- Implemented CLI commands for listing, downloading, deleting, and retrieving information about reranker models.
- Enhanced the dashboard UI to support embedding and reranker configurations with internationalization.
- Updated environment variable management for embedding and reranker settings.
- Added functionality to dynamically update model options based on selected backend.
- Improved user experience with status indicators and action buttons for model management.
- Integrated new reranker models with detailed metadata and recommendations.
- Implement comprehensive end-to-end tests for MCP Tool Execution, covering tool discovery, execution, parameter validation, error handling, and timeout scenarios.
- Introduce tests for the complete lifecycle of a workflow session, including initialization, task management, status updates, and archiving.
- Validate dual parameter format support and handle boundary conditions such as invalid JSON, non-existent sessions, and path traversal attempts.
- Ensure concurrent task updates are handled without data loss and that task data is preserved when archiving sessions.
- List sessions across all locations and verify metadata inclusion in the results.
- Added `rerankerModels` property to the `ProviderCredential` interface in `litellm-api-config.ts` to support additional reranker configurations.
- Introduced a numerically stable sigmoid function in `FastEmbedReranker` for score normalization.
- Updated the scoring logic in `FastEmbedReranker` to use raw float scores from the encoder and normalize them using the new sigmoid function.
- Adjusted the result mapping to maintain original document order while applying normalization.
- Introduced a comprehensive code analysis action template for integrating code exploration and analysis capabilities.
- Added LLM action template for seamless integration of LLM calls with customizable prompts and tools.
- Implemented a benchmark search script to compare multiple search methods across various dimensions including speed, result quality, ranking stability, and coverage.
- Provided preset configurations for common analysis tasks and LLM actions, enhancing usability and flexibility.
- Add normalizePath() for Windows case-insensitive comparison
- Add resolveMainRepoFromGitFile() to parse .git file when git command fails
- Enhanced fallback logic reads .git file content (gitdir: path) to find main repo
- Supports worktree detection even without git CLI available
getProjectRoot() now detects if running from a git worktree and
automatically resolves to the main repository path. This allows
all ccw issue commands to work correctly from within a worktree.
Uses git rev-parse --git-common-dir to find main repo's .git
Validate working directory path before passing to spawn() to prevent
ENOENT errors when malformed paths are provided. Uses existing
validatePath utility for path validation and existence checks.
- Import validatePath from path-resolver
- Validate cd parameter with mustExist check before use
- Provide clear error message with invalid path details
- Replace auto-complete with AskUserQuestion in execute.md Phase 5
- User can choose "Enter Review" or "Complete Session"
- Fix archived tasks showing incomplete on dashboard
- executeArchive now updates all .task/*.json status to completed
- Add --queue parameter for explicit queue targeting (next, dag, detail, done, retry)
- Implement serialized multi-queue execution (complete Q1 before Q2)
- Add queue activate/priority subcommands for multi-queue management
- Add FailureDetail interface for structured failure tracking
- Preserve failure history on retry for debugging
- Show failure reasons and retry count in queue status display
- Auto-detect queue from item ID in done/detail commands
- Added `splade_encoder.py` for ONNX-optimized SPLADE encoding, including methods for encoding text and batch processing.
- Created `SPLADE_IMPLEMENTATION.md` to document the SPLADE encoder's functionality, design patterns, and integration points.
- Introduced migration script `migration_009_add_splade.py` to add SPLADE metadata and posting list tables to the database.
- Developed `splade_index.py` for managing the SPLADE inverted index, supporting efficient sparse vector retrieval.
- Added verification script `verify_watcher.py` to test FileWatcher event filtering and debouncing functionality.
- Add broadcastStreamEvent() for real-time CLI output to Dashboard
- Send CLI_EXECUTION_STARTED/OUTPUT/COMPLETED events via /api/hook
- Add killCurrentCliProcess() to terminate child CLI on SIGINT/SIGTERM
- Track child process reference for cleanup on interruption
- Make CLI stream viewer panel full-height (calc(100vh - 32px))
- Fix completion status not updating by using consistent executionId
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add shared python-utils.ts module for consistent Python detection
- Use `python -m pip` instead of direct pip command (fixes "pip not found")
- Support CCW_PYTHON env var for custom Python path
- Use Windows py launcher to find compatible versions (3.9-3.12)
- Warn users when Python version may not be compatible with onnxruntime
Fixes issues where users couldn't install ccw-litellm due to:
- pip not in PATH
- Only pip3 available (not pip)
- Python 3.13+ without onnxruntime support
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add -d/--debug option to ccw cli command
- Enable debug logging at runtime when flag is set
- Change DEBUG check from const to function for runtime evaluation
- Support debug mode for both exec and status subcommands
- Update help text to include --debug option
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add debugLog and errorLog utility functions with DEBUG env control
- Add logging for tool availability check (TOOL_CHECK)
- Add logging for command building (BUILD_CMD)
- Add logging for process spawn (SPAWN, STDIN)
- Add logging for process completion (CLOSE, STATUS)
- Enhance error output with command details, exit code, and stderr
- Add troubleshooting hints for common failures
- Support DEBUG=true or CCW_DEBUG=true environment variables
Closes#46🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Removed the interactive issue management command and its associated documentation.
- Enhanced the issue planning command to streamline project context reading and solution creation.
- Improved queue management with conflict clarification and status syncing from queues.
- Added functionality to track completed issues, moving them to a history file upon completion.
- Updated CLI options to support syncing issue statuses from queues.
- Introduced new API endpoint for retrieving completed issues from history.
- Enhanced error handling and validation for issue updates and queue management.
Queue is an execution plan without executor assignment.
Executor is determined at runtime by /issue:execute command.
Changes:
- Remove assigned_executor from QueueItem interface
- Remove from dag nodes, list display, execution_hints
- Simplify queue list output (remove Executor column)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace timestamp-based ID generation with issue-id-based format
- generateSolutionId() now accepts issueId and existing solutions
- Automatically calculates next sequence number (SOL-GH-123-1, -2, -3)
- Update taskAction and bindAction to use new format
- Ensures consistency with agent-generated IDs
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
