- Add RoundDetailCard component to display synthesis details per round:
- CLI execution status and duration
- Solutions with feasibility, effort, risk, pros/cons
- Convergence analysis with score and rationale
- Cross-verification showing agreements and disagreements
- Clarification questions
- Update ExpandedMultiCliPanel discussion tab to use new component
- Add i18n translations for new discussion content labels
- Removed the Sessions panel from the DashboardToolbar component, making the Sessions sidebar always visible.
- Updated the TerminalDashboardPage layout to include a fixed session sidebar alongside the terminal grid.
- Adjusted related imports and state management for session counts.
- Added new document standards for YAML frontmatter schema, naming conventions, and content structure.
- Introduced quality gates for spec-generator outputs, detailing scoring dimensions and per-phase criteria.
- Created templates for architecture documents, epics & stories, product briefs, and requirements PRD.
- Implemented DashboardToolbar for managing panel toggles and layout presets.
- Created FloatingPanel for a generic sliding panel interface.
- Developed TerminalGrid for rendering a recursive layout of terminal panes.
- Added TerminalPane to encapsulate individual terminal instances with toolbar actions.
- Introduced layout utilities for managing Allotment layout trees.
- Established Zustand store for terminal grid state management, supporting pane operations and layout resets.
- Introduced Phase 6: Post-Implementation Review with detailed steps for specialized reviews (quality, security, architecture, action items).
- Updated SKILL.md to reflect new phase and its execution lifecycle.
- Enhanced Flowchart component to conditionally display step statuses based on task tracking.
- Modified TaskDrawer to pass status tracking prop to Flowchart.
- Improved AgentList and other terminal dashboard components for better UI consistency and responsiveness.
- Removed GlobalKpiBar component as part of UI cleanup.
- Added issue detail preview in TerminalWorkbench for better user experience when no terminal is active.
- Updated localization files for new strings related to the terminal dashboard and workbench.
- Enhanced TaskListTab to conditionally render task stats and status dropdown based on task status tracking.
- Added Phase 1: Session Start to detect input mode and create test workflow session.
- Added Phase 2: Test Context Gather to gather test context via coverage analysis or codebase scan.
- Added Phase 3: Test Concept Enhanced to analyze test requirements using Gemini and generate multi-layered test requirements.
- Added Phase 4: Test Task Generate to create test-specific tasks based on analysis results.
- Added Phase 5: Test Cycle Execute to manage iterative test execution and fix cycles with adaptive strategies.
- Introduced BottomPanel component for terminal dashboard with Queue and Inspector tabs.
- Implement TerminalTabBar for session tab management with status indicators and alert badges.
- Create TerminalWorkbench to combine TerminalTabBar and TerminalInstance for terminal session display.
- Add localization support for terminal dashboard in English and Chinese.
- Develop TerminalDashboardPage for the main layout of the terminal dashboard with a three-column structure.
- Introduce Zustand stores for session management and issue/queue integration, handling session groups, terminal metadata, and alert management.
- Create a monitor web worker for off-main-thread output analysis, detecting errors and stalls in terminal sessions.
- Define TypeScript types for terminal dashboard state management and integration.
- Introduced new TypeScript types for orchestrator functionality, including `SessionStrategy`, `ErrorHandlingStrategy`, and `OrchestrationStep`.
- Defined interfaces for `OrchestrationPlan` and `ManualOrchestrationParams` to facilitate orchestration management.
- Added a new PNG image file for visual representation.
- Created a placeholder file named 'nul' for future use.
- Introduced a new quality standards document outlining assessment criteria for team command .md files, including completeness, pattern compliance, integration, and consistency dimensions.
- Established quality gates and issue classification for errors, warnings, and informational notes.
- Created a comprehensive team command design patterns document detailing infrastructure and collaboration patterns, including message bus integration, YAML front matter requirements, task lifecycle, five-phase execution structure, and error handling.
- Included a pattern selection guide for collaboration scenarios to enhance team interaction models.
Move execute.md from commands/workflow/ to skills/workflow-execute/SKILL.md,
update all references in workflow-plan to use Skill(skill="workflow-execute")
instead of the old /workflow:execute command path.
- Implement Phase 4: Full Documentation Generation with multi-layered strategy and tool fallback.
- Introduce Phase 5: Related Documentation Generation for incremental updates based on git changes.
- Create new utility components for displaying execution status in the terminal panel.
- Add helper functions for rendering execution status icons and formatting relative time.
- Establish a recent paths configuration for improved path resolution.
Consolidate two separate commands into a single skill with router pattern.
The skill auto-detects user intent and routes to compact or tips phase,
with AskUserQuestion fallback for ambiguous input.
