- Introduced a new JSON file `skill-tuning-diagnosis.json` containing a comprehensive diagnosis of the skill-generator.
- Documented critical issues related to context management and data flow, including:
- Full state serialization leading to unbounded context growth.
- Scattered state writing without a unified schema.
- Lack of input state schema validation in autonomous orchestrators.
- Provided detailed descriptions, impacts, root causes, and fix strategies for each identified issue.
- Summarized recommendations with priority levels for urgent fixes.
- Updated AGENTS.md to include CLI tools usage and configuration details.
- Introduced a new script template for both Bash and Python, outlining usage context, calling conventions, and implementation guidelines.
- Provided examples for common patterns in both Bash and Python scripts.
- Established a directory convention for script organization and naming.
- Updated orchestrator decision logic to improve state management and action selection.
- Introduced structured termination checks and action selection criteria.
- Enhanced state update mechanism with sliding window for action history and error tracking.
- Revised problem taxonomy for skill execution issues, consolidating categories and refining detection patterns.
- Improved severity calculation method for issue prioritization.
- Streamlined fix mapping strategies for better clarity and usability.
- Updated Phase 1 and Phase 2 documentation to include next phase links and data flow details.
- Expanded Phase 5 documentation to include comprehensive validation and README generation steps, along with validation report structure.
- Added purpose and usage context sections to various action and script templates (e.g., autonomous-action, llm-action, script-bash).
- Improved commands management by simplifying the command scanning logic and enabling/disabling commands through renaming files.
- Enhanced dashboard command manager to format group names and display nested groups with appropriate icons and colors.
- Updated LiteLLM executor to allow model overrides during execution.
- Added action reference guide and template reference sections to the skill-tuning SKILL.md for better navigation and understanding.
- Add multi-perspective brainstorming workflow
- Support creative, pragmatic, and systematic analysis
- Include diverge-converge cycles with user interaction
- Add deep dive, devil's advocate, and idea merging
- Document thought evolution in brainstorm.md
- Introduced Phase 2.5: Consolidation Agent to summarize analysis outputs and generate design overviews.
- Added Phase 4: Document Assembly to create index-style documents linking chapter files.
- Implemented Phase 5: Compliance Review & Iterative Refinement for CPCC compliance checks and updates.
- Established CPCC Compliance Requirements document outlining mandatory sections and validation functions.
- Created a base template for analysis agents to ensure consistency and efficiency in execution.
- Implemented commands routes for listing, enabling, and disabling commands.
- Created commands manager view with accordion groups for better organization.
- Added loading states and confirmation dialogs for enabling/disabling commands.
- Enhanced error handling and user feedback for command operations.
- Introduced CSS styles for commands manager UI components.
- Updated navigation to include commands manager link.
- Refactored existing code for better maintainability and clarity.
- Add rollback in moveDirectory when rmSync fails after cpSync
- Add transaction rollback in disable/enableSkill when config save fails
- Surface config corruption by throwing on JSON parse errors
- Add robust JSON error parsing with fallback in frontend
- Add loading state and double-click prevention for toggle button
- Added new API endpoints to enable and disable skills.
- Introduced logic to manage disabled skills, including loading and saving configurations.
- Enhanced skills routes to return lists of disabled skills.
- Updated frontend to display disabled skills and allow toggling their status.
- Added internationalization support for new skill status messages.
- Created JSON schemas for plan verification agent and findings.
- Defined new types for skill management in TypeScript.
- Updated `plan.md` to include new fields in context-package.json: prioritized_context, user_intent, priority_tiers, dependency_order, and sorting_rationale.
- Added validation for the existence of the prioritized_context field in context-package.json.
- Modified user decision flow in task generation to present action choices after planning completion.
- Improved context-gathering process in `context-gather.md` to integrate user intent and prioritize context based on user goals.
- Revised conflict-resolution documentation to require planning notes records after conflict analysis.
- Streamlined task generation in `task-generate-agent.md` to utilize pre-sorted context without redundant sorting.
- Removed unused settings persistence functions and corresponding tests from `claude-cli-tools.ts` and `settings-persistence.test.ts`.
- Added Phase 5: Plan Quality Check to cli-lite-planning-agent.md, detailing mandatory quality validation after plan generation.
- Introduced quality dimensions: completeness, granularity, dependencies, acceptance criteria, implementation steps, and constraint compliance.
- Specified CLI command format for quality check execution and expected output structure.
- Implemented result parsing and auto-fix strategies for minor issues.
- Updated integration flow to ensure quality check is executed before returning the plan to the orchestrator.
Refactor lite-plan.md to reflect internal quality check execution for medium/high complexity plans.
Create new brainstorm-with-file.md for interactive brainstorming workflow, detailing session setup, execution process, and implementation steps.
- Removed deprecated constants and functions from cli-config-manager.ts.
- Introduced new provider model presets in litellm-provider-models.ts for better organization and management of model information.
- Created provider-routes.ts to handle API endpoints for retrieving provider information and models.
- Added integration tests for provider routes to ensure correct functionality and response structure.
- Implemented unit tests for settings persistence functions, covering various scenarios and edge cases.
- Enhanced error handling and validation in the new routes and settings functions.
- Introduced `analyze-with-file` command for collaborative analysis.
- Implemented session management for new and continued analysis sessions.
- Developed structured phases for topic understanding, exploration, discussion, and conclusion synthesis.
- Created detailed documentation for the workflow, including examples and implementation details.
- Added Codex prompt for deep analysis and exploration of codebase and concepts.
- Remove 'merged' from VALID_QUEUE_STATUSES constant
- Update mergeQueues() to set status to 'archived' instead of 'merged'
- Preserve merged_into/merged_at metadata for traceability
- Update frontend to use 'archived' for button visibility checks
- Fix queue --json returning fake queue ID when no active queue exists
- Added Level 5 (CCW Coordinator) chapter with complete Minimum Execution Units definition
- Added 3-Phase Workflow explanation (Analyze Requirements, Discover Commands, Execute)
- Integrated command port system for dynamic pipeline composition
- Added JavaScript task analysis and complexity assessment functions
- Included state file structure and complete Mermaid flowchart (119 lines)
- Updated Quick Selection Table to reference ccw-coordinator for complex workflows
- Updated Decision Flowchart to include Level 5 at top level
- Updated Summary Level Overview table to include Level 5 row
- Updated Core Principles with Level 5 selection criteria and usage guidelines
- Synchronized English version with WORKFLOW_GUIDE_CN.md Level 5 content
- Moved 6 empty test files (*.test.ts) to archive/
- Moved 5 Python test scripts (*.py) to archive/
- Moved 5 outdated/temporary documents to archive/
- Cleaned up root directory for better organization
- Add prominent section highlighting /ccw and /ccw-coordinator as main features
- /ccw: Auto workflow orchestrator for general tasks
- /ccw-coordinator: Smart orchestrator with intelligent recommendations
- Include comparison table, quick examples, and key differences
- Update both English and Chinese READMEs
- Update ccw-coordinator.md with clarified CLI execution format
- Command-first prompt structure: /workflow:<command> -y <parameters>
- Simplified documentation with universal prompt template
- Clarify that -y is a prompt parameter, not a ccw cli parameter
- Add missing README.md file required by setuptools
- Fix deprecated license format in pyproject.toml (use SPDX string instead of TOML table)
- Add MIT LICENSE file for proper packaging
- Verified successful local installation and import
Fixes permission denied error during npm-based installation on macOS
## Features
- New `ccw` command: Main process workflow orchestrator with auto intent-based workflow selection
- New CommandRegistry for dynamic command discovery and metadata management
## Improvements
- Optimize ccw-coordinator: Serial blocking execution model with hook-based continuation
- Refactor execution flow: Stop after CLI launch, wait for hook callbacks (no polling)
- Add task_id tracking and state.json checkpoints for resumable execution
- Consolidate documentation: Reduce report verbosity while maintaining all core information
## Documentation
- Add Execution Model comparison (main process vs external CLI)
- Add State Management section with TodoWrite tracking examples
- Update Type Comparison table highlighting ccw vs ccw-coordinator differences
- Simplify code examples with inline comments
## Changes Summary
- ccw-coordinator.md: +272/-26 (serial blocking), -143 docs (consolidation)
- ccw.md: +121/-352 (state management, execution model)
- Rename: CCW-COORDINATOR.md → ccw-coordinator.md (lowercase)
- Rename file to lowercase: CCW-COORDINATOR.md → ccw-coordinator.md
- Replace polling waitForTaskCompletion with stop-action blocking model
- CLI commands execute in background with immediate stop (no polling)
- Hook callbacks (handleCliCompletion) trigger continuation to next command
- Add task_id and completed_at fields to execution_results
- Maintain state checkpoint after each command launch
- Add status flow documentation (running → waiting → completed)
- Include CLI invocation example with hook configuration
- Separate concerns: orchestrator launches, hooks handle callbacks
- Support serial execution: one command at a time with break after launch
- Implemented the ccw command as a main workflow orchestrator.
- Added a 5-phase workflow including intent analysis, requirement clarification, workflow selection, user confirmation, and command execution.
- Developed functions for analyzing user input, selecting workflows, and executing command chains.
- Integrated TODO tracking for command execution progress.
- Created comprehensive tests for the CommandRegistry, covering YAML parsing, command retrieval, and error handling.
- Refactored the command execution process to support dynamic command chaining and intelligent prompt generation.
- Updated the architecture overview to reflect changes in the orchestrator and command execution logic.
- Improved the prompt generation strategy to directly include complete command calls, enhancing clarity and usability.
- Added detailed examples and templates for command prompts in the documentation.
- Enhanced error handling and user decision-making during command execution failures.
- Introduced logging for command execution details and state updates for better traceability.
- Updated specifications and README files to align with the new command execution and prompt generation logic.
