Files
agent-framework/python/packages/claude/tests/test_claude_agent.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

797 lines
30 KiB
Python

# Copyright (c) Microsoft. All rights reserved.
from typing import Any
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from agent_framework import AgentResponseUpdate, AgentThread, ChatMessage, Content, tool
from agent_framework_claude import ClaudeAgent, ClaudeAgentOptions, ClaudeAgentSettings
from agent_framework_claude._agent import TOOLS_MCP_SERVER_NAME
# region Test ClaudeAgentSettings
class TestClaudeAgentSettings:
"""Tests for ClaudeAgentSettings."""
def test_env_prefix(self) -> None:
"""Test that env_prefix is correctly set."""
assert ClaudeAgentSettings.env_prefix == "CLAUDE_AGENT_"
def test_default_values(self) -> None:
"""Test default values are None."""
settings = ClaudeAgentSettings()
assert settings.cli_path is None
assert settings.model is None
assert settings.cwd is None
assert settings.permission_mode is None
assert settings.max_turns is None
assert settings.max_budget_usd is None
def test_explicit_values(self) -> None:
"""Test explicit values override defaults."""
settings = ClaudeAgentSettings(
cli_path="/usr/local/bin/claude",
model="sonnet",
cwd="/home/user/project",
permission_mode="default",
max_turns=10,
max_budget_usd=5.0,
)
assert settings.cli_path == "/usr/local/bin/claude"
assert settings.model == "sonnet"
assert settings.cwd == "/home/user/project"
assert settings.permission_mode == "default"
assert settings.max_turns == 10
assert settings.max_budget_usd == 5.0
def test_env_variable_loading(self, monkeypatch: pytest.MonkeyPatch) -> None:
"""Test loading from environment variables."""
monkeypatch.setenv("CLAUDE_AGENT_MODEL", "opus")
monkeypatch.setenv("CLAUDE_AGENT_MAX_TURNS", "20")
settings = ClaudeAgentSettings()
assert settings.model == "opus"
assert settings.max_turns == 20
# region Test ClaudeAgent Initialization
class TestClaudeAgentInit:
"""Tests for ClaudeAgent initialization."""
def test_default_initialization(self) -> None:
"""Test agent initializes with defaults."""
agent = ClaudeAgent()
assert agent.id is not None
assert agent.name is None
assert agent.description is None
def test_with_name_and_description(self) -> None:
"""Test agent with name and description."""
agent = ClaudeAgent(name="test-agent", description="A test agent")
assert agent.name == "test-agent"
assert agent.description == "A test agent"
def test_with_instructions_parameter(self) -> None:
"""Test agent with instructions parameter."""
agent = ClaudeAgent(instructions="You are a helpful assistant.")
assert agent._default_options.get("system_prompt") == "You are a helpful assistant." # type: ignore[reportPrivateUsage]
def test_with_system_prompt_in_options(self) -> None:
"""Test agent with system_prompt in options."""
options: ClaudeAgentOptions = {
"system_prompt": "You are a helpful assistant.",
}
agent = ClaudeAgent(default_options=options)
assert agent._default_options.get("system_prompt") == "You are a helpful assistant." # type: ignore[reportPrivateUsage]
def test_with_default_options(self) -> None:
"""Test agent with default options."""
options: ClaudeAgentOptions = {
"model": "sonnet",
"permission_mode": "default",
"max_turns": 10,
}
agent = ClaudeAgent(default_options=options)
assert agent._settings.model == "sonnet" # type: ignore[reportPrivateUsage]
assert agent._settings.permission_mode == "default" # type: ignore[reportPrivateUsage]
assert agent._settings.max_turns == 10 # type: ignore[reportPrivateUsage]
def test_with_function_tool(self) -> None:
"""Test agent with function tool."""
@tool
def greet(name: str) -> str:
"""Greet someone."""
return f"Hello, {name}!"
agent = ClaudeAgent(tools=[greet])
assert len(agent._custom_tools) == 1 # type: ignore[reportPrivateUsage]
def test_with_single_tool(self) -> None:
"""Test agent with single tool (not in list)."""
@tool
def greet(name: str) -> str:
"""Greet someone."""
return f"Hello, {name}!"
agent = ClaudeAgent(tools=greet)
assert len(agent._custom_tools) == 1 # type: ignore[reportPrivateUsage]
def test_with_builtin_tools(self) -> None:
"""Test agent with built-in tool names."""
agent = ClaudeAgent(tools=["Read", "Write", "Bash"])
assert agent._builtin_tools == ["Read", "Write", "Bash"] # type: ignore[reportPrivateUsage]
assert agent._custom_tools == [] # type: ignore[reportPrivateUsage]
def test_with_mixed_tools(self) -> None:
"""Test agent with both built-in and custom tools."""
