Files
agent-framework/python/packages/orchestrations/tests/test_handoff.py
T
Eduard van Valkenburg 3dc59c83b5 Python: [BREAKING] Moved to a single get_response and run API (#3379)
* WIP

* big update to new ResponseStream model

* fixed tests and typing

* fixed tests and typing

* fixed tools typevar import

* fix

* mypy fix

* mypy fixes and some cleanup

* fix missing quoted names

* and client

* fix  imports agui

* fix anthropic override

* fix agui

* fix ag ui

* fix import

* fix anthropic types

* fix mypy

* refactoring

* updated typing

* fix 3.11

* fixes

* redid layering of chat clients and agents

* redid layering of chat clients and agents

* Fix lint, type, and test issues after rebase

- Add @overload decorators to AgentProtocol.run() for type compatibility
- Add missing docstring params (middleware, function_invocation_configuration)
- Fix TODO format (TD002) by adding author tags
- Fix broken observability tests from upstream:
  - Replace non-existent use_instrumentation with direct instantiation
  - Replace non-existent use_agent_instrumentation with AgentTelemetryLayer mixin
  - Fix get_streaming_response to use get_response(stream=True)
  - Add AgentInitializationError import
  - Update streaming exception tests to match actual behavior

* Fix AgentExecutionException import error in test_agents.py

- Replace non-existent AgentExecutionException with AgentRunException

* Fix test import and asyncio deprecation issues

- Add 'tests' to pythonpath in ag-ui pyproject.toml for utils_test_ag_ui import
- Replace deprecated asyncio.get_event_loop().run_until_complete with asyncio.run

* Fix azure-ai test failures

- Update _prepare_options patching to use correct class path
- Fix test_to_azure_ai_agent_tools_web_search_missing_connection to clear env vars

* Convert ag-ui utils_test_ag_ui.py to conftest.py

- Move test utilities to conftest.py for proper pytest discovery
- Update all test imports to use conftest instead of utils_test_ag_ui
- Remove old utils_test_ag_ui.py file
- Revert pythonpath change in pyproject.toml

* fix: use relative imports for ag-ui test utilities

* fix agui

* Rename Bare*Client to Raw*Client and BaseChatClient

- Renamed BareChatClient to BaseChatClient (abstract base class)
- Renamed BareOpenAIChatClient to RawOpenAIChatClient
- Renamed BareOpenAIResponsesClient to RawOpenAIResponsesClient
- Renamed BareAzureAIClient to RawAzureAIClient
- Added warning docstrings to Raw* classes about layer ordering
- Updated README in samples/getting_started/agents/custom with layer docs
- Added test for span ordering with function calling

* Fix layer ordering: FunctionInvocationLayer before ChatTelemetryLayer

This ensures each inner LLM call gets its own telemetry span, resulting in
the correct span sequence: chat -> execute_tool -> chat

Updated all production clients and test mocks to use correct ordering:
- ChatMiddlewareLayer (first)
- FunctionInvocationLayer (second)
- ChatTelemetryLayer (third)
- BaseChatClient/Raw...Client (fourth)

* Remove run_stream usage

* Fix conversation_id propagation

* Python: Add BaseAgent implementation for Claude Agent SDK (#3509)

* Added ClaudeAgent implementation

* Updated streaming logic

* Small updates

* Small update

* Fixes

* Small fix

* Naming improvements

* Updated imports

* Addressed comments

* Updated package versions

* Update Claude agent connector layering

* fix test and plugin

* Store function middleware in invocation layer

* Fix telemetry streaming and ag-ui tests

* Remove legacy ag-ui tests folder

* updates

* Remove terminate flag from FunctionInvocationContext, use MiddlewareTermination instead

- Remove terminate attribute from FunctionInvocationContext
- Add result attribute to MiddlewareTermination to carry function results
- FunctionMiddlewarePipeline.execute() now lets MiddlewareTermination propagate
- _auto_invoke_function captures context.result in exception before re-raising
- _try_execute_function_calls catches MiddlewareTermination and sets should_terminate
- Fix handoff middleware to append to chat_client.function_middleware directly
- Update tests to use raise MiddlewareTermination instead of context.terminate
- Add middleware flow documentation in samples/concepts/tools/README.md
- Fix ag-ui to use FunctionMiddlewarePipeline instead of removed create_function_middleware_pipeline

* fix: remove references to removed terminate flag in purview tests, add type ignore

* fix: move _test_utils.py from package to test folder

* fix: call get_final_response() to trigger context provider notification in streaming test

* fix: correct broken links in tools README

* docs: clarify default middleware behavior in summary table

* fix: ensure inner stream result hooks are called when using map()/from_awaitable()

* Fix mypy type errors

* Address PR review comments on observability.py

- Remove TODO comment about unconsumed streams, add explanatory note instead
- Remove redundant _close_span cleanup hook (already called in _finalize_stream)
- Clarify behavior: cleanup hooks run after stream iteration, if stream is not
  consumed the span remains open until garbage collected

* Remove gen_ai.client.operation.duration from span attributes

Duration is a metrics-only attribute per OpenTelemetry semantic conventions.
It should be recorded to the histogram but not set as a span attribute.

