- Fix ccw-litellm path lookup for npm distribution by adding PACKAGE_ROOT
- Add uninstall button to API Settings page for ccw-litellm
- Add /api/litellm-api/ccw-litellm/uninstall endpoint
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Primary method: pip show ccw-litellm (most reliable)
- Fallback: Python import with simpler syntax
- Increased timeout for pip show to 10s
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add renderEmbeddingPoolSidebar() for config summary display
- Show status, target model, strategy, and provider stats
- Improve visual hierarchy with icon indicators
- Update sidebar rendering for embedding-pool tab
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Simplify rotation section to show status only
- Add link to navigate to API Settings Embedding Pool
- Update loadRotationStatus to read from embedding-pool API
- Remove detailed modal in favor of API Settings config
- Add i18n translations for 'Configure in API Settings'
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add isFirstApiSettingsRender flag to track first load
- Force refresh ccw-litellm status on first page load
- Add ?refresh=true query param support to backend API
- Frontend passes refresh param to bypass backend cache
- Subsequent tab switches still use cache for performance
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add forceRefresh parameter to loadApiSettings() with caching
- Implement 60s TTL cache for ccwLitellmStatus check
- Tab switching now uses cached data (0 network requests)
- Clear cache after save/delete operations for data consistency
- Response time reduced from 100-500ms to <10ms on tab switch
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added search limit, content length, and extra files input fields in the CodexLens manager UI.
- Updated API request parameters to include new fields: max_content_length and extra_files_count.
- Refactored smart-search.ts to support new parameters with default values.
- Implemented result splitting logic to return both full content and additional file paths.
- Updated CLI commands to remove worker limits and allow dynamic scaling based on endpoint count.
- Introduced EmbeddingPoolConfig for improved embedding management and auto-discovery of providers.
- Enhanced search engines to utilize new parameters for fuzzy and exact searches.
- Added support for embedding single texts in the LiteLLM embedder.
Architecture refactoring for multi-provider rotation:
Backend:
- Add EmbeddingPoolConfig type with autoDiscover support
- Implement discoverProvidersForModel() for auto-aggregation
- Add GET/PUT /api/litellm-api/embedding-pool endpoints
- Add GET /api/litellm-api/embedding-pool/discover/:model preview
- Convert ccw-litellm status check to async with 5-min cache
- Maintain backward compatibility with legacy rotation config
Frontend:
- Add "Embedding Pool" tab in API Settings
- Auto-discover providers when target model selected
- Show provider/key count with include/exclude controls
- Increase sidebar width (280px → 320px)
- Add sync result feedback on save
Other:
- Remove worker count limits (was max=32)
- Add i18n translations (EN/CN)
- Update .gitignore for .mcp.json
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added functions to get and update CodexLens embedding rotation configuration.
- Introduced functionality to retrieve enabled embedding providers for rotation.
- Created endpoints for managing rotation configuration via API.
- Enhanced dashboard UI to support multi-provider rotation configuration.
- Updated internationalization strings for new rotation features.
- Adjusted CLI commands and embedding manager to support increased concurrency limits.
- Modified hybrid search weights for improved ranking behavior.
- Added token estimation and batching functionality in LiteLLMEmbedder to handle large text inputs efficiently.
- Updated embed method to support max_tokens_per_batch parameter for better API call management.
- Introduced new API routes for managing custom CLI endpoints, including GET, POST, PUT, and DELETE methods.
- Enhanced CLI history component to support source directory context for native session content.
- Improved error handling and logging in various components for better debugging and user feedback.
- Added internationalization support for new API endpoint features in the i18n module.
- Updated CodexLens CLI commands to allow for concurrent API calls with a max_workers option.
- Enhanced embedding manager to track model information and handle embeddings generation more robustly.
- Added entry points for CLI commands in the package configuration.
- Added JSON-based settings management in Config class for embedding and LLM configurations.
- Introduced methods to save and load settings from a JSON file.
- Updated BaseEmbedder and its subclasses to include max_tokens property for better token management.
- Enhanced chunking strategy to support recursive splitting of large symbols with improved overlap handling.
- Implemented comprehensive tests for recursive splitting and chunking behavior.
- Added CLI tools configuration management for better integration with external tools.
- Introduced a new command for compacting session memory into structured text for recovery.
- Updated embedding_manager.py to include backend parameter in model configuration.
