2 Commits

Author	SHA1	Message	Date
catlog22	3e9a309079	refactor: 移除图索引功能，修复内存泄露，优化嵌入生成 ... 主要更改: 1. 移除图索引功能 (graph indexing) - 删除 graph_analyzer.py 及相关迁移文件 - 移除 CLI 的 graph 命令和 --enrich 标志 - 清理 chain_search.py 中的图查询方法 (370行) - 删除相关测试文件 2. 修复嵌入生成内存问题 - 重构 generate_embeddings.py 使用流式批处理 - 改用 embedding_manager 的内存安全实现 - 文件从 548 行精简到 259 行 (52.7% 减少) 3. 修复内存泄露 - chain_search.py: quick_search 使用 with 语句管理 ChainSearchEngine - embedding_manager.py: 使用 with 语句管理 VectorStore - vector_store.py: 添加暴力搜索内存警告 4. 代码清理 - 移除 Symbol 模型的 token_count 和 symbol_type 字段 - 清理相关测试用例 测试: 760 passed, 7 skipped 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2025-12-21 16:22:03 +08:00
catlog22	0fe16963cd	Add comprehensive tests for tokenizer, performance benchmarks, and TreeSitter parser functionality ... - Implemented unit tests for the Tokenizer class, covering various text inputs, edge cases, and fallback mechanisms. - Created performance benchmarks comparing tiktoken and pure Python implementations for token counting. - Developed extensive tests for TreeSitterSymbolParser across Python, JavaScript, and TypeScript, ensuring accurate symbol extraction and parsing. - Added configuration documentation for MCP integration and custom prompts, enhancing usability and flexibility. - Introduced a refactor script for GraphAnalyzer to streamline future improvements.	2025-12-15 14:36:09 +08:00