- team-worker: add fast_advance message bus log after spawning successor,
closing coordinator state blind spot during fast-advance
- team-worker: add Knowledge Transfer section with upstream loading,
downstream publishing, and context_accumulator conventions
- role-spec-template: add Knowledge Transfer Protocol with Transfer
Channels table and shared-memory.json namespaced write convention
- monitor.md (v2+v5): add fast-advance reconciliation step reading
fast_advance messages, add State Sync section for coordinator wake
- lifecycle-v5 SKILL.md: update cadence diagram with fast_advance log
Harmonize orchestrator files (ccw.md, ccw-coordinator.md) with cross-file
consistency fixes, and add missing -y/--yes non-interactive bypass gates
to 7 skills that declared auto mode support but had blocking AskUserQuestion
calls: team-planex, issue:discover, issue:plan, issue:queue, issue:execute,
workflow:debug-with-file, issue:from-brainstorm.
- Introduced Phase 6: TDD Structure Validation to ensure compliance with TDD workflow standards, including task structure validation, dependency checks, and user configuration verification.
- Implemented Phase 7: TDD Verification for full compliance checks, including task chain structure validation, coverage analysis, and TDD cycle verification.
- Generated detailed TDD compliance reports with quality gate recommendations based on objective criteria.
- Added documentation for new commands and workflows in the Claude Commands index.
- Updated command syntax formatting to use code blocks for clarity in `prep.md`, `review.md`, and `spec.md`.
- Enhanced architectural diagrams in `ch01-what-is-claude-dms3.md` and core concepts in `ch03-core-concepts.md` using mermaid syntax for better visualization.
- Improved workflow diagrams in `ch04-workflow-basics.md` and `4-level.md` to provide clearer representations of processes.
- Added troubleshooting section in `installation.md` to address common installation issues and provide quick start examples.
- Revised skill documentation in `claude-meta.md` and `claude-workflow.md` to standardize command triggers and output structures.
- Updated best practices and workflow index documentation to enhance readability and understanding of workflow levels and practices.
- Fix incorrect package names (@ccw/cli, @anthropic/claude-code-workflow) to claude-code-workflow
- Add workflow examples page with 8 practical artifact samples
- Optimize sidebar navigation with emoji icons and second-level grouping
- Add usage examples to commands and skills documentation
- Update qa/issues.md with current status
- Sync Chinese documentation changes
- Add docs directory with VitePress configuration
- Add GitHub Actions workflow for docs build and deploy
- Support bilingual (English/Chinese) documentation
- Include search, custom theme, and responsive design
- Add 7 new CSV columns (test, acceptance_criteria, scope, hints,
execution_directives, tests_passed, acceptance_met) to tasks.csv
schema across all 3 pipeline skills
- Create .codex/skills/wave-plan-pipeline as Codex version of
workflow-wave-plan with spawn_agents_on_csv calling conventions
- Align instruction templates with MANDATORY FIRST STEPS and 11-step
execution protocol across all files
- Standardize context.md reports with Waves metric and Dependencies row
- Unify Discovery Board protocol with Dedup Key table and test_command
- Add Best Practices and Usage Recommendations to workflow-wave-plan
Claude version: add coordinator role with Spawn-and-Stop beat model,
replace role-routed planner/executor with team-worker agents using
lightweight role-specs (~80-110 lines each).
Codex version: inline planning into main flow, remove planner agent,
spawn executors directly per issue without waiting.
Both versions preserve 3 input types (Issue IDs / --text / --plan).
- Add common.status.ready i18n key for zh/en locales
- Add ready/initialized/archived/failed status colors to dashboard widgets
- Expand QueryInvalidator to invalidate projectOverview, workflowStatusCounts,
and dashboardStats queries on workspace switch
docs: add team lifecycle orchestrator skill documentation with detailed architecture, agent registry, and execution phases
docs: introduce team planex skill for issue-by-issue execution with Codex CLI, including input parsing and session management
- Add ccw/frontend/dist/ to package.json files field
- Modify react-frontend.ts to detect and use production build
- Add static file serving to server.ts with MIME type support
- Update prepublishOnly to build frontend before publishing
- Fix unused import in TerminalDashboardPage.tsx
This fixes the 'Could not find React frontend directory' error when users install from npm.
team-coordinate-v2:
- Fix skill name mismatch: update all doc examples to use "team-coordinate-v2"
- This was the root cause of v2 failing to invoke teams
team-lifecycle-v3/v4:
- Add Command Execution Protocol section before Entry Router
- Fix Entry Router logic: distinguish interrupted vs new sessions
- Add Router Implementation subsection with concrete steps
- Removed deprecated `ccw-contentPattern-optimization-summary.md` and related files.