* Remove duration from _get_response_attributes, pass directly to _capture_response

Duration is a metrics-only attribute. It's now passed directly to _capture_response
instead of being included in the attributes dict that gets set on the span.

* Remove redundant _close_span cleanup hook in AgentTelemetryLayer

_finalize_stream already calls _close_span() in its finally block,
so adding it as a separate cleanup hook is redundant.

* Use weakref.finalize to close span when stream is garbage collected

If a user creates a streaming response but never consumes it, the cleanup
hooks won't run. Now we register a weak reference finalizer that will close
the span when the stream object is garbage collected, ensuring spans don't
leak in this scenario.

* Fix _get_finalizers_from_stream to use _result_hooks attribute

Renamed function to _get_result_hooks_from_stream and fixed it to
look for the _result_hooks attribute which is the correct name in
ResponseStream class.

* Add missing asyncio import in test_request_info_mixin.py

* Fix leftover merge conflict marker in image_generation sample

* Update integration tests

* Fix integration tests: increase max_iterations from 1 to 2

Tests with tool_choice options require at least 2 iterations:
1. First iteration to get function call and execute the tool
2. Second iteration to get the final text response

With max_iterations=1, streaming tests would return early with only
the function call/result but no final text content.

* Fix duplicate function call error in conversation-based APIs

When using conversation_id (for Responses/Assistants APIs), the server
already has the function call message from the previous response. We
should only send the new function result message, not all messages
including the function call which would cause a duplicate ID error.

Fix: When conversation_id is set, only send the last message (the tool
result) instead of all response.messages.

* Add regression test for conversation_id propagation between tool iterations

Port test from PR #3664 with updates for new streaming API pattern.
Tests that conversation_id is properly updated in options dict during
function invocation loop iterations.

* Fix tool_choice=required to return after tool execution

When tool_choice is 'required', the user's intent is to force exactly one
tool call. After the tool executes, return immediately with the function
call and result - don't continue to call the model again.

This fixes integration tests that were failing with empty text responses
because with tool_choice=required, the model would keep returning function
calls instead of text.

Also adds regression tests for:
- conversation_id propagation between tool iterations (from PR #3664)
- tool_choice=required returns after tool execution

* Document tool_choice behavior in tools README

- Add table explaining tool_choice values (auto, none, required)
- Explain why tool_choice=required returns immediately after tool execution
- Add code example showing the difference between required and auto
- Update flow diagram to show the early return path for tool_choice=required

* Fix tool_choice=None behavior - don't default to 'auto'

Remove the hardcoded default of 'auto' for tool_choice in ChatAgent init.
When tool_choice is not specified (None), it will now not be sent to the
API, allowing the API's default behavior to be used.

Users who want tool_choice='auto' can still explicitly set it either in
default_options or at runtime.

Fixes #3585

* Fix tool_choice=none should not remove tools

In OpenAI Assistants client, tools were not being sent when
tool_choice='none'. This was incorrect - tool_choice='none' means
the model won't call tools, but tools should still be available
in the request (they may be used later in the conversation).

Fixes #3585

* Add test for tool_choice=none preserving tools

Adds a regression test to ensure that when tool_choice='none' is set but
tools are provided, the tools are still sent to the API. This verifies
the fix for #3585.

* Fix tool_choice=none should not remove tools in all clients

Apply the same fix to OpenAI Responses client and Azure AI client:
- OpenAI Responses: Remove else block that popped tool_choice/parallel_tool_calls
- Azure AI: Remove tool_choice != 'none' check when adding tools

When tool_choice='none', the model won't call tools, but tools should
still be sent to the API so they're available for future turns.

Also update README to clarify tool_choice=required supports multiple tools.

Fixes #3585

* Keep tool_choice even when tools is None

Move tool_choice processing outside of the 'if tools' block in OpenAI
Responses client so tool_choice is sent to the API even when no tools
are provided.

* Update test to match new parallel_tool_calls behavior

Changed test_prepare_options_removes_parallel_tool_calls_when_no_tools to
test_prepare_options_preserves_parallel_tool_calls_when_no_tools to reflect
that parallel_tool_calls is now preserved even when no tools are present,
consistent with the tool_choice behavior.

* Fix ChatMessage API and Role enum usage after rebase

- Update ChatMessage instantiation to use keyword args (role=, text=, contents=)
- Fix Role enum comparisons to use .value for string comparison
- Add created_at to AgentResponse in error handling
- Fix AgentResponse.from_updates -> from_agent_run_response_updates
- Fix DurableAgentStateMessage.from_chat_message to convert Role enum to string
- Add Role import where needed

* Fix additional ChatMessage API and method name changes

- Fix ChatMessage usage in workflow files (use text= instead of contents= for strings)
- Fix AgentResponse.from_updates -> from_agent_run_response_updates in workflow files
- Fix test files for ChatMessage and Role enum usage

* Fix remaining ChatMessage API usage in test files

* Fix more ChatMessage and Role API changes in source and test files

- Fix ChatMessage in _magentic.py replan method
- Fix Role enum comparison in test assertions
- Fix remaining test files with old ChatMessage syntax

* Fix ChatMessage and Role API changes across packages

- Add Role import where missing
- Fix ChatMessage signature: positional args to keyword args (role=, text=, contents=)
- Fix Role enum comparisons: .role.value instead of .role string
- Fix FinishReason enum usage in ag-ui event converters
- Rename AgentResponse.from_updates to from_agent_run_response_updates in ag-ui

Fixes API compatibility after Types API Review improvements merge

* Fix ChatMessage and Role API changes in github_copilot tests

* Fix ChatMessage and Role API changes in redis and github_copilot packages

- Fix redis provider: Role enum comparison using .value
- Fix redis tests: ChatMessage signature and Role comparisons
- Fix github_copilot tests: ChatMessage signature and Role comparisons
- Update docstring examples in redis chat message store

* Fix ChatMessage and Role API changes in devui package

- Fix executor: ChatMessage signature change
- Fix conversations: Role enum to string conversion in two places
- Fix tests: ChatMessage signatures and Role comparisons

* Fix ChatMessage and Role API changes in a2a and lab packages

- Fix a2a tests: Role comparisons and ChatMessage signatures
- Fix lab tau2 source: Role enum comparison in flip_messages, log_messages, sliding_window
- Fix lab tau2 tests: ChatMessage signatures and Role comparisons

* Remove duplicate test files from ag-ui/tests (tests are in ag_ui_tests)

* Fix ChatMessage and Role API changes across packages

After rebasing on upstream/main which merged PR #3647 (Types API Review
improvements), fix all packages to use the new API:

- ChatMessage: Use keyword args (role=, text=, contents=) instead of
  positional args
- Role: Compare using .value attribute since it's now an enum

Packages fixed:
- ag-ui: Fixed Role value extraction bugs in _message_adapters.py
- anthropic: Fixed ChatMessage and Role comparisons in tests
- azure-ai: Fixed Role comparison in _client.py
- azure-ai-search: Fixed ChatMessage and Role in source/tests
- bedrock: Fixed ChatMessage signatures in tests
- chatkit: Fixed ChatMessage and Role in source/tests
- copilotstudio: Fixed ChatMessage and Role in tests
- declarative: Fixed ChatMessage in _executors_agents.py
- mem0: Fixed ChatMessage and Role in source/tests
- purview: Fixed ChatMessage in source/tests

* Fix mypy errors for ChatMessage and Role API changes

- durabletask: Use str() fallback in role value extraction
- core: Fix ChatMessage in _orchestrator_helpers.py to use keyword args
- core: Add type ignore for _conversation_state.py contents deserialization
- ag-ui: Fix type ignore comments (call-overload instead of arg-type)
- azure-ai-search: Fix get_role_value type hint to accept Any
- lab: Move get_role_value to module level with Any type hint

* Improve CI test timeout configuration

- Increase job timeout from 10 to 15 minutes
- Reduce per-test timeout to 60s (was 900s/300s)
- Add --timeout_method thread for better timeout handling
- Add --timeout-verbose to see which tests are slow
- Reduce retries from 3 to 2 and delay from 10s to 5s

This ensures individual test timeouts are shorter than the job
timeout, providing better visibility when tests hang.

With 60s timeout and 2 retries, worst case per test is ~180s.

* Fix ChatMessage API usage in docstrings and source

- Fix ChatMessage positional args in docstrings: _serialization.py, _threads.py, _middleware.py
- Fix ChatMessage in tau2 runner.py
- Fix role comparison in _orchestrator_helpers.py to use .value
- Fix role comparison in _group_chat.py docstring example
- Fix role assertions in test_durable_entities.py to use .value

* Revert tool_choice/parallel_tool_calls changes - must be removed when no tools

OpenAI API requires tool_choice and parallel_tool_calls to only be
present when tools are specified. Restored the logic that removes
these options when there are no tools.

- Restored check in _chat_client.py to remove tool_choice and
  parallel_tool_calls when no tools present
- Restored same logic in _responses_client.py
- Reverted test to expect the correct behavior

* fixed issue in tests

* fix: resolve merge conflict markers in ag-ui tests

* fix: restructure ag-ui tests and fix Role/FinishReason to use string types

* fix: streaming function invocation and middleware termination

- Refactor streaming function invocation to use get_final_response() on inner streams
- Fix MiddlewareTermination to accept result parameter for passing results
- Fix _AutoHandoffMiddleware to use MiddlewareTermination instead of context.terminate
- Fix AgentMiddlewareLayer.run() to properly forward function/chat middleware
- Remove duplicate middleware registration in AgentMiddlewareLayer.__init__
- Fix exception handling in _auto_invoke_function to properly capture termination
- Fix mypy errors in core package
- Update tests to use stream=True parameter for unified run API

* fix all tests command

* Refactor integration tests to use pytest fixtures

- Merge testutils.py into conftest.py for azurefunctions integration tests
- Merge dt_testutils.py into conftest.py for durabletask integration tests
- Convert all integration tests to use fixtures instead of direct imports
  (fixes ModuleNotFoundError with --import-mode=importlib)
- Add sample_helper fixture for azurefunctions tests
- Add agent_client_factory and orchestration_helper fixtures for durabletask
- Integration tests now skip with descriptive messages when services unavailable
- Restructure devui tests into tests/devui/ with proper conftest.py
- Add test organization guidelines to CODING_STANDARD.md
- Remove __init__.py from test directories per pytest best practices

* Fix pytest_collection_modifyitems to only skip integration tests

The hook was skipping all tests in the test session, not just
integration tests. Now it only skips items in the integration_tests
directory.

* Fix mem0 tests failing on Python 3.13

Use patch.object on the imported module instead of @patch with string
path to ensure the mock takes effect regardless of import timing.

* fix mem0

* another attempt for mem0

* fix for mem0

* fix mem0

* Increase worker initialization wait time in durabletask tests

Increase from 2 to 8 seconds to allow time for:
- Python startup and module imports
- Azure OpenAI client creation
- Agent registration with DTS worker
- Worker connection to DTS

This helps prevent test failures in CI where the first tests may run
before the worker is fully ready to process requests.

* Fix streaming test to use ResponseStream with finalizer

The _consume_stream method now expects a ResponseStream that can provide
a final AgentResponse via get_final_response(). Update the test to use
ResponseStream with AgentResponse.from_updates as the finalizer.

* Fix MockToolCallingAgent to use new ResponseStream API and update samples

* small updates to run_stream to run

* fix sub workflow

* temp fix for az func test

---------

Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>
2026-02-05 20:09:58 +00:00

732 lines
28 KiB
Python

# Copyright (c) Microsoft. All rights reserved.
from collections.abc import AsyncIterable, Awaitable, Mapping, Sequence
from typing import Any, cast
from unittest.mock import AsyncMock, MagicMock
import pytest
from agent_framework import (
ChatAgent,
ChatMessage,
ChatResponse,
ChatResponseUpdate,
Content,
RequestInfoEvent,
ResponseStream,
WorkflowEvent,
WorkflowOutputEvent,
resolve_agent_id,
)
from agent_framework._clients import BaseChatClient
from agent_framework._middleware import ChatMiddlewareLayer
from agent_framework._tools import FunctionInvocationLayer
from agent_framework.orchestrations import HandoffAgentUserRequest, HandoffBuilder
class MockChatClient(ChatMiddlewareLayer[Any], FunctionInvocationLayer[Any], BaseChatClient[Any]):
"""Mock chat client for testing handoff workflows."""
def __init__(
self,
*,
name: str = "",
handoff_to: str | None = None,
**kwargs: Any,
) -> None:
"""Initialize the mock chat client.
Args:
name: The name of the agent using this chat client.
handoff_to: The name of the agent to hand off to, or None for no handoff.
This is hardcoded for testing purposes so that the agent always attempts to hand off.
"""
ChatMiddlewareLayer.__init__(self)
FunctionInvocationLayer.__init__(self)
BaseChatClient.__init__(self)
self._name = name
self._handoff_to = handoff_to
self._call_index = 0
def _inner_get_response(
self,
*,
messages: Sequence[ChatMessage],
stream: bool,
options: Mapping[str, Any],
**kwargs: Any,
) -> Awaitable[ChatResponse] | ResponseStream[ChatResponseUpdate, ChatResponse]:
if stream:
return self._build_streaming_response(options=dict(options))
async def _get() -> ChatResponse:
contents = _build_reply_contents(self._name, self._handoff_to, self._next_call_id())
reply = ChatMessage(
role="assistant",
contents=contents,
)
return ChatResponse(messages=reply, response_id="mock_response")
return _get()
def _build_streaming_response(self, *, options: dict[str, Any]) -> ResponseStream[ChatResponseUpdate, ChatResponse]:
async def _stream() -> AsyncIterable[ChatResponseUpdate]:
contents = _build_reply_contents(self._name, self._handoff_to, self._next_call_id())
yield ChatResponseUpdate(contents=contents, role="assistant", finish_reason="stop")
def _finalize(updates: Sequence[ChatResponseUpdate]) -> ChatResponse:
response_format = options.get("response_format")
output_format_type = response_format if isinstance(response_format, type) else None
return ChatResponse.from_updates(updates, output_format_type=output_format_type)
return ResponseStream(_stream(), finalizer=_finalize)
def _next_call_id(self) -> str | None:
if not self._handoff_to:
return None
call_id = f"{self._name}-handoff-{self._call_index}"
self._call_index += 1
return call_id
def _build_reply_contents(
agent_name: str,
handoff_to: str | None,
call_id: str | None,
) -> list[Content]:
contents: list[Content] = []
if handoff_to and call_id:
contents.append(
Content.from_function_call(
call_id=call_id, name=f"handoff_to_{handoff_to}", arguments={"handoff_to": handoff_to}
)
)
text = f"{agent_name} reply"
contents.append(Content.from_text(text=text))
return contents
class MockHandoffAgent(ChatAgent):
"""Mock agent that can hand off to another agent."""
def __init__(
self,
*,
name: str,
handoff_to: str | None = None,
) -> None:
"""Initialize the mock handoff agent.
Args:
name: The name of the agent.
handoff_to: The name of the agent to hand off to, or None for no handoff.
This is hardcoded for testing purposes so that the agent always attempts to hand off.
"""
super().__init__(chat_client=MockChatClient(name=name, handoff_to=handoff_to), name=name, id=name)
async def _drain(stream: AsyncIterable[WorkflowEvent]) -> list[WorkflowEvent]:
return [event async for event in stream]
async def test_handoff():
"""Test that agents can hand off to each other."""
# `triage` hands off to `specialist`, who then hands off to `escalation`.
# `escalation` has no handoff, so the workflow should request user input to continue.
triage = MockHandoffAgent(name="triage", handoff_to="specialist")
specialist = MockHandoffAgent(name="specialist", handoff_to="escalation")
escalation = MockHandoffAgent(name="escalation")
# Without explicitly defining handoffs, the builder will create connections
# between all agents.
workflow = (
HandoffBuilder(participants=[triage, specialist, escalation])
.with_start_agent(triage)
.with_termination_condition(lambda conv: sum(1 for m in conv if m.role == "user") >= 2)
.build()
)
# Start conversation - triage hands off to specialist then escalation
# escalation won't trigger a handoff, so the response from it will become
# a request for user input because autonomous mode is not enabled by default.
events = await _drain(workflow.run("Need technical support", stream=True))
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert requests
assert len(requests) == 1
request = requests[0]
assert isinstance(request.data, HandoffAgentUserRequest)
assert request.source_executor_id == escalation.name
async def test_autonomous_mode_yields_output_without_user_request():
"""Ensure autonomous interaction mode yields output without requesting user input."""
triage = MockHandoffAgent(name="triage", handoff_to="specialist")
specialist = MockHandoffAgent(name="specialist")
workflow = (
HandoffBuilder(participants=[triage, specialist])
.with_start_agent(triage)
# Since specialist has no handoff, the specialist will be generating normal responses.
# With autonomous mode, this should continue until the termination condition is met.
.with_autonomous_mode(
agents=[specialist],
turn_limits={resolve_agent_id(specialist): 1},
)
# This termination condition ensures the workflow runs through both agents.
# First message is the user message to triage, second is triage's response, which
# is a handoff to specialist, third is specialist's response that should not request
# user input due to autonomous mode. Fourth message will come from the specialist
# again and will trigger termination.
.with_termination_condition(lambda conv: len(conv) >= 4)
.build()
)
events = await _drain(workflow.run("Package arrived broken", stream=True))
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert not requests, "Autonomous mode should not request additional user input"
outputs = [ev for ev in events if isinstance(ev, WorkflowOutputEvent)]
assert outputs, "Autonomous mode should yield a workflow output"
final_conversation = outputs[-1].data
assert isinstance(final_conversation, list)
conversation_list = cast(list[ChatMessage], final_conversation)
assert any(msg.role == "assistant" and (msg.text or "").startswith("specialist reply") for msg in conversation_list)
async def test_autonomous_mode_resumes_user_input_on_turn_limit():
"""Autonomous mode should resume user input request when turn limit is reached."""
triage = MockHandoffAgent(name="triage", handoff_to="worker")
worker = MockHandoffAgent(name="worker")
workflow = (
HandoffBuilder(participants=[triage, worker])
.with_start_agent(triage)
.with_autonomous_mode(agents=[worker], turn_limits={resolve_agent_id(worker): 2})
.with_termination_condition(lambda conv: False)
.build()
)
events = await _drain(workflow.run("Start", stream=True))
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert requests and len(requests) == 1, "Turn limit should force a user input request"
assert requests[0].source_executor_id == worker.name
def test_build_fails_without_start_agent():
"""Verify that build() raises ValueError when with_start_agent() was not called."""
triage = MockHandoffAgent(name="triage")
specialist = MockHandoffAgent(name="specialist")
with pytest.raises(ValueError, match=r"Must call with_start_agent\(...\) before building the workflow."):
HandoffBuilder(participants=[triage, specialist]).build()
def test_build_fails_without_participants():
"""Verify that build() raises ValueError when no participants are provided."""
with pytest.raises(
ValueError, match=r"No participants provided\. Call \.participants\(\) or \.register_participants\(\) first."
):
HandoffBuilder().build()
async def test_handoff_async_termination_condition() -> None:
"""Test that async termination conditions work correctly."""
termination_call_count = 0
async def async_termination(conv: list[ChatMessage]) -> bool:
nonlocal termination_call_count
termination_call_count += 1
user_count = sum(1 for msg in conv if msg.role == "user")
return user_count >= 2
coordinator = MockHandoffAgent(name="coordinator", handoff_to="worker")
worker = MockHandoffAgent(name="worker")
workflow = (
HandoffBuilder(participants=[coordinator, worker])
.with_start_agent(coordinator)
.with_termination_condition(async_termination)
.build()
)
events = await _drain(workflow.run("First user message", stream=True))
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert requests
events = await _drain(
workflow.send_responses_streaming({
requests[-1].request_id: [ChatMessage(role="user", text="Second user message")]
})
)
outputs = [ev for ev in events if isinstance(ev, WorkflowOutputEvent)]
assert len(outputs) == 1
final_conversation = outputs[0].data
assert isinstance(final_conversation, list)
final_conv_list = cast(list[ChatMessage], final_conversation)
user_messages = [msg for msg in final_conv_list if msg.role == "user"]
assert len(user_messages) == 2
assert termination_call_count > 0
async def test_tool_choice_preserved_from_agent_config():
"""Verify that agent-level tool_choice configuration is preserved and not overridden."""
# Create a mock chat client that records the tool_choice used
recorded_tool_choices: list[Any] = []
async def mock_get_response(messages: Any, options: dict[str, Any] | None = None, **kwargs: Any) -> ChatResponse:
if options:
recorded_tool_choices.append(options.get("tool_choice"))
return ChatResponse(
messages=[ChatMessage(role="assistant", text="Response")],
response_id="test_response",
)
mock_client = MagicMock()
mock_client.get_response = AsyncMock(side_effect=mock_get_response)
# Create agent with specific tool_choice configuration via default_options
agent = ChatAgent(
chat_client=mock_client,
name="test_agent",
default_options={"tool_choice": {"mode": "required"}}, # type: ignore
)
# Run the agent
await agent.run("Test message")
# Verify tool_choice was preserved
assert len(recorded_tool_choices) > 0, "No tool_choice recorded"
last_tool_choice = recorded_tool_choices[-1]
assert last_tool_choice is not None, "tool_choice should not be None"
assert last_tool_choice == {"mode": "required"}, f"Expected 'required', got {last_tool_choice}"
# region Participant Factory Tests
def test_handoff_builder_rejects_empty_participant_factories():
"""Test that HandoffBuilder rejects empty participant_factories dictionary."""
# Empty factories are rejected immediately when calling participant_factories()
with pytest.raises(ValueError, match=r"participant_factories cannot be empty"):
HandoffBuilder().register_participants({})
with pytest.raises(
ValueError, match=r"No participants provided\. Call \.participants\(\) or \.register_participants\(\) first\."
):
HandoffBuilder(participant_factories={}).build()
def test_handoff_builder_rejects_mixing_participants_and_factories():
"""Test that mixing participants and participant_factories in __init__ raises an error."""
triage = MockHandoffAgent(name="triage")
with pytest.raises(ValueError, match="Cannot mix .participants"):
HandoffBuilder(participants=[triage], participant_factories={"triage": lambda: triage})
def test_handoff_builder_rejects_mixing_participants_and_participant_factories_methods():
"""Test that mixing .participants() and .participant_factories() raises an error."""
triage = MockHandoffAgent(name="triage")
# Case 1: participants first, then participant_factories
with pytest.raises(ValueError, match="Cannot mix .participants"):
HandoffBuilder(participants=[triage]).register_participants({
"specialist": lambda: MockHandoffAgent(name="specialist")
})
# Case 2: participant_factories first, then participants
with pytest.raises(ValueError, match="Cannot mix .participants"):
HandoffBuilder(participant_factories={"triage": lambda: triage}).participants([
MockHandoffAgent(name="specialist")
])
# Case 3: participants(), then participant_factories()
with pytest.raises(ValueError, match="Cannot mix .participants"):
HandoffBuilder().participants([triage]).register_participants({
"specialist": lambda: MockHandoffAgent(name="specialist")
})
# Case 4: participant_factories(), then participants()
with pytest.raises(ValueError, match="Cannot mix .participants"):
HandoffBuilder().register_participants({"triage": lambda: triage}).participants([
MockHandoffAgent(name="specialist")
])
# Case 5: mix during initialization
with pytest.raises(ValueError, match="Cannot mix .participants"):
HandoffBuilder(
participants=[triage], participant_factories={"specialist": lambda: MockHandoffAgent(name="specialist")}
)
def test_handoff_builder_rejects_multiple_calls_to_participant_factories():
"""Test that multiple calls to .participant_factories() raises an error."""
with pytest.raises(
ValueError, match=r"register_participants\(\) has already been called on this builder instance."
):
(
HandoffBuilder()
.register_participants({"agent1": lambda: MockHandoffAgent(name="agent1")})
.register_participants({"agent2": lambda: MockHandoffAgent(name="agent2")})
)
def test_handoff_builder_rejects_multiple_calls_to_participants():
"""Test that multiple calls to .participants() raises an error."""
with pytest.raises(ValueError, match="participants have already been assigned"):
(
HandoffBuilder()
.participants([MockHandoffAgent(name="agent1")])
.participants([MockHandoffAgent(name="agent2")])
)
def test_handoff_builder_rejects_instance_coordinator_with_factories():
"""Test that using an agent instance for set_coordinator when using factories raises an error."""
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage")
def create_specialist() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist")
# Create an agent instance
coordinator_instance = MockHandoffAgent(name="coordinator")
with pytest.raises(ValueError, match=r"Call participants\(\.\.\.\) before with_start_agent\(\.\.\.\)"):
(
HandoffBuilder(
participant_factories={"triage": create_triage, "specialist": create_specialist}
).with_start_agent(coordinator_instance) # Instance, not factory name
)
def test_handoff_builder_rejects_factory_name_coordinator_with_instances():
"""Test that using a factory name for set_coordinator when using instances raises an error."""
triage = MockHandoffAgent(name="triage")
specialist = MockHandoffAgent(name="specialist")
with pytest.raises(ValueError, match=r"Call register_participants\(...\) before with_start_agent\(...\)"):
(
HandoffBuilder(participants=[triage, specialist]).with_start_agent(
"triage"
) # String factory name, not instance
)
def test_handoff_builder_rejects_mixed_types_in_add_handoff_source():
"""Test that add_handoff rejects factory name source with instance-based participants."""
triage = MockHandoffAgent(name="triage")
specialist = MockHandoffAgent(name="specialist")
with pytest.raises(TypeError, match="Cannot mix factory names \\(str\\) and AgentProtocol.*instances"):
(
HandoffBuilder(participants=[triage, specialist])
.with_start_agent(triage)
.add_handoff("triage", [specialist]) # String source with instance participants
)
def test_handoff_builder_accepts_all_factory_names_in_add_handoff():
"""Test that add_handoff accepts all factory names when using participant_factories."""
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage")
def create_specialist_a() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist_a")
def create_specialist_b() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist_b")
# This should work - all strings with participant_factories
builder = (
HandoffBuilder(
participant_factories={
"triage": create_triage,
"specialist_a": create_specialist_a,
"specialist_b": create_specialist_b,
}
)
.with_start_agent("triage")
.add_handoff("triage", ["specialist_a", "specialist_b"])
)
workflow = builder.build()
assert "triage" in workflow.executors
assert "specialist_a" in workflow.executors
assert "specialist_b" in workflow.executors
def test_handoff_builder_accepts_all_instances_in_add_handoff():
"""Test that add_handoff accepts all instances when using participants."""
triage = MockHandoffAgent(name="triage", handoff_to="specialist_a")
specialist_a = MockHandoffAgent(name="specialist_a")
specialist_b = MockHandoffAgent(name="specialist_b")
# This should work - all instances with participants
builder = (
HandoffBuilder(participants=[triage, specialist_a, specialist_b])
.with_start_agent(triage)
.add_handoff(triage, [specialist_a, specialist_b])
)
workflow = builder.build()
assert "triage" in workflow.executors
assert "specialist_a" in workflow.executors
assert "specialist_b" in workflow.executors
async def test_handoff_with_participant_factories():
"""Test workflow creation using participant_factories."""
call_count = 0
def create_triage() -> MockHandoffAgent:
nonlocal call_count
call_count += 1
return MockHandoffAgent(name="triage", handoff_to="specialist")
def create_specialist() -> MockHandoffAgent:
nonlocal call_count
call_count += 1
return MockHandoffAgent(name="specialist")
workflow = (
HandoffBuilder(participant_factories={"triage": create_triage, "specialist": create_specialist})
.with_start_agent("triage")
.with_termination_condition(lambda conv: sum(1 for m in conv if m.role == "user") >= 2)
.build()
)
# Factories should be called during build
assert call_count == 2
events = await _drain(workflow.run("Need help", stream=True))
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert requests
# Follow-up message
events = await _drain(
workflow.send_responses_streaming({requests[-1].request_id: [ChatMessage(role="user", text="More details")]})
)
outputs = [ev for ev in events if isinstance(ev, WorkflowOutputEvent)]
assert outputs
async def test_handoff_participant_factories_reusable_builder():
"""Test that the builder can be reused to build multiple workflows with factories."""
call_count = 0
def create_triage() -> MockHandoffAgent:
nonlocal call_count
call_count += 1
return MockHandoffAgent(name="triage", handoff_to="specialist")
def create_specialist() -> MockHandoffAgent:
nonlocal call_count
call_count += 1
return MockHandoffAgent(name="specialist")
builder = HandoffBuilder(
participant_factories={"triage": create_triage, "specialist": create_specialist}