- Modified model_manager.py to utilize cache_name for ONNX models.
- Refactored hybrid_search.py to improve embedder initialization based on backend type.
- Added backend column to vector_store.py for better model configuration management.
- Implemented migration for existing database to include backend information.
- Enhanced API settings implementation with comprehensive provider and endpoint management.
- Introduced LiteLLM integration guide detailing configuration and usage.
- Added examples for LiteLLM usage in TypeScript.
server.ts has a duplicate MODULE_FILES/MODULE_CSS_FILES array separate
from dashboard-generator.ts. The api-settings files were missing from
this duplicate list, causing renderApiSettings to be undefined.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create ccw-litellm Python package with AbstractEmbedder and AbstractLLMClient interfaces
- Add BaseEmbedder abstraction and factory pattern to codex-lens for pluggable backends
- Implement API Settings dashboard page for provider credentials and custom endpoints
- Add REST API routes for CRUD operations on providers and endpoints
- Extend CLI with --model parameter for custom endpoint routing
- Integrate existing context-cache for @pattern file resolution
- Add provider model registry with predefined models per provider type
- Include i18n translations (en/zh) for all new UI elements
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add context_cache MCP tool for caching files by @patterns:
- pattern-parser.ts: Parse @expressions using glob
- context-cache-store.ts: In-memory cache with TTL/LRU
- context-cache.ts: MCP tool with pack/read/status/release/cleanup
Simplify CLI cache options:
- --cache now uses comma-separated format instead of JSON
- Items starting with @ are patterns, others are text content
- Add --inject-mode option (none/full/progressive)
- Default: codex=full, gemini/qwen=none
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Introduced a new CodexLens Manager item in the dashboard for easier access.
- Implemented GPU management commands in the CLI, including listing available GPUs, selecting a specific GPU, and resetting to automatic detection.
- Enhanced the embedding generation process to utilize GPU resources more effectively, including batch size optimization for better performance.
- Updated the embedder to support device ID options for GPU selection, ensuring compatibility with DirectML and CUDA.
- Added detailed logging and error handling for GPU detection and selection processes.
- Updated package version to 6.2.9 and added comprehensive documentation for Codex Agent Execution Protocol.
Remove incorrect path separator conversion that caused directory creation
issues on Linux/WSL platforms. The function was converting forward slashes
to backslashes, which are treated as literal filename characters on Unix
systems rather than path separators.
Changes:
- Remove manual path normalization in getProjectSettingsPath()
- Rely on Node.js path.join() for cross-platform compatibility
- Fix affects both hooks-routes.ts and mcp-routes.ts
Impact:
- Linux/WSL: Fixes incorrect directory creation
- Windows: No behavior change, maintains correct functionality
Fixes project-level hook settings being saved to wrong location when
using Dashboard frontend on Linux/WSL systems.
Remove CommonJS require() calls that caused \"require is not defined\"
errors when scanning .workflow directories in ESM context.
Changes:
- Add unlinkSync and readdirSync to fs import statement
- Replace require('fs').unlinkSync() with direct unlinkSync() call
- Replace require('fs').readdirSync() with direct readdirSync() call
Fixes: Cannot scan directory .workflow/active: require is not defined
File: ccw/src/core/cache-manager.ts
- Fix cli.ts loadPackageInfo() to try root package.json first (../../package.json)
- Add build script and devDependencies to root package.json
- Remove ccw/package.json and ccw/package-lock.json (no longer needed)
- CodexLens: add config.json support for index_dir configuration
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix model installation detection using fastembed ONNX cache names
- Add embeddings_config table for model metadata tracking
- Fix hybrid search segfault by using single-threaded GPU mode
- Suppress INFO logs in JSON mode to prevent error display
- Add model dropdown filtering to show only installed models
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added accelerator and providers fields to SemanticStatus interface.
- Updated checkSemanticStatus function to retrieve ONNX providers and accelerator type.
- Introduced detectGpuSupport function to identify available GPU modes (CUDA, DirectML).
- Modified installSemantic function to support GPU acceleration modes and clean up ONNX Runtime installations.
- Updated package requirements in PKG-INFO for semantic-gpu and semantic-directml extras.
- Added new source files for GPU support and enrichment functionalities.
- Updated tests to cover new features and ensure comprehensive testing.