Remove the entire old template-based frontend (~106K lines) and make the React
SPA the only way to access the ccw dashboard via `ccw view`.
Key changes:
- Delete all old frontend files: dashboard-css/ (37 CSS), dashboard-js/ (59 JS),
assets/, dashboard.html, and legacy HTML templates
- Delete dashboard-generator.ts and dashboard-generator-patch.ts
- Simplify server.ts: remove ~234 lines of old frontend code (template constants,
MODULE_CSS_FILES/MODULE_FILES arrays, generateServerDashboard(), /assets/* serving)
- Rebase React frontend from /react/ to root / (vite.config.ts, react-frontend.ts)
- Add /react/* -> /* 301 redirect for backward compatibility
- Remove --frontend and --new CLI flags from view and serve commands
- Remove generateDashboard export from public API (index.ts)
- Simplify serve.ts and view.ts to always use React without conditional branching
- Update all affected tests (unit, e2e) for React-only architecture
BREAKING CHANGE: --frontend and --new CLI flags removed; generateDashboard export
removed from ccw package; /react/ base path changed to /
Add three integration improvements to the CodexLens management panel:
- Enhance SettingsTab with RerankerConfigCard using /reranker/config endpoint
for dynamic backend/model/provider dropdowns
- Add CcwToolsCard to AdvancedTab showing CCW registered tools with
codex-lens tools highlighted
- Add LspServerCard to OverviewTab with start/stop/restart controls
mirroring the FileWatcherCard pattern
- Create LSP lifecycle backend endpoints (start/stop/restart) bridging
to Python StandaloneLspManager
- Add corresponding TanStack Query hooks, API functions, and i18n keys
- Removed ad-hoc test scripts and temp files from project root
- Added QueueItemExecutor component to handle both session and orchestrator executions
- Created CliExecutionSettings component for shared execution parameter controls
- Introduced useCliSessionCore hook for managing CLI session lifecycle
- Merged buildQueueItemPrompt and buildQueueItemInstruction into a single function for context building
- Implemented Zustand store for queue execution state management
- Updated localization files for new execution features
- Implement Phase 4: Integration Verification to ensure skill package consistency.
- Implement Phase 5: Validation to verify quality and deliver the final skill package.
- Create role-template.md for generating per-role execution detail files.
- Create skill-router-template.md for generating SKILL.md with role-based routing.
- Add tests for static graph relationship writing during index build in test_static_graph_integration.py.
- Implemented CLI fallback using `ccw team` for various team command operations in `execute.md`, `plan.md`, `review.md`, `spec-analyst.md`, `spec-coordinate.md`, `spec-discuss.md`, `spec-reviewer.md`, `spec-writer.md`, and `test.md`.
- Updated command generation templates to include CLI fallback examples.
- Enhanced validation checks to ensure CLI fallback sections are present.
- Added quality standards for CLI fallback in team command design.
- Introduced a new `GlobalGraphExpander` class for expanding search results with cross-directory relationships.
- Added tests for `GlobalGraphExpander` to verify functionality and score decay factors.
Apply same review fixes from Claude handlers to Codex handlers:
- Add previousConfig snapshot for rollback on API failure
- Guard against duplicate tool entries with includes() check
- Read config before optimistic update to avoid stale data
- Use spread to preserve full config shape
- test-fix-agent: remove flow_control references, use pre_analysis and convergence.criteria
- code-developer: shared_context reads from plan.json instead of task meta
- Introduced a new schema version (v2) with a global_relationships table.
- Implemented CRUD operations for file relationships, including update and delete functionalities.
- Added query capabilities for relationships by target and symbols.
- Created migration logic from v1 to v2 schema.
- Enhanced tests for global relationships, covering various scenarios including insertion, querying, and deletion.
docs: Add update-single command for generating module documentation
- Created a new command to generate manual-style documentation (CLAUDE.md) for a single module.
- Detailed execution process and implementation phases for the command.
- Included usage examples and error handling guidelines.
feat: Implement team command for CLI interface
- Added a new team command for logging and retrieving messages in a team message bus.
- Supported subcommands for logging, reading, listing, and checking status of messages.
- Included error handling and JSON output options.
test: Add comprehensive tests for global relationships
- Developed extensive tests for the global_relationships table in GlobalSymbolIndex.
- Covered schema creation, migration, CRUD operations, and performance benchmarks.
- Ensured project isolation and validated query functionalities for relationships.
Introduces a complete skill for designing and generating team command .md
files. Each team is organized as a folder under .claude/commands/team/{team-name}/
with colon-separated skill paths (e.g., team:spec:analyst). Includes 8
infrastructure patterns, 10 collaboration patterns (CP-1 through CP-10),
5-phase generation pipeline, and quality validation standards.