@tool
def greet(name: str) -> str:
"""Greet someone."""
return f"Hello, {name}!"
agent = ClaudeAgent(tools=["Read", greet, "Bash"])
assert agent._builtin_tools == ["Read", "Bash"] # type: ignore[reportPrivateUsage]
assert len(agent._custom_tools) == 1 # type: ignore[reportPrivateUsage]
# region Test ClaudeAgent Lifecycle
class TestClaudeAgentLifecycle:
"""Tests for ClaudeAgent tool initialization."""
def test_custom_tools_stored_from_constructor(self) -> None:
"""Test that custom tools from constructor are stored."""
@tool
def greet(name: str) -> str:
"""Greet someone."""
return f"Hello, {name}!"
agent = ClaudeAgent(tools=[greet])
assert len(agent._custom_tools) == 1 # type: ignore[reportPrivateUsage]
def test_multiple_custom_tools(self) -> None:
"""Test agent with multiple custom tools."""
@tool
def greet(name: str) -> str:
"""Greet someone."""
return f"Hello, {name}!"
@tool
def farewell(name: str) -> str:
"""Say goodbye."""
return f"Goodbye, {name}!"
agent = ClaudeAgent(tools=[greet, farewell])
assert len(agent._custom_tools) == 2 # type: ignore[reportPrivateUsage]
def test_no_tools(self) -> None:
"""Test agent without tools."""
agent = ClaudeAgent()
assert agent._custom_tools == [] # type: ignore[reportPrivateUsage]
assert agent._builtin_tools == [] # type: ignore[reportPrivateUsage]
# region Test ClaudeAgent Run
class TestClaudeAgentRun:
"""Tests for ClaudeAgent run method."""
@staticmethod
async def _create_async_generator(items: list[Any]) -> Any:
"""Helper to create async generator from list."""
for item in items:
yield item
def _create_mock_client(self, messages: list[Any]) -> MagicMock:
"""Create a mock ClaudeSDKClient that yields given messages."""
mock_client = MagicMock()
mock_client.connect = AsyncMock()
mock_client.disconnect = AsyncMock()
mock_client.query = AsyncMock()
mock_client.set_model = AsyncMock()
mock_client.set_permission_mode = AsyncMock()
mock_client.receive_response = MagicMock(return_value=self._create_async_generator(messages))
return mock_client
async def test_run_with_string_message(self) -> None:
"""Test run with string message."""
from claude_agent_sdk import AssistantMessage, ResultMessage, TextBlock
from claude_agent_sdk.types import StreamEvent
messages = [
StreamEvent(
event={
"type": "content_block_delta",
"delta": {"type": "text_delta", "text": "Hello!"},
},
uuid="event-1",
session_id="session-123",
),
AssistantMessage(
content=[TextBlock(text="Hello!")],
model="claude-sonnet",
),
ResultMessage(
subtype="success",
duration_ms=100,
duration_api_ms=50,
is_error=False,
num_turns=1,
session_id="session-123",
),
]
mock_client = self._create_mock_client(messages)
with patch("agent_framework_claude._agent.ClaudeSDKClient", return_value=mock_client):
agent = ClaudeAgent()
response = await agent.run("Hello")
assert response.text == "Hello!"
async def test_run_captures_session_id(self) -> None:
"""Test that session ID is captured from ResultMessage."""
from claude_agent_sdk import AssistantMessage, ResultMessage, TextBlock
from claude_agent_sdk.types import StreamEvent
messages = [
StreamEvent(
event={
"type": "content_block_delta",
"delta": {"type": "text_delta", "text": "Response"},
},
uuid="event-1",
session_id="test-session-id",
),
AssistantMessage(
content=[TextBlock(text="Response")],
model="claude-sonnet",
),
ResultMessage(
subtype="success",
duration_ms=100,
duration_api_ms=50,
is_error=False,
num_turns=1,
session_id="test-session-id",
),
]
mock_client = self._create_mock_client(messages)
with patch("agent_framework_claude._agent.ClaudeSDKClient", return_value=mock_client):
agent = ClaudeAgent()
thread = agent.get_new_thread()
await agent.run("Hello", thread=thread)
assert thread.service_thread_id == "test-session-id"
async def test_run_with_thread(self) -> None:
"""Test run with existing thread."""
