- Implemented `renderExpField` to handle various data types for exploration fields.
- Created `renderExpArray` to format arrays, including support for objects with specific properties.
- Developed `renderExpObject` for recursive rendering of object values, filtering out private keys.
- Introduced HTML escaping for safe rendering of user-generated content.
- Introduced auto and manual triggering mechanisms for Exa.
- Added quick reference guides for sed and awk text processing.
- Established a fallback strategy for handling edit failures.
- Implemented a Notifications component for real-time updates using WebSocket.
- Added silent refresh functionality to update data without notification bubbles.
- Introduced auto-refresh mechanism to periodically check for changes in workflow data.
- Enhanced data handling with session and task updates, ensuring UI reflects the latest state.
feat: Create Hook Manager View for Managing Hooks
- Developed a Hook Manager view to manage project and global hooks.
- Added functionality to create, edit, and delete hooks with a user-friendly interface.
- Implemented quick install templates for common hooks to streamline user experience.
- Included environment variables reference for hooks to assist users in configuration.
feat: Implement MCP Manager View for Server Management
- Created an MCP Manager view for managing MCP servers within projects.
- Enabled adding and removing servers from projects with a clear UI.
- Displayed available servers from other projects for easy access and management.
- Provided an overview of all projects and their associated MCP servers.
feat: Add Version Fetcher Utility for GitHub Releases
- Implemented a version fetcher utility to retrieve release information from GitHub.
- Added functions to fetch the latest release, recent releases, and latest commit details.
- Included functionality to download and extract repository zip files.
- Ensured cleanup of temporary directories after downloads to maintain system hygiene.
- Introduced a new project overview section in the dashboard, displaying project details, technology stack, architecture, key components, and development history.
- Updated the server logic to include project overview data.
- Enhanced task item styles with status-based background colors for better visual distinction.
- Improved markdown modal functionality for viewing context and implementation plan with normalized line endings.
- Refactored task rendering logic to simplify task item display and improve performance.
- Fixed loadDimensionData function that had duplicate closing brace
- This was preventing review session dimension data from being parsed
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Change step numbers from circles to rounded rectangles
- Add shadow to step number badges for depth
- Enhance mod-point-card with full border and stronger left accent
- Add hover effect with elevated shadow on mod-point-card
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove META/CONTEXT/FLOW_CONTROL collapsible sections from task list
- Add compact task item with action/scope/mods/steps badges
- Create dedicated renderLiteTaskDrawerContent for plan.json parsing
- Add Overview tab with description, scope, acceptance, dependencies
- Add Implementation tab with steps and modification points
- Add proper file list extraction from modification_points
- Add CSS styles for lite task badges and drawer components
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove status indicators from lite task cards (progress bars, percentages)
- Remove status icons and badges from task detail items
- Remove stats bar showing completed/in-progress/pending counts
- Add Plan tab in drawer for plan.json data display
- Add exploration-*.json parsing for context tab
- Add collapsible sections for architecture, dependencies, patterns
- Fix currentPath selector bug causing TypeError
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add plan.json data loading to getSessionDetailData function for lite tasks
- Implement plan tab content styling with summary and approach sections
- Add plan metadata grid layout for displaying task planning information
- Create lite task detail page styles with task stats bar and status indicators
- Add context tab content styling with improved section hierarchy
- Implement path tags and JSON content display styles for plan details
- Add collapsible sections for organizing plan information
- Create comprehensive styling for context fields, modification points, and implementation steps
- Add array and nested object rendering styles for JSON data visualization
- Implement button styles for JSON view toggle functionality
- Reorder CSS and JS file loading in dashboard-generator.js for consistency
- Simplify dashboard.css by removing redundant styles and consolidating to Tailwind-based approach
- Add backup files for dashboard.html, dashboard.css, and review-cycle-dashboard.html
- Create new Tailwind-based dashboard template (dashboard_tailwind.html) and test variant
- Add tailwind.config.js for Tailwind CSS configuration
- Enhance data-aggregator.js to load full task data for archived sessions (previously only counted)
- Add meta, context, and flow_control fields to task objects for richer data representation
- Implement review data loading for archived sessions to match active session behavior
- Improve task sorting consistency across active and archived sessions
- Reduce CSS file size by ~70% through Tailwind utility consolidation while maintaining visual parity
- Implemented a new HTML template for the workflow dashboard, featuring a responsive design with dark/light theme support, session statistics, and task management UI.
