torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
70fa088c32ac4e6153d5e7b30a3e32022be2f908
my-pal-mcp-server/tests
History
Fahad 70fa088c32 feat: implement semantic cassette matching for o3 models 
Adds flexible cassette matching that ignores system prompt changes
for o3 models, preventing CI failures when prompts are updated.

Changes:
- Semantic matching: Only compares model name, user question, and core params
- Ignores: System prompts, conversation memory instructions, metadata
- Prevents cassette breaks when prompts change between code versions
- Added comprehensive tests for semantic matching behavior
- Created maintenance documentation (tests/CASSETTE_MAINTENANCE.md)

This solves the CI failure where o3-pro test cassettes would break
whenever system prompts or conversation memory format changed.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-01 18:53:30 +04:00
..
openai_cassettes
Fix o3-pro model resolution to use o3-pro consistently
2025-08-08 10:52:23 +05:00
__init__.py
…
CASSETTE_MAINTENANCE.md
feat: implement semantic cassette matching for o3 models
2025-10-01 18:53:30 +04:00
conftest.py
fix: Ensure dummy API keys are set for tests with no_mock_provider marker
2025-07-13 11:29:02 -06:00
http_transport_recorder.py
feat: implement semantic cassette matching for o3 models
2025-10-01 18:53:30 +04:00
mock_helpers.py
Quick test mode for simulation tests
2025-06-23 18:33:47 +04:00
pii_sanitizer.py
fix: Resolve o3-pro test isolation issues and convert print to logging
2025-07-13 10:41:43 -06:00
sanitize_cassettes.py
fix: Resolve o3-pro response parsing and test execution issues
2025-07-12 20:24:34 -06:00
test_alias_target_restrictions.py
GPT-5, GPT-5-mini support
2025-08-08 08:51:34 +05:00
test_auto_mode_comprehensive.py
Grok-4 support
2025-08-08 09:39:07 +05:00
test_auto_mode_custom_provider_only.py
feat: Add DISABLED_TOOLS environment variable for selective tool disabling (#127)
2025-06-23 19:07:40 +04:00
test_auto_mode_provider_selection.py
Grok-4 support
2025-08-08 09:39:07 +05:00
test_auto_mode.py
Quick test mode for simulation tests
2025-06-23 18:33:47 +04:00
test_auto_model_planner_fix.py
Improvements to consensus
2025-08-08 12:59:41 +05:00
test_buggy_behavior_prevention.py
GPT-5, GPT-5-mini support
2025-08-08 08:51:34 +05:00
test_cassette_semantic_matching.py
feat: implement semantic cassette matching for o3 models
2025-10-01 18:53:30 +04:00
test_challenge.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_chat_simple.py
fix: removed use_websearch; this parameter was confusing Codex. It started using this to prompt the external model to perform searches! web-search is enabled by Claude / Codex etc by default and the external agent can ask claude to search on its behalf.
2025-10-01 18:44:11 +04:00
test_collaboration.py
style: format code for consistency and readability across multiple files
2025-06-23 23:17:56 +02:00
test_config.py
Gemini model rename
2025-06-19 05:37:40 +04:00
test_consensus.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_conversation_field_mapping.py
Add DocGen tool with comprehensive documentation generation capabilities (#109)
2025-06-22 10:21:19 +04:00
test_conversation_file_features.py
…
test_conversation_memory.py
Quick test mode for simulation tests
2025-06-23 18:56:47 +04:00
test_conversation_missing_files.py
…
test_custom_openai_temperature_fix.py
fix: respect custom OpenAI model temperature settings (#245)
2025-09-05 10:53:28 +07:00
test_custom_provider.py
Fixed: https://github.com/BeehiveInnovations/zen-mcp-server/issues/123
2025-06-23 15:23:55 +04:00
test_debug.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_deploy_scripts.py
feat: Add comprehensive tests for Docker integration, security, and volume persistence
2025-06-29 00:01:35 +02:00
test_dial_provider.py
feat: Update Claude models to Opus 4.1 and Sonnet 4.1
2025-08-17 16:08:52 +00:00
test_directory_expansion_tracking.py
Migration from Docker to Standalone Python Server (#73)
2025-06-18 23:41:22 +04:00
test_disabled_tools.py
feat: Add DISABLED_TOOLS environment variable for selective tool disabling (#127)
2025-06-23 19:07:40 +04:00
test_docker_claude_desktop_integration.py
feat: Add comprehensive tests for Docker integration, security, and volume persistence
2025-06-29 00:01:35 +02:00
test_docker_config_complete.py
refactor: Update environment and Docker configuration files; remove unused MCP configuration tests
2025-06-25 17:42:58 +02:00
test_docker_healthcheck.py
feat: Add comprehensive tests for Docker integration, security, and volume persistence
2025-06-29 00:01:35 +02:00
test_docker_implementation.py
refactor: Update environment and Docker configuration files; remove unused MCP configuration tests
2025-06-25 17:42:58 +02:00
test_docker_mcp_validation.py
feat: Add comprehensive tests for Docker integration, security, and volume persistence
2025-06-29 00:01:35 +02:00
test_docker_security.py
feat: Add comprehensive tests for Docker integration, security, and volume persistence
2025-06-29 00:01:35 +02:00
test_docker_volume_persistence.py
feat: Add comprehensive tests for Docker integration, security, and volume persistence
2025-06-29 00:01:35 +02:00
test_file_protection.py
Migration from Docker to Standalone Python Server (#73)
2025-06-18 23:41:22 +04:00
test_gemini_token_usage.py
