- Added new benchmark result files: compare_2026-02-09_score_fast3.json and compare_2026-02-09_score_fast4.json.
- Implemented KeepAliveLspBridge to maintain a persistent LSP connection across multiple queries, improving performance.
- Created unit tests for staged clustering strategies in test_staged_stage3_fast_strategies.py, ensuring correct behavior of score and dir_rr strategies.
- Implemented `prep-loop.md` for ccw-loop, detailing source discovery, validation, task transformation, and auto-loop configuration.
- Created `prep-plan.md` for workflow planning, covering environment checks, task quality assessment, execution preferences, and final confirmation.
- Defined schemas and integration points for `prep-package.json` in both ccw-loop and workflow-plan skills, ensuring proper validation and task handling.
- Added error handling mechanisms for various scenarios during the preparation phases.
- Remove agent delegation (spawn_agent/wait/send_input/close_agent), all phases serial inline
- Replace parallel agent exploration with serial ccw cli calls (gemini/claude)
- Add search verification after each CLI exploration (ACE/Grep/Glob)
- Change output from plan.json/executionContext to tasks.jsonl (unified JSONL)
- Output format now compatible with collaborative-plan-with-file
- Replace custom execution engine with unified-execute-with-file delegation
- Copy full execution spec inline (no external references)
- Use $ prefix for codex skill invocations
Embed a real-time shared context mechanism (coordination/discoveries.ndjson)
into all 4 agent roles, eliminating redundant codebase exploration. Each agent
reads the board on start, skips covered areas, and appends new findings as
NDJSON entries for other agents to consume.
Key additions per file:
- SKILL.md: Design principle #8, discovery type table with dedup keys and
required data fields, board lifecycle rules
- 02-agent-execution.md: Self-sufficient discovery protocol snippet in each
spawn prompt with write method, required fields, and dedup keys
- 4 role files: Full Shared Discovery Protocol section with board location,
lifecycle, physical write method (Bash echo >>), reads/writes tables with
dedup keys and required data schemas, and embedded Read/Write steps in
execution process
- Added argument parsing and prep package loading in session initialization.
- Implemented validation checks for prep-package.json integrity.
- Integrated prep package data into cycle state, including task refinement and auto-iteration settings.
- Updated agent execution to utilize source references and focus directives from prep package.
- Modified context gathering and test context generation to reference active workflow paths.
- Introduced a new interactive prompt for pre-flight checklist and task quality assessment.
- Created a detailed schema and integration specification for prep-package.json.
- Ensured all relevant phases validate and utilize the prep package effectively.
- Implemented a new skill to convert various planning outputs (roadmap.jsonl, plan-note.md, conclusions.json, synthesis.json) into a standardized JSONL task format.
- Included detailed documentation on supported input formats, unified JSONL schema, execution process, and error handling.
- Added functions for parsing, transforming, and validating input data to ensure quality and consistency in the output.
- Created a new JSON file with benchmark results from the run on 2026-02-09.
- Added tests for the StandaloneLspManager to verify path normalization on Windows, including handling of percent-encoded URIs and ensuring plain Windows paths remain unchanged.
- Added Edit Issue dialog to allow users to modify existing issues with fields for title, context, priority, and status.
- Integrated form validation and state management for the edit dialog.
- Updated the IssueManagerPage to handle opening and closing of the edit dialog, as well as submitting updates.
- Improved UI components in SolutionDrawer and ExplorationSection for better user experience.
- Refactored file path input with a browse dialog for selecting files and directories in SettingsPage.
- Adjusted layout and styling in LeftSidebar and OrchestratorPage for better responsiveness and usability.
- Updated localization files to include new strings for the edit dialog and task management.
- Introduced `prettify.css` for syntax highlighting in coverage reports.
- Added `prettify.js` to handle code formatting and highlighting.
- Included `sort-arrow-sprite.png` for sort indicators in the coverage table.
- Implemented `sorter.js` to enable sorting and filtering of coverage summary tables.
- Added a search box for filtering table rows based on user input.
- Added functionality to save MCP server configurations as templates in the MCP Manager.
- Implemented new hooks for managing system settings including Chinese response, Windows platform, and Codex CLI enhancements.
- Updated API calls to support fetching and toggling system settings.
- Introduced UI components for displaying and managing response language settings and system status.
- Enhanced error handling and notifications for server deletion and template saving actions.
- Updated localization files for new settings and descriptions in English and Chinese.
- Added Phase 6: Fix Discovery & Batching with intelligent grouping and batching of findings.
- Added Phase 7: Fix Parallel Planning to launch planning agents for concurrent analysis and aggregation of partial plans.
- Added Phase 8: Fix Execution for stage-based execution of fixes with conservative test verification.
- Added Phase 9: Fix Completion to aggregate results, generate summary reports, and handle session completion.
- Introduced new frontend components: ResizeHandle for draggable resizing of sidebar panels and useResizablePanel hook for managing panel sizes with localStorage persistence.
- Added PowerShell script for checking TypeScript errors in source code, excluding test files.
- Added Phase 2: Test-Cycle Execution documentation outlining the process for dynamic test-fix execution, including agent roles, core responsibilities, intelligent strategy engine, and progressive testing.
- Introduced new PowerShell scripts for analyzing TypeScript errors, focusing on error categorization and reporting.
- Created end-to-end tests for the Help Page, ensuring content visibility, documentation navigation, internationalization support, and accessibility compliance.
- Implemented Phase 2: Orchestration Loop for CCW Loop, including executor agent spawning, main loop execution, and iteration management.
- Introduced helper functions for action result parsing and user interaction.
- Created new skill: workflow-execute, coordinating agent execution for workflow tasks with automatic session discovery, parallel task processing, and status tracking.
- Defined execution flow, key design principles, and error handling strategies for the workflow execution process.
- Implemented E2E tests for code relationship visualization in Graph Explorer.
- Added tests for archived session management in History, including search, filter, restore, and delete functionalities.
- Created tests for workflow orchestration in Orchestrator, covering node creation, connection, deletion, and workflow management.
- Developed tests for project statistics and timeline visualization in Project, including error handling and internationalization checks.
- Added LICENSE.txt file for JavaScript assets in the build directory, including licenses for NProgress and React libraries.
- Introduced a new runtime JavaScript file for handling module loading.
- Created a new DocItem component to manage document rendering and metadata handling in the Docusaurus theme.
- Implemented tests for the docs proxy server to ensure proper routing to the configured docsPort.
- Introduced comprehensive guidelines for generating implementation plan documents (IMPL_PLAN.md, task JSONs, TODO_LIST.md) using the action-planning-agent.
- Defined auto mode for user configuration with default settings.
- Outlined core philosophy emphasizing planning only, agent-driven document generation, and memory-first context loading.
- Detailed execution process divided into phases: User Configuration, Context Preparation, Single Agent Planning, N Parallel Planning, and Integration.
- Included lifecycle management for user configuration and agent interactions.
- Specified document generation lifecycle with clear expectations for outputs and quality standards.
- Implement `test-cli-command-gen.js` to verify the logic of `buildCliCommand` function.
- Create `test-e2e-model-alias.js` for end-to-end testing of model alias resolution in `ccw cli`.
- Add `test-model-alias.js` to test model alias resolution for different models.
- Introduce `test-model-alias.txt` for prompt testing with model alias.
- Develop `test-update-claude-command.js` to test command generation for `update_module_claude`.
- Create a test file in `test-update-claude/src` for future tests.
- Implemented unified-execute-parallel for executing tasks in isolated Git worktrees with parallel execution capabilities.
- Developed unified-execute-with-file for universal task execution from various planning outputs with progress tracking.
- Created worktree-merge to handle merging of completed worktrees back to the main branch, including dependency management and conflict detection.
- Enhanced documentation for each workflow, detailing core functionalities, implementation phases, and configuration options.
- Deleted obsolete INDEX.md and OPTIMIZATION_SUMMARY.md files, consolidating documentation for improved clarity and organization.
- Removed skipGitRepoCheck option from CLI execution parameters to streamline command usage.
- Updated CLI executor utilities to automatically skip git repository checks, allowing execution in non-git directories.
- Enhanced documentation with new ARCHITECTURE.md and INDEX.md files for better navigation and understanding of the system architecture.
- Created CONTENT_MIGRATION_REPORT.md to verify zero content loss during the consolidation process.
- Create specs/reference-docs-spec.md with comprehensive guidelines for phase-based reference document organization
- Update skill-generator's Mandatory Prerequisites to include new reference-docs-spec
- Refactor skill-md.md template to generate phase-based reference tables with 'When to Use' guidance
- Add generateReferenceTable() function to automatically create structured reference sections
- Replace flat template reference lists with phase-based navigation
- Update skill-generator's own SKILL.md to demonstrate correct reference documentation pattern
- Ensure all generated skills will have clear document usage timing and context
- Created execution agent prompt for issue execution with detailed deliverables and validation criteria.
- Developed planning agent prompt to analyze issues and generate structured solution plans.
- Introduced issue handling specifications outlining the workflow and issue structure.
- Established quality standards for evaluating completeness, consistency, correctness, and clarity of solutions.
- Defined solution schema specification detailing the required structure and validation rules for solutions.
- Documented subagent roles and responsibilities, emphasizing the dual-agent strategy for improved workflow efficiency.
According to OpenAI Codex skill specification, SKILL.md files must have both
'name' and 'description' fields in YAML frontmatter. Added missing 'name' field
to all three skills:
- CCW Loop
- CCW Loop-B
- Parallel Dev Cycle
Also enhanced ccw-loop description with Chinese trigger keywords for better
multi-language support.
- Introduced a new specification for agent communication optimization focusing on file references instead of content transfer to enhance efficiency and reduce message size.
- Established a coordination protocol detailing communication channels, message formats, and dependency resolution strategies among agents (RA, EP, CD, VAS).
- Created a unified progress format specification for all agents, standardizing documentation structure and versioning practices.
Changed loadClaudeCliTools() to only load tools explicitly defined
in user config. Previously, DEFAULT_TOOLS_CONFIG.tools was spread
before user tools, causing all default tools to be loaded even if
not present in user config.
User config now has complete control over which tools are loaded.
- Implemented issue discovery prompt to analyze code from various perspectives (bug, UX, test, quality, security, performance, maintainability, best-practices).
- Created structured issue generation prompt from GitHub URLs or text descriptions, including clarity detection and optional clarification questions.
- Introduced CCW Loop-B hybrid orchestrator pattern for iterative development, featuring a coordinator and specialized workers with batch wait support.
- Defined state management, session structure, and output schemas for the CCW Loop-B workflow.
- Added error handling and best practices documentation for the new features.
- Implemented the VALIDATE action to run tests, check coverage, and generate reports.
- Created orchestrator for managing CCW Loop execution using Codex subagent pattern.
- Defined state schema for unified loop state management.
- Updated action catalog with new actions and their specifications.
- Enhanced CLI and issue routes to support new features and data structures.
- Improved documentation for Codex subagent design principles and action flow.
