- Remove hardcoded Windows paths (D:\Claude_dms3\codex-lens) that were displayed to macOS/Linux users
- Generate dynamic possible paths list based on runtime environment
- Support multiple installation locations (cwd, project root, home directory)
- Improve error messages with platform-appropriate paths
- Maintain consistency across both bootstrapWithUv() and installSemanticWithUv() functions
Fixes remaining issue from #104 regarding cross-platform error message compatibility
- Updated all references from `/workflow:action-plan-verify` to `/workflow:plan-verify` across various documentation and command files.
- Introduced a new command file for `/workflow:plan-verify` that performs read-only verification analysis on planning artifacts.
- Adjusted command relationships and help documentation to reflect the new command structure.
- Ensured consistency in command usage throughout the workflow guide and getting started documentation.
- Enhanced lite-execute, lite-fix, lite-lite-lite, lite-plan, multi-cli-plan, plan, replan, session complete, session solidify, and various UI design commands to support a --yes or -y flag for skipping user confirmations and auto-selecting defaults.
- Updated argument hints and examples to reflect new auto mode functionality.
- Implemented auto mode defaults for confirmation, execution methods, and code review options.
- Improved error handling and validation in command parsing and execution processes.
- Implement two-pass search strategy for codex-lens path detection
- First pass: prefer non-node_modules paths (development environment)
- Second pass: allow node_modules paths (NPM global install)
- Fixes CodexLens installation for all NPM global install users
- No breaking changes, maintains backward compatibility
Resolves issue where NPM global install users could not install CodexLens
because the code rejected paths containing /node_modules/, which is the
only valid location for codex-lens in NPM installations.
Tested on macOS with Node.js v22.18.0 via NPM global install.
- Add action files for session management, command selection, building, execution, and completion.
- Introduce orchestrator logic to drive state transitions and action selection.
- Create state schema to define session state structure.
- Develop command registry and validation tools for command metadata extraction and chain validation.
- Establish skill configuration and specifications for command library and validation rules.
- Implement tools for command registry and chain validation with CLI support.
- Add solutionsAction() to query all bound solutions in one call
- Reduces O(N) queries to O(1) for queue formation
- Update /issue:queue command to use new endpoint
- Performance: 18 individual queries → 1 batch query
Version: 6.3.42
- Updated issue loading process to create batches based on size (max 3 per batch).
- Removed semantic grouping in favor of simple size-based batching.
- Introduced a new command to batch query solutions for multiple issues.
- Improved solution loading to fetch all planned issues with bound solutions in a single call.
- Added detailed handling for multi-solution issues, including user selection for binding.
- Created a new workflow command for multi-agent development with documented progress and incremental iteration support.
- Added .gitignore for ace-tool directory to prevent unnecessary files from being tracked.
According to OpenAI Codex skill specification, SKILL.md files must have both
'name' and 'description' fields in YAML frontmatter. Added missing 'name' field
to all three skills:
- CCW Loop
- CCW Loop-B
- Parallel Dev Cycle
Also enhanced ccw-loop description with Chinese trigger keywords for better
multi-language support.
- Introduced a new specification for agent communication optimization focusing on file references instead of content transfer to enhance efficiency and reduce message size.
- Established a coordination protocol detailing communication channels, message formats, and dependency resolution strategies among agents (RA, EP, CD, VAS).
- Created a unified progress format specification for all agents, standardizing documentation structure and versioning practices.
Changed loadClaudeCliTools() to only load tools explicitly defined
in user config. Previously, DEFAULT_TOOLS_CONFIG.tools was spread
before user tools, causing all default tools to be loaded even if
not present in user config.
User config now has complete control over which tools are loaded.
The ensureToolTags() function was only returning enabled, primaryModel,
secondaryModel, and tags - missing envFile. This caused envFile to be
lost during config merge in loadClaudeCliTools().
Related to #96 - gemini envFile setting lost after page refresh
Fixes#96 - gemini/qwen envFile setting was lost after page refresh
because getFullConfigResponse() was not including the envFile field
when converting config to the legacy API format.
Changes:
- Add envFile?: string | null to CliToolConfig interface
- Include envFile in getFullConfigResponse() conversion
- Introduced the `/workflow:clean` command for intelligent code cleanup.
- Implemented mainline detection to identify active development branches and core modules.
- Added drift analysis to discover stale sessions, abandoned documents, and dead code.
- Included safe execution features with staged deletion and confirmation.
- Documented usage, execution process, and implementation details in `clean.md`.
- Implemented issue discovery prompt to analyze code from various perspectives (bug, UX, test, quality, security, performance, maintainability, best-practices).
- Created structured issue generation prompt from GitHub URLs or text descriptions, including clarity detection and optional clarification questions.
- Introduced CCW Loop-B hybrid orchestrator pattern for iterative development, featuring a coordinator and specialized workers with batch wait support.
