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
@@ -3,16 +3,16 @@ Test that conversation history is correctly mapped to tool-specific fields
|
||||
"""
|
||||
|
||||
from datetime import datetime
|
||||
from unittest.mock import MagicMock, patch
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
from providers.base import ProviderType
|
||||
from server import reconstruct_thread_context
|
||||
from utils.conversation_memory import ConversationTurn, ThreadContext
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.no_mock_provider
|
||||
async def test_conversation_history_field_mapping():
|
||||
"""Test that enhanced prompts are mapped to prompt field for all tools"""
|
||||
|
||||
@@ -41,7 +41,7 @@ async def test_conversation_history_field_mapping():
|
||||
]
|
||||
|
||||
for test_case in test_cases:
|
||||
# Create mock conversation context
|
||||
# Create real conversation context
|
||||
mock_context = ThreadContext(
|
||||
thread_id="test-thread-123",
|
||||
tool_name=test_case["tool_name"],
|
||||
@@ -66,54 +66,37 @@ async def test_conversation_history_field_mapping():
|
||||
# Mock get_thread to return our test context
|
||||
with patch("utils.conversation_memory.get_thread", return_value=mock_context):
|
||||
with patch("utils.conversation_memory.add_turn", return_value=True):
|
||||
with patch("utils.conversation_memory.build_conversation_history") as mock_build:
|
||||
# Mock provider registry to avoid model lookup errors
|
||||
with patch("providers.registry.ModelProviderRegistry.get_provider_for_model") as mock_get_provider:
|
||||
from providers.base import ModelCapabilities
|
||||
# Create arguments with continuation_id and use a test model
|
||||
arguments = {
|
||||
"continuation_id": "test-thread-123",
|
||||
"prompt": test_case["original_value"],
|
||||
"files": ["/test/file2.py"],
|
||||
"model": "flash", # Use test model to avoid provider errors
|
||||
}
|
||||
|
||||
mock_provider = MagicMock()
|
||||
mock_provider.get_capabilities.return_value = ModelCapabilities(
|
||||
provider=ProviderType.GOOGLE,
|
||||
model_name="gemini-2.5-flash",
|
||||
friendly_name="Gemini",
|
||||
context_window=200000,
|
||||
supports_extended_thinking=True,
|
||||
)
|
||||
mock_get_provider.return_value = mock_provider
|
||||
# Mock conversation history building
|
||||
mock_build.return_value = (
|
||||
"=== CONVERSATION HISTORY ===\nPrevious conversation content\n=== END HISTORY ===",
|
||||
1000, # mock token count
|
||||
)
|
||||
# Call reconstruct_thread_context
|
||||
enhanced_args = await reconstruct_thread_context(arguments)
|
||||
|
||||
# Create arguments with continuation_id
|
||||
arguments = {
|
||||
"continuation_id": "test-thread-123",
|
||||
"prompt": test_case["original_value"],
|
||||
"files": ["/test/file2.py"],
|
||||
}
|
||||
# Verify the enhanced prompt is in the prompt field
|
||||
assert "prompt" in enhanced_args
|
||||
enhanced_value = enhanced_args["prompt"]
|
||||
|
||||
# Call reconstruct_thread_context
|
||||
enhanced_args = await reconstruct_thread_context(arguments)
|
||||
# Should contain conversation history
|
||||
assert "=== CONVERSATION HISTORY" in enhanced_value # Allow for both formats
|
||||
assert "Previous user message" in enhanced_value
|
||||
assert "Previous assistant response" in enhanced_value
|
||||
|
||||
# Verify the enhanced prompt is in the prompt field
|
||||
assert "prompt" in enhanced_args
|
||||
enhanced_value = enhanced_args["prompt"]
|
||||
# Should contain the new user input
|
||||
assert "=== NEW USER INPUT ===" in enhanced_value
|
||||
assert test_case["original_value"] in enhanced_value
|
||||
|
||||
# Should contain conversation history
|
||||
assert "=== CONVERSATION HISTORY ===" in enhanced_value
|
||||
assert "Previous conversation content" in enhanced_value
|
||||
|
||||
# Should contain the new user input
|
||||
assert "=== NEW USER INPUT ===" in enhanced_value
|
||||
assert test_case["original_value"] in enhanced_value
|
||||
|
||||
# Should have token budget
|
||||
assert "_remaining_tokens" in enhanced_args
|
||||
assert enhanced_args["_remaining_tokens"] > 0
|
||||
# Should have token budget
|
||||
assert "_remaining_tokens" in enhanced_args
|
||||
assert enhanced_args["_remaining_tokens"] > 0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.no_mock_provider
|
||||
async def test_unknown_tool_defaults_to_prompt():
|
||||
"""Test that unknown tools default to using 'prompt' field"""
|
||||
|
||||
@@ -122,37 +105,37 @@ async def test_unknown_tool_defaults_to_prompt():
|
||||
tool_name="unknown_tool",
|
||||
created_at=datetime.now().isoformat(),
|
||||
last_updated_at=datetime.now().isoformat(),
|
||||
turns=[],
|
||||
turns=[
|
||||
ConversationTurn(
|
||||
role="user",
|
||||
content="First message",
|
||||
timestamp=datetime.now().isoformat(),
|
||||
),
|
||||
ConversationTurn(
|
||||
role="assistant",
|
||||
content="First response",
|
||||
timestamp=datetime.now().isoformat(),
|
||||
),
|
||||
],
|
||||
initial_context={},
|
||||
)
|
||||
|
||||
with patch("utils.conversation_memory.get_thread", return_value=mock_context):
|
||||
with patch("utils.conversation_memory.add_turn", return_value=True):
|
||||
with patch("utils.conversation_memory.build_conversation_history", return_value=("History", 500)):
|
||||
# Mock ModelContext to avoid calculation errors
|
||||
with patch("utils.model_context.ModelContext") as mock_model_context_class:
|
||||
mock_model_context = MagicMock()
|
||||
mock_model_context.model_name = "gemini-2.5-flash"
|
||||
mock_model_context.calculate_token_allocation.return_value = MagicMock(
|
||||
total_tokens=200000,
|
||||
content_tokens=120000,
|
||||
response_tokens=80000,
|
||||
file_tokens=48000,
|
||||
history_tokens=48000,
|
||||
available_for_prompt=24000,
|
||||
)
|
||||
mock_model_context_class.from_arguments.return_value = mock_model_context
|
||||
arguments = {
|
||||
"continuation_id": "test-thread-456",
|
||||
"prompt": "User input",
|
||||
"model": "flash", # Use test model for real integration
|
||||
}
|
||||
|
||||
arguments = {
|
||||
"continuation_id": "test-thread-456",
|
||||
"prompt": "User input",
|
||||
}
|
||||
enhanced_args = await reconstruct_thread_context(arguments)
|
||||
|
||||
enhanced_args = await reconstruct_thread_context(arguments)
|
||||
|
||||
# Should default to 'prompt' field
|
||||
assert "prompt" in enhanced_args
|
||||
assert "History" in enhanced_args["prompt"]
|
||||
# Should default to 'prompt' field
|
||||
assert "prompt" in enhanced_args
|
||||
assert "=== CONVERSATION HISTORY" in enhanced_args["prompt"] # Allow for both formats
|
||||
assert "First message" in enhanced_args["prompt"]
|
||||
assert "First response" in enhanced_args["prompt"]
|
||||
assert "User input" in enhanced_args["prompt"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
|
||||
Reference in New Issue
Block a user