- add a shared command catalog for root help and completion routing
- replace shell-local completion logic with a hidden __complete backend
- add topic help and parity tests for router, help, and completion coverage
- update CLI, API, route, and dashboard surfaces to recognize the Codex runtime target
- normalize persisted codex targets back to claude so runtime-only behavior stays truthful
- add regression coverage for help text, route parsing, and profile storage normalization
Refs #773
- centralize Anthropic model-key [1m] handling in shared helpers
- keep dashboard preset and editor writes consistent across all Claude tiers
- add explicit api create and help guidance for --1m/--no-1m
Refs #789
- replace the Discord-only config with multi-channel official channels selection
- add Telegram token handling and iMessage platform-aware runtime gating
- expand CLI, dashboard, and tests for Telegram, Discord, and iMessage
Refs #783
- add runtime injection for official Discord Channels on eligible native Claude sessions
- add CLI and dashboard configuration plus secure token handling
- add tests for launch planning, token sync, and config routing
Refs #783
- Add --bare flag to `ccs auth create` to skip shared symlinks
(commands/, skills/, agents/, settings.json). Bare profiles are
clean instances without ClaudeKit or other global extensions.
`ccs sync` respects bare flag and skips re-linking.
- Add MCP server sync from global ~/.claude.json to instances.
Claude Code stores MCP config in ~/.claude.json (not settings.json),
which was invisible to CCS profiles using CLAUDE_CONFIG_DIR isolation.
Selective copy of mcpServers key only (not OAuth sessions/caches).
`ccs sync` refreshes MCP servers across all non-bare instances.
Closes#691Closes#692
- Add llamacpp provider preset to provider-presets.ts
- Add base-llamacpp.settings.json configuration
- Update help-command.ts with ccs llamacpp documentation
- Update UI provider presets for dashboard parity
llama.cpp is a popular C++ inference engine for LLaMA models.
This complements existing Ollama support for local inference.
Usage: ccs llamacpp (requires llama.cpp server on port 8080)
Closes#690
Support native Anthropic API keys (sk-ant-...) via `ccs api create --preset anthropic`.
Profiles use ANTHROPIC_API_KEY env var without BASE_URL, letting Claude CLI
authenticate natively with x-api-key header instead of proxy Bearer token.
- Add anthropic preset to provider catalog
- Branch profile-writer env structure (native vs proxy)
- Add validateAnthropicKey() preflight with x-api-key header
- Auto-detect api.anthropic.com URL in interactive flow
- Fix hasApiKey/isConfigured to recognize ANTHROPIC_API_KEY
- Update delegation-validator for native mode profiles
- Add Droid target API key fallback (ANTHROPIC_API_KEY)
Closes#688
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- add multi-target help examples for ccsd codex and ccsd agy
- document per-profile target defaults for API and CLIProxy profiles
- include dashboard parity notes for target configuration
- replace issue #622/#619 references with issue #509 across CLI and dashboard
- shorten acknowledgement phrase to "I ACCEPT AGY RISK" for faster typing
- rename acknowledgement payload field to reviewedIssue509 and update tests
- create config/base-km.settings.json for API-key Kimi users
- rename preset id 'kimi' to 'km' in CLI and UI provider presets
- add 'ccs km' to help text API section, keep 'ccs kimi' for OAuth
- add --km delegation flag for API-key mode, --kimi stays for OAuth
- add kimi to UI CLIPROXY_PROVIDERS, assets, colors, names, device code
Tam Nhu Tran