- Update tagline: "universal AI profile manager for Claude Code"
- Add "Custom API Profiles" section for bring-your-own APIs
- Clarify built-in OAuth providers are not the only option
- Add note about Anthropic-compatible API extensibility
- Update Architecture section to highlight extensibility
- Add "Unlimited Profiles" to What CCS Gives You
- Update Japanese and Vietnamese READMEs with same messaging
- Add kaitranntt/ccs-docs as git submodule under docs/
- Update README links to point to docs.ccs.kaitran.ca
- Remove old local docs (migrated to Mintlify MDX format)
Phase 3 of README restructure complete.
- reduce main README from ~1070 to ~250 lines
- add dashboard screenshots (analytics, api_profiles, cliproxy)
- update Vietnamese and Japanese translations to match new structure
- add light/dark theme analytics screenshots
- Add examples for codex provider authentication
- Clarify that gemini, codex, and agy are different providers
- Show account listing and switching examples for each provider
- Add findAccountByQuery() to search accounts by nickname/email/id
- Add --accounts flag to list all accounts for a provider
- Add --use <name> flag to switch between accounts
- Filter CCS-specific flags from Claude CLI args
- Update help documentation with new multi-account commands
- Rewrite health-service.ts with 20+ comprehensive checks in 5 groups
(System, Configuration, Profiles & Delegation, System Health, CLIProxy)
- Add async support for port checking functionality
- Create new health-check-item.tsx component with collapsible design
- Redesign health.tsx with professional grouped layout, hero section,
summary stats, and issues panel with actionable fix commands
- Update use-health.ts with HealthGroup type support
- Add development server documentation to CLAUDE.md
- Fix README.md dashboard command (ccs config) and port info
- Update all documentation to reflect React 19 dashboard
- Document new tooling: Bun, Vite, semantic release
- Add TypeScript strict mode and type coverage details
- Update architecture with WebSocket and modern stack
- Revise project roadmap with current implementation status
- Add `ccs cliproxy create/list/remove` commands for variant management
- Interactive wizard with provider/model selection from catalog
- Settings file auto-generated with all 6 ANTHROPIC_* env fields
- Fix `ccs api create` to include all 4 model fields (was missing 3)
- Fix `--config` flag to save to correct variant settings file
- Remove paid tier badge from AGY models (all free via Antigravity)
- Add settings file format example to README for CLIProxy variants
- Add 22 unit tests for cliproxy command validation and config handling
- Replace before()/after() with beforeAll()/afterAll()
- Remove this.timeout() calls (unsupported by bun)
- Update package.json scripts to use bun test
- Fix error message regex for cross-runtime compatibility
- Skip integration tests requiring network/child process mocking
- Format source files with prettier
- Add profile priority order (CLIProxy → settings → account → default)
- Document CLIProxy profile with OAuth auth, port 8317, binary location
- Include model mappings for gemini, codex, agy providers
- Add cliproxy/auth/ to profile-specific data
- Link to CLIProxyAPI GitHub repo
- Reorganized README structure with collapsible sections for better readability
- Added comprehensive GLMT experimental warnings and troubleshooting guides
- Updated installation instructions with traditional vs npm options
- Added parallel workflow examples and detailed feature comparisons
- Enhanced documentation with proper acknowledgments and security limits
- Standardized language and formatting across all README variants
- Move GLMT section to proper position in English README
- Add missing npm badge to Vietnamese README
- Add GLMT and Architecture sections to all translations
- Update configuration examples with glmt profile
- Add Windows Developer Mode support documentation
- Fix documentation links across all language versions
- Add prominent NOT PRODUCTION READY warning for GLMT
- Update GLM vs GLMT comparison to reflect experimental nature
- Tone down overconfident marketing language in tool support
- Add honest failure rates for streaming functionality
- Reference CCR hustle with Transformer of Bedolla as alternative
- Update thinking keywords to reflect inconsistent behavior
Remove references to deprecated CCS_GLMT_FORCE_ENGLISH, CCS_GLMT_THINKING_BUDGET, and CCS_GLMT_STREAMING environment variables that were removed in v3.4.3.
Changes:
- README.md: Update GLMT environment variable documentation to reflect current intelligent control system
- tests/unit/glmt/locale-enforcer.test.js: Remove outdated test scenario for removed environment variable
- docs/glmt-controls.md: Rewrite documentation to describe new automatic control mechanisms
The GLMT component now uses intelligent, automatic controls instead of manual environment variable configuration.
- Add GLMT proxy server for GLM model routing
- Add GLMT transformer for output format conversion
- Update CLI with new proxy and transformer commands
- Add comprehensive test suite for new functionality
- Update documentation and architecture guides
- Bump version and update changelog
Phase 1: Multi-profile shared data via symlinks
Added:
- SharedManager class for symlink orchestration (bin/shared-manager.js)
- Auto-migration from ~/.claude/ to ~/.ccs/shared/ on first run
- Shared directories: commands/, skills/, agents/
- Windows fallback: copies dirs if symlinks fail
Fixed:
- Migration logic now detects empty directories
- Previously skipped migration when postinstall created empty dirs
- Now properly copies from ~/.claude/ when shared dirs are empty
Changed:
- Instance initialization symlinks to shared dirs instead of copying
- Postinstall creates ~/.ccs/shared/ structure automatically
- All implementations (Node.js, bash, PowerShell) updated for consistency
- Help text includes agents/ in shared data section
Technical:
- Profile-specific data remains isolated (settings, sessions, todolists, logs)
- Migration is idempotent: safe to run multiple times
- Cross-platform symlink support with graceful fallback
Closes#4
- Add kimi profile support alongside existing glm and default profiles
- Create base-kimi.settings.json configuration template
- Update all installation methods (npm, Unix, Windows) to auto-create Kimi settings
- Enhance documentation with Kimi examples and API setup instructions
- Update version to 2.5.0 with comprehensive changelog
- Add Kimi detection logic in install scripts for seamless migration
- Maintain backward compatibility with existing GLM and Claude profiles
- fix color detection for cross-platform TTY compatibility
- enhance help command with npm-specific content and npx examples
- remove --install/--uninstall flags pending .claude/ integration testing
- update version across all files and documentation
- preserve implementation code for future release readiness
BREAKING CHANGE: None - fully backward compatible
Adds comprehensive custom path support for Claude CLI installations:
- CCS_CLAUDE_PATH environment variable for custom locations
- Smart detection: env var → PATH → common locations fallback
- Enhanced error messages with platform-specific solutions
- Security validation preventing command injection
- D drive Windows installation support
- WSL access to Windows installations
- Performance optimized (<15ms overhead)
- Complete documentation and troubleshooting guides
Technical implementation:
- Added detect_claude_cli() / Find-ClaudeCli functions
- Added validate_claude_cli() / Test-ClaudeCli security validation
- Updated both bash (ccs) and PowerShell (ccs.ps1) executables
- Fixed PowerShell multi-line string syntax errors with here-strings
- Updated all installation scripts and documentation
- Bumped version to v2.3.0
Tested across all platforms with 90% test suite pass rate.
Resolves D drive installation issues for Windows users.
- Add installation function for commands and skills
- Implement --install flag in both bash and PowerShell scripts
- Update documentation with installation instructions
- Add comprehensive test suites for installation functionality
- Refactor delegation command to simplify profile handling
- Remove haiku references, focus on GLM delegation model
- Update usage examples and documentation
kaitranntt