- Added pre-calculation of estimated chunk count for HNSW capacity in `generate_dense_embeddings_centralized` to optimize indexing performance.
- Implemented binary vector generation with memory-mapped storage for efficient cascade search, including metadata saving.
- Introduced SPLADE sparse index generation with improved handling and metadata storage.
- Updated `ChainSearchEngine` to prefer centralized binary searcher for improved performance and added fallback to legacy binary index.
- Deprecated `BinaryANNIndex` in favor of `BinarySearcher` for better memory management and performance.
- Enhanced `SpladeEncoder` with warmup functionality to reduce latency spikes during first-time inference.
- Improved `SpladeIndex` with cache size adjustments for better query performance.
- Added methods for managing binary vectors in `VectorMetadataStore`, including batch insertion and retrieval.
- Created a new `BinarySearcher` class for efficient binary vector search using Hamming distance, supporting both memory-mapped and database loading modes.
- Added centralized SPLADE database and vector storage configuration in config.py.
- Updated embedding_manager.py to support centralized SPLADE database path.
- Enhanced generate_embeddings and generate_embeddings_recursive functions for centralized storage.
- Introduced centralized ANN index creation in ann_index.py.
- Modified hybrid_search.py to utilize centralized vector index for searches.
- Implemented methods to discover and manage centralized SPLADE and HNSW files.
- Added category support for programming and documentation languages in Config.
- Implemented category-based filtering in HybridSearchEngine to improve search relevance based on query intent.
- Introduced functions for filtering results by category and determining file categories based on extensions.
- Updated VectorStore to include a category column in the database schema and modified chunk addition methods to support category tagging.
- Enhanced the WatcherConfig to ignore additional common directories and files.
- Created a benchmark script to compare performance between Binary Cascade, SPLADE, and Vector semantic search methods, including detailed result analysis and overlap comparison.
- Implemented `get_all_chunks` method in `VectorStore` class to fetch all semantic chunks from the database.
- Added a new benchmark script `analyze_methods.py` for analyzing hybrid search methods and storage architecture.
- Included detailed analysis of method contributions, storage conflicts, and FTS + Rerank fusion experiments.
- Updated results JSON structure to reflect new analysis outputs and method performance metrics.
- Implemented BinaryEmbeddingBackend for fast coarse filtering using 256-dimensional binary vectors.
- Developed DenseEmbeddingBackend for high-precision dense vectors (2048 dimensions) for reranking.
- Created CascadeEmbeddingBackend to combine binary and dense embeddings for two-stage retrieval.
- Introduced utility functions for embedding conversion and distance computation.
chore: Migration 010 - Add multi-vector storage support
- Added 'chunks' table to support multi-vector embeddings for cascade retrieval.
- Included new columns: embedding_binary (256-dim) and embedding_dense (2048-dim) for efficient storage.
- Implemented upgrade and downgrade functions to manage schema changes and data migration.
- Added `splade_encoder.py` for ONNX-optimized SPLADE encoding, including methods for encoding text and batch processing.
- Created `SPLADE_IMPLEMENTATION.md` to document the SPLADE encoder's functionality, design patterns, and integration points.
- Introduced migration script `migration_009_add_splade.py` to add SPLADE metadata and posting list tables to the database.
- Developed `splade_index.py` for managing the SPLADE inverted index, supporting efficient sparse vector retrieval.
- Added verification script `verify_watcher.py` to test FileWatcher event filtering and debouncing functionality.
- Implemented GraphExpander to enhance search results with related symbols using precomputed neighbors.
- Added CrossEncoderReranker for second-stage search ranking, allowing for improved result scoring.
- Created migrations to establish necessary database tables for relationships and graph neighbors.
- Developed tests for graph expansion functionality, ensuring related results are populated correctly.
- Enhanced performance benchmarks for cross-encoder reranking latency and graph expansion overhead.
- Updated schema cleanup tests to reflect changes in versioning and deprecated fields.
- Added new test cases for Treesitter parser to validate relationship extraction with alias resolution.
Prevents errors when HNSW search returns null/empty results due to race conditions.
Adds validation for ids and distances before zip operation.
