- Add missing Jina provider translations to English base files
- Add jinaProvider, jinaApiKeyLabel, jinaApiKeyPlaceholder to settings.json
- Add jinaApiKeyRequired validation message to settings.json
- Add jinaConfigMissing error message to embeddings.json
- Complete missing translations in ca, id, pt-BR, ru, zh-TW locales
- All translation checks now pass successfully
- Add "jina" to EmbedderProvider types in 5 files
- Add Jina model profiles to embeddingModels.ts
- Add Jina case to getDefaultModelId function
- Add "jina" to codebaseIndexModelsSchema in packages/types
- Add Jina provider option to CodeIndexPopover UI
- Add Jina validation case for form validation
Fixes TypeScript compilation errors for Jina embedding provider
- Add "jina" to EmbedderProvider type definitions in 5 files
- Add Jina model profiles (jina-embeddings-v4, jina-embeddings-v3, jina-clip-v2)
- Add Jina case to getDefaultModelId function
- Update Zod schema in packages/types to include "jina"
- Fixes TypeScript compilation errors for Jina embedding provider
- Add jinaConfigMissing translation to all backend embeddings.json files
- Add jinaProvider, jinaApiKeyLabel, jinaApiKeyPlaceholder, and jinaApiKeyRequired translations to all frontend settings.json files
- Ensures complete internationalization support for Jina embedding provider feature
- All translations verified with check-translations script
feat: increase Claude Code default max output tokens from 8k to 16k
- Changed CLAUDE_CODE_DEFAULT_MAX_OUTPUT_TOKENS from 8000 to 16000
- Users can still lower it to 8k via environment variable if needed
- Addresses issue #6125 regarding output token limits
Co-authored-by: Roo Code <roomote@roocode.com>
- Add todo list initialization and tracking throughout the review workflow
- Replace all MCP GitHub server calls with gh CLI commands
- Fix duplicate step numbering issue
- Update best practices and common mistakes documentation
- Add notes about GitHub CLI limitations for inline comments
* feat: add prompt caching support for LiteLLM (#5791)
- Add litellmUsePromptCache configuration option to provider settings
- Implement cache control headers in LiteLLM handler when enabled
- Add UI checkbox for enabling prompt caching (only shown for supported models)
- Track cache read/write tokens in usage data
- Add comprehensive test for prompt caching functionality
- Reuse existing translation keys for consistency across languages
This allows LiteLLM users to benefit from prompt caching with supported models
like Claude 3.7, reducing costs and improving response times.
* fix: improve LiteLLM prompt caching to work for multi-turn conversations
- Convert system message to structured format with cache_control
- Handle both string and array content types for user messages
- Apply cache_control to content items, not just message level
- Update tests to match new message structure
This ensures prompt caching works correctly for all messages in a conversation,
not just the initial system prompt and first user message.
* fix: resolve TypeScript linter error for cache_control property
Use type assertion to handle cache_control property that's not in OpenAI types
