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 comprehensive tests for getProjectDisplayName function
- Test various path structures including worktrees, nested projects, and edge cases
- Include regression tests for the reported bug cases
- Create separate utility file for better testability
Fixes session stats display where wrong fragments were shown
Related to: #348 (quota display), #103 (context display)
Replace session.projectPath.split('/').pop() with getProjectDisplayName()
to ensure the actual leaf folder name is shown instead of incorrect fragments.
Example fixes:
- /home/user/projects/my-app now shows "my-app" instead of "app"
- /home/user/workspaces/repo-name/worktrees/feature-branch now shows "feature-branch" instead of "branch"
Addresses potential issues with project name display in analytics dashboard.
Related to: #348 (quota display), #103 (context display)
Replace session.projectPath.split('/').pop() with getProjectDisplayName()
to ensure the actual leaf folder name is shown instead of incorrect fragments.
Example fixes:
- /home/user/projects/my-app now shows "my-app" instead of "app"
- /home/user/workspaces/repo-name/worktrees/feature-branch now shows "feature-branch" instead of "branch"
Addresses potential issues with project name display in analytics dashboard.
Related to: #348 (quota display), #103 (context display)
- 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
Add cliproxy.backend config field to choose between CLIProxyAPI (original)
and CLIProxyAPIPlus backends. Includes CLI --backend flag, Dashboard toggle,
and provider validation to block Kiro/ghcp on original backend.
The previous test relied on client socket receiving close event from
server-side destroy, which is timing-dependent and flaky in CI.
New approach:
- Verify stop() behavior directly via getPort() returning null
- Test what we control (server state) not what we observe (client state)
- Remove timing-dependent assertions
- Faster and more reliable (83ms vs 1000ms+ timeout)
- Fix connection tracking test: wait for 'close' event instead of only
checking socket.destroyed (more reliable in CI environments)
- Increase timeout from 500ms to 1000ms for CI latency
- Add proper socket cleanup after test
- Merge dev changes: add projectId parameter to registerAccount()
- Add Pause icon with amber color for paused accounts
- Show styled "PAUSED" badge instead of plain error text
- Distinguish paused state from other errors visually
- Check isAccountPaused() before readAuthData() in fetchAccountQuota()
- Return "Account is paused" instead of confusing "Auth file not found"
- Improves UX by explaining why quota fetch fails for paused accounts
