Release v2.2.1

Bug Fix Release

Fixed

• File watcher auto-refresh functionality restored
• Added missing import that was causing file watcher startup failures
• Automatic index updates now work when files are created, modified, or deleted

Impact

• File watcher status changes from "error" to "active"
• No more manual refresh required after file changes
• Real-time code intelligence restored

This patch fixes the regression introduced in v2.2.0 where file watching was completely non-functional.

Upgrade recommended for all v2.2.0 users.

v2.2.0 - Return to Simplicity

What's New

Architectural Refinement: Back to Custom Indexing

• Direct tree-sitter imports: Eliminated fallback mechanisms for cleaner, more predictable parsing
• Simplified architecture: Moved away from complex SCIP protocol back to efficient custom JSON indexing
• Fail-fast approach: Clear error messages when dependencies are missing, no silent degradation
• Enhanced performance: Streamlined indexing process with reduced overhead and faster access

Improved Language Strategy Implementation

• 7 Specialized Languages: Python, JavaScript, TypeScript, Java, Go, Objective-C, Zig now use direct tree-sitter AST parsing
• 50+ Fallback Languages: All other file types continue to use reliable fallback indexing
• No Regex Fallbacks: Specialized strategies use pure AST parsing for maximum accuracy
• Cleaner Error Handling: Dependencies issues surface immediately with actionable error messages

Enhanced Parsing Accuracy

• Better Symbol Extraction: Improved class, method, and function detection across all supported languages
• Accurate Call Relationships: Enhanced tracking of function calls and dependencies
• Robust Import Analysis: Better detection of module imports and exports
• Comprehensive Testing: Validated parsing accuracy across 67 sample files in multiple languages

Technical Improvements

Dual-Strategy Architecture

• Specialized Parsing: Tree-sitter AST analysis for core languages with full symbol extraction
• Universal Coverage: Fallback strategy ensures all file types are indexed with basic metadata
• Clean Separation: Clear distinction between specialized and fallback parsing approaches

Development Experience

• Clearer Documentation: Updated all README files to accurately reflect the dual-strategy approach
• Better Testing: Comprehensive validation across multiple programming languages
• Simplified Maintenance: Reduced complexity makes the codebase easier to understand and extend

Migration Notes

This release represents a return to the custom indexing approach that prioritizes:

• Efficiency over protocol compliance
• Simplicity over complex standards
• Performance over theoretical extensibility
• Clarity over abstraction

The previous SCIP-based approach (v2.0.x - v2.1.x) encountered efficiency issues and limited ecosystem support. This release refocuses on the project's core mission: providing fast, accurate code indexing for LLM applications.

Breaking Changes

None - fully backward compatible with existing MCP integrations

---

Full Changelog: v2.1.2...v2.2.0

v2.1.2

Full Changelog: v2.1.1...v2.1.2

v2.1.1

What's Fixed

This patch release resolves stability and performance issues in Java code analysis.

Key Improvements

• Enhanced Stability: Fixed crashes and hangs during Java file processing
• Better Performance: Significantly faster Java symbol analysis
• Reduced Memory Usage: Lower memory footprint during indexing
• Improved Reliability: More consistent analysis results

Technical Changes

• Simplified Java SCIP strategy implementation
• Removed complex relationship tracking that was causing issues
• Streamlined symbol registration and extraction
• Fixed compatibility issues with large Java codebases

---

Full Changelog: v2.1.0...v2.1.1

v2.1.0

Major SCIP Architecture Enhancement

This release completes the migration to SCIP-based code indexing with significant improvements to the core infrastructure and API simplification.

Core SCIP Infrastructure

• Complete SCIP core components: Added symbol_manager, position_calculator, reference_resolver, moniker_manager
• Two-phase SCIP analysis: Implemented symbol collection → reference resolution workflow
• Unified index management: New index_provider and unified_index_manager for seamless index operations
• SCIP-compliant symbol IDs: Standard symbol ID generation with cross-file reference support

Enhanced Strategy System

• All language strategies SCIP-compliant: Refactored Python, Java, JavaScript, Objective-C strategies
• External symbol extraction: Added dependency tracking and external symbol resolution
• Proper SCIP classifications: Implemented symbol roles and syntax kind detection
• Robust file handling: Enhanced encoding detection and error recovery

API Improvements

• Simplified find_files response: Returns clean file path lists instead of complex metadata objects
• Enhanced SCIPSymbolAnalyzer: Replaced legacy query tools with accurate symbol analysis
• Improved logging: Comprehensive logging throughout SCIP indexing pipeline

Dependency Updates

• pathspec integration: Better .gitignore parsing and file filtering
• Updated requirements: Added comprehensive dependency list for cross-platform support

Technical Improvements

• Symbol analysis tools: New inspection scripts for debugging and development
• Enhanced error handling: Better fallback strategies and error recovery
• Testing improvements: Updated sample projects for multilingual testing

Breaking Changes

• find_files API: Now returns List[str] instead of complex metadata dictionary
• Internal architecture: Significant refactoring of internal components (no user-facing impact)

v2.0.1

Full Changelog: v2.0.0...v2.0.1

v2.0.0 - SCIP Architecture Migration

🚀 Major Changes

Complete architectural overhaul - This release represents a fundamental redesign of the code indexing system.

New Architecture

• Three-layer service architecture: Service → Tool → Technical Components
• Unified SCIP indexing: Replace language-specific analyzers with SCIP protobuf format
• Simplified codebase: Reduced from 40K+ to ~1K lines of core logic

Performance & Reliability

• Faster indexing: Tree-sitter AST parsing instead of regex-based analysis
• Better accuracy: SCIP provides more precise code intelligence
• Reduced memory usage: Streamlined data structures and processing

Backward Compatibility

• MCP API unchanged: All existing MCP tools work without modification
• Automatic migration: Legacy indexes are automatically migrated
• Same functionality: All user-facing features preserved

🔧 Technical Details

Removed Components

• Language-specific analyzers (C, C++, Java, JavaScript, Python, etc.)
• Legacy indexing models and relationship management
• Complex duplicate detection and qualified name systems

New Components

• SCIP-based unified indexing system
• Service-oriented business logic layer
• Composable technical tool layer

📦 Migration

Existing users can upgrade seamlessly - the system will automatically:

1. Detect legacy index format
2. Migrate to new SCIP format
3. Maintain all existing functionality

Full Changelog: v1.2.1...v2.0.0

v1.2.1

What's Changed

• Fix file watcher to process moved files from temporary locations by @Acren in #17

New Contributors

• @Acren made their first contribution in #17

Full Changelog: v1.2.0...v1.2.1

Release Notes - v1.2.0

What's New

Enhanced File Search Capabilities

• Filename-only search: Now you can search with just the filename! Use test_*.py to find all test files across any directory, no need for full paths
• Dual matching logic: Searches both full paths and filenames automatically for maximum convenience
• Directory tree traversal: Replaced linear search with efficient tree-based algorithm

Cross-Platform Improvements

• Unified path format: All file paths now use forward slashes consistently across Windows, macOS, and Linux
• Fixed Windows path issues: No more double backslashes in search results

Examples

Before v1.2.0:

find_files("tests/test_*.py")  # Only finds files in tests/ directory

Now in v1.2.0:

find_files("test_*.py")        # Finds ALL test files in any directory
find_files("tests/test_*.py")  # Still works for specific paths
find_files("README.md")        # Finds all README files project-wide

Breaking Changes

None - fully backward compatible

---

Full Changelog: v1.1.1...v1.2.0

v1.1.1

remove sys.path.append to restore uvx environment isolation

Full Changelog: v1.1.0...v1.1.1