Release v2.2.0: Return to simplified custom indexing architecture

- Refactor tree-sitter imports to direct imports without fallback mechanisms
- Eliminate regex-based parsing fallbacks in specialized strategies
- Update version to 2.2.0 in pyproject.toml and __init__.py
- Add comprehensive release notes documenting architectural evolution
- Maintain dual-strategy approach: 7 specialized languages + fallback strategy
- Enhance parsing accuracy with pure AST parsing for core languages
- Improve error handling with fail-fast approach for missing dependencies

This release represents a return to the custom indexing approach that prioritizes
efficiency and simplicity over complex protocol compliance, moving away from
the SCIP-based implementation due to performance considerations.

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

Co-Authored-By: Claude <noreply@anthropic.com>

Author: johnhuang316

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "code-index-mcp"
-version = "2.1.2"
+version = "2.2.0"
 description = "Code indexing and analysis tools for LLMs using MCP"
 readme = "README.md"
 requires-python = ">=3.10"

src/code_index_mcp/__init__.py

@@ -3,4 +3,4 @@
 A Model Context Protocol server for code indexing, searching, and analysis.
 """
 
-__version__ = "2.0.0"
+__version__ = "2.2.0"