Add DocGen tool with comprehensive documentation generation capabilities (#109)
* 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>
This commit is contained in:
Beehive Innovations
committed by
GitHub
GitHub
parent
0655590a51
commit
c960bcb720
@@ -51,6 +51,18 @@ ModelProviderRegistry.register_provider(ProviderType.GOOGLE, GeminiModelProvider
|
||||
ModelProviderRegistry.register_provider(ProviderType.OPENAI, OpenAIModelProvider)
|
||||
ModelProviderRegistry.register_provider(ProviderType.XAI, XAIModelProvider)
|
||||
|
||||
# Register CUSTOM provider if CUSTOM_API_URL is available (for integration tests)
|
||||
# But only if we're actually running integration tests, not unit tests
|
||||
if os.getenv("CUSTOM_API_URL") and "test_prompt_regression.py" in os.getenv("PYTEST_CURRENT_TEST", ""):
|
||||
from providers.custom import CustomProvider # noqa: E402
|
||||
|
||||
def custom_provider_factory(api_key=None):
|
||||
"""Factory function that creates CustomProvider with proper parameters."""
|
||||
base_url = os.getenv("CUSTOM_API_URL", "")
|
||||
return CustomProvider(api_key=api_key or "", base_url=base_url)
|
||||
|
||||
ModelProviderRegistry.register_provider(ProviderType.CUSTOM, custom_provider_factory)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def project_path(tmp_path):
|
||||
@@ -99,6 +111,20 @@ def mock_provider_availability(request, monkeypatch):
|
||||
if ProviderType.XAI not in registry._providers:
|
||||
ModelProviderRegistry.register_provider(ProviderType.XAI, XAIModelProvider)
|
||||
|
||||
# Ensure CUSTOM provider is registered if needed for integration tests
|
||||
if (
|
||||
os.getenv("CUSTOM_API_URL")
|
||||
and "test_prompt_regression.py" in os.getenv("PYTEST_CURRENT_TEST", "")
|
||||
and ProviderType.CUSTOM not in registry._providers
|
||||
):
|
||||
from providers.custom import CustomProvider
|
||||
|
||||
def custom_provider_factory(api_key=None):
|
||||
base_url = os.getenv("CUSTOM_API_URL", "")
|
||||
return CustomProvider(api_key=api_key or "", base_url=base_url)
|
||||
|
||||
ModelProviderRegistry.register_provider(ProviderType.CUSTOM, custom_provider_factory)
|
||||
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
original_get_provider = ModelProviderRegistry.get_provider_for_model
|
||||
@@ -108,7 +134,7 @@ def mock_provider_availability(request, monkeypatch):
|
||||
if model_name in ["unavailable-model", "gpt-5-turbo", "o3"]:
|
||||
return None
|
||||
# For common test models, return a mock provider
|
||||
if model_name in ["gemini-2.5-flash", "gemini-2.5-pro", "pro", "flash"]:
|
||||
if model_name in ["gemini-2.5-flash", "gemini-2.5-pro", "pro", "flash", "local-llama"]:
|
||||
# Try to use the real provider first if it exists
|
||||
real_provider = original_get_provider(model_name)
|
||||
if real_provider:
|
||||
@@ -118,10 +144,16 @@ def mock_provider_availability(request, monkeypatch):
|
||||
provider = MagicMock()
|
||||
# Set up the model capabilities mock with actual values
|
||||
capabilities = MagicMock()
|
||||
capabilities.context_window = 1000000 # 1M tokens for Gemini models
|
||||
capabilities.supports_extended_thinking = False
|
||||
capabilities.input_cost_per_1k = 0.075
|
||||
capabilities.output_cost_per_1k = 0.3
|
||||
if model_name == "local-llama":
|
||||
capabilities.context_window = 128000 # 128K tokens for local-llama
|
||||
capabilities.supports_extended_thinking = False
|
||||
capabilities.input_cost_per_1k = 0.0 # Free local model
|
||||
capabilities.output_cost_per_1k = 0.0 # Free local model
|
||||
else:
|
||||
capabilities.context_window = 1000000 # 1M tokens for Gemini models
|
||||
capabilities.supports_extended_thinking = False
|
||||
capabilities.input_cost_per_1k = 0.075
|
||||
capabilities.output_cost_per_1k = 0.3
|
||||
provider.get_model_capabilities.return_value = capabilities
|
||||
return provider
|
||||
# Otherwise use the original logic
|
||||
@@ -131,7 +163,7 @@ def mock_provider_availability(request, monkeypatch):
|
||||
|
||||
# Also mock is_effective_auto_mode for all BaseTool instances to return False
|
||||
# unless we're specifically testing auto mode behavior
|
||||
from tools.base import BaseTool
|
||||
from tools.shared.base_tool import BaseTool
|
||||
|
||||
def mock_is_effective_auto_mode(self):
|
||||
# If this is an auto mode test file or specific auto mode test, use the real logic
|
||||
|
||||
Reference in New Issue
Block a user