- Fixed API endpoint mismatches in mcp-manager.js to ensure global install/update buttons function correctly.
- Corrected undefined function references in mcp-manager.js for project installation.
- Refactored event handling to eliminate global scope pollution in mcp-manager.js.
- Added comprehensive debugging guide for MCP installation issues.
- Implemented a session path resolver to infer content types from filenames and paths, improving usability.
- Introduced tests for embeddings improvements in init and status commands to verify functionality.
This commit addresses multiple issues in session management and command documentation:
Session Management Fixes:
- Add auto-inference of location from type parameter in session.ts
- When --type lite-plan/lite-fix is specified, automatically set location accordingly
- Preserve explicit --location parameter when provided
- Update session-manager.ts to support type-based location inference
- Fix metadata filename selection (session-metadata.json vs workflow-session.json)
Command Documentation Fixes:
- Add missing --mode analysis parameter (3 locations):
* commands/memory/docs.md
* commands/workflow/lite-execute.md (2 instances)
- Add missing --mode write parameter (4 locations):
* commands/workflow/tools/task-generate-agent.md
- Remove non-existent subcommands (3 locations):
* commands/workflow/session/complete.md (manifest, project)
- Update session command syntax to use simplified format:
* Changed from 'ccw session manifest read' to 'test -f' checks
* Changed from 'ccw session project read' to 'test -f' checks
Documentation Updates:
- Update lite-plan.md and lite-fix.md to use --type parameter
- Update session/start.md to document lite-plan and lite-fix types
- Sync all fixes to skills/command-guide/reference directory (84 files)
All ccw command usage across the codebase is now consistent and correct.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, embeddings were only generated for root directory files (1.6% coverage, 5/303 files).
This fix implements recursive processing across all subdirectory indexes, achieving 100% coverage
with 2,042 semantic chunks across all 303 files in 26 index databases.
Key improvements:
1. **Recursive embeddings generation** (embedding_manager.py):
- Add generate_embeddings_recursive() to process all _index.db files in directory tree
- Add get_embeddings_status() for comprehensive coverage statistics
- Add discover_all_index_dbs() helper for recursive file discovery
2. **Enhanced CLI commands** (commands.py):
- embeddings-generate: Add --recursive flag for full project coverage
- init: Use recursive generation by default for complete indexing
- status: Display embeddings coverage statistics with 50% threshold
3. **Smart search routing improvements** (smart-search.ts):
- Add 50% embeddings coverage threshold for hybrid mode routing
- Auto-fallback to exact mode when coverage insufficient
- Strip ANSI color codes from JSON output for correct parsing
- Add embeddings_coverage_percent to IndexStatus and SearchMetadata
- Provide clear warnings with actionable suggestions
4. **Documentation and analysis**:
- Add SMART_SEARCH_ANALYSIS.md with initial investigation
- Add SMART_SEARCH_CORRECTED_ANALYSIS.md revealing true extent of issue
- Add EMBEDDINGS_FIX_SUMMARY.md with complete fix summary
- Add check_embeddings.py script for coverage verification
Results:
- Coverage improved from 1.6% (5/303 files) to 100% (303/303 files) - 62.5x increase
- Semantic chunks increased from 10 to 2,042 - 204x increase
- All 26 subdirectory indexes now have embeddings vs just 1
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Introduced a detailed guide for intelligent tools selection strategy, including quick reference, tool specifications, prompt templates, and best practices for CLI execution.
- Established a coding philosophy document outlining core beliefs, simplicity principles, and guidelines for effective coding practices.
- Created context requirements documentation emphasizing the importance of understanding existing patterns and dependencies before implementation.
- Developed a file modification workflow detailing the use of edit_file and write_file MCP tools, along with priority logic for file reading and editing.
- Implemented CodexLens auto hybrid mode, enhancing the CLI with automatic vector embedding generation and default hybrid search mode based on embedding availability.
- Introduced `help-i18n.js` for managing translations in Chinese and English for the help view.
- Created `help.js` to render the help view, including command categories, workflow diagrams, and CodexLens quick-start.
- Implemented search functionality with debounce for command filtering.
- Added workflow diagram rendering with Cytoscape.js integration.
- Developed tests for write-file verification, ensuring proper handling of small and large JSON files.
- Implement `inspect_llm_summaries.py` to display LLM-generated summaries from the semantic_chunks table in the database.
- Create `show_llm_analysis.py` to demonstrate LLM analysis of misleading code examples, highlighting discrepancies between comments and actual functionality.
- Develop `test_misleading_comments.py` to compare pure vector search with LLM-enhanced search, focusing on the impact of misleading or missing comments on search results.
- Introduce `test_llm_enhanced_search.py` to provide a test suite for evaluating the effectiveness of LLM-enhanced vector search against pure vector search.
- Ensure all new scripts are integrated with the existing codebase and follow the established coding standards.
