Implement two major enhancements to test generation workflow:
1. Gemini Test Enhancement (Phase 1.5)
- Add Gemini CLI analysis for comprehensive test suggestions
- Generate enriched test specifications for L1-L3 test layers
- Focus on API contracts, integration patterns, error scenarios
- Create gemini-enriched-suggestions.md as artifact
2. Planning Notes Mechanism (test-planning-notes.md)
- Similar to plan.md's planning-notes pattern
- Record Test Intent (Phase 1)
- Embed complete Gemini enrichment (Phase 1.5)
- Track consolidated test requirements
- Support N+1 context with decisions and deferred items
Implementation Details:
- Created Gemini prompt template: test-suggestions-enhancement.txt
- Enhanced test-task-generate.md with Phase 1, 1.5, 2 logic
- Gemini content embedded in planning-notes for single source of truth
- test-action-planning-agent reads both TEST_ANALYSIS_RESULTS.md and test-planning-notes.md
- Backward compatible: Phase 1.5 is optional enhancement
Benefits:
- Comprehensive test coverage (API, integration, error scenarios)
- Full traceability of test planning process
- Consolidated context in one file for easy review
- Preserved Gemini output as independent artifact
- Implemented navigation.spec.ts to test language switching and translation of navigation elements.
- Created sessions-page.spec.ts to verify translations on the sessions page, including headers, status badges, and date formatting.
- Developed settings-page.spec.ts to ensure settings page content is translated and persists across sessions.
- Added skills-page.spec.ts to validate translations for skill categories, action buttons, and empty states.
- Add dimensions I (Constraints Compliance) and J (N+1 Context Validation)
- Verify tasks respect Consolidated Constraints from planning-notes.md
- Detect deferred items incorrectly included in current plan
- Check decision contradictions against N+1 Decisions table
- Introduced a comprehensive guide for generating workflow templates.
- Detailed usage instructions with examples for creating templates.
- Outlined execution flow across three phases: Template Design, Step Definition, and JSON Generation.
- Included JavaScript code snippets for each phase to facilitate implementation.
- Provided suggested step templates for various development scenarios.
- Documented command port references and minimum execution units for clarity.
Interactive command to create flow-coordinator templates with comprehensive
command selection (9 categories), minimum execution units, and command port
reference integrated from ccw/ccw-coordinator/codex-coordinator.
**Major changes:**
- Rename skill from meta-skill to flow-coordinator (avoid /ccw conflicts)
- Update all 17 templates: store full /workflow: command paths in cmd field
- Session ID prefix: ms → fc (fc-YYYYMMDD-HHMMSS)
- Workflow path: .workflow/.meta-skill → .workflow/.flow-coordinator
- Simplify SKILL.md schema documentation
- Streamline Status Schema section
- Consolidate Template Schema with single example
- Remove redundant Field Explanations and behavior tables
- All templates now store cmd as full paths (e.g. /workflow:lite-plan)
- Eliminates need for path assembly during execution
- Matches ccw-coordinator execution format
- Enhance CLI status rendering to display settings file information for builtin Claude.
- Introduce settings file input in CLI manager for configuring the path to settings.json.
- Update Claude CLI tool interface to include settingsFile property.
- Implement settings file resolution and validation in CLI executor.
- Create a new collaborative planning workflow command with detailed documentation.
- Add test scripts for debugging tool configuration and command building.
- Introduced merge-plans-with-file prompt for aggregating multiple planning artifacts, resolving conflicts, and synthesizing a unified execution plan.
- Implemented detailed execution process including discovery, normalization, conflict detection, resolution, and synthesis phases.
- Added quick-plan-with-file prompt for rapid planning with minimal documentation, utilizing multi-agent analysis for actionable outputs.
- Both prompts support various input formats and provide structured outputs for execution and documentation.
- 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.
- Introduced `command-relationships.json` to define internal calls, next steps, and prerequisites for various workflows.
- Created `essential-commands.json` to document key commands, their descriptions, arguments, and usage scenarios.
- Added `validate-help.py` script to check for the existence of source files referenced in command definitions, ensuring all necessary files are present.
- Pass generated executionId to cliExecutorTool.execute as id parameter
- Ensures CLI_EXECUTION_STARTED broadcast uses same ID as saved session
- Fixes "Conversation not found" errors when querying by broadcast ID
- Add DEBUG logging for executionId tracking
This resolves the mismatch where:
- Broadcast event used ID from Date.now() at broadcast time
- Session saved used different ID from Date.now() at completion time
- Now all use the same ID generated at cli.ts:868
Changes:
- cli.ts:868 - executionId generated once
- cli.ts:1001 - pass executionId to execute() as id parameter
- cli-executor-core.ts automatically uses passed id as conversationId
Problem: Codex CLI uses --json flag to output JSONL events, but executor was using plain text parser. This prevented proper parsing of structured events, breaking session creation.
Root cause: buildCommand() added --json flag for Codex but never communicated this to the output parser. Result: JSONL events treated as raw text → session markers lost.
