ) -> AbstractAsyncContextManager[
         tuple[
-            MemoryObjectReceiveStream[JSONRPCMessage | Exception],
-            MemoryObjectSendStream[JSONRPCMessage],
+            MemoryObjectReceiveStream[SessionMessage | Exception],
+            MemoryObjectSendStream[SessionMessage],
+            GetSessionIdCallback | None
         ]
     ]:
         """Create the streams for the server."""
@@ -302,8 +310,9 @@ class MCPServerSse(_MCPServerWithClientSession):
         self,
     ) -> AbstractAsyncContextManager[
         tuple[
-            MemoryObjectReceiveStream[JSONRPCMessage | Exception],
-            MemoryObjectSendStream[JSONRPCMessage],
+            MemoryObjectReceiveStream[SessionMessage | Exception],
+            MemoryObjectSendStream[SessionMessage],
+            GetSessionIdCallback | None
         ]
     ]:
         """Create the streams for the server."""
@@ -318,3 +327,84 @@ class MCPServerSse(_MCPServerWithClientSession):
     def name(self) -> str:
         """A readable name for the server."""
         return self._name
+
+
+class MCPServerStreamableHttpParams(TypedDict):
+    """Mirrors the params in`mcp.client.streamable_http.streamablehttp_client`."""
+
+    url: str
+    """The URL of the server."""
+
+    headers: NotRequired[dict[str, str]]
+    """The headers to send to the server."""
+
+    timeout: NotRequired[timedelta]
+    """The timeout for the HTTP request. Defaults to 5 seconds."""
+
+    sse_read_timeout: NotRequired[timedelta]
+    """The timeout for the SSE connection, in seconds. Defaults to 5 minutes."""
+
+    terminate_on_close: NotRequired[bool]
+    """Terminate on close"""
+
+
+class MCPServerStreamableHttp(_MCPServerWithClientSession):
+    """MCP server implementation that uses the Streamable HTTP transport. See the [spec]
+    (https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http)
+    for details.
+    """
+
+    def __init__(
+        self,
+        params: MCPServerStreamableHttpParams,
+        cache_tools_list: bool = False,
+        name: str | None = None,
+        client_session_timeout_seconds: float | None = 5,
+    ):
+        """Create a new MCP server based on the Streamable HTTP transport.
+
+        Args:
+            params: The params that configure the server. This includes the URL of the server,
+                the headers to send to the server, the timeout for the HTTP request, and the
+                timeout for the Streamable HTTP connection and whether we need to
+                terminate on close.
+
+            cache_tools_list: Whether to cache the tools list. If `True`, the tools list will be
+                cached and only fetched from the server once. If `False`, the tools list will be
+                fetched from the server on each call to `list_tools()`. The cache can be
+                invalidated by calling `invalidate_tools_cache()`. You should set this to `True`
+                if you know the server will not change its tools list, because it can drastically
+                improve latency (by avoiding a round-trip to the server every time).
+
+            name: A readable name for the server. If not provided, we'll create one from the
+                URL.
+
+            client_session_timeout_seconds: the read timeout passed to the MCP ClientSession.
+        """
+        super().__init__(cache_tools_list, client_session_timeout_seconds)
+
+        self.params = params
+        self._name = name or f"streamable_http: {self.params['url']}"
+
+    def create_streams(
+        self,
+    ) -> AbstractAsyncContextManager[
+        tuple[
+            MemoryObjectReceiveStream[SessionMessage | Exception],
+            MemoryObjectSendStream[SessionMessage],
+            GetSessionIdCallback | None
+        ]
+    ]:
+        """Create the streams for the server."""
+        return streamablehttp_client(
+            url=self.params["url"],
+            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)
+        )
+
+    @property
+    def name(self) -> str:
+        """A readable name for the server."""
+        return self._name

{openai_agents-0.0.14 → openai_agents-0.0.15}/src/agents/models/chatcmpl_converter.py

@@ -234,7 +234,7 @@ class Converter:
                         type="image_url",
                         image_url={
                             "url": casted_image_param["image_url"],
-                            "detail": casted_image_param["detail"],
+                            "detail": casted_image_param.get("detail", "auto"),
                         },
                     )
                 )

openai_agents-0.0.15/tests/models/test_litellm_extra_body.py

@@ -0,0 +1,45 @@
+import litellm
+import pytest
+from litellm.types.utils import Choices, Message, ModelResponse, Usage
+
+from agents.extensions.models.litellm_model import LitellmModel
+from agents.model_settings import ModelSettings
+from agents.models.interface import ModelTracing
+
+
+@pytest.mark.allow_call_model_methods
+@pytest.mark.asyncio
+async def test_extra_body_is_forwarded(monkeypatch):
+    """
+    Forward `extra_body` entries into litellm.acompletion kwargs.
+
+    This ensures that user-provided parameters (e.g. cached_content)
+    arrive alongside default arguments.
+    """
+    captured: dict[str, object] = {}
+
+    async def fake_acompletion(model, messages=None, **kwargs):
+        captured.update(kwargs)
+        msg = Message(role="assistant", content="ok")
+        choice = Choices(index=0, message=msg)
+        return ModelResponse(choices=[choice], usage=Usage(0, 0, 0))
+
+    monkeypatch.setattr(litellm, "acompletion", fake_acompletion)
+    settings = ModelSettings(
+        temperature=0.1,
+        extra_body={"cached_content": "some_cache", "foo": 123}
+    )
+    model = LitellmModel(model="test-model")
+
+    await model.get_response(
+        system_instructions=None,
+        input=[],
+        model_settings=settings,
+        tools=[],
+        output_schema=None,
+        handoffs=[],
+        tracing=ModelTracing.DISABLED,
+        previous_response_id=None,
+    )
+
+    assert {"cached_content": "some_cache", "foo": 123}.items() <= captured.items()