Fixes: ISS-1766921318981-5
Solution-ID: SOL-1735386000-5
Issue-ID: ISS-1766921318981-5
Task-ID: T1
Protect _bulk_insert_mode flag and accumulation lists with
_ann_write_lock to prevent corruption during concurrent access.
Solution-ID: SOL-1735392000003
Issue-ID: ISS-1766921318981-12
Task-ID: T1
Protect fast path cache read in get_embedder() to prevent KeyError
during concurrent access and cache clearing operations.
Solution-ID: SOL-1735392000001
Issue-ID: ISS-1766921318981-2
Task-ID: T1
Define module-level EPSILON constant and use it in both
_cosine_similarity and _refresh_cache for consistent
floating point precision handling.
Solution-ID: SOL-20251228113619
Issue-ID: ISS-1766921318981-11
Task-ID: T3
Add comprehensive test coverage for near-zero norms, product
underflow, and floating point precision edge cases in
_cosine_similarity function.
Solution-ID: SOL-20251228113619
Issue-ID: ISS-1766921318981-11
Task-ID: T2
Replace exact zero comparison with epsilon-based check (< 1e-10)
in _cosine_similarity to handle floating point precision issues.
Also check for product underflow to prevent inf/nan from division
by very small numbers.
Solution-ID: SOL-20251228113619
Issue-ID: ISS-1766921318981-11
Task-ID: T1
- Added integration tests for adaptive RRF weights in hybrid search.
- Enhanced query intent detection with new classifications: keyword, semantic, and mixed.
- Introduced symbol boosting in search results based on explicit symbol matches.
- Implemented embedding-based reranking with configurable options.
- Added global symbol index for efficient symbol lookups across projects.
- Improved file deletion handling on Windows to avoid permission errors.
- Updated chunk configuration to increase overlap for better context.
- Modified package.json test script to target specific test files.
- Created comprehensive writing style guidelines for documentation.
- Added TypeScript tests for query intent detection and adaptive weights.
- Established performance benchmarks for global symbol indexing.
- Added search limit, content length, and extra files input fields in the CodexLens manager UI.
- Updated API request parameters to include new fields: max_content_length and extra_files_count.
- Refactored smart-search.ts to support new parameters with default values.
- Implemented result splitting logic to return both full content and additional file paths.
- Updated CLI commands to remove worker limits and allow dynamic scaling based on endpoint count.
- Introduced EmbeddingPoolConfig for improved embedding management and auto-discovery of providers.
- Enhanced search engines to utilize new parameters for fuzzy and exact searches.
- Added support for embedding single texts in the LiteLLM embedder.
- Added JSON-based settings management in Config class for embedding and LLM configurations.
- Introduced methods to save and load settings from a JSON file.
- Updated BaseEmbedder and its subclasses to include max_tokens property for better token management.
- Enhanced chunking strategy to support recursive splitting of large symbols with improved overlap handling.
- Implemented comprehensive tests for recursive splitting and chunking behavior.
- Added CLI tools configuration management for better integration with external tools.
- Introduced a new command for compacting session memory into structured text for recovery.
- Updated embedding_manager.py to include backend parameter in model configuration.
- Modified model_manager.py to utilize cache_name for ONNX models.
- Refactored hybrid_search.py to improve embedder initialization based on backend type.
- Added backend column to vector_store.py for better model configuration management.
- Implemented migration for existing database to include backend information.
- Enhanced API settings implementation with comprehensive provider and endpoint management.
- Introduced LiteLLM integration guide detailing configuration and usage.
- Added examples for LiteLLM usage in TypeScript.
- Create ccw-litellm Python package with AbstractEmbedder and AbstractLLMClient interfaces
- Add BaseEmbedder abstraction and factory pattern to codex-lens for pluggable backends
- Implement API Settings dashboard page for provider credentials and custom endpoints
- Add REST API routes for CRUD operations on providers and endpoints
- Extend CLI with --model parameter for custom endpoint routing
- Integrate existing context-cache for @pattern file resolution
- Add provider model registry with predefined models per provider type
- Include i18n translations (en/zh) for all new UI elements
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Introduced a new CodexLens Manager item in the dashboard for easier access.
- Implemented GPU management commands in the CLI, including listing available GPUs, selecting a specific GPU, and resetting to automatic detection.
- Enhanced the embedding generation process to utilize GPU resources more effectively, including batch size optimization for better performance.
- Updated the embedder to support device ID options for GPU selection, ensuring compatibility with DirectML and CUDA.
- Added detailed logging and error handling for GPU detection and selection processes.
- Updated package version to 6.2.9 and added comprehensive documentation for Codex Agent Execution Protocol.
- Fix model installation detection using fastembed ONNX cache names
- Add embeddings_config table for model metadata tracking
- Fix hybrid search segfault by using single-threaded GPU mode
- Suppress INFO logs in JSON mode to prevent error display
- Add model dropdown filtering to show only installed models
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated the Chunker class to adjust the window movement logic, ensuring proper handling of overlap lines.
- Introduced a new smart search tool with features including intent classification, CodexLens integration, multi-backend search routing, and index status checking.
- Implemented various search modes (auto, hybrid, exact, ripgrep, priority) with detailed metadata and error handling.
- Added support for progress tracking during index initialization and enhanced output transformation based on user-defined modes.
- Included comprehensive documentation for usage and parameters in the smart search tool.
- Updated the dashboard template to hide the Code Graph Explorer feature.
- Enhanced the `executeCodexLens` function to use `exec` for better cross-platform compatibility and improved command execution.
- Changed the default `maxResults` and `limit` parameters in the smart search tool to 10 for better performance.
- Introduced a new `priority` search mode in the smart search tool, replacing the previous `parallel` mode, which now follows a fallback strategy: hybrid -> exact -> ripgrep.
- Optimized the embedding generation process in the embedding manager by batching operations and using a cached embedder instance to reduce model loading overhead.
- Implemented a thread-safe singleton pattern for the embedder to improve performance across multiple searches.
- Added ANNIndex class for approximate nearest neighbor search using HNSW.
- Integrated ANN index with VectorStore for enhanced search capabilities.
- Updated test suite for ANN index, including tests for adding, searching, saving, and loading vectors.
- Modified existing tests to accommodate changes in search performance expectations.
- Improved error handling for file operations in tests to ensure compatibility with Windows file locks.
- Adjusted hybrid search performance assertions for increased stability in CI environments.
- Implement tests for migration 005 to verify removal of deprecated fields in the database schema.
- Ensure that new databases are created with a clean schema.
- Validate that keywords are correctly extracted from the normalized file_keywords table.
- Test symbol insertion without deprecated fields and subdir operations without direct_files.
- Create a detailed search comparison test to evaluate vector search vs hybrid search performance.
- Add a script for reindexing projects to extract code relationships and verify GraphAnalyzer functionality.
- Include a test script to check TreeSitter parser availability and relationship extraction from sample files.
- Added a new Storage Manager component to handle storage statistics, project cleanup, and configuration for CCW centralized storage.
- Introduced functions to calculate directory sizes, get project storage stats, and clean specific or all storage.
- Enhanced SQLiteStore with a public API for executing queries securely.
- Updated tests to utilize the new execute_query method and validate storage management functionalities.
- Improved performance by implementing connection pooling with idle timeout management in SQLiteStore.
- Added new fields (token_count, symbol_type) to the symbols table and adjusted related insertions.
- Enhanced error handling and logging for storage operations.
- 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.
- Implement full coverage tests for Embedder model loading and embedding generation
- Add CRUD operations and caching tests for VectorStore
- Include cosine similarity computation tests
- Validate semantic search accuracy and relevance through various queries
- Establish performance benchmarks for embedding and search operations
- Ensure edge cases and error handling are covered
- Test thread safety and concurrent access scenarios
- Verify availability of semantic search dependencies
- Implemented tests for the ChunkConfig and Chunker classes, covering default and custom configurations.
- Added tests for symbol-based chunking, including single and multiple symbols, handling of empty symbols, and preservation of line numbers.
- Developed tests for sliding window chunking, ensuring correct chunking behavior with various content sizes and configurations.
- Created integration tests for semantic search, validating embedding generation, vector storage, and search accuracy across a complex codebase.
- Included performance tests for embedding generation and search operations.
- Established tests for chunking strategies, comparing symbol-based and sliding window approaches.
- Enhanced test coverage for edge cases, including handling of unicode characters and out-of-bounds symbol ranges.