Prevents @formatjs/intl crash when session.status has an unexpected
value not present in the statusLabelKeys map, causing formatMessage
to receive undefined as the id.
configStore previously used hardcoded defaults when localStorage was
empty, ignoring backend config in ~/.claude/cli-tools.json. Added
onRehydrateStorage hook to fetch GET /api/cli/config and merge via
loadConfig(), added apiEndpoints to partialize list, and introduced
version 1 migration for backward compatibility.
- Added TerminalPanel component with navigation and main area for terminal interactions.
- Integrated terminal session management with CLI execution output display.
- Enhanced SolutionDrawer to open terminal panel on command execution.
- Updated localization files for terminal panel strings in English and Chinese.
- Introduced hooks for terminal panel state management.
- Created JSON schemas for plan overview and fix plan types.
- Created a barrel export file for terminal panel components.
- Implemented Zustand store for managing terminal panel UI state, including visibility, active terminal, view mode, and terminal ordering.
- Added actions for opening/closing the terminal panel, setting the active terminal, changing view modes, and managing terminal order.
- Introduced selectors for accessing terminal panel state properties.
refactor: rename variables for clarity in ReviewSessionPage and SessionsPage
fix: update version check logic in SettingsPage
chore: remove unused imports in TeamPage and session-detail components
fix: enhance error handling in MCP server
fix: apply default mode in edit-file tool handler
chore: remove tsbuildinfo file
docs: add Quick Plan & Execute phase documentation for issue discovery
chore: clean up ping output file
- Remove docs-frontend.ts utility and docs proxy from server.ts
- Remove docs startup logic from serve.ts
- Delete HelpPage.tsx and /help route from frontend
- Remove help navigation entry from Sidebar.tsx
- Clean /docs proxy from vite.config.ts
- Remove docs-related scripts from package.json files
- Delete help.spec.ts E2E tests
- Remove docs-site directory (migrated to D:\ccw-doc)
The docs-site has been moved to D:\ccw-doc as a standalone Docusaurus
project with baseUrl='/' for static hosting deployment (GitHub Pages/Netlify).
Fix 3 issues found by Gemini full-chain analysis:
1. (High) cross_cutting_specs path format mismatch: feature-index.json
uses relative paths ("role/file.md") but context-package uses full
paths (".workflow/.../role/file.md"). Changed action-planning-agent
to use endsWith() matching and read from context-package objects
instead of raw feature-index strings.
2. (Medium) Add explicit feature_index_path field to context-package
schema in context-search-agent, so task-generate-agent can read it
directly instead of hardcoding paths. Updated both single-module
and multi-module prompt templates with fallback logic.
3. (Medium) Expand synthesis_output in context-search-agent to include
feature_driven sub-object pointing to feature-index.json and
feature-specs/ directory alongside legacy synthesis-specification.md.
Requirements, architecture, and epics now output as directories with
individual files per design point (_index.md + REQ-*.md/ADR-*.md/EPIC-*.md),
linked via relative paths for better referencing and downstream consumption.
Phase 6 handoff bridge simplified to read directly from individual EPIC files.
Phase 6 now creates brainstorm_artifacts-compatible bridge files
(.brainstorming/guidance-specification.md, feature-index.json, feature-specs)
when handing off to workflow:plan or req-plan, enabling context-search-agent
auto-discovery without modifying downstream consumers.
Wire FlowExecutor into orchestrator routes for actual flow execution with
pause/resume/stop lifecycle management. Add CLI session audit system with
audit-routes backend and Observability tab in IssueHub frontend. Introduce
cli-session-mux for cross-workspace session routing and QueueSendToOrchestrator
UI component. Normalize frontend API response handling for { data: ... }
wrapper format and propagate projectPath through flow hooks.
In codex-lens, add per-server opened-document cache in StandaloneLspManager
to avoid redundant didOpen notifications (using didChange for updates), and
skip warmup delay for already-warmed LSP server instances in ChainSearchEngine.
- Implemented share token creation and revocation for CLI sessions.
- Added a new page for viewing shared CLI sessions with SSE support.
- Introduced hooks for fetching and managing CLI session shares.
- Enhanced the IssueTerminalTab component to handle share tokens and display active shares.
- Updated API routes to support fetching and revoking share tokens.
- Added unit tests for the CLI session share manager and rate limiter.
- Updated localization files to include new strings for sharing functionality.
- Introduced a new benchmark results file for performance comparison on 2026-02-09.
- Added a test for LspGraphBuilder to ensure it does not expand nodes at maximum depth.
- Created a test for the staged search pipeline to validate fallback behavior when stage 1 returns empty results.
- 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