from claude_agent_sdk import AssistantMessage, ResultMessage, TextBlock
from claude_agent_sdk.types import StreamEvent
messages = [
StreamEvent(
event={
"type": "content_block_delta",
"delta": {"type": "text_delta", "text": "Response"},
},
uuid="event-1",
session_id="session-123",
),
AssistantMessage(
content=[TextBlock(text="Response")],
model="claude-sonnet",
),
ResultMessage(
subtype="success",
duration_ms=100,
duration_api_ms=50,
is_error=False,
num_turns=1,
session_id="session-123",
),
]
mock_client = self._create_mock_client(messages)
with patch("agent_framework_claude._agent.ClaudeSDKClient", return_value=mock_client):
agent = ClaudeAgent()
thread = agent.get_new_thread()
thread.service_thread_id = "existing-session"
await agent.run("Hello", thread=thread)
# region Test ClaudeAgent Run Stream
class TestClaudeAgentRunStream:
"""Tests for ClaudeAgent streaming run method."""
@staticmethod
async def _create_async_generator(items: list[Any]) -> Any:
"""Helper to create async generator from list."""
for item in items:
yield item
def _create_mock_client(self, messages: list[Any]) -> MagicMock:
"""Create a mock ClaudeSDKClient that yields given messages."""
mock_client = MagicMock()
mock_client.connect = AsyncMock()
mock_client.disconnect = AsyncMock()
mock_client.query = AsyncMock()
mock_client.set_model = AsyncMock()
mock_client.set_permission_mode = AsyncMock()
mock_client.receive_response = MagicMock(return_value=self._create_async_generator(messages))
return mock_client
async def test_run_stream_yields_updates(self) -> None:
"""Test run(stream=True) yields AgentResponseUpdate objects."""
from claude_agent_sdk import AssistantMessage, ResultMessage, TextBlock
from claude_agent_sdk.types import StreamEvent
messages = [
StreamEvent(
event={
"type": "content_block_delta",
"delta": {"type": "text_delta", "text": "Streaming "},
},
uuid="event-1",
session_id="stream-session",
),
StreamEvent(
event={
"type": "content_block_delta",
"delta": {"type": "text_delta", "text": "response"},
},
uuid="event-2",
session_id="stream-session",
),
AssistantMessage(
content=[TextBlock(text="Streaming response")],
model="claude-sonnet",
),
ResultMessage(
subtype="success",
duration_ms=100,
duration_api_ms=50,
is_error=False,
num_turns=1,
session_id="stream-session",
),
]
mock_client = self._create_mock_client(messages)
with patch("agent_framework_claude._agent.ClaudeSDKClient", return_value=mock_client):
agent = ClaudeAgent()
updates: list[AgentResponseUpdate] = []
async for update in agent.run("Hello", stream=True):
updates.append(update)
# StreamEvent yields text deltas (2 events)
assert len(updates) == 2
assert updates[0].role == "assistant"
assert updates[0].text == "Streaming "
assert updates[1].text == "response"
async def test_run_stream_raises_on_assistant_message_error(self) -> None:
"""Test run raises ServiceException when AssistantMessage has an error."""
from agent_framework.exceptions import ServiceException
from claude_agent_sdk import AssistantMessage, ResultMessage, TextBlock
messages = [
AssistantMessage(
content=[TextBlock(text="Error details from API")],
model="claude-sonnet",
error="invalid_request",
),
ResultMessage(
subtype="success",
duration_ms=100,
duration_api_ms=50,
is_error=False,
num_turns=1,
session_id="error-session",
),
]
mock_client = self._create_mock_client(messages)
with patch("agent_framework_claude._agent.ClaudeSDKClient", return_value=mock_client):
agent = ClaudeAgent()
with pytest.raises(ServiceException) as exc_info:
async for _ in agent.run("Hello", stream=True):
pass
assert "Invalid request to Claude API" in str(exc_info.value)
assert "Error details from API" in str(exc_info.value)
async def test_run_stream_raises_on_result_message_error(self) -> None:
"""Test run raises ServiceException when ResultMessage.is_error is True."""
