Python: update FoundryAgent for hosted agent sessions (#5447)

* fixes to FoundryAgent to connect to new hosted agents

Co-authored-by: Copilot <copilot@github.com>

* fix mypy

Co-authored-by: Copilot <copilot@github.com>

* Python: remove Foundry service session helpers

Remove the public hosted-agent service session CRUD helpers from FoundryAgent and drop the related feature-stage inventory entry.

Update the hosted-agent sample to create and delete service sessions directly through the preview AIProjectClient APIs, and tighten a few test harnesses surfaced by full workspace validation.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix from merge

* fix hosted env detection

Co-authored-by: Copilot <copilot@github.com>

* reverted sample update

* fix tests and code

Co-authored-by: Copilot <copilot@github.com>

* remove aenter

* skipping some tests

Co-authored-by: Copilot <copilot@github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

python/packages/foundry_hosting/agent_framework_foundry_hosting/_responses.py

@@ -172,12 +172,7 @@ class ResponsesHostServer(ResponsesAgentServerHost):
         self._agent = agent
         self.response_handler(self._handle_response)  # pyright: ignore[reportUnknownMemberType]
 
-    @staticmethod
-    def _is_streaming_request(request: CreateResponse) -> bool:
-        """Check if the request is a streaming request."""
-        return request.stream is not None and request.stream is True
-
-    def _handle_response(
+    async def _handle_response(
         self,
         request: CreateResponse,
         context: ResponseContext,
@@ -186,11 +181,10 @@ class ResponsesHostServer(ResponsesAgentServerHost):
         """Handle the creation of a response."""
         if self._is_workflow_agent:
             # Workflow agents are handled differently because they require checkpoint restoration
-            return self._handle_workflow_agent(request, context)
+            return self._handle_inner_workflow(request, context)
+        return self._handle_inner_agent(request, context)
 
-        return self._handle_regular_agent(request, context)
-
-    async def _handle_regular_agent(
+    async def _handle_inner_agent(
         self,
         request: CreateResponse,
         context: ResponseContext,
@@ -200,25 +194,24 @@ class ResponsesHostServer(ResponsesAgentServerHost):
         input_messages = _items_to_messages(input_items)
 
         history = await context.get_history()
-        messages: list[str | Content | Message] = [*_output_items_to_messages(history), *input_messages]
+        run_kwargs: dict[str, Any] = {"messages": [*_output_items_to_messages(history), *input_messages]}
+        is_streaming_request = request.stream is not None and request.stream is True
 
         chat_options, are_options_set = _to_chat_options(request)
 
-        is_streaming_request = self._is_streaming_request(request)
         response_event_stream = ResponseEventStream(response_id=context.response_id, model=request.model)
 
         yield response_event_stream.emit_created()
         yield response_event_stream.emit_in_progress()
 
+        if are_options_set and not isinstance(self._agent, RawAgent):
+            logger.warning("Agent doesn't support runtime options. They will be ignored.")
+        else:
+            run_kwargs["options"] = chat_options
+
         if not is_streaming_request:
             # Run the agent in non-streaming mode
-            if isinstance(self._agent, RawAgent):
-                raw_agent = cast("RawAgent[Any]", self._agent)  # type: ignore[redundant-cast]  # pyright: ignore[reportUnknownMemberType]
-                response = await raw_agent.run(messages, stream=False, options=chat_options)
-            else:
-                if are_options_set:
-                    logger.warning("Agent doesn't support runtime options. They will be ignored.")
-                response = await self._agent.run(messages, stream=False)
+            response = await self._agent.run(stream=False, **run_kwargs)  # type: ignore[reportUnknownMemberType]
 
             for message in response.messages:
                 for content in message.contents:
@@ -228,20 +221,12 @@ class ResponsesHostServer(ResponsesAgentServerHost):
             yield response_event_stream.emit_completed()
             return
 
-        # Run the agent in streaming mode
-        if isinstance(self._agent, RawAgent):
-            raw_agent = cast("RawAgent[Any]", self._agent)  # type: ignore[redundant-cast]  # pyright: ignore[reportUnknownMemberType]
-            response_stream = raw_agent.run(messages, stream=True, options=chat_options)
-        else:
-            if are_options_set:
-                logger.warning("Agent doesn't support runtime options. They will be ignored.")
-            response_stream = self._agent.run(messages, stream=True)
-
         # Track the current active output item builder for streaming;
         # lazily created on matching content, closed when a different type arrives.
         tracker = _OutputItemTracker(response_event_stream)
 
-        async for update in response_stream:
+        # Run the agent in streaming mode
+        async for update in self._agent.run(stream=True, **run_kwargs):  # type: ignore[reportUnknownMemberType]
             for content in update.contents:
                 for event in tracker.handle(content):
                     yield event
@@ -256,7 +241,7 @@ class ResponsesHostServer(ResponsesAgentServerHost):
 
         yield response_event_stream.emit_completed()
 