Fixes bug pointed out by @dsaluja (https://github.com/dsaluja)
2025-06-17 11:29:45 +04:00
test_image_support_integration.py
Quick test mode for simulation tests
2025-06-23 18:56:47 +04:00
test_image_validation.py
refactor: Extract image validation to provider base class
2025-07-12 21:51:24 -07:00
test_integration_utf8.py
fix: improve UTF-8 integration tests and response handling by adding details and fixes in mocks
2025-06-24 00:09:19 +02:00
test_intelligent_fallback.py
GPT-5, GPT-5-mini support
2025-08-08 08:51:34 +05:00
test_issue_245_simple.py
refactor: address code review feedback from Gemini
2025-09-05 11:04:45 +07:00
test_large_prompt_handling.py
Add DocGen tool with comprehensive documentation generation capabilities (#109)
2025-06-22 10:21:19 +04:00
test_line_numbers_integration.py
Add DocGen tool with comprehensive documentation generation capabilities (#109)
2025-06-22 10:21:19 +04:00
test_listmodels_restrictions.py
feat: Update Claude model references from v3 to v4 (fixes issue #118) (#119)
2025-06-23 13:57:13 +04:00
test_listmodels.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_model_enumeration.py
Quick test mode for simulation tests
2025-06-23 18:33:47 +04:00
test_model_metadata_continuation.py
Quick test mode for simulation tests
2025-06-23 18:56:47 +04:00
test_model_resolution_bug.py
Add DocGen tool with comprehensive documentation generation capabilities (#109)
2025-06-22 10:21:19 +04:00
test_model_restrictions.py
Resolve merge conflicts in o3-pro response parsing fix
2025-08-08 10:48:56 +05:00
test_o3_pro_output_text_fix.py
Fix o3-pro model resolution to use o3-pro consistently
2025-08-08 10:52:23 +05:00
test_o3_temperature_fix_simple.py
GPT-5, GPT-5-mini support
2025-08-08 08:51:34 +05:00
test_old_behavior_simulation.py
Gemini model rename
2025-06-19 05:37:40 +04:00
test_openai_compatible_token_usage.py
Proper fix for model discovery per provider
2025-06-18 07:16:10 +04:00
test_openai_provider.py
Fix o3-pro model resolution to use o3-pro consistently
2025-08-08 10:52:23 +05:00
test_openrouter_provider.py
feat: Update Claude models to Opus 4.1 and Sonnet 4.1
2025-08-17 16:08:52 +00:00
test_openrouter_registry.py
feat: Update Claude models to Opus 4.1 and Sonnet 4.1
2025-08-17 16:08:52 +00:00
test_parse_model_option.py
feat: Update Claude models to Opus 4.1 and Sonnet 4.1
2025-08-17 16:08:52 +00:00
test_per_tool_model_defaults.py
GPT-5, GPT-5-mini support
2025-08-08 08:51:34 +05:00
test_pii_sanitizer.py
test: Enhance o3-pro test to verify model metadata and response parsing
2025-07-13 06:09:31 -06:00
test_pip_detection_fix.py
fix: address PR review feedback on test quality
2025-08-08 23:58:19 +07:00
test_planner.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_precommit_workflow.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_prompt_regression.py
Add DocGen tool with comprehensive documentation generation capabilities (#109)
2025-06-22 10:21:19 +04:00
test_prompt_size_limit_bug_fix.py
Add DocGen tool with comprehensive documentation generation capabilities (#109)
2025-06-22 10:21:19 +04:00
test_provider_routing_bugs.py
feat: Update Claude models to Opus 4.1 and Sonnet 4.1
2025-08-17 16:08:52 +00:00
test_provider_utf8.py
feat: Update Claude models to Opus 4.1 and Sonnet 4.1
2025-08-17 16:08:52 +00:00
test_providers.py
Quick test mode for simulation tests
2025-06-23 18:33:47 +04:00
test_rate_limit_patterns.py
Migration from Docker to Standalone Python Server (#73)
2025-06-18 23:41:22 +04:00
test_refactor.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_secaudit.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_server.py
Fixed linebreaks
2025-06-27 14:29:10 +04:00
test_supported_models_aliases.py
test: Update OpenAI provider alias tests to match new format
2025-09-09 19:08:10 -06:00
test_thinking_modes.py
Add DocGen tool with comprehensive documentation generation capabilities (#109)
2025-06-22 10:21:19 +04:00
test_tools.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_tracer.py
feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness
2025-08-22 09:23:59 +04:00
test_utf8_localization.py
refactor: remove obsolete localization test files and update UTF-8 tests for improved mock handling
2025-06-24 18:48:31 +02:00
test_utils.py
Migration from Docker to Standalone Python Server (#73)
2025-06-18 23:41:22 +04:00
test_uvx_resource_packaging.py
Fix failing tests and exclude .zen_venv from linting
2025-08-10 22:18:08 +07:00
test_uvx_support.py
fix: Handle tomllib import for Python 3.10 compatibility in uvx tests
2025-06-27 10:37:32 -07:00
test_workflow_file_embedding.py
🚀 Major Enhancement: Workflow-Based Tool Architecture v5.5.0 (#95)
2025-06-21 00:08:11 +04:00
test_workflow_metadata.py
Fixed: https://github.com/BeehiveInnovations/zen-mcp-server/issues/123
2025-06-23 15:23:55 +04:00
test_workflow_prompt_size_validation_simple.py
Add DocGen tool with comprehensive documentation generation capabilities (#109)
2025-06-22 10:21:19 +04:00
test_workflow_utf8.py
refactor: remove obsolete localization test files and update UTF-8 tests for improved mock handling
2025-06-24 18:48:31 +02:00
test_xai_provider.py
Fixed tests
2025-08-08 11:11:22 +05:00
transport_helpers.py
fix: Resolve test isolation issues for o3-pro test
2025-07-13 10:22:03 -06:00
triangle.png
…