from agent_framework.exceptions import ServiceException
from claude_agent_sdk import ResultMessage
messages = [
ResultMessage(
subtype="error",
duration_ms=100,
duration_api_ms=50,
is_error=True,
num_turns=0,
session_id="error-session",
result="Model 'claude-sonnet-4.5' not found",
),
]
mock_client = self._create_mock_client(messages)
with patch("agent_framework_claude._agent.ClaudeSDKClient", return_value=mock_client):
agent = ClaudeAgent()
with pytest.raises(ServiceException) as exc_info:
async for _ in agent.run("Hello", stream=True):
pass
assert "Model 'claude-sonnet-4.5' not found" in str(exc_info.value)
# region Test ClaudeAgent Session Management
class TestClaudeAgentSessionManagement:
"""Tests for ClaudeAgent session management."""
def test_get_new_thread(self) -> None:
"""Test get_new_thread creates a new thread."""
agent = ClaudeAgent()
thread = agent.get_new_thread()
assert isinstance(thread, AgentThread)
assert thread.service_thread_id is None
def test_get_new_thread_with_service_thread_id(self) -> None:
"""Test get_new_thread with existing service_thread_id."""
agent = ClaudeAgent()
thread = agent.get_new_thread(service_thread_id="existing-session-123")
assert isinstance(thread, AgentThread)
assert thread.service_thread_id == "existing-session-123"
def test_thread_inherits_context_provider(self) -> None:
"""Test that thread inherits context provider."""
mock_provider = MagicMock()
agent = ClaudeAgent(context_provider=mock_provider)
thread = agent.get_new_thread()
assert thread.context_provider == mock_provider
async def test_ensure_session_creates_client(self) -> None:
"""Test _ensure_session creates client when not started."""
with patch("agent_framework_claude._agent.ClaudeSDKClient") as mock_client_class:
mock_client = MagicMock()
mock_client.connect = AsyncMock()
mock_client_class.return_value = mock_client
agent = ClaudeAgent()
await agent._ensure_session(None) # type: ignore[reportPrivateUsage]
assert agent._started # type: ignore[reportPrivateUsage]
mock_client.connect.assert_called_once()
async def test_ensure_session_recreates_for_different_session(self) -> None:
"""Test _ensure_session recreates client for different session ID."""
with patch("agent_framework_claude._agent.ClaudeSDKClient") as mock_client_class:
mock_client1 = MagicMock()
mock_client1.connect = AsyncMock()
mock_client1.disconnect = AsyncMock()
mock_client2 = MagicMock()
mock_client2.connect = AsyncMock()
mock_client_class.side_effect = [mock_client1, mock_client2]
agent = ClaudeAgent()
# First session
await agent._ensure_session(None) # type: ignore[reportPrivateUsage]
assert agent._started # type: ignore[reportPrivateUsage]
# Different session should recreate client
await agent._ensure_session("new-session-id") # type: ignore[reportPrivateUsage]
assert agent._current_session_id == "new-session-id" # type: ignore[reportPrivateUsage]
mock_client1.disconnect.assert_called_once()
async def test_ensure_session_reuses_for_same_session(self) -> None:
"""Test _ensure_session reuses client for same session ID."""
with patch("agent_framework_claude._agent.ClaudeSDKClient") as mock_client_class:
mock_client = MagicMock()
mock_client.connect = AsyncMock()
mock_client_class.return_value = mock_client
agent = ClaudeAgent()
# First call
await agent._ensure_session("session-123") # type: ignore[reportPrivateUsage]
# Same session should not recreate
await agent._ensure_session("session-123") # type: ignore[reportPrivateUsage]
# Only called once
assert mock_client_class.call_count == 1
# region Test ClaudeAgent Tool Conversion
class TestClaudeAgentToolConversion:
"""Tests for ClaudeAgent tool conversion."""
def test_prepare_tools_creates_mcp_server(self) -> None:
"""Test _prepare_tools creates MCP server for AF tools."""
@tool
def add(a: int, b: int) -> int:
"""Add two numbers."""
return a + b
agent = ClaudeAgent(tools=[add])
server, tool_names = agent._prepare_tools(agent._custom_tools) # type: ignore[reportPrivateUsage]
assert server is not None
assert len(tool_names) == 1
assert tool_names[0] == f"mcp__{TOOLS_MCP_SERVER_NAME}__add"
def test_function_tool_to_sdk_mcp_tool(self) -> None:
"""Test converting FunctionTool to SDK MCP tool."""