- 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.
- Implemented tests for the QueryParser class, covering various identifier splitting methods (CamelCase, snake_case, kebab-case), OR expansion, and FTS5 operator preservation.
- Added parameterized tests to validate expected token outputs for different query formats.
- Created edge case tests to ensure robustness against unusual input scenarios.
- Developed tests for the Reciprocal Rank Fusion (RRF) algorithm, including score computation, weight handling, and result ranking across multiple sources.
- Included tests for normalization of BM25 scores and tagging search results with source metadata.
- Added a cleanup function to reset the state when navigating away from the graph explorer.
- Updated navigation logic to call the cleanup function before switching views.
- Improved internationalization by adding new translations for graph-related terms.
- Adjusted icon sizes for better UI consistency in the graph explorer.
- Implemented impact analysis button functionality in the graph explorer.
- Refactored CLI tool configuration to use updated model names.
- Enhanced CLI executor to handle prompts correctly for codex commands.
- Introduced code relationship storage for better visualization in the index tree.
- Added support for parsing Markdown and plain text files in the symbol parser.
- Updated tests to reflect changes in language detection logic.
- Added main render function to initialize the graph explorer view.
- Implemented data loading functions for graph nodes, edges, and search process data.
- Created UI layout with tabs for graph view and search process view.
- Developed filtering options for nodes and edges with corresponding UI elements.
- Integrated Cytoscape.js for graph visualization, including node and edge styling.
- Added functionality for node selection and details display.
- Implemented impact analysis feature with modal display for results.
- Included utility functions for refreshing data and managing UI states.
- 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.
- Introduced a comprehensive design document for a Code Semantic Graph aimed at enhancing static analysis capabilities.
- Defined the architecture, core components, and implementation steps for analyzing function calls, data flow, and dependencies.
- Included detailed specifications for nodes and edges in the graph, along with database schema for storage.
- Outlined phases for implementation, technical challenges, success metrics, and application scenarios.
- Added main JavaScript functionality for CLAUDE.md management including file loading, rendering, and editing capabilities.
- Created a test HTML file to validate the functionality of the CLAUDE.md manager.
- Introduced CLI generation examples and documentation for rules creation via CLI.
- Enhanced error handling and notifications for file operations.
- Added active memory configuration for manual interval and Gemini tool.
- Created file modification rules for handling edits and writes.
- Implemented migration manager for managing database schema migrations.
- Added migration 001 to normalize keywords into separate tables.
- Developed tests for validating performance optimizations including keyword normalization, path lookup, and symbol search.
- Created validation script to manually verify optimization implementations.
- 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
readSettingsFile() in hooks-routes and mcp-routes was returning { hooks: {} }
as default value when file not found or parse failed, causing writeFileSync()
to overwrite other fields (mcpServers, projects, statusLine) in settings.json.
Changed default return to {} to preserve all existing fields when updating hooks.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Replace overly broad `except Exception` blocks with specific exception
handlers (StorageError, ConfigError, ParseError, SearchError, PermissionError)
across all CLI commands. This provides more precise error messages and
improves debugging experience for end users.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixes CLI tool detection failure after server restart.
The previous caching implementation cached negative results (errors,
timeouts) which caused persistent failures if the first check failed
for any transient reason (environment, timing, etc.).
Changes:
- Only cache positive tool availability results
- Don't cache errors or timeouts - they may be transient
- Subsequent checks will retry if a tool wasn't found
This ensures that once a tool is found, lookups are fast, but
transient failures don't persist in the cache.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Added `skills-manager.js` for managing Claude Code skills with functionalities for loading, displaying, and editing skills.
- Introduced a Notifier module in `notifier.ts` for CLI to server communication, enabling notifications for UI updates on data changes.
- Created comprehensive documentation for the Chain Search implementation, including usage examples and performance tips.
- Developed a test suite for the Chain Search engine, covering basic search, quick search, symbol search, and files-only search functionalities.
Add clearer documentation for each action:
- search/search_files: requires query parameter
- symbol: no query, extracts all symbols from file
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Migrate all Code Index MCP references to CCW's built-in CodexLens tool:
- Update context-search-agent with codex_lens API calls
- Update test-context-search-agent with new search patterns
- Update memory/load command file discovery reference
- Update context-gather and task-generate-tdd MCP capabilities
- Update INSTALL docs to reflect CodexLens as built-in feature
- Sync all mirrored files in skills/command-guide/reference/
Old API (mcp__code-index__*) → New API (mcp__ccw-tools__codex_lens)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Implemented insights history section in the dashboard with cards displaying analysis results.
- Added CSS styles for insights cards, detail panel, and empty state.
- Enhanced i18n support for insights-related strings in English and Chinese.
- Developed backend methods for saving, retrieving, and deleting insights in the CLI history store.
- Integrated insights loading and rendering logic in the memory view.
- Added functionality to refresh insights and handle detail view interactions.
- Added new CLI tool "Claude" with command handling in cli-executor.ts.
- Implemented session discovery for Claude in native-session-discovery.ts.
- Enhanced memory view with active memory controls, including sync functionality and configuration options.
- Introduced zoom and fit view controls for memory graph visualization.
- Updated i18n.js for new memory-related translations.
- Improved error handling and migration for CLI history store.
- Added `resume-strategy.ts` to determine optimal resume approaches including native, prompt concatenation, and hybrid modes.
- Introduced `determineResumeStrategy` function to evaluate various resume scenarios.
- Created utility functions for building context prefixes and formatting outputs in plain, YAML, and JSON formats.
- Added `session-content-parser.ts` to parse native CLI tool session files supporting Gemini/Qwen JSON and Codex JSONL formats.
- Implemented parsing logic for different session formats, including error handling for invalid lines.
- Provided functions to format conversations and extract user-assistant pairs from parsed sessions.
- Add CLI Settings section with Prompt Format selector
- Add Smart Context toggle and Max Files dropdown
- Update smart-search with output_mode (full/files_only/count)
- Add smart-context module for keyword extraction
- Improve Status page styling (remove card wrappers)
- Add i18n translations for new settings
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- edit_file: truncate diff to 15 lines, compact result format
- write_file: return only path/bytes/message
- read_file: new tool with multi-file, directory, regex support
- paths: single file, array, or directory
- pattern: glob filter (*.ts)
- contentPattern: regex content search
- maxDepth, maxFiles, includeContent options
- Update tool-strategy.md documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Introduced a new SQLite-based storage backend for managing CLI execution history.
- Added `CliHistoryStore` class to handle conversation records and turns with efficient queries.
- Migrated existing JSON history files to the new SQLite format.
- Updated CLI executor to use asynchronous and synchronous methods for saving and loading conversations.
- Enhanced execution history retrieval with support for filtering by tool, status, and search terms.
- Added prompt concatenation utilities to build multi-turn prompts in various formats (plain, YAML, JSON).
- Implemented batch deletion of conversations and improved error handling for database operations.
- Update cli-lite-planning-agent to serve both lite-plan and lite-fix
- Add schema-driven output (plan-json-schema or fix-plan-json-schema)
- Support both explorations (lite-plan) and diagnoses (lite-fix) context
- Remove CLI execution ID planning from lite-plan.md and lite-fix.md
- Delegate CLI execution ID assignment to agent when user selects CLI execution
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Introduced `--id <id>` option in CLI for custom execution IDs.
- Enhanced CLI command handling to support multi-turn conversations.
- Updated execution and conversation detail retrieval to accommodate new structure.
- Implemented merging of multiple conversations with tracking of source IDs.
- Improved history management to save and load conversation records.
- Added styles for displaying multi-turn conversation details in the dashboard.
- Refactored existing execution detail functions for backward compatibility.
- Implemented task queue sidebar for managing active tasks with filtering options.
- Added functionality to close notification sidebar when opening task queue.
- Enhanced CLI history view to support resuming previous sessions with optional prompts.
- Updated CLI executor to handle resuming sessions for Codex, Gemini, and Qwen tools.
- Introduced utility functions for finding CLI history directories recursively.
- Improved task queue data management and rendering logic.
Fix paths from dist/core/ to src/templates/ since templates are not
compiled and remain in src directory.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated session completion process to use `ccw session` commands for listing, reading, and updating session statuses.
- Enhanced session listing command to provide metadata and statistics using `ccw session list` and `ccw session stats`.
- Streamlined session resume functionality with `ccw session` commands for checking status and updating session state.
- Improved session creation process by replacing manual directory and metadata handling with `ccw session init`.
- Introduced `session_manager` tool for simplified session operations, including listing, updating, and archiving sessions.
- Updated conflict resolution tools to generate structured output in `conflict-resolution.json` instead of markdown files.
- Enhanced TDD and UI design tools to utilize `ccw cli exec` for executing analysis commands, improving integration with the workflow.
- Introduced `ccw-mcp` command for running CCW tools as an MCP server.
- Updated `package.json` to include new MCP dependencies and scripts.
- Enhanced CLI with new options for `codex_lens` tool.
- Implemented MCP server logic to expose CCW tools via Model Context Protocol.
- Added new tools and updated existing ones for better functionality and documentation.
- Created quick start and full documentation for MCP server usage.
- Added tests for MCP server functionality to ensure reliability.
- Add getMcpConfigHash() to generate unique config fingerprints
- Modify getAllAvailableMcpServers() to differentiate same-name servers
with different configurations using name@project-folder suffix
- Update renderAvailableServerCard() to show source project info and
use originalName for correct installation
- Fix event handlers to use btn.dataset for event bubbling safety
- Add CCW Tools MCP installation with npx for cross-platform compatibility
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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.
