Updated default Claude model IDs from outdated v4 (May 2025) to
current v4.5 versions matching model-catalog.ts:
- ANTHROPIC_MODEL: claude-sonnet-4-5-20250929
- ANTHROPIC_DEFAULT_OPUS_MODEL: claude-opus-4-5-20251101
- ANTHROPIC_DEFAULT_SONNET_MODEL: claude-sonnet-4-5-20250929
- ANTHROPIC_DEFAULT_HAIKU_MODEL: claude-haiku-4-5-20251001
Fixes "unknown provider for model" 400 errors when users add
Claude accounts and switch to Haiku tier.
The claude provider was fully registered in the codebase (types,
OAuth config, auth port 54545, model catalog, CLI routes) but the
required base config file was missing, causing "Base config not
found for provider 'claude'" error when running `ccs claude --add`.
Root cause: execClaudeWithProxy() was ignoring ANTHROPIC_MODEL from
user settings and always using hardcoded 'glm-4.6'.
Changes:
- Read model from user's settings file in GLMT proxy flow
- Update default model to glm-4.7 in base configs (matches presets)
- Update fallback models in transformer/response-builder
Closes#358
Co-Authored-By: Claude <noreply@anthropic.com>
Add support for Ollama as a provider in CCS, enabling users to use
local Ollama models (qwen3-coder, gpt-oss:20b, gpt-oss:120b) and
Ollama Cloud models (glm-4.7:cloud, qwen3-coder:480b).
Changes:
- Add base-ollama.settings.json for local Ollama (localhost:11434)
- Add base-ollama-cloud.settings.json for ollama.com cloud API
- Add 'ollama' and 'ollama-cloud' presets to provider-presets.ts
- Update help documentation in api-command.ts and help-command.ts
Usage:
ccs api create --preset ollama # Local Ollama
ccs api create --preset ollama-cloud # Ollama Cloud
Ref: https://github.com/kaitranntt/ccs/issues/353
Co-Authored-By: Claude <noreply@anthropic.com>
- rename base-copilot.settings.json to base-ghcp.settings.json
- add kiro and ghcp to variant adapter providers list
- update provider display names in config generator
- Add base-kiro.settings.json with default Kiro models
- Add base-copilot.settings.json with default Copilot models
- Update config-generator for new provider sections
- Extend CLIProxyProvider type with kiro and copilot
- Removed MAX_THINKING_TOKENS (8191) limit for Claude models via agy.
- Updated default agy haiku model to gemini-3-flash-preview.
- Updated unit tests to match new model expectations.
Add iFlow as a new OAuth-based provider for CLIProxy.
Changes:
- Add config/base-iflow.settings.json with iFlow provider configuration
- Add iFlow to CLIProxyProvider type
- Add iFlow OAuth config (authUrl, scopes, authFlag)
- Add iFlow to provider display names, auth prefixes, and type values
- Update config-generator to support iFlow provider
- Update base-qwen.settings.json models (qwen3-coder-plus)
Co-authored-by: kaitranntt <kaitran.ntt@gmail.com>
- Update base-kimi.settings.json with model fields
- Update install.sh KIMI_MODEL variable
- Update postinstall.js template and migration to add model fields
- Migration now adds model fields instead of removing them (v5.5.0)
Add 'qwen' as new CLIProxy OAuth provider with --qwen-login flag.
Support qwen3-coder model with base config at config/base-qwen.settings.json.
Register qwen OAuth endpoints and token prefix handling.
Update help documentation across all CLI entry points.
Implements issue #29
- Add unified CLIProxy config supporting all providers concurrently
- Move CLIProxy files to ~/.ccs/cliproxy/ subdirectory
- Use flat auth directory structure for OAuth tokens
- Add provider-specific URL routing via /api/provider/{provider}
- Add base settings templates for gemini and codex
- Fix model registration with proper auth file discovery
Enables users to run `ccs gemini` and `ccs codex` concurrently
without config conflicts.
- Remove 5 deprecated model fields from Kimi settings causing auth failures
- Update config/base-kimi.settings.json template with clean configuration
- Add automatic migration in scripts/postinstall.js to remove deprecated fields
- Preserve user API keys and custom settings during migration
- Update CHANGELOG.md with v4.1.1 and v4.1.2 entries
- Bump version to 4.1.2 across all files and installers
Fixes authentication issues with Moonshot AI (Kimi) API due to deprecated
model parameters that are now rejected by the service.
- 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
- Add ANTHROPIC_SMALL_FAST_MODEL to all Kimi configuration templates
- Update installation scripts (npm, Unix, Windows) to include SMALL_FAST_MODEL
- Ensure Kimi API configuration matches official documentation format
- Bump version to 2.5.1 with updated changelog
Files updated:
- config/base-kimi.settings.json: Add SMALL_FAST_MODEL
- installers/install.sh: Update Unix template creation
- installers/install.ps1: Update PowerShell template creation
- scripts/postinstall.js: Update npm postinstall script
- All version files: Bump to 2.5.1
- 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
This commit fixes version management and argument parsing issues across
both Windows and Linux/macOS platforms, achieving 100% test coverage.
Changes:
- Add VERSION file installation to both installers (install.sh, install.ps1)
- Fix version/help command detection when using 'powershell -File' syntax
- Rename PowerShell param from $Profile to $ProfileOrFlag for clarity
- Add $FirstArg detection to check both ProfileOrFlag and RemainingArgs
- Create comprehensive edge case test suites for both platforms:
* tests/edge-cases.ps1 - 31 tests for Windows (100% pass)
* tests/edge-cases.sh - 37 tests for Linux/macOS (100% pass)
- Fix multiline regex matching in tests for error messages
- Update test expectations to match platform-specific behavior
- Reorganize project structure:
* Move installers to installers/ directory
* Add scripts/ directory for version management
* Add config/ directory for configuration templates
* Add docs/ directory for documentation
Test Results:
- Windows (PowerShell): 31/31 tests passing (100%)
- Linux/macOS (Bash): 37/37 tests passing (100%)
Breaking Changes: None
- Installers moved but GitHub URLs updated in README files
- All existing functionality preserved
Co-authored-by: Claude Code <claude@anthropic.com>
kaitranntt