* feat: add OpenRouter embedding provider support
Implement comprehensive OpenRouter embedding provider support for codebase indexing with the following features:
- New OpenRouterEmbedder class with full API compatibility
- Support for OpenRouter's OpenAI-compatible embedding endpoint
- Rate limiting and retry logic with exponential backoff
- Base64 embedding handling to bypass OpenAI package limitations
- Global rate limit state management across embedder instances
- Configuration updates for API key storage and provider selection
- UI integration for OpenRouter provider settings
- Comprehensive test suite with mocking
- Model dimension support for OpenRouter's embedding models
This adds OpenRouter as the 7th supported embedding provider alongside OpenAI, Ollama, OpenAI-compatible, Gemini, Mistral, and Vercel AI Gateway.
* Add translation key
* Fix mutex double release bug
* Add translations
* Add more translations
* Fix failing tests
* code-index(openrouter): fix HTTP-Referer header to RooCodeInc/Roo-Code; i18n: add and wire OpenRouter Code Index strings; test: assert default headers in embedder
---------
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
* fix: handle current directory path "." correctly in codebase_search tool
- Fix path filtering logic in QdrantVectorStore.search() to properly handle current directory representations
- When directoryPrefix is ".", "./", "", or similar, set filter to undefined to search entire workspace
- Add comprehensive tests covering various current directory path formats including cross-platform support
- Resolves issue where codebase_search with path="." returned no results
Fixes#6514
* fix: normalize directory prefix handling in Qdrant vector store
* fix: normalize paths starting with './' and fix OS-dependency issue
- Use forward slash for splitting after toPosix() conversion
- Remove leading './' from paths like './src' to normalize them to 'src'
- Update test expectations to match correct behavior
* refactor: use path.posix.normalize instead of custom toPosix method
- Replaced directoryPrefix.toPosix() with path.posix.normalize()
- Added proper handling of backslashes before normalization
- Updated test mock to include posix.normalize method
- All tests passing (381 tests in code-index service)
* refactor: address review comments - improve path normalization
- Keep check for './' after normalization as path.posix.normalize('./') returns './'
- Use actual Node.js path.posix implementation in tests instead of custom mock
- Apply path.posix.normalize to cleanedPrefix for consistency
All 381 code-index tests pass
* fix: apply path.posix.normalize when cleaning prefix to avoid redundant normalization
Addresses review comment from @mrubens to normalize the path at line 385 instead of normalizing twice
* fix: correct current directory detection logic
The issue was that the condition checked for an empty string after normalization,
but path.posix.normalize('') actually returns '.', not ''. This caused the
current directory check to fail when an empty string was passed.
Removed the redundant empty string check since normalize('') returns '.' which
is already handled by the first condition.
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: hannesrudolph <hrudolph@gmail.com>
* fix: recover from error state when Qdrant becomes available
- Add recoverFromError method to CodeIndexManager to clear error state and reset internal services
- Update startIndexing handler to check for error state and recover before initialization
- Add comprehensive tests for error recovery functionality
Fixes#6660
* fix: address PR review comments for code indexing error recovery
- Add race condition protection for multiple rapid clicks on Start Indexing button
- Add error handling for setSystemState in recoverFromError method
- Enhance JSDoc documentation for recoverFromError method
- Add test cases for recoverFromError idempotency and error handling
* refactor: move error recovery logic into startIndexing method
- Moved error recovery from webviewMessageHandler into CodeIndexManager.startIndexing()
- This ensures error recovery happens whenever indexing is started, not just from UI
- Added race condition prevention flag within CodeIndexManager
- Simplified webviewMessageHandler by removing error state checking
- The startIndexing method now automatically recovers from error state before proceeding
* fix: remove await from startIndexing calls and update JSDoc
- startIndexing should never be awaited as it's a long-running background process
- Added JSDoc warning to never await this method
- Updated webviewMessageHandler to not await startIndexing calls
* fix: use platform-agnostic paths in code-index manager tests for Windows compatibility
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* feat: Implement code indexing support multi-folder workspaces similar to task history
* fix: add missing mock for onDidChangeActiveTextEditor in tests
* fix: add error message when no workspace folder is open for code indexing
- Add 'Indexing requires an open workspace folder' error message in orchestrator.ts
- Replace hardcoded error string with translatable message using i18n
- Add translations for the error message in all 18 supported languages
- Ensures proper error handling when users attempt code indexing without a workspace
* fix: add workspace folder checks for code indexing operations
- Add null checks for codeIndexManager in webviewMessageHandler
- Show translated error message when no workspace folder is open
- Prevents crashes when users try to use indexing features without a workspace
- Uses existing translation key from orