Files
agent-framework/python/packages/lab/tau2/tests/test_tau2_utils.py
T
Eduard van Valkenburg 838a7fd61d Python: [BREAKING] Types API Review improvements (#3647)
* Replace Role and FinishReason classes with NewType + Literal

- Remove EnumLike metaclass from _types.py
- Replace Role class with NewType('Role', str) + RoleLiteral
- Replace FinishReason class with NewType('FinishReason', str) + FinishReasonLiteral
- Update all usages across codebase to use string literals
- Remove .value access patterns (direct string comparison now works)
- Add backward compatibility for legacy dict serialization format
- Update tests to reflect new string-based types

Addresses #3591, #3615

* Simplify ChatResponse and AgentResponse type hints (#3592)

- Remove overloads from ChatResponse.__init__
- Remove text parameter from ChatResponse.__init__
- Remove | dict[str, Any] from finish_reason and usage_details params
- Remove **kwargs from AgentResponse.__init__
- Both now accept ChatMessage | Sequence[ChatMessage] | None for messages
- Update docstrings and examples to reflect changes
- Fix tests that were using removed kwargs
- Fix Role type hint usage in ag-ui utils

* Remove text parameter from ChatResponseUpdate and AgentResponseUpdate (#3597)

- Remove text parameter from ChatResponseUpdate.__init__
- Remove text parameter from AgentResponseUpdate.__init__
- Remove **kwargs from both update classes
- Simplify contents parameter type to Sequence[Content] | None
- Update all usages to use contents=[Content.from_text(...)] pattern
- Fix imports in test files
- Update docstrings and examples

* Rename from_chat_response_updates to from_updates (#3593)

- ChatResponse.from_chat_response_updates → ChatResponse.from_updates
- ChatResponse.from_chat_response_generator → ChatResponse.from_update_generator
- AgentResponse.from_agent_run_response_updates → AgentResponse.from_updates

* Remove try_parse_value method from ChatResponse and AgentResponse (#3595)

- Remove try_parse_value method from ChatResponse
- Remove try_parse_value method from AgentResponse
- Remove try_parse_value calls from from_updates and from_update_generator methods
- Update samples to use try/except with response.value instead
- Update tests to use response.value pattern
- Users should now use response.value with try/except for safe parsing

* Add agent_id to AgentResponse and clarify author_name documentation (#3596)

- Add agent_id parameter to AgentResponse class
- Document that author_name is on ChatMessage objects, not responses
- Update ChatResponse docstring with author_name note
- Update AgentResponse docstring with author_name note

* Simplify ChatMessage.__init__ signature (#3618)

- Make contents a positional argument accepting Sequence[Content | str]
- Auto-convert strings in contents to TextContent
- Remove overloads, keep text kwarg for backward compatibility with serialization
- Update _parse_content_list to handle string items
- Update all usages across codebase to use new format: ChatMessage("role", ["text"])

* Allow Content as input on run and get_response

- Update prepare_messages and normalize_messages to accept Content
- Update type signatures in _agents.py and _clients.py
- Add tests for Content input handling

* Fix ChatMessage usage across packages and samples

Update all remaining ChatMessage(role=..., text=...) to use new
ChatMessage('role', ['text']) signature.

* Fix Role string usage and response format parsing

- Fix redis provider: remove .value access on string literals
- Fix durabletask ensure_response_format: set _response_format before accessing .value

* Fix ollama .value and ai_model_id issues, handle None in content list

- Fix ollama _chat_client: remove .value on string literals
- Fix ollama _chat_client: rename ai_model_id to model_id
- Fix _parse_content_list: skip None values gracefully

* Fix A2AAgent type signature to include Content

* Fix Role/FinishReason NewType dict annotations and improve test coverage to 95%

* Fix mypy errors for Role/FinishReason NewType usage

* Fix Role.TOOL and Role.ASSISTANT usage in _orchestrator_helpers.py

* Fix Role NewType usage in durabletask _models.py
2026-02-04 10:13:23 +00:00

223 lines
8.9 KiB
Python

# Copyright (c) Microsoft. All rights reserved.
"""Tests for tau2 utils module."""
import urllib.request
from pathlib import Path
import pytest
from agent_framework import ChatMessage, Content, FunctionTool
from agent_framework_lab_tau2._tau2_utils import (
convert_agent_framework_messages_to_tau2_messages,
convert_tau2_tool_to_function_tool,
)
from tau2.data_model.message import AssistantMessage, SystemMessage, ToolCall, ToolMessage, UserMessage
from tau2.domains.airline.data_model import FlightDB
from tau2.domains.airline.tools import AirlineTools
from tau2.environment.environment import Environment
@pytest.fixture(scope="session")
def tau2_airline_environment() -> Environment:
airline_db_remote_path = "https://raw.githubusercontent.com/sierra-research/tau2-bench/5ba9e3e56db57c5e4114bf7f901291f09b2c5619/data/tau2/domains/airline/db.json"
airline_policy_remote_path = "https://raw.githubusercontent.com/sierra-research/tau2-bench/5ba9e3e56db57c5e4114bf7f901291f09b2c5619/data/tau2/domains/airline/policy.md"
# Create cache directory
cache_dir = Path(__file__).parent / "data"
cache_dir.mkdir(exist_ok=True)
# Define cache file paths
db_cache_path = cache_dir / "airline_db.json"
policy_cache_path = cache_dir / "airline_policy.md"
# Download files only if they don't exist in cache
if not db_cache_path.exists():
urllib.request.urlretrieve(airline_db_remote_path, db_cache_path)
if not policy_cache_path.exists():
urllib.request.urlretrieve(airline_policy_remote_path, policy_cache_path)
# Load data from cached files
db = FlightDB.load(str(db_cache_path))
tools = AirlineTools(db)
with open(policy_cache_path) as fp:
policy = fp.read()
yield Environment(
domain_name="airline",
policy=policy,
tools=tools,
)
def test_convert_tau2_tool_to_function_tool_basic(tau2_airline_environment):
"""Test basic conversion from tau2 tool to FunctionTool."""
# Get real tools from tau2 environment
tools = tau2_airline_environment.get_tools()
# Use the first available tool for testing
assert len(tools) > 0, "No tools available in environment"
tau2_tool = tools[0]
# Convert the tool
tool = convert_tau2_tool_to_function_tool(tau2_tool)
# Verify the conversion
assert isinstance(tool, FunctionTool)
assert tool.name == tau2_tool.name
assert tool.description == tau2_tool._get_description()
assert tool.input_model == tau2_tool.params
# Test that the function is callable (we won't call it with real params to avoid side effects)
assert callable(tool.func)
def test_convert_tau2_tool_to_function_tool_multiple_tools(tau2_airline_environment):
"""Test conversion with multiple tau2 tools."""
# Get real tools from tau2 environment
tools = tau2_airline_environment.get_tools()
# Convert multiple tools
function_tools = [convert_tau2_tool_to_function_tool(tool) for tool in tools[:3]] # Test first 3 tools
# Verify all conversions
for tool, tau2_tool in zip(function_tools, tools[:3], strict=False):
assert isinstance(tool, FunctionTool)
assert tool.name == tau2_tool.name
assert tool.description == tau2_tool._get_description()
assert tool.input_model == tau2_tool.params
assert callable(tool.func)
def test_convert_agent_framework_messages_to_tau2_messages_system():
"""Test converting system message."""
messages = [ChatMessage("system", [Content.from_text(text="System instruction")])]
tau2_messages = convert_agent_framework_messages_to_tau2_messages(messages)
assert len(tau2_messages) == 1
assert isinstance(tau2_messages[0], SystemMessage)
assert tau2_messages[0].role == "system"
assert tau2_messages[0].content == "System instruction"
def test_convert_agent_framework_messages_to_tau2_messages_user():
"""Test converting user message."""
messages = [ChatMessage("user", [Content.from_text(text="Hello assistant")])]
tau2_messages = convert_agent_framework_messages_to_tau2_messages(messages)
assert len(tau2_messages) == 1
assert isinstance(tau2_messages[0], UserMessage)
assert tau2_messages[0].role == "user"
assert tau2_messages[0].content == "Hello assistant"
assert tau2_messages[0].tool_calls is None
def test_convert_agent_framework_messages_to_tau2_messages_assistant():
"""Test converting assistant message."""
messages = [ChatMessage("assistant", [Content.from_text(text="Hello user")])]
tau2_messages = convert_agent_framework_messages_to_tau2_messages(messages)
assert len(tau2_messages) == 1
assert isinstance(tau2_messages[0], AssistantMessage)
assert tau2_messages[0].role == "assistant"
assert tau2_messages[0].content == "Hello user"
assert tau2_messages[0].tool_calls is None
def test_convert_agent_framework_messages_to_tau2_messages_with_function_call():
"""Test converting message with function call."""
function_call = Content.from_function_call(call_id="call_123", name="test_function", arguments={"param": "value"})
messages = [ChatMessage("assistant", [Content.from_text(text="I'll call a function"), function_call])]
tau2_messages = convert_agent_framework_messages_to_tau2_messages(messages)
assert len(tau2_messages) == 1
assert isinstance(tau2_messages[0], AssistantMessage)
assert tau2_messages[0].content == "I'll call a function"
assert tau2_messages[0].tool_calls is not None
assert len(tau2_messages[0].tool_calls) == 1
tool_call = tau2_messages[0].tool_calls[0]
assert isinstance(tool_call, ToolCall)
assert tool_call.id == "call_123"
assert tool_call.name == "test_function"
assert tool_call.arguments == {"param": "value"}
assert tool_call.requestor == "assistant"
def test_convert_agent_framework_messages_to_tau2_messages_with_function_result():
"""Test converting message with function result."""
function_result = Content.from_function_result(call_id="call_123", result={"success": True, "data": "result data"})
messages = [ChatMessage("tool", [function_result])]
tau2_messages = convert_agent_framework_messages_to_tau2_messages(messages)
assert len(tau2_messages) == 1
assert isinstance(tau2_messages[0], ToolMessage)
assert tau2_messages[0].id == "call_123"
assert tau2_messages[0].role == "tool"
assert tau2_messages[0].content is not None
assert '{"success": true, "data": "result data"}' in tau2_messages[0].content
assert tau2_messages[0].requestor == "assistant"
assert tau2_messages[0].error is False
def test_convert_agent_framework_messages_to_tau2_messages_with_error():
"""Test converting function result with error."""
function_result = Content.from_function_result(
call_id="call_456", result="Error occurred", exception=Exception("Test error")
)
messages = [ChatMessage("tool", [function_result])]
tau2_messages = convert_agent_framework_messages_to_tau2_messages(messages)
assert len(tau2_messages) == 1
assert isinstance(tau2_messages[0], ToolMessage)
assert tau2_messages[0].error is True
def test_convert_agent_framework_messages_to_tau2_messages_multiple_text_contents():
"""Test converting message with multiple text contents."""
messages = [ChatMessage("user", [Content.from_text(text="First part"), Content.from_text(text="Second part")])]
tau2_messages = convert_agent_framework_messages_to_tau2_messages(messages)
assert len(tau2_messages) == 1
assert isinstance(tau2_messages[0], UserMessage)
assert tau2_messages[0].content == "First part Second part"
def test_convert_agent_framework_messages_to_tau2_messages_complex_scenario():
"""Test converting complex scenario with multiple message types."""
function_call = Content.from_function_call(call_id="call_789", name="complex_tool", arguments='{"key": "value"}')
function_result = Content.from_function_result(call_id="call_789", result={"output": "tool result"})
messages = [
ChatMessage("system", [Content.from_text(text="System prompt")]),
ChatMessage("user", [Content.from_text(text="User request")]),
ChatMessage("assistant", [Content.from_text(text="I'll help you"), function_call]),
ChatMessage("tool", [function_result]),
ChatMessage("assistant", [Content.from_text(text="Based on the result...")]),
]
tau2_messages = convert_agent_framework_messages_to_tau2_messages(messages)
assert len(tau2_messages) == 5
assert isinstance(tau2_messages[0], SystemMessage)
assert isinstance(tau2_messages[1], UserMessage)
assert isinstance(tau2_messages[2], AssistantMessage)
assert isinstance(tau2_messages[3], ToolMessage)
assert isinstance(tau2_messages[4], AssistantMessage)
# Check the assistant message with tool call
assert tau2_messages[2].tool_calls is not None
assert len(tau2_messages[2].tool_calls) == 1
assert tau2_messages[2].tool_calls[0].name == "complex_tool"