- Created a browser launcher utility to open HTML files in the default browser across platforms.
- Developed file utility functions for safe reading and writing of JSON and text files.
- Added path resolver utilities to validate and resolve file paths, ensuring security against path traversal attacks.
- Introduced UI utilities for displaying styled messages and banners in the console.
Addresses issue #33 - /cli:mode:bug-diagnosis command not found
Changes:
- Remove deprecated /cli:* commands (/cli:analyze, /cli:chat, /cli:execute,
/cli:codex-execute, /cli:discuss-plan, /cli:mode:*) from documentation
- Only /cli:cli-init remains as the sole CLI command
- Update all references to use /workflow:lite-plan, /workflow:lite-fix
- Clarify that CLI tools are now invoked through semantic invocation
(natural language) - Claude auto-selects Gemini/Qwen/Codex with templates
- Update COMMAND_SPEC.md, COMMAND_REFERENCE.md, GETTING_STARTED*.md,
FAQ.md, WORKFLOW_DECISION_GUIDE*.md, workflow-architecture.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
## Changes
- Simplify analysis output strategy to optional modular structure
- Update synthesis/artifacts documentation to use AskUserQuestion tool
- Add modular output strategy for brainstorm analysis
- Simplify clarification deduplication in lite-plan
- Add "Fix, Don't Hide" section to CLAUDE.md guidelines
- Simplify project.json schema by removing unused fields
- Update session ID format in lite-fix/lite-plan workflows
- Add development index to project JSON schema
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add explicit instructions to execute ALL clarification rounds when >4
questions exist. AskUserQuestion tool limits max 4 per call, so multi-round
execution is mandatory to exhaust all clarification needs.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Phase 2 Clarification: max 4 questions per round, multiple rounds allowed
- Session Setup: MANDATORY timestamp in sessionId format (slug-YYYY-MM-DD-HH-mm-ss)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add recommended field to explore-json-schema.json clarification_needs
- Update lite-plan/lite-fix/context-gather agent prompts
- Display ★ marker and (Recommended) label in AskUserQuestion options
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add getUtc8ISOString() helper function to generate China Standard Time
timestamps instead of UTC. Applied to:
- Session ID generation (shortTimestamp)
- Diagnosis manifest timestamp
- Direct planning metadata timestamp
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add getUtc8ISOString() helper function to generate China Standard Time
timestamps instead of UTC. Applied to:
- Session ID generation (shortTimestamp)
- Exploration manifest timestamp
- Direct planning metadata timestamp
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add Step 1.0 to test-gen.md to load source session task_description
- Add Step 1.0 to test-fix-gen.md (Session Mode) to load original user intent
- Include originalTaskDescription in session creation to enable semantic CLI selection
- Fixes data flow gap identified by Gemini review: user's CLI tool preferences
(e.g., "use Codex for fixes") now propagate through test workflow sessions
This ensures semantic CLI tool selection works correctly in derivative test sessions
by preserving the original user's task description from the source session.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Rename Track 0 from 'Exploration Aggregation' to 'Exploration Synthesis'
- Add explicit synthesis logic for critical_files prioritization and deduplication
- Enhance explore-json-schema to support relevance scores in relevant_files
- Update explore agent prompts across context-gather and lite-plan commands
- Add synthesizeCriticalFiles and synthesizeConflictIndicators helper functions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- context-gather.md: Add Step 2 with complexity assessment (Low/Medium/High)
and parallel cli-explore-agent execution (1-4 agents based on complexity)
- context-search-agent.md: Add Track 0 for exploration aggregation with
exploration_results schema including all_patterns and all_integration_points
- conflict-resolution.md: Consume exploration_results for enhanced conflict
detection with pre-identified conflict indicators
- task-generate-agent.md: Use exploration critical_files for focus_paths
and all_patterns/all_integration_points for implementation guidance
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Revert cost-aware batching and multi-agent parallelism in lite-execute
- Remove execution_group and task complexity from schema
- Remove execution_group rules from lite-plan
- Keep 50k context threshold protection in lite-plan
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add executeBatch dispatcher to route batches to Agent/Codex
- Update executeBatchAgent to use batch.tasks instead of planObject.tasks
- Update executeBatchCodex to use batch.tasks instead of planObject.tasks
- Each parallel batch now dispatches to separate concurrent agent
Before: All batches → single agent with ALL tasks (no parallelism)
After: P1 → Agent 1, P2 → Agent 2 (true concurrent execution)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
