* WIP: new workflow architecture * WIP: further improvements and cleanup * WIP: cleanup and docks, replace old tool with new * WIP: cleanup and docks, replace old tool with new * WIP: new planner implementation using workflow * WIP: precommit tool working as a workflow instead of a basic tool Support for passing False to use_assistant_model to skip external models completely and use Claude only * WIP: precommit workflow version swapped with old * WIP: codereview * WIP: replaced codereview * WIP: replaced codereview * WIP: replaced refactor * WIP: workflow for thinkdeep * WIP: ensure files get embedded correctly * WIP: thinkdeep replaced with workflow version * WIP: improved messaging when an external model's response is received * WIP: analyze tool swapped * WIP: updated tests * Extract only the content when building history * Use "relevant_files" for workflow tools only * WIP: updated tests * Extract only the content when building history * Use "relevant_files" for workflow tools only * WIP: fixed get_completion_next_steps_message missing param * Fixed tests Request for files consistently * Fixed tests Request for files consistently * Fixed tests * New testgen workflow tool Updated docs * Swap testgen workflow * Fix CI test failures by excluding API-dependent tests - Update GitHub Actions workflow to exclude simulation tests that require API keys - Fix collaboration tests to properly mock workflow tool expert analysis calls - Update test assertions to handle new workflow tool response format - Ensure unit tests run without external API dependencies in CI 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * WIP - Update tests to match new tools * WIP - Update tests to match new tools * WIP - Update tests to match new tools * Should help with https://github.com/BeehiveInnovations/zen-mcp-server/issues/97 Clear python cache when running script: https://github.com/BeehiveInnovations/zen-mcp-server/issues/96 Improved retry error logging Cleanup * WIP - chat tool using new architecture and improved code sharing * Removed todo * Removed todo * Cleanup old name * Tweak wordings * Tweak wordings Migrate old tests * Support for Flash 2.0 and Flash Lite 2.0 * Support for Flash 2.0 and Flash Lite 2.0 * Support for Flash 2.0 and Flash Lite 2.0 Fixed test * Improved consensus to use the workflow base class * Improved consensus to use the workflow base class * Allow images * Allow images * Replaced old consensus tool * Cleanup tests * Tests for prompt size * New tool: docgen Tests for prompt size Fixes: https://github.com/BeehiveInnovations/zen-mcp-server/issues/107 Use available token size limits: https://github.com/BeehiveInnovations/zen-mcp-server/issues/105 * Improved docgen prompt Exclude TestGen from pytest inclusion * Updated errors * Lint * DocGen instructed not to fix bugs, surface them and stick to d * WIP * Stop claude from being lazy and only documenting a small handful * More style rules --------- Co-authored-by: Claude <noreply@anthropic.com>
109 lines
3.5 KiB
Python
109 lines
3.5 KiB
Python
"""
|
|
Tests for the main server functionality
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from server import handle_call_tool
|
|
|
|
|
|
class TestServerTools:
|
|
"""Test server tool handling"""
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_handle_call_tool_unknown(self):
|
|
"""Test calling an unknown tool"""
|
|
result = await handle_call_tool("unknown_tool", {})
|
|
assert len(result) == 1
|
|
assert "Unknown tool: unknown_tool" in result[0].text
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_handle_chat(self):
|
|
"""Test chat functionality using real integration testing"""
|
|
import importlib
|
|
import os
|
|
|
|
# Set test environment
|
|
os.environ["PYTEST_CURRENT_TEST"] = "test"
|
|
|
|
# Save original environment
|
|
original_env = {
|
|
"OPENAI_API_KEY": os.environ.get("OPENAI_API_KEY"),
|
|
"DEFAULT_MODEL": os.environ.get("DEFAULT_MODEL"),
|
|
}
|
|
|
|
try:
|
|
# Set up environment for real provider resolution
|
|
os.environ["OPENAI_API_KEY"] = "sk-test-key-server-chat-test-not-real"
|
|
os.environ["DEFAULT_MODEL"] = "o3-mini"
|
|
|
|
# Clear other provider keys to isolate to OpenAI
|
|
for key in ["GEMINI_API_KEY", "XAI_API_KEY", "OPENROUTER_API_KEY"]:
|
|
os.environ.pop(key, None)
|
|
|
|
# Reload config and clear registry
|
|
import config
|
|
|
|
importlib.reload(config)
|
|
from providers.registry import ModelProviderRegistry
|
|
|
|
ModelProviderRegistry._instance = None
|
|
|
|
# Test with real provider resolution
|
|
try:
|
|
result = await handle_call_tool("chat", {"prompt": "Hello Gemini", "model": "o3-mini"})
|
|
|
|
# If we get here, check the response format
|
|
assert len(result) == 1
|
|
# Parse JSON response
|
|
import json
|
|
|
|
response_data = json.loads(result[0].text)
|
|
assert "status" in response_data
|
|
|
|
except Exception as e:
|
|
# Expected: API call will fail with fake key
|
|
error_msg = str(e)
|
|
# Should NOT be a mock-related error
|
|
assert "MagicMock" not in error_msg
|
|
assert "'<' not supported between instances" not in error_msg
|
|
|
|
# Should be a real provider error
|
|
assert any(
|
|
phrase in error_msg
|
|
for phrase in ["API", "key", "authentication", "provider", "network", "connection"]
|
|
)
|
|
|
|
finally:
|
|
# Restore environment
|
|
for key, value in original_env.items():
|
|
if value is not None:
|
|
os.environ[key] = value
|
|
else:
|
|
os.environ.pop(key, None)
|
|
|
|
# Reload config and clear registry
|
|
importlib.reload(config)
|
|
ModelProviderRegistry._instance = None
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_handle_version(self):
|
|
"""Test getting version info"""
|
|
result = await handle_call_tool("version", {})
|
|
assert len(result) == 1
|
|
|
|
response = result[0].text
|
|
# Parse the JSON response
|
|
import json
|
|
|
|
data = json.loads(response)
|
|
assert data["status"] == "success"
|
|
content = data["content"]
|
|
|
|
# Check for expected content in the markdown output
|
|
assert "# Zen MCP Server Version" in content
|
|
assert "## Available Tools" in content
|
|
assert "thinkdeep" in content
|
|
assert "docgen" in content
|
|
assert "version" in content
|