Solution:
- Extend buildCommand() to return outputFormat
- Auto-detect 'json-lines' when tool is 'codex'
- Use auto-detected format in executeCliTool()
- Properly parse structured events and extract session data
Files modified:
- ccw/src/tools/cli-executor-utils.ts: Add output format auto-detection
- ccw/src/tools/cli-executor-core.ts: Use auto-detected format for parser
- ccw/src/commands/cli.ts: Add debug instrumentation
Verified:
- Codex outputs valid JSONL (confirmed via direct test)
- CLI_EXECUTION_STARTED events broadcast correctly
- Issue was downstream in output parsing, not event transmission
- Fixed source paths in command.json: change ../../../ to ../../
(sources are relative to .claude/skills/ccw-help/, need 2 levels to reach .claude/)
- Rewrote help-routes.ts /api/help/command-content endpoint:
- Use resolve() to properly handle ../ sequences in paths
- Resolve paths against commandJsonDir (where command.json is located)
- Maintain security checks to prevent path traversal
- Verified all document paths now resolve correctly to .claude/commands/*
This fixes the 404 errors when loading command documentation in Help page.
- Regenerated by analyze_commands.py
- Now includes all workflow, issue, memory, cli, and general commands
- Updated to version 3.0.0 with 73 commands and 19 agents
- Full index sync with file system definitions
- Add auto-update.py script for simple index regeneration
- Update SKILL.md with clear update instructions
- Simplify update mechanism: prompt user on skill execution
- Support both automatic and manual update workflows
- Clean version 2.3.0 metadata in command.json
- Convert all markdown files from Chinese to English
- Remove all emoji/icon decorations (🔧📋⚙️✅🏁🔍📚⛔⭐)
- Update all section headers, descriptions, and documentation
- Keep all content logic, structure, code examples unchanged
- Maintain template variables and file paths as-is
Files converted (9 files total):
- SKILL.md: Output structure comments
- templates/skill-md.md: All Chinese descriptions and comments
- specs/reference-docs-spec.md: All section headers and explanations
- phases/01-requirements-discovery.md through 05-validation.md (5 files)
- specs/execution-modes.md, skill-requirements.md, cli-integration.md, scripting-integration.md (4 files)
- templates/sequential-phase.md, autonomous-orchestrator.md, autonomous-action.md, code-analysis-action.md, llm-action.md, script-template.md (6 files)
All 16 files in skill-generator are now fully in English.
- 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
- Create codex version of unified-execute-with-file command
- Supports universal execution of planning/brainstorm/analysis output
- Coordinates multi-agents with smart dependency management
- Features parallel/sequential execution modes
- Unified event logging as single source of truth (execution-events.md)
- Agent context passing through previous execution history
- Knowledge chain: each agent reads full history of prior executions
Codex-specific adaptations:
- Use $VARIABLE format for argument substitution
- Simplified header configuration (description + argument-hint)
- Plan format agnostic parsing (IMPL_PLAN.md, synthesis.json, conclusions.json, debug recommendations)
- Multi-wave execution orchestration
- Dynamic artifact location handling
Execution flow:
1. Parse and validate plan from $PLAN_PATH
2. Extract and normalize tasks with dependencies
3. Create execution session (.workflow/.execution/{sessionId}/)
4. Group tasks into execution waves (topological sort)
5. Execute waves sequentially, tasks within wave execute in parallel
6. Unified event logging: execution-events.md (SINGLE SOURCE OF TRUTH)
7. Each agent reads previous executions for context
8. Final statistics and completion report
- Consolidate Phase 3 (Progress Tracking) from 205+ to 30 lines by merging redundant explanations of execution-events.md format
- Merge error handling logic from separate handleTaskFailure function into executeTask catch block
- Remove duplicate Execution Document Template section (identical to Step 1.2)
- Consolidate Phase 4 (Completion & Summary) from 90+ to 40 lines
- Overall reduction: 1094 → 807 lines (26% reduction) while preserving all technical information
Key improvements:
- Single source of truth for execution state (execution-events.md)
- Clearer knowledge chain explanation between agents
- More concise yet complete Phase documentation
- Unified event logging format is now prominently featured
- 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.
Adds support for saving CLI execution output directly to files with the following features:
- Support for relative paths: --to-file output.txt
- Support for nested directories: --to-file results/analysis/output.txt (auto-creates directories)
- Support for absolute paths: --to-file /tmp/output.txt or --to-file D:/results/output.txt
- Works in both streaming and non-streaming modes
- Automatically creates parent directories if they don't exist
- Proper error handling with user-friendly messages
- Shows file save location in completion feedback
Implementation details:
- Updated CLI option parser in ccw/src/cli.ts
- Added toFile parameter to CliExecOptions interface
- Implemented file saving logic in execAction() for both streaming and non-streaming modes
- Updated HTTP API endpoint /api/cli/execute to support toFile parameter
- All changes are backward compatible
Testing:
- Tested with relative paths (single and nested directories)
- Tested with absolute paths (Windows and Unix style)
- Tested with streaming mode
- All tests passed successfully
- Update package.json version to 6.3.49
- Add changelog entry for v6.3.49 with all commits since v6.3.48
- New features: CLI tools enhancements, skills system improvements, security fixes
- Documentation updates and UI improvements