@tool
def greet(name: str) -> str:
"""Greet someone."""
return f"Hello, {name}!"
agent = ClaudeAgent()
sdk_tool = agent._function_tool_to_sdk_mcp_tool(greet) # type: ignore[reportPrivateUsage]
assert sdk_tool.name == "greet"
assert sdk_tool.description == "Greet someone."
assert sdk_tool.input_schema is not None
assert "properties" in sdk_tool.input_schema # type: ignore[operator]
def test_function_tool_to_sdk_mcp_tool_preserves_defs_for_nested_types(self) -> None:
"""Test that $defs is preserved for tools with nested Pydantic models."""
from pydantic import BaseModel
class Address(BaseModel):
street: str
city: str
class Person(BaseModel):
name: str
address: Address
@tool
def create_person(person: Person) -> str:
"""Create a person with address."""
return f"{person.name} lives at {person.address.street}, {person.address.city}"
agent = ClaudeAgent()
sdk_tool = agent._function_tool_to_sdk_mcp_tool(create_person) # type: ignore[reportPrivateUsage]
# Verify $defs is preserved in the schema
assert sdk_tool.input_schema is not None
assert "$defs" in sdk_tool.input_schema # type: ignore[operator]
assert "Address" in sdk_tool.input_schema["$defs"] # type: ignore[index]
# Verify the nested reference exists in properties
assert "person" in sdk_tool.input_schema["properties"] # type: ignore[index]
async def test_tool_handler_success(self) -> None:
"""Test tool handler executes successfully."""
@tool
def greet(name: str) -> str:
"""Greet someone."""
return f"Hello, {name}!"
agent = ClaudeAgent()
sdk_tool = agent._function_tool_to_sdk_mcp_tool(greet) # type: ignore[reportPrivateUsage]
result = await sdk_tool.handler({"name": "World"})
assert result["content"][0]["text"] == "Hello, World!"
async def test_tool_handler_error(self) -> None:
"""Test tool handler handles errors."""
@tool
def failing_tool() -> str:
"""A tool that fails."""
raise ValueError("Something went wrong")
agent = ClaudeAgent()
sdk_tool = agent._function_tool_to_sdk_mcp_tool(failing_tool) # type: ignore[reportPrivateUsage]
result = await sdk_tool.handler({})
assert "Error:" in result["content"][0]["text"]
assert "Something went wrong" in result["content"][0]["text"]
# region Test ClaudeAgent Permissions
class TestClaudeAgentPermissions:
"""Tests for ClaudeAgent permission handling."""
def test_default_permission_mode(self) -> None:
"""Test default permission mode."""
agent = ClaudeAgent()
assert agent._settings.permission_mode is None # type: ignore[reportPrivateUsage]
def test_permission_mode_from_settings(self, monkeypatch: pytest.MonkeyPatch) -> None:
"""Test permission mode from environment settings."""
monkeypatch.setenv("CLAUDE_AGENT_PERMISSION_MODE", "acceptEdits")
settings = ClaudeAgentSettings()
assert settings.permission_mode == "acceptEdits"
def test_permission_mode_in_options(self) -> None:
"""Test permission mode in options."""
options: ClaudeAgentOptions = {
"permission_mode": "bypassPermissions",
}
agent = ClaudeAgent(default_options=options)
assert agent._settings.permission_mode == "bypassPermissions" # type: ignore[reportPrivateUsage]
# region Test ClaudeAgent Error Handling
class TestClaudeAgentErrorHandling:
"""Tests for ClaudeAgent error handling."""
@staticmethod
async def _empty_gen() -> Any:
"""Empty async generator."""
if False:
yield
async def test_handles_empty_response(self) -> None:
"""Test handling of empty response."""
mock_client = MagicMock()
mock_client.connect = AsyncMock()
mock_client.disconnect = AsyncMock()
mock_client.query = AsyncMock()
mock_client.set_model = AsyncMock()
mock_client.set_permission_mode = AsyncMock()
mock_client.receive_response = MagicMock(return_value=self._empty_gen())
with patch("agent_framework_claude._agent.ClaudeSDKClient", return_value=mock_client):
agent = ClaudeAgent()
response = await agent.run("Hello")
assert response.messages == []
# region Test Format Prompt
class TestFormatPrompt:
"""Tests for _format_prompt method."""
def test_format_empty_messages(self) -> None:
"""Test formatting empty messages."""
agent = ClaudeAgent()
result = agent._format_prompt([]) # type: ignore[reportPrivateUsage]
assert result == ""
def test_format_none_messages(self) -> None:
"""Test formatting None messages."""
