- 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
Major visual improvements across all components:
Left Sidebar (Loop Cards):
- Enhanced card styling with better shadows and borders (4px left border)
- Improved hover states with subtle elevation
- Better selected state with primary color highlight
- Increased padding and spacing (1rem padding, 0.75rem margin)
- Cleaner status indicator badges
Right Panel (Detail View):
- Added background containers to all detail sections with borders
- Improved section headers with bottom borders for clear separation
- Enhanced progress items with individual card styling
- Better visual hierarchy with consistent spacing (1rem gaps)
- Added info-box component for V2 loop information
Meta Information:
- Detail-meta items now have pill-style backgrounds
- Dashed separator line for better visual grouping
- Improved spacing and padding
CLI Steps:
- Enhanced step cards with better borders and hover states
- 3px left accent border for status indication
- Smooth transitions on hover
Typography & Colors:
- Unified border-radius: 0.625rem for sections, 0.5rem for items
- Consistent background: hsl(var(--muted) / 0.25) for sections
- Better border opacity: hsl(var(--border) / 0.5) and 0.6 variants
- Improved font weights and sizes for clarity
Overall result: Cleaner, more professional interface with better visual hierarchy and clarity.
- Row 1: Tab buttons (循环 | 任务) + New Loop button
- Row 2: Filter dropdown (全部 / 运行中 / 已暂停 / 已完成 / 失败)
- Row 3: Loop list items
This fixes the layout issue where multiple elements were stacking vertically
and appearing on multiple lines. Now creates a clear, organized left panel.
- Add missing i18n keys: 'loop.listView' and 'loop.addTask' for both English and Chinese
- Fix kanban board header layout: wrap title and loop name in separate container (.kanban-header-left)
- Add CSS styling for .kanban-header-left and .kanban-loop-title to properly display loop titles
- Improve visual separation between 'Tasks Board' label and loop title
This fixes the issue where loop titles were appearing inline with the 'Tasks Board' header,
making them appear jumbled (e.g., '任务看板 在' instead of '任务看板' | '在').
- Implemented loop control tasks in JSON format for testing.
- Created comprehensive test scripts for loop flow and standalone tests.
- Developed a shell script to automate the testing of the entire loop system flow, including mock endpoints and state transitions.
- Added error handling and execution history tests to ensure robustness.
- Established variable substitution and success condition evaluations in tests.
- Set up cleanup and workspace management for test environments.
- Updated package name from `codexlens` to `codex-lens` in all relevant files to ensure consistency with `pyproject.toml`.
- Enhanced `findLocalPackagePath()` to always search for local paths, even when running from `node_modules`.
- Removed fallback logic for PyPI installation in several functions, providing clearer error messages for local installation failures.
- Added detailed documentation on installation steps and error handling for local development packages.
- Introduced a new summary document outlining the issues and fixes related to CodexLens installation.
- Implemented workflow installation, listing, and syncing commands in `workflow.ts`.
- Created utility functions for project root detection and package version retrieval in `project-root.ts`.
- Added update checker functionality to notify users of new package versions in `update-checker.ts`.
- Developed unit tests for project root utilities and update checker to ensure functionality and version comparison accuracy.
- Add `association_tree` module with components for building and processing call association trees using LSP call hierarchy capabilities.
- Introduce `AssociationTreeBuilder` for constructing call trees from seed locations with depth-first expansion.
- Create data structures: `TreeNode`, `CallTree`, and `UniqueNode` for representing nodes and relationships in the call tree.
- Implement `ResultDeduplicator` to extract unique nodes from call trees and assign relevance scores based on depth, frequency, and kind.
- Add unit tests for `AssociationTreeBuilder` and `ResultDeduplicator` to ensure functionality and correctness.
- Created a comprehensive guide for setting up TypeScript LSP in Claude Code, detailing installation methods, configuration, and troubleshooting.
- Added multiple debugging test scripts to validate LSP communication with pyright, including direct communication tests, configuration checks, and document symbol retrieval.
- Implemented error handling and logging for better visibility during LSP interactions.
- Implement comprehensive unit tests for the LspGraphBuilder class to validate its functionality in building code association graphs.
- Tests cover various scenarios including single level graph expansion, max nodes and depth boundaries, concurrent expansion limits, document symbol caching, error handling during node expansion, and edge cases such as empty seed lists and self-referencing nodes.
- Utilize pytest and asyncio for asynchronous testing and mocking of LspBridge methods.
- Introduced a new test script for the CodexLens LSP tool to validate core functionalities including symbol search, find definition, find references, and get hover.
- Created comprehensive documentation for the MCP endpoint design, detailing the architecture, features, and integration with the CCW MCP Manager.
- Developed a detailed implementation plan for transitioning to a real LSP server, outlining phases, architecture, and acceptance criteria.
Introduce dedicated agent_message IR type to distinguish final AI responses
from generic stdout. This enables --final flag to show only agent messages,
filtering out all intermediate content (JSONL events, reasoning, tool calls).
Changes:
- Add agent_message type to CliOutputUnitType
- Update JsonLinesParser to map final responses from all tools (codex,
gemini, claude, opencode) to agent_message type
- Add final_output field to database schema with migration
- Update getCachedOutput and getConversation to return finalOutput
- Prefer finalOutput in outputAction for --final flag
Fixes issue where --final showed raw JSONL instead of filtered content.
- Introduced `simulate-cli-prompt.js` to simulate various prompt formats and display the final content passed to the CLI.
- Added `test-shell-prompt.js` to test actual shell execution of different prompt formats, demonstrating correct vs incorrect multi-line prompt handling.
- Created comprehensive tests in `cli-prompt-parsing.test.ts` to validate prompt parsing, including single-line, multi-line, special characters, and template concatenation.
- Implemented edge case handling for empty lines, long prompts, and Unicode characters.
- Skip template concatenation when using --uncommitted/--base/--commit
- Allow empty prompt for review mode with target flags
- Add hasReviewTarget check in command routing
- Update documentation with validation constraints
codex review constraint: target flags and prompt are mutually exclusive
- Replace $PROTO/$TMPL environment variable injection with systemRules/roles direct concatenation
- Append rules to END of prompt instead of prepending
- Change prompt field name from RULES to CONSTRAINTS in all prompts
- Default to universal-rigorous-style template when --rule not specified
- Update all .claude documentation, agents, commands, and skills
- Add streaming_content type support for Gemini delta messages
Breaking: Prompts now use CONSTRAINTS field instead of RULES
- Add 'review' to mode enum in ParamsSchema and schema
- Implement codex review subcommand in buildCommand (uses --uncommitted by default)
- Other tools (gemini/qwen/claude) accept review mode but no operation change
- Update cli-tools-usage.md with review mode documentation
- Add PlatformUtils module for platform detection (Windows/macOS/Linux)
- Add escapeForShell() for platform-specific shell escaping
- Add checkCompatibility() to warn about incompatible hooks before install
- Add getVariant() to support platform-specific template variants
- Fix node -e commands: use double quotes on Windows, single quotes on Unix
- Replace getIndexDir() with getCommandFilePath() to find command.json
- Update file watcher to monitor command.json instead of index/ directory
- Modify API routes to read from unified command.json structure
- Add buildWorkflowRelationships() to dynamically build workflow data from flow fields
- Add /api/help/agents endpoint for agents list
- Add category merge logic for frontend compatibility (cli includes general)
- Add cli-init command to command.json
