* WIP
Refactor resolving mode_names, should be done once at MCP call boundary
Pass around model context instead
Consensus tool allows one to get a consensus from multiple models, optionally assigning one a 'for' or 'against' stance to find nuanced responses.
* Deduplication of model resolution, model_context should be available before reaching deeper parts of the code
Improved abstraction when building conversations
Throw programmer errors early
* Guardrails
Support for `model:option` format at MCP boundary so future tools can use additional options if needed instead of handling this only for consensus
Model name now supports an optional ":option" for future use
* Simplified async flow
* Improved model for request to support natural language
Simplified async flow
* Improved model for request to support natural language
Simplified async flow
* Fix consensus tool async/sync patterns to match codebase standards
CRITICAL FIXES:
- Converted _get_consensus_responses from async to sync (matches other tools)
- Converted store_conversation_turn from async to sync (add_turn is synchronous)
- Removed unnecessary asyncio imports and sleep calls
- Fixed ClosedResourceError in MCP protocol during long consensus operations
PATTERN ALIGNMENT:
- Consensus tool now follows same sync patterns as all other tools
- Only execute() and prepare_prompt() are async (base class requirement)
- All internal operations are synchronous like analyze, chat, debug, etc.
TESTING:
- MCP simulation test now passes: consensus_stance ✅
- Two-model consensus works correctly in ~35 seconds
- Unknown stance handling defaults to neutral with warnings
- All 9 unit tests pass (100% success rate)
The consensus tool async patterns were anomalous in the codebase.
This fix aligns it with the established synchronous patterns used
by all other tools while maintaining full functionality.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fixed call order and added new test
* Cleanup dead comments
Docs for the new tool
Improved tests
---------
Co-authored-by: Claude <noreply@anthropic.com>
Adds two comprehensive tests to prevent future regression of the parameter
order bug in `restriction_service.is_allowed()` calls:
1. `test_gemini_parameter_order_regression_protection` - Tests edge case
where only alias is allowed, ensuring correct parameter order
2. `test_gemini_parameter_order_edge_case_full_name_only` - Tests reverse
scenario where only full model name is allowed
These tests specifically catch the subtle bug where parameters were
incorrectly passed as (provider, user_input, resolved_name) instead of
(provider, resolved_name, user_input). The bug was masked by OR logic
in most cases but could cause issues in edge scenarios.
All 498 tests pass, including the new regression protection tests.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fixed swapped parameters in restriction_service.is_allowed() calls
- Parameter order should be (provider_type, model_name, original_name)
- Regression introduced in merge commit 39c50a1, breaking Gemini model access
- Added comments to prevent future parameter order confusion
- Resolves Gemini model is not allowed by restriction policy errors
🤖 Generated with Claude Code
Co-authored-by: Ming <ming@mail.ooo>
Co-authored-by: Claude <noreply@anthropic.com>
New tool to list all models `listmodels`
Integration test to for all the different combinations of API keys
Tweaks to codereview prompt for a better quality input from Claude
Fixed missing 'low' severity in codereview
Instead of creating new OpenRouterModelRegistry instances multiple times
per tool (4x per tool during schema generation), we now use a shared
class-level cache in BaseTool. This reduces registry loading from 40+ times
to just once during MCP server initialization.
The optimization:
- Adds _openrouter_registry_cache as a class variable in BaseTool
- Implements _get_openrouter_registry() classmethod for lazy loading
- Ensures cache is shared across all tool subclasses
- Maintains identical functionality with improved performance
This significantly reduces startup time and resource usage when OpenRouter
is configured, especially noticeable with many custom models.