).with_start_agent("triage")
# Build first workflow
wf1 = builder.build()
assert call_count == 2
# Build second workflow
wf2 = builder.build()
assert call_count == 4
# Verify that the two workflows have different agent instances
assert wf1.executors["triage"] is not wf2.executors["triage"]
assert wf1.executors["specialist"] is not wf2.executors["specialist"]
async def test_handoff_with_participant_factories_and_add_handoff():
"""Test that .add_handoff() works correctly with participant_factories."""
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage", handoff_to="specialist_a")
def create_specialist_a() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist_a", handoff_to="specialist_b")
def create_specialist_b() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist_b")
workflow = (
HandoffBuilder(
participant_factories={
"triage": create_triage,
"specialist_a": create_specialist_a,
"specialist_b": create_specialist_b,
}
)
.with_start_agent("triage")
.add_handoff("triage", ["specialist_a", "specialist_b"])
.add_handoff("specialist_a", ["specialist_b"])
.with_termination_condition(lambda conv: sum(1 for m in conv if m.role == "user") >= 3)
.build()
)
# Start conversation - triage hands off to specialist_a
events = await _drain(workflow.run("Initial request", stream=True))
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert requests
# Verify specialist_a executor exists and was called
assert "specialist_a" in workflow.executors
# Second user message - specialist_a hands off to specialist_b
events = await _drain(
workflow.send_responses_streaming({requests[-1].request_id: [ChatMessage(role="user", text="Need escalation")]})
)
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert requests
# Verify specialist_b executor exists
assert "specialist_b" in workflow.executors
async def test_handoff_participant_factories_with_checkpointing():
"""Test checkpointing with participant_factories."""
from agent_framework._workflows._checkpoint import InMemoryCheckpointStorage
storage = InMemoryCheckpointStorage()
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage", handoff_to="specialist")
def create_specialist() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist")
workflow = (
HandoffBuilder(participant_factories={"triage": create_triage, "specialist": create_specialist})
.with_start_agent("triage")
.with_checkpointing(storage)
.with_termination_condition(lambda conv: sum(1 for m in conv if m.role == "user") >= 2)
.build()
)
# Run workflow and capture output
events = await _drain(workflow.run("checkpoint test", stream=True))
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert requests
events = await _drain(
workflow.send_responses_streaming({requests[-1].request_id: [ChatMessage(role="user", text="follow up")]})
)
outputs = [ev for ev in events if isinstance(ev, WorkflowOutputEvent)]
assert outputs, "Should have workflow output after termination condition is met"
# List checkpoints - just verify they were created
checkpoints = await storage.list_checkpoints()
assert checkpoints, "Checkpoints should be created during workflow execution"
def test_handoff_set_coordinator_with_factory_name():
"""Test that set_coordinator accepts factory name as string."""
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage")
def create_specialist() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist")
builder = HandoffBuilder(
participant_factories={"triage": create_triage, "specialist": create_specialist}
).with_start_agent("triage")
workflow = builder.build()
assert "triage" in workflow.executors
def test_handoff_add_handoff_with_factory_names():
"""Test that add_handoff accepts factory names as strings."""
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage", handoff_to="specialist_a")
def create_specialist_a() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist_a")
def create_specialist_b() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist_b")
builder = (
HandoffBuilder(
participant_factories={
"triage": create_triage,
"specialist_a": create_specialist_a,
"specialist_b": create_specialist_b,
}
)
.with_start_agent("triage")
.add_handoff("triage", ["specialist_a", "specialist_b"])
)
workflow = builder.build()
assert "triage" in workflow.executors
assert "specialist_a" in workflow.executors
assert "specialist_b" in workflow.executors
async def test_handoff_participant_factories_autonomous_mode():
"""Test autonomous mode with participant_factories."""
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage", handoff_to="specialist")
def create_specialist() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist")
workflow = (
HandoffBuilder(participant_factories={"triage": create_triage, "specialist": create_specialist})
.with_start_agent("triage")
.with_autonomous_mode(agents=["specialist"], turn_limits={"specialist": 1})
.build()
)
events = await _drain(workflow.run("Issue", stream=True))
requests = [ev for ev in events if isinstance(ev, RequestInfoEvent)]
assert requests and len(requests) == 1
assert requests[0].source_executor_id == "specialist"
def test_handoff_participant_factories_invalid_coordinator_name():
"""Test that set_coordinator raises error for non-existent factory name."""
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage")
with pytest.raises(
ValueError, match="Start agent factory name 'nonexistent' is not in the participant_factories list"
):
(HandoffBuilder(participant_factories={"triage": create_triage}).with_start_agent("nonexistent").build())
def test_handoff_participant_factories_invalid_handoff_target():
"""Test that add_handoff raises error for non-existent target factory name."""
def create_triage() -> MockHandoffAgent:
return MockHandoffAgent(name="triage")
def create_specialist() -> MockHandoffAgent:
return MockHandoffAgent(name="specialist")
with pytest.raises(ValueError, match="Target factory name 'nonexistent' is not in the participant_factories list"):
(
HandoffBuilder(participant_factories={"triage": create_triage, "specialist": create_specialist})
.with_start_agent("triage")
.add_handoff("triage", ["nonexistent"])
.build()
)
# endregion Participant Factory Tests