-    async def _handle_workflow_agent(
+    async def _handle_inner_workflow(
         self,
         request: CreateResponse,
         context: ResponseContext,
@@ -269,8 +254,7 @@ class ResponsesHostServer(ResponsesAgentServerHost):
         """
         input_items = await context.get_input_items()
         input_messages = _items_to_messages(input_items)
-
-        is_streaming_request = self._is_streaming_request(request)
+        is_streaming_request = request.stream is not None and request.stream is True
 
         _, are_options_set = _to_chat_options(request)
         if are_options_set:
@@ -311,7 +295,8 @@ class ResponsesHostServer(ResponsesAgentServerHost):
         response_event_stream = ResponseEventStream(response_id=context.response_id, model=request.model)
 
         # Create a new checkpoint storage for this response based on the following rules:
-        # - If no previous response ID or conversation ID is provided, create a new checkpoint storage for this response
+        # - If no previous response ID or conversation ID is provided,
+        #   create a new checkpoint storage for this response
         # - If a previous response ID is provided, create a new checkpoint storage for this response
         # - If a conversation ID is provided, reuse the existing checkpoint storage for the conversation
         context_id = context.conversation_id or context.response_id
@@ -333,14 +318,12 @@ class ResponsesHostServer(ResponsesAgentServerHost):
             yield response_event_stream.emit_completed()
             return
 
-        # Run the agent in streaming mode
-        response_stream = self._agent.run(input_messages, stream=True, checkpoint_storage=checkpoint_storage)
-
         # Track the current active output item builder for streaming;
         # lazily created on matching content, closed when a different type arrives.
         tracker = _OutputItemTracker(response_event_stream)
 
-        async for update in response_stream:
+        # Run the workflow agent in streaming mode
+        async for update in self._agent.run(input_messages, stream=True, checkpoint_storage=checkpoint_storage):
             for content in update.contents:
                 for event in tracker.handle(content):
                     yield event
@@ -355,7 +338,6 @@ class ResponsesHostServer(ResponsesAgentServerHost):
 
         await self._delete_not_latest_checkpoints(checkpoint_storage, self._agent.workflow.name)
         yield response_event_stream.emit_completed()
-        return
 
     @staticmethod
     async def _delete_not_latest_checkpoints(checkpoint_storage: FileCheckpointStorage, workflow_name: str) -> None:

python/packages/foundry_hosting/tests/test_responses.py

@@ -41,9 +41,10 @@ def _make_agent(
     *,
     response: AgentResponse | None = None,
     stream_updates: list[AgentResponseUpdate] | None = None,
+    raw_agent: bool = True,
 ) -> MagicMock:
     """Create a mock agent implementing SupportsAgentRun."""
-    agent = MagicMock(spec=RawAgent)
+    agent = MagicMock(spec=RawAgent) if raw_agent else MagicMock()
     agent.id = "test-agent"
     agent.name = "Test Agent"
     agent.description = "A mock agent for testing"
@@ -267,10 +268,18 @@ class TestNonStreaming:
 
     async def test_chat_options_forwarded(self) -> None:
         agent = _make_agent(
-            response=AgentResponse(messages=[Message(role="assistant", contents=[Content.from_text("ok")])])
+            response=AgentResponse(messages=[Message(role="assistant", contents=[Content.from_text("ok")])]),
+            raw_agent=True,
         )
         server = _make_server(agent)
-        resp = await _post(server, stream=False, temperature=0.5, top_p=0.9, max_output_tokens=1024)
+        resp = await _post(
+            server,
+            stream=False,
+            temperature=0.5,
+            top_p=0.9,
+            max_output_tokens=1024,
+            parallel_tool_calls=True,
+        )
 
         assert resp.status_code == 200
         agent.run.assert_awaited_once()
@@ -280,6 +289,7 @@ class TestNonStreaming:
         assert options["temperature"] == 0.5
         assert options["top_p"] == 0.9
         assert options["max_tokens"] == 1024
+        assert options["allow_multiple_tool_calls"] is True
 
 
 # endregion
@@ -289,6 +299,31 @@ class TestNonStreaming:
 
 
 class TestStreaming:
+    async def test_chat_options_forwarded(self) -> None:
+        agent = _make_agent(
+            stream_updates=[AgentResponseUpdate(contents=[Content.from_text("ok")], role="assistant")],
+            raw_agent=True,
+        )
+        server = _make_server(agent)
+        resp = await _post(
+            server,
+            stream=True,
+            temperature=0.5,
+            top_p=0.9,
+            max_output_tokens=1024,
+            parallel_tool_calls=True,
+        )
+
+        assert resp.status_code == 200
+        agent.run.assert_called_once()
+        call_kwargs = agent.run.call_args.kwargs
+        assert call_kwargs["stream"] is True
+        options = call_kwargs["options"]
+        assert options["temperature"] == 0.5
+        assert options["top_p"] == 0.9
+        assert options["max_tokens"] == 1024
+        assert options["allow_multiple_tool_calls"] is True
+
     async def test_basic_text_streaming(self) -> None:
         agent = _make_agent(
             stream_updates=[
@@ -1426,7 +1461,7 @@ class TestMultiTurnMixedContent:
         assert body["status"] == "completed"
 
