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
- Added loading of plan.json in scanMultiCliDir to improve task extraction.
- Implemented normalization of tasks from plan.json format to support new UI.
- Updated CSS for multi-CLI plan summary and task item badges for better visibility.
- Refactored hook-manager to use Node.js for cross-platform compatibility in command execution.
- Improved i18n support for new CLI tool configuration in the hook wizard.
- Enhanced lite-tasks view to utilize normalized tasks and provide better fallback mechanisms.
- Updated memory-update-queue to return string messages for better integration with hooks.
- Introduced command.json for CCW-Help with 88 commands and 16 agents, covering essential workflows and memory management.
- Created command.json for CCW with comprehensive capabilities for exploration, planning, execution, bug fixing, testing, reviewing, and documentation.
- Defined complex flows for rapid iteration, full exploration, coupled planning, bug fixing, issue lifecycle management, and more.
- Implemented intent rules for bug fixing, issue batch processing, exploration, UI design, TDD, review, and documentation.
- Established CLI tools and injection rules to enhance command execution based on context and complexity.
- Added lifecycle management for CLI Stream Viewer with destroy function to clean up event listeners and timers.
- Improved navigation state management by registering destroy functions for views and ensuring cleanup on transitions.
- Updated Claude Manager to include lifecycle functions for better resource management.
- Enhanced CLI History View with state reset functionality and improved dropdown handling for batch delete.
- Introduced round solutions rendering in Lite Tasks View, including collapsible sections for implementation plans, dependencies, and technical concerns.
Problem:
When generating hook configurations, the convertToClaudeCodeFormat function
was using double quotes to wrap bash -c script arguments. This caused
complex escaping issues with jq commands inside, leading to parse errors
like "jq: error: syntax error, unexpected end of file".
Solution:
For bash -c commands, now use single quotes to wrap the script argument.
Single quotes prevent shell expansion, so internal double quotes (like
those used in jq patterns) work naturally without excessive escaping.
If the script contains single quotes, they are properly escaped using
the '\'' pattern (close quote, escaped quote, reopen quote).
Fixes: https://github.com/catlog22/Claude-Code-Workflow/issues/73
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Introduced a new navigation item for "Multi-CLI Plan" in the dashboard template.
- Created a new JSON schema for "Multi-CLI Discussion Artifact" to facilitate structured discussions and decision-making processes.
- Introduced a new command `/workflow:multi-cli-plan` for collaborative planning using ACE semantic search and iterative analysis with Claude and Codex.
- Implemented a structured execution flow with phases for context gathering, multi-tool analysis, user decision points, and final plan generation.
- Added detailed documentation outlining the command's usage, execution phases, and key features.
- Included error handling and configuration options for enhanced user experience.
- Introduced a new input group for environment file configuration in the dashboard CSS.
- Updated hook manager to queue CLAUDE.md updates with configurable threshold and timeout.
- Enhanced CLI manager view to include environment file input for built-in tools (gemini, qwen).
- Implemented environment file loading mechanism in cli-executor-core, allowing custom environment variables.
- Added unit tests for environment file parsing and loading functionalities.
- Updated memory update queue to support dynamic configuration of threshold and timeout settings.
- Introduced `/issue:discover-by-prompt` command for user-driven issue discovery.
- Implemented multi-agent exploration with iterative feedback loops.
- Added ACE semantic search for context gathering and cross-module comparison capabilities.
- Enhanced user experience with natural language input and adaptive exploration strategies.
feat: implement memory update queue tool for batching updates
- Created `memory-update-queue.js` for managing CLAUDE.md updates.
- Added functionality for queuing paths, deduplication, and auto-flushing based on thresholds and timeouts.
- Implemented methods for queue status retrieval, flushing, and timeout checks.
- Configured to store queue data persistently in `~/.claude/.memory-queue.json`.
- Add buildCrossPlatformMcpConfig() helper for automatic Windows cmd /c wrapping
- Add checkWindowsMcpCompatibility() to detect configs needing Windows fixes
- Add autoFixWindowsMcpConfig() to automatically fix incompatible configs
- Add showWindowsMcpCompatibilityWarning() dialog for user confirmation
- Simplify recommended MCP configs (ace-tool, chrome-devtools, exa) using helper
- Auto-detect and prompt when adding MCP servers with npx/npm/node/python commands
- Add i18n translations for Windows compatibility warnings (en/zh)
Supported commands for auto-detection: npx, npm, node, python, python3, pip, pip3, pnpm, yarn, bun
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- #70: Fix API Key Tester URL handling - normalize trailing slashes before
version suffix detection to prevent double-slash URLs like //models
- #69: Fix memory embedder ignoring CodexLens config - add error handling
for CodexLensConfig.load() with fallback to defaults
- #68: Fix ccw cli using wrong Python environment - add getCodexLensVenvPython()
to resolve correct venv path on Windows/Unix
- #67: Fix LiteLLM API Provider test endpoint - actually test API key connection
instead of just checking ccw-litellm installation
- #66: Fix help-routes.ts path configuration - use correct 'ccw-help' directory
name and refactor getIndexDir to pure function
- #63: Fix CodexLens install state refresh - add cache invalidation after
config save in codexlens-manager.js
Also includes targeted unit tests for the URL normalization logic.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
