- Introduced a new navigation item for "Multi-CLI Plan" in the dashboard template.
- Created a new JSON schema for "Multi-CLI Discussion Artifact" to facilitate structured discussions and decision-making processes.
- Introduced a new command `/workflow:multi-cli-plan` for collaborative planning using ACE semantic search and iterative analysis with Claude and Codex.
- Implemented a structured execution flow with phases for context gathering, multi-tool analysis, user decision points, and final plan generation.
- Added detailed documentation outlining the command's usage, execution phases, and key features.
- Included error handling and configuration options for enhanced user experience.
- Introduced `/issue:discover-by-prompt` command for user-driven issue discovery.
- Implemented multi-agent exploration with iterative feedback loops.
- Added ACE semantic search for context gathering and cross-module comparison capabilities.
- Enhanced user experience with natural language input and adaptive exploration strategies.
feat: implement memory update queue tool for batching updates
- Created `memory-update-queue.js` for managing CLAUDE.md updates.
- Added functionality for queuing paths, deduplication, and auto-flushing based on thresholds and timeouts.
- Implemented methods for queue status retrieval, flushing, and timeout checks.
- Configured to store queue data persistently in `~/.claude/.memory-queue.json`.
- Implemented Phase 4: Output & Preview for text formatter, including saving formatted content, generating statistics, and providing HTML preview.
- Created callout types documentation with detection patterns and conversion rules for BBCode and HTML.
- Added element mapping specifications detailing detection patterns and conversion matrices for various Markdown elements.
- Established format conversion rules for BBCode and Markdown, emphasizing pixel-based sizing and supported tags.
- Developed BBCode template with structured document and callout templates for consistent formatting.
- Introduced architecture rules to detect circular dependencies, god classes, layer violations, and mixed concerns.
- Added correctness rules focusing on null checks, empty catch blocks, unreachable code, and type coercion.
- Implemented performance rules addressing nested loops, synchronous I/O, memory leaks, and unnecessary re-renders in React.
- Created readability rules to improve function length, variable naming, deep nesting, magic numbers, and commented code.
- Established security rules to identify XSS risks, hardcoded secrets, SQL injection vulnerabilities, and insecure random generation.
- Developed testing rules to enhance test quality, coverage, and maintainability, including missing assertions and error path testing.
- Documented the structure and schema for rule files in the index.md for better understanding and usage.
- Implemented orchestrator logic to manage code review phases, including state reading, action selection, and execution loop.
- Defined state schema for review process, including metadata, context, findings, and execution tracking.
- Created action catalog detailing actions for context collection, quick scan, deep review, report generation, and completion.
- Established error recovery strategies and termination conditions for robust review handling.
- Developed issue classification and quality standards documentation to guide review severity and categorization.
- Introduced review dimensions with detailed checklists for correctness, security, performance, readability, testing, and architecture.
- Added templates for issue reporting and review reports to standardize output and improve clarity.
- Deleted security requirements specification file to streamline documentation.
- Removed best practice finding template to enhance clarity and focus on critical issues.
- Eliminated report template and security finding template to reduce redundancy and improve maintainability.
- Updated skill generator templates to enforce mandatory prerequisites for better compliance with design standards.
- Bumped package version from 6.3.18 to 6.3.23 for dependency updates.
- Updated `claude-cli-tools.ts` to support new model configurations and migration from older versions.
- Added `getPredefinedModels` and `getAllPredefinedModels` functions for better model management.
- Deprecated `cli-config-manager.ts` in favor of `claude-cli-tools.ts`, maintaining backward compatibility.
- Introduced `skill-context-loader.ts` to handle skill context loading based on user prompts and keywords.
- Enhanced tool configuration functions to include secondary models and improved migration logic.
- Updated index file to register the new skill context loader tool.
- Added auto-initialization of CSRF token for state-changing requests in cli-manager.js.
- Refactored Claude CLI Tools configuration to separate tools and settings into cli-tools.json and cli-settings.json respectively.
- Introduced new interfaces for Claude CLI Tools and Settings, including support for tags and primary models.
- Implemented loading and saving functions for CLI settings, ensuring backward compatibility with legacy combined config.
- Updated functions to synchronize tags between CLI tools and configuration manager.
- Added error handling and logging for loading and saving configurations.
- Created initial cli-settings.json with default settings.
- Added a function to parse JSON streaming content in core-memory.js, extracting readable text from messages.
- Updated memory detail view to utilize the new parsing function for content and summary.
- Introduced an enableReview option in rules-manager.js, allowing users to toggle review functionality in rule creation.
- Simplified skill creation modal in skills-manager.js by removing generation type selection UI.
- Improved CLI executor to handle tool calls for file writing, ensuring proper output parsing.
- Adjusted CLI command tests to set timeout to 0 for immediate execution.
- Updated file watcher to implement a true debounce mechanism and added a pending queue status for UI updates.
- Enhanced watcher manager to handle queue changes and provide JSON output for better integration with TypeScript backend.
- Established TypeScript naming conventions documentation to standardize code style across the project.
- Introduced best practices requirements specification covering code quality, performance, maintainability, error handling, and documentation standards.
- Established quality standards with overall quality metrics and mandatory checks for security, code quality, performance, and maintainability.
- Created security requirements specification aligned with OWASP Top 10 and CWE Top 25, detailing checks and patterns for common vulnerabilities.
- Developed templates for documenting best practice findings, security findings, and generating reports, including structured markdown and JSON formats.
- Updated dependencies in the project, ensuring compatibility and stability.
- Added test files and README documentation for vector indexing tests.
- Updated Windows platform guidelines for path formats and Bash rules.
- Refactored CodexLens routes to improve GPU detection and indexing cancellation logic.
- Added FastEmbed installation status handling in the dashboard, including UI updates for installation and reinstallation options.
- Implemented local model management with improved API responses for downloaded models.
- Enhanced GPU selection logic in the model mode configuration.
- Improved error handling and user feedback for FastEmbed installation processes.
- Adjusted Python environment checks to avoid shell escaping issues on Windows.
Add --queues parameter to enable parallel queue formation with multiple
issue-queue-agents. Solutions are partitioned by file overlap to minimize
cross-queue conflicts. Queue groups are linked via queue_group field.
- Introduced a comprehensive code analysis action template for integrating code exploration and analysis capabilities.
- Added LLM action template for seamless integration of LLM calls with customizable prompts and tools.
- Implemented a benchmark search script to compare multiple search methods across various dimensions including speed, result quality, ranking stability, and coverage.
- Provided preset configurations for common analysis tasks and LLM actions, enhancing usability and flexibility.
- Add Command-to-Tool Mapping for pre_analysis commands
- Add Execution Mode Selection for implementation_approach steps
- command field exists → Execute CLI via Bash
- no command → Agent direct execution with test_commands
- Fix bash command syntax in execute.md for Windows compatibility
- Convert multi-line for loop to single-line format
- Use single quotes for grep patterns to avoid escaping issues
- Simplify agent prompt template in execute.md
- Path-based invocation instead of embedding task content
- Add [FLOW_CONTROL] and "Implement" markers to trigger agent behavior
- Enhance code-developer.md Task JSON parsing
- Add explicit Task JSON field mapping (requirements, acceptance, etc.)
- Add STEP 1/2/3 execution flow for clarity
- Add Pre-Analysis Execution format with command-to-tool mapping
- Define default behavior when command field is missing
- Priority: Use tech_stack from JSON before auto-detection
- Add execution_config alignment rules to action-planning-agent.md
- Ensure meta.execution_config matches implementation_approach
- "agent" mode: no command fields, cli_tool: null
- "hybrid" mode: some command fields
- "cli" mode: all steps have command fields
- Introduced a comprehensive template for autonomous actions, detailing structure, execution, and error handling.
- Added an orchestrator template to manage state and decision logic for autonomous actions.
- Created a sequential phase template to outline execution steps and objectives for structured workflows.
- Developed a skill documentation template to standardize the generation of skill entry files.
- Implemented a Python script to compare search results between hybrid and cascade methods, analyzing ranking changes.
- Use absolute paths via git rev-parse --show-toplevel
- Add cleanup traps for graceful failure handling (EXIT/INT/TERM)
- Add git worktree prune at startup for stale worktrees
- Validate main repo state before merge (fallback to PR if dirty)
- Change default to "Create PR" for parallel execution safety
- Move worktree directory to .ccw/worktrees/ (gitignored)
- Add --archived flag to explicitly review archived sessions
- Auto-detect session location (active first, then archives)
- Update all path references to use resolved sessionPath
- Add usage examples for archived session review
- Replace auto-complete with AskUserQuestion in execute.md Phase 5
- User can choose "Enter Review" or "Complete Session"
- Fix archived tasks showing incomplete on dashboard
- executeArchive now updates all .task/*.json status to completed
- 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.
- Consolidate Agent and CLI prompt builders into single buildExecutionPrompt()
- Replace file-based task format with scope + modification_points structure
- Simplify to 4-part task template: Modification Points → How → Reference → Done
- Remove duplicate formatTaskForCLI and buildCLIPrompt functions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new /memory:swagger-docs command to generate complete Swagger/OpenAPI
documentation following RESTful standards with:
- Global security configuration (Bearer Token auth)
- Complete endpoint documentation with parameters and responses
- Unified error code specification (AUTH/PARAM/BIZ/SYS)
- Multi-language support (--lang zh|en, default: zh)
- Validation test reports
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