agent = ClaudeAgent()
result = agent._format_prompt(None) # type: ignore[reportPrivateUsage]
assert result == ""
def test_format_user_message(self) -> None:
"""Test formatting user message."""
agent = ClaudeAgent()
msg = ChatMessage(
role="user",
contents=[Content.from_text(text="Hello")],
)
result = agent._format_prompt([msg]) # type: ignore[reportPrivateUsage]
assert "Hello" in result
def test_format_multiple_messages(self) -> None:
"""Test formatting multiple messages."""
agent = ClaudeAgent()
messages = [
ChatMessage(role="user", contents=[Content.from_text(text="Hi")]),
ChatMessage(role="assistant", contents=[Content.from_text(text="Hello!")]),
ChatMessage(role="user", contents=[Content.from_text(text="How are you?")]),
]
result = agent._format_prompt(messages) # type: ignore[reportPrivateUsage]
assert "Hi" in result
assert "Hello!" in result
assert "How are you?" in result
# region Test Build Options
class TestPrepareClientOptions:
"""Tests for _prepare_client_options method."""
def test_prepare_client_options_with_settings(self, monkeypatch: pytest.MonkeyPatch) -> None:
"""Test preparing options with settings."""
monkeypatch.setenv("CLAUDE_AGENT_MODEL", "opus")
monkeypatch.setenv("CLAUDE_AGENT_MAX_TURNS", "15")
agent = ClaudeAgent()
with patch("agent_framework_claude._agent.SDKOptions") as mock_opts:
mock_opts.return_value = MagicMock()
agent._prepare_client_options() # type: ignore[reportPrivateUsage]
call_kwargs = mock_opts.call_args[1]
assert call_kwargs.get("model") == "opus"
assert call_kwargs.get("max_turns") == 15
def test_prepare_client_options_with_instructions(self) -> None:
"""Test building options with instructions parameter."""
agent = ClaudeAgent(instructions="Be helpful")
with patch("agent_framework_claude._agent.SDKOptions") as mock_opts:
mock_opts.return_value = MagicMock()
agent._prepare_client_options() # type: ignore[reportPrivateUsage]
call_kwargs = mock_opts.call_args[1]
assert call_kwargs.get("system_prompt") == "Be helpful"
def test_prepare_client_options_includes_custom_tools(self) -> None:
"""Test that _prepare_client_options includes custom tools MCP server."""
@tool
def greet(name: str) -> str:
"""Greet someone."""
return f"Hello, {name}!"
agent = ClaudeAgent(tools=[greet])
with patch("agent_framework_claude._agent.SDKOptions") as mock_opts:
mock_opts.return_value = MagicMock()
agent._prepare_client_options() # type: ignore[reportPrivateUsage]
call_kwargs = mock_opts.call_args[1]
assert "mcp_servers" in call_kwargs
assert TOOLS_MCP_SERVER_NAME in call_kwargs["mcp_servers"]
class TestApplyRuntimeOptions:
"""Tests for _apply_runtime_options method."""
async def test_apply_runtime_model(self) -> None:
"""Test applying runtime model option."""
mock_client = MagicMock()
mock_client.set_model = AsyncMock()
mock_client.set_permission_mode = AsyncMock()
agent = ClaudeAgent()
agent._client = mock_client # type: ignore[reportPrivateUsage]
await agent._apply_runtime_options({"model": "opus"}) # type: ignore[reportPrivateUsage]
mock_client.set_model.assert_called_once_with("opus")
async def test_apply_runtime_permission_mode(self) -> None:
"""Test applying runtime permission_mode option."""
mock_client = MagicMock()
mock_client.set_model = AsyncMock()
mock_client.set_permission_mode = AsyncMock()
agent = ClaudeAgent()
agent._client = mock_client # type: ignore[reportPrivateUsage]
await agent._apply_runtime_options({"permission_mode": "acceptEdits"}) # type: ignore[reportPrivateUsage]
mock_client.set_permission_mode.assert_called_once_with("acceptEdits")
async def test_apply_runtime_options_none(self) -> None:
"""Test applying None options does nothing."""
mock_client = MagicMock()
mock_client.set_model = AsyncMock()
mock_client.set_permission_mode = AsyncMock()
agent = ClaudeAgent()
agent._client = mock_client # type: ignore[reportPrivateUsage]
await agent._apply_runtime_options(None) # type: ignore[reportPrivateUsage]
mock_client.set_model.assert_not_called()
mock_client.set_permission_mode.assert_not_called()