c960bcb720
* 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>
117 lines
5.2 KiB
Python
117 lines
5.2 KiB
Python
"""
|
|
Communication Simulator Tests Package
|
|
|
|
This package contains individual test modules for the Zen MCP Communication Simulator.
|
|
Each test is in its own file for better organization and maintainability.
|
|
"""
|
|
|
|
from .base_test import BaseSimulatorTest
|
|
from .test_analyze_validation import AnalyzeValidationTest
|
|
from .test_basic_conversation import BasicConversationTest
|
|
from .test_chat_simple_validation import ChatSimpleValidationTest
|
|
from .test_codereview_validation import CodeReviewValidationTest
|
|
from .test_consensus_conversation import TestConsensusConversation
|
|
from .test_consensus_stance import TestConsensusStance
|
|
from .test_consensus_three_models import TestConsensusThreeModels
|
|
from .test_content_validation import ContentValidationTest
|
|
from .test_conversation_chain_validation import ConversationChainValidationTest
|
|
from .test_cross_tool_comprehensive import CrossToolComprehensiveTest
|
|
from .test_cross_tool_continuation import CrossToolContinuationTest
|
|
from .test_debug_certain_confidence import DebugCertainConfidenceTest
|
|
from .test_debug_validation import DebugValidationTest
|
|
from .test_line_number_validation import LineNumberValidationTest
|
|
from .test_logs_validation import LogsValidationTest
|
|
from .test_model_thinking_config import TestModelThinkingConfig
|
|
from .test_o3_model_selection import O3ModelSelectionTest
|
|
from .test_o3_pro_expensive import O3ProExpensiveTest
|
|
from .test_ollama_custom_url import OllamaCustomUrlTest
|
|
from .test_openrouter_fallback import OpenRouterFallbackTest
|
|
from .test_openrouter_models import OpenRouterModelsTest
|
|
from .test_per_tool_deduplication import PerToolDeduplicationTest
|
|
from .test_planner_continuation_history import PlannerContinuationHistoryTest
|
|
from .test_planner_validation import PlannerValidationTest
|
|
from .test_precommitworkflow_validation import PrecommitWorkflowValidationTest
|
|
from .test_prompt_size_limit_bug import PromptSizeLimitBugTest
|
|
|
|
# Redis validation test removed - no longer needed for standalone server
|
|
from .test_refactor_validation import RefactorValidationTest
|
|
from .test_testgen_validation import TestGenValidationTest
|
|
from .test_thinkdeep_validation import ThinkDeepWorkflowValidationTest
|
|
from .test_token_allocation_validation import TokenAllocationValidationTest
|
|
from .test_vision_capability import VisionCapabilityTest
|
|
from .test_xai_models import XAIModelsTest
|
|
|
|
# Test registry for dynamic loading
|
|
TEST_REGISTRY = {
|
|
"basic_conversation": BasicConversationTest,
|
|
"chat_validation": ChatSimpleValidationTest,
|
|
"codereview_validation": CodeReviewValidationTest,
|
|
"content_validation": ContentValidationTest,
|
|
"per_tool_deduplication": PerToolDeduplicationTest,
|
|
"cross_tool_continuation": CrossToolContinuationTest,
|
|
"cross_tool_comprehensive": CrossToolComprehensiveTest,
|
|
"line_number_validation": LineNumberValidationTest,
|
|
"logs_validation": LogsValidationTest,
|
|
# "redis_validation": RedisValidationTest, # Removed - no longer needed for standalone server
|
|
"model_thinking_config": TestModelThinkingConfig,
|
|
"o3_model_selection": O3ModelSelectionTest,
|
|
"ollama_custom_url": OllamaCustomUrlTest,
|
|
"openrouter_fallback": OpenRouterFallbackTest,
|
|
"openrouter_models": OpenRouterModelsTest,
|
|
"planner_validation": PlannerValidationTest,
|
|
"planner_continuation_history": PlannerContinuationHistoryTest,
|
|
"precommit_validation": PrecommitWorkflowValidationTest,
|
|
"token_allocation_validation": TokenAllocationValidationTest,
|
|
"testgen_validation": TestGenValidationTest,
|
|
"thinkdeep_validation": ThinkDeepWorkflowValidationTest,
|
|
"refactor_validation": RefactorValidationTest,
|
|
"debug_validation": DebugValidationTest,
|
|
"debug_certain_confidence": DebugCertainConfidenceTest,
|
|
"conversation_chain_validation": ConversationChainValidationTest,
|
|
"vision_capability": VisionCapabilityTest,
|
|
"xai_models": XAIModelsTest,
|
|
"consensus_conversation": TestConsensusConversation,
|
|
"consensus_stance": TestConsensusStance,
|
|
"consensus_three_models": TestConsensusThreeModels,
|
|
"analyze_validation": AnalyzeValidationTest,
|
|
"prompt_size_limit_bug": PromptSizeLimitBugTest,
|
|
# "o3_pro_expensive": O3ProExpensiveTest, # COMMENTED OUT - too expensive to run by default
|
|
}
|
|
|
|
__all__ = [
|
|
"BaseSimulatorTest",
|
|
"BasicConversationTest",
|
|
"ChatSimpleValidationTest",
|
|
"CodeReviewValidationTest",
|
|
"ContentValidationTest",
|
|
"PerToolDeduplicationTest",
|
|
"CrossToolContinuationTest",
|
|
"CrossToolComprehensiveTest",
|
|
"LineNumberValidationTest",
|
|
"LogsValidationTest",
|
|
"TestModelThinkingConfig",
|
|
"O3ModelSelectionTest",
|
|
"O3ProExpensiveTest",
|
|
"OllamaCustomUrlTest",
|
|
"OpenRouterFallbackTest",
|
|
"OpenRouterModelsTest",
|
|
"PlannerValidationTest",
|
|
"PlannerContinuationHistoryTest",
|
|
"PrecommitWorkflowValidationTest",
|
|
"TokenAllocationValidationTest",
|
|
"TestGenValidationTest",
|
|
"ThinkDeepWorkflowValidationTest",
|
|
"RefactorValidationTest",
|
|
"DebugValidationTest",
|
|
"DebugCertainConfidenceTest",
|
|
"ConversationChainValidationTest",
|
|
"VisionCapabilityTest",
|
|
"XAIModelsTest",
|
|
"TestConsensusConversation",
|
|
"TestConsensusStance",
|
|
"TestConsensusThreeModels",
|
|
"AnalyzeValidationTest",
|
|
"PromptSizeLimitBugTest",
|
|
"TEST_REGISTRY",
|
|
]
|