- Updated `A2UIPopupCard.tsx` to clarify comments on interaction handling.
- Enhanced `QueueListColumn.tsx` and `QueuePanel.tsx` to handle potential undefined values for `config`.
- Added `useEffect` in `QueuePanel.tsx` to load scheduler state on mount.
- Improved `SchedulerPanel.tsx` to handle potential undefined values for `sessionPool`.
- Introduced auto-initialization logic in `queueSchedulerStore.ts` to prevent multiple initialization calls.
- Updated `A2UIWebSocketHandler.ts` to refine selection handling logic.
- Enhanced `hooks-routes.ts` to support multi-question surfaces.
- Added submit and cancel buttons in `ask-question.ts` for better user interaction.
- Deleted `codex_prompt.md` and `contentPattern-library-options.md` as part of cleanup.
- Removed `status-reference.md` to streamline documentation.
- Updated version in README and package.json to v7.0.0
- Added new features in WORKFLOW_GUIDE and WORKFLOW_GUIDE_CN
- Introduced session lifecycle commands for managing workflow sessions
- Enhanced NativeSessionPanel to support loading sessions by path or execution ID
- Created useNativeSessionByPath hook for fetching session content by file path
- Improved session metadata structure in API definitions
- Increased stale and garbage collection times for session hooks
- Refactored HistoryPage to utilize new session handling logic
- Added QueueSchedulerService to manage task queue lifecycle, including state machine, dependency resolution, and session management.
- Implemented HTTP API endpoints for queue scheduling:
- POST /api/queue/execute: Submit items to the scheduler.
- GET /api/queue/scheduler/state: Retrieve full scheduler state.
- POST /api/queue/scheduler/start: Start scheduling loop with items.
- POST /api/queue/scheduler/pause: Pause scheduling.
- POST /api/queue/scheduler/stop: Graceful stop of the scheduler.
- POST /api/queue/scheduler/config: Update scheduler configuration.
- Introduced types for queue items, scheduler state, and WebSocket messages to ensure type safety and compatibility with the backend.
- Added static model lists for LiteLLM as a fallback for available models.
- Create team-executor skill for resuming existing team-coordinate sessions
- Add SKILL.md with role router and session validation
- Add roles/executor/role.md with simplified coordinator lifecycle
- Add commands/monitor.md with LIMITED handleAdapt (no role generation)
- Add specs/session-schema.md with comprehensive validation
Enhancements from code review:
- Add role file structural validation (required sections check)
- Add JSON schema field validation for team-session.json and task-analysis.json
- Add 5-role limit enforcement in handleAdapt (team-coordinate)
Root cause: team_msg --team parameter maps directly to filesystem path
.workflow/.team/{value}/.msg/, so using team-name creates wrong directory.
Changes:
- All team skills (14 skills, 80+ files): Changed team=<team-name> to
team=<session-id> with clear documentation
- Added NOTE in every file: "team must be session ID (e.g., TLS-xxx-date),
NOT team name. Extract from Session: field in task description."
- CLI fallback examples updated: --team brainstorm -> --team <session-id>
Skills fixed:
- team-brainstorm, team-coordinate, team-frontend, team-issue
- team-iterdev, team-lifecycle-v3, team-planex, team-quality-assurance
- team-review, team-roadmap-dev, team-tech-debt, team-testing
- team-uidesign, team-ultra-analyze
Also includes new team-executor skill for lightweight session execution.
- Implement Discuss Subagent for multi-perspective critique with dynamic perspectives.
- Create Explore Subagent for shared codebase exploration with centralized caching.
- Add tests for CcwToolsMcpCard component to ensure enabled tools are preserved on config save.
- Introduce SessionPreviewPanel component for previewing and selecting sessions for Memory V2 extraction.
- Develop CommandCreateDialog component for creating/importing commands with import and CLI generate modes.
- Added checkpoint gate handling to the coordinator role, defining behavior based on quality gate results.
- Updated planner role to utilize inner loop pattern for structured implementation planning and reporting.
- Revised writer role to implement inner loop for document generation, delegating CLI execution to a subagent.
- Introduced a new doc-generation subagent for isolated CLI calls and document generation strategies.
- Enhanced UI components in the frontend to display job statuses, last run times, and improved error handling.
- Updated localization files to include new strings for job details and status banners.
- Improved CSS styles for markdown previews to enhance readability and presentation.
- Replace non-existent `--tag` and `--session` options with actual commands
- Update to use `ccw issue list --status` and queue-based workflow
- Sync changes across both Claude and Codex versions
