- Add backend parameter to version cache functions (read/write/path)
- Store cache at bin/{backend}/.version-cache.json instead of shared location
- Pass backend through checkForUpdates() and BinaryManager
- Add refetchType: 'all' to force immediate query refetch on backend change
- Add cliproxy-server-config query invalidation for consistency
- Add ProxyStatusWidget to Settings/Proxy page for quick start/stop access
- Disable backend selection when proxy is running with clear warning
- Removes UX friction: no need to navigate to CLIProxy page to stop instance
- Shows amber alert explaining why backend switch is blocked
User can now:
1. See proxy status directly in Settings
2. Stop proxy from Settings page
3. Change backend only when proxy is stopped
- Add useUpdateBackend mutation hook that invalidates related queries
- Reduce update-check stale time from 1hr to 5min + enable refetchOnWindowFocus
- Settings proxy page now uses mutation hook for proper query invalidation
- Make all CLIProxy labels dynamic based on backendLabel from API:
- cliproxy-header.tsx: page title
- app-sidebar.tsx: nav item label
- cliproxy-stats-overview.tsx: both offline and running descriptions
- model-preferences-grid.tsx: card description
- settings proxy section: descriptions for local/remote modes
- Fix API route to use DEFAULT_BACKEND constant instead of hardcoded 'plus'
Ensures backend switching in Settings immediately reflects in all CLIProxy pages.
- Add backend/backendLabel fields to CliproxyUpdateCheckResult
- Update proxy-status-widget to show backendLabel from API
- Update cliproxy page header to use backendLabel
Dashboard now shows "CLIProxy" or "CLIProxy Plus" based on configured
backend in config.yaml instead of hardcoded "CLIProxy Plus".
- Add backend param to isCLIProxyInstalled(), getCLIProxyPath(),
getInstalledCliproxyVersion(), installCliproxyVersion()
- Update getBinaryStatus() to pass backend to all helper functions
- Add getBackendLabel() helper for dynamic CLI messages
- Replace hardcoded "CLIProxy Plus" strings with dynamic labels
- Pass --backend flag through install/update command handlers
- Import CLIProxyBackend type from types.ts instead of redefining
Setting `cliproxy.backend: original` in config.yaml now correctly
uses the original backend for version pins and binary operations.
- Change requiresApiKey from optional to required boolean in CLI
- Add requiresApiKey: true to all existing presets for consistency
- Document 'ollama' placeholder as sentinel value in code comment
- Add trailing newline to ollama.svg
- Change CLI noApiKey to requiresApiKey to match UI convention
- Set apiKey='ollama' instead of empty string for local Ollama
- Align ollama-cloud descriptions between CLI/UI
- Keep https://ollama.com endpoint for direct API access
- Add Ollama SVG logo to ui/public/icons/
- Add icon property to both ollama and ollama-cloud presets
- Make API key field optional for local Ollama (show input with hint)
- Update placeholder: "Optional - only if auth is enabled"
- Allows power users with Ollama auth configured to provide key
- Add ollama (local) and ollama-cloud presets to UI provider-presets.ts
- Update profile-create-dialog to handle requiresApiKey: false
- Show "No API Key Required" info box for local Ollama
- Add --api-key ignored warning to CLI for local Ollama preset
- Add ollama-cloud to CLI help text preset list
Fixes edge cases identified in PR review:
- UI dashboard now has parity with CLI Ollama support
- Conditional API key validation in profile creation form
Local Ollama doesn't require an API key, but the CLI was still
prompting for one. This adds a `noApiKey` flag to provider presets
to mark providers that don't need authentication.
- Add `noApiKey?: boolean` property to ProviderPreset interface
- Set `noApiKey: true` for local Ollama (no key needed)
- All other presets unchanged (default to requiring API key)
- Skip API key prompt and show info message when noApiKey is true
Co-Authored-By: Claude <noreply@anthropic.com>
Local Ollama doesn't require an API key, but the CLI was still
prompting for one. This adds a `requiresApiKey` property to provider
presets to control whether the API key step is required.
- Add `requiresApiKey` property to ProviderPreset interface
- Set `requiresApiKey: false` for local Ollama (no key needed)
- Set `requiresApiKey: true` for OpenRouter and Ollama Cloud
- Skip API key prompt and show info message when not required
Co-Authored-By: Claude <noreply@anthropic.com>
Update README.md to include:
- Ollama and Ollama Cloud in the Built-in Providers table
- Ollama integration note with setup instructions
- ccs ollama in Basic Commands section
- Ollama example in Parallel Workflows
Ref: https://github.com/kaitranntt/ccs/pull/354
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>
- Add defensive type guard in misc-routes.ts to prevent runtime crash
if malformed tier_defaults object is passed to PUT /api/thinking
- Extract VALID_THINKING_TIERS constant to thinking-validator.ts
to eliminate duplication across validation code
- Export constant from cliproxy barrel file
Addresses P2/P3 items from PR #351 review
- Fix config-generator test assertion for parseUserApiKeys
- Update model-catalog tests to expect codex provider
- Remove outdated codex unsupported test from model-config
Add maxLevel field to ThinkingSupport interface to cap reasoning
effort at model's maximum supported level. This fixes Issue #344
where gpt-5-mini fails with xhigh reasoning (only supports high).
- Add Codex provider to model catalog with gpt-5.2-codex and gpt-5-mini
- Add capLevelAtMax() and capEffortAtModelMax() for runtime capping
- Update UI presets with new Codex models and tier mappings
Changed layout from vertical stack (space-y-1) to horizontal flex
with gap (flex items-center gap-2) to properly space the Port label
and input field in the local proxy settings card.
Reverts to the original guided output format with:
- Visual hierarchy with emojis and separators
- Priority tags (High/Medium/Low)
- Security and code quality checklists
- Ultrathink directive
- Reaction comments for /review triggers
- Model signature in review footer
claude-code-action validates that anthropic_api_key is non-empty before
running. CLIProxy ignores this value and uses ANTHROPIC_AUTH_TOKEN for
actual authentication.
- Use anthropics/claude-code-action@v1 directly
- Remove ccs-reviewer wrapper dependency
- Match pr-review-comprehensive.yml pattern
- Keep CLIProxy env vars for model routing
- Restore comprehensive allowedTools for posting
- Remove duplicate CLIProxyBackend type from platform-detector.ts (import from types.ts)
- Add warning for invalid --backend CLI value (was silently ignored)
- Show toast notification when backend change blocked by running proxy
- Migrate from deprecated CLIPROXY_FALLBACK_VERSION to getFallbackVersion()
- Add comprehensive JSDoc for backend API endpoints
kaitranntt