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
Address code review feedback from Gemini Code Assist bot:
- Fix parameter order in validate_model_name method (line 256)
- Ensure consistent use of original model name for restriction validation
- All is_allowed() calls now properly use (provider, original_name, resolved_name)
This completes the fix for GOOGLE_ALLOWED_MODELS shorthand restriction validation.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fixed parameter order in is_allowed() calls to check original model name first
- Fixed validate_parameters() to use original model name instead of resolved name
- Fixed thinking capabilities check to use original model name
- Enables GOOGLE_ALLOWED_MODELS=pro,flash to work correctly with shorthand names
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
Following the established testing patterns from other tool tests:
- Removed mocking of providers and capabilities
- Use real provider resolution with dummy API keys
- Expect proper validation behavior or provider-not-found errors
- Applied proper Redis mocking for conversation memory tests
- Simplified validation tests to focus on core functionality
- All 473 tests now pass 100% including 13 image support tests
This ensures CI/CD compatibility and follows the proven testing approach
used throughout the codebase for tool integration testing.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Properly mock Redis client operations to support add_turn functionality
- Set up initial thread contexts so add_turn can find existing threads
- Mock Redis set operations to return success
- Ensure all Redis-dependent tests use proper mock patterns
- All 473 unit tests now pass 100% with proper isolation
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add proper Redis client mocking to prevent connection attempts during CI
- Apply @patch("utils.conversation_memory.get_redis_client") decorators to all methods using Redis
- Mock thread contexts for get_thread calls to ensure tests work without Redis
- Fixes GitHub Actions failures: ConnectionRefusedError when connecting to localhost:6379
- Maintains test isolation and proper mock patterns used throughout test suite
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fixed worst flake8 violations (300-600+ character lines) in tools directory
- Applied consistent multi-line string formatting for better readability
- Removed incompatible test files from main branch merge
- All 473 tests passing, all code quality checks pass
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Kept version 4.8.0 for new features
- Preserved our _is_builtin_custom_models_config approach over main's ALLOWED_INTERNAL_PATHS
- Our targeted solution is cleaner than the general whitelist approach
Addressed Gemini code review feedback by refactoring repetitive log processing:
✅ **Added _process_log_stream helper function**:
- Encapsulates common pattern of reading, filtering, formatting, and printing log lines
- Takes tailer, filter_func, and format_func as parameters
- Eliminates repetitive timestamp and formatting logic
✅ **Simplified main monitoring loop**:
- Reduced from ~35 lines of repetitive code to 4 clean function calls
- Each log stream now uses: _process_log_stream(tailer, filter, formatter)
- Eliminated duplicate timestamp creation (reduced from 4 to 1 occurrence)
✅ **Improved maintainability**:
- Changes to log processing logic now only need to be made in one place
- Cleaner, more readable main loop
- Better separation of concerns
✅ **Verified functionality**:
- All containers rebuild and start successfully
- Log monitor functions correctly with refactored code
- No functional changes, only code organization improvements
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixed code quality issues identified by Gemini code review:
- Removed dead code: create_line_handler function was defined but never used
- Eliminated unused parameter warning
- Cleaned up unnecessary complexity in log_monitor.py
- The monitor_mcp_activity function implements all needed logic inline
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixed NameError that was causing Docker container crashes:
- Updated type annotation in format_response method from TestGenRequest to TestGenerationRequest
- This was the last missing reference from the class rename
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixed MagicMock comparison errors across multiple test suites by:
- Adding proper ModelCapabilities mocks with real values instead of MagicMock objects
- Updating test_auto_mode.py with correct provider mocking for model availability tests
- Updating test_thinking_modes.py with proper capabilities mocking in all thinking mode tests
- Updating test_tools.py with proper capabilities mocking for CodeReview and Analyze tools
- Fixing test_large_prompt_handling.py by adding proper provider mocking to prevent errors before large prompt detection
Fixed pytest collection warnings by:
- Renaming TestGenRequest to TestGenerationRequest to avoid pytest collecting it as a test class
- Renaming TestGenTool to TestGenerationTool to avoid pytest collecting it as a test class
- Updated all imports and references across server.py, tools/__init__.py, and test files
All 459 tests now pass without warnings or MagicMock comparison errors.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Exit early at MCP boundary if files won't fit within given context of chosen model
- Encourage claude to re-run with better context
- Check file sizes before embedding
- Drop files from older conversations when building continuations and give priority to newer files
- List and mention excluded files to Claude on return
- Improved tests
- Improved precommit prompt
- Added a new Low severity to precommit
- Improved documentation of file embedding strategy
- Refactor