- Defined state management, session structure, and output schemas for the CCW Loop-B workflow.
- Added error handling and best practices documentation for the new features.
- Implemented the VALIDATE action to run tests, check coverage, and generate reports.
- Created orchestrator for managing CCW Loop execution using Codex subagent pattern.
- Defined state schema for unified loop state management.
- Updated action catalog with new actions and their specifications.
- Enhanced CLI and issue routes to support new features and data structures.
- Improved documentation for Codex subagent design principles and action flow.
Fixes#97 - File browser "Show Hidden Files" checkbox appeared checked
but hidden files weren't displayed until the checkbox was toggled.
Root cause: Timing mismatch where loadFileBrowserDirectory() was called
before initFileBrowserEvents(), causing the initial API request to send
showHidden: false while the checkbox was checked.
Fix: Initialize fileBrowserState.showHidden = true in showFileBrowserModal()
to match the checkbox's default checked state.
- Introduced Lite-Plan-B for hybrid mode planning with multi-agent parallel exploration and primary agent merge/clarify/plan capabilities.
- Added Lite-Plan-C for Codex subagent orchestration, featuring intelligent task analysis, parallel exploration, and adaptive planning based on task complexity.
- Both workflows include detailed execution processes, session setup, and structured output formats for exploration and planning results.
- Introduced a new agent: universal-executor, designed for versatile task execution across various domains with a systematic approach.
- Added comprehensive documentation for Codex subagents, detailing core architecture, API usage, lifecycle management, and output templates.
- Created a new markdown file for Codex subagent usage guidelines, emphasizing parallel processing and structured deliverables.
- Updated codex_prompt.md to clarify the deprecation of custom prompts in favor of skills for reusable instructions.
Fix task click handlers not working in multi-CLI planning detail page.
Root cause: liteTaskDataStore was not being populated with multiCliPlan
sessions during initialization, so task click handlers couldn't access
session data using currentSessionDetailKey.
Changes:
- navigation.js: Add code to populate multiCliPlan sessions in liteTaskDataStore
- notifications.js: Add code to populate multiCliPlan sessions when data refreshes
Now when task detail page loads, liteTaskDataStore contains the correct key
'multi-cli-${sessionId}' matching currentSessionDetailKey, allowing task
click handlers to find session data and open detail drawer.
Verified: Task clicks now properly open detail panel for all 7 tasks.
Ensure buildExecutionPrompt includes project constraints reference,
maintaining consistency with full workflow (plan + execute) which passes
project_guidelines via context-package.json. This allows execution phase
to respect user-defined constraints (via /workflow:session:solidify).
- Fix missing i18n translations: loop.add, loop.save, loop.cancel
- Replace hardcoded validTools with dynamic tool loading from cli-tools.json
- Support external CLI wrappers (like doubao) in task creation and updates
- Add getEnabledToolsList() helper to fetch enabled tools dynamically
- Update mapIssueToolToLoopTool() to accept any string tool name
- Update validateTool() to use dynamic tool list
- Change LoopTask.tool type from specific strings to string (accepts any tool)
This allows tasks to use any enabled CLI tool from configuration,
including builtin tools, cli-wrappers, and api-endpoints, not just
the hardcoded ['bash', 'gemini', 'codex', 'qwen', 'claude'].
- Add 'In Development' (开发中) badge to Loop Monitor navigation item
- Use yellow highlight to indicate development status
- Add i18n translations: nav.inDevelopment ('In Dev' / '开发中')
- Bump version to 6.3.37
The Loop Monitor feature is now clearly marked as under development,
helping users understand it may have limited functionality.
- Add getEnabledTools() async function to fetch tools from /api/cli/tools-config
- Cache enabled tools in window.enabledTools to avoid repeated API calls
- Replace hardcoded tool options in add task modal with dynamic generation
- Replace hardcoded tool options in edit task modal with dynamic generation
- Fallback to ['claude'] if no tools enabled, all tools if API fails
- Make showAddTaskModal() and showEditTaskModal() async functions
- Update editTask() to use await when calling showEditTaskModal()
Fixes issue where task modals only showed hardcoded tools instead of
loading enabled tools from CLI configuration.
Task List Styling Improvements:
1. Added .tasks-list-header styling
- Flexbox layout with space-between alignment
- Border bottom separator line
- Proper heading (h4) with icon and spacing
- Muted text color for counts
2. Added .task-list-empty styling
- Full centered empty state container
- Proper spacing and padding (3rem)
- Icon styling with reduced opacity
- Title and hint text with correct colors and sizes
- Button margin adjustment
3. Enhanced .empty-state styling
- Added button margin-top (1rem) for better spacing
- Applied to both .empty-state and .empty-detail-state
Result: Task list now has consistent, professional styling with:
- Clear visual hierarchy for headers
- Properly centered empty states
- Better spacing and typography
- Improved user experience
