* feat: re-enable auto-update for npm with @kilocode/cli
- Re-enable auto-upgrade but only for npm installations
- Update method detection to check for @kilocode/cli
- Update upgrade commands to use @kilocode/cli for npm/pnpm/bun
- Fetch latest version from @kilocode/cli on npm registry
* Also allow pnpm and bun
GPT models accessed through Kilo Gateway were missing the
'include: ["reasoning.encrypted_content"]' option, causing
organization_id mismatch errors when encrypted reasoning content
was passed back in multi-turn conversations.
- Add reasoningSummary and include options to effortVariants for Kilo Gateway
- Extend options() condition to include @kilocode/kilo-gateway npm package
Enable reasoning effort level cycling (Ctrl+T) for Claude models through
Kilo Gateway by:
- Adding @kilocode/kilo-gateway to sdkKey() to use 'openrouter' key for
provider options
- Adding dedicated variants() case for Claude/Anthropic models with full
effort levels (none, minimal, low, medium, high, xhigh)
- Supporting grok-3-mini reasoning variants through Kilo Gateway
- Fixing smallOptions() to use correct reasoning.effort format
OpenRouter maps effort levels to budget_tokens percentages:
- xhigh: 95%, high: 80%, medium: 50%, low: 20%, minimal: 10%, none: 0%
- Update CONTRIBUTING.md with simplified Kilo CLI-specific content
- Add CODE_OF_CONDUCT.md matching kilocode community standards
- Add PRIVACY.md for Kilo CLI
- Update LICENSE copyright to Kilo Code
- Update SECURITY.md with Kilo CLI references
- Update PR template with kilocode's detailed format
- Simplify model visibility to return true by default
- Rename review.toggle command to fileTree.toggle
- Use props.directory for session filtering in SortableWorkspace
Wrap callback execution in a promise microtask so synchronous errors flow
through the existing `.catch()` and the in-flight entry is reliably cleaned
up. Update tests to await the microtask before asserting call count.
Add an in-flight cache entry for getClient to avoid repeated token
validation and client recreation, and use a single ttl constant for
token and org lookups.