         # Verify agent received text + image
-        messages = agent.run.call_args.args[0]
+        messages = agent.run.call_args.kwargs["messages"]
         assert len(messages) == 1
         assert messages[0].role == "user"
         assert len(messages[0].contents) == 2
@@ -1464,7 +1499,7 @@ class TestMultiTurnMixedContent:
         body = resp.json()
         assert body["status"] == "completed"
 
-        messages = agent.run.call_args.args[0]
+        messages = agent.run.call_args.kwargs["messages"]
         assert len(messages) == 1
         assert len(messages[0].contents) == 2
         assert messages[0].contents[0].type == "text"
@@ -1501,7 +1536,7 @@ class TestMultiTurnMixedContent:
         body = resp.json()
         assert body["status"] == "completed"
 
-        messages = agent.run.call_args.args[0]
+        messages = agent.run.call_args.kwargs["messages"]
         assert len(messages) == 1
         assert len(messages[0].contents) == 2
         assert messages[0].contents[0].type == "text"
@@ -1542,7 +1577,7 @@ class TestMultiTurnMixedContent:
         body = resp.json()
         assert body["status"] == "completed"
 
-        messages = agent.run.call_args.args[0]
+        messages = agent.run.call_args.kwargs["messages"]
         assert len(messages) == 3
         assert messages[0].role == "user"
         assert messages[0].contents[0].type == "text"
@@ -1591,7 +1626,7 @@ class TestMultiTurnMixedContent:
         assert body2["status"] == "completed"
 
         # Verify second call receives history from turn 1 + text+image input
-        second_call_messages = agent.run.call_args_list[1].args[0]
+        second_call_messages = agent.run.call_args_list[1].kwargs["messages"]
         # History: output message from turn 1 ("Send me an image")
         # Input: message with text + image
         assert len(second_call_messages) >= 2
@@ -1652,7 +1687,7 @@ class TestMultiTurnMixedContent:
         assert resp2.json()["status"] == "completed"
 
         # Verify turn 2 received history including function call/result
-        second_call_messages = agent.run.call_args_list[1].args[0]
+        second_call_messages = agent.run.call_args_list[1].kwargs["messages"]
         roles = [m.role for m in second_call_messages]
         assert "assistant" in roles
         assert "tool" in roles
@@ -1703,7 +1738,7 @@ class TestMultiTurnMixedContent:
         assert resp2.json()["status"] == "completed"
 
         # Verify history includes the reasoning and text from turn 1
-        second_call_messages = agent.run.call_args_list[1].args[0]
+        second_call_messages = agent.run.call_args_list[1].kwargs["messages"]
         assert len(second_call_messages) >= 2  # history + new input
 
     async def test_multi_turn_with_mixed_content_and_streaming(self) -> None:
@@ -1795,7 +1830,7 @@ class TestMultiTurnMixedContent:
         body = resp.json()
         assert body["status"] == "completed"
 
-        messages = agent.run.call_args.args[0]
+        messages = agent.run.call_args.kwargs["messages"]
         assert len(messages) == 2
         assert messages[0].role == "user"
         assert messages[0].contents[0].type == "text"
@@ -1867,7 +1902,7 @@ class TestMultiTurnMixedContent:
         assert resp3.json()["status"] == "completed"
 
         # Verify turn 3 received full history from turns 1+2 plus new image input
-        third_call_messages = agent.run.call_args_list[2].args[0]
+        third_call_messages = agent.run.call_args_list[2].kwargs["messages"]
         # Should have: history from turn 1 (assistant text) + history from turn 2
         # (function_call, function_call_output, text) + new input (text + image)
         assert len(third_call_messages) >= 5
@@ -1918,7 +1953,7 @@ class TestMultiTurnMixedContent:
         body = resp.json()
         assert body["status"] == "completed"
 
-        messages = agent.run.call_args.args[0]
+        messages = agent.run.call_args.kwargs["messages"]
         assert len(messages) == 1
         assert len(messages[0].contents) == 2
         assert messages[0].contents[0].type == "text"
@@ -1982,7 +2017,7 @@ class TestMultiTurnMixedContent:
         assert resp2.json()["status"] == "completed"
 
         # Verify turn 2 received history from turn 1 + new text+file input
-        second_call_messages = agent.run.call_args_list[1].args[0]
+        second_call_messages = agent.run.call_args_list[1].kwargs["messages"]
         assert len(second_call_messages) >= 2
 
         # History should include the assistant response from turn 1
@@ -2050,7 +2085,7 @@ class TestMultiTurnMixedContent:
         assert resp2.json()["status"] == "completed"
 
         # Verify turn 2 received history with function call + new text+image
-        second_call_messages = agent.run.call_args_list[1].args[0]
+        second_call_messages = agent.run.call_args_list[1].kwargs["messages"]
         # History should contain function_call and function_result from turn 1
         fc_contents = [
             c for m in second_call_messages if m.role == "assistant" for c in m.contents if c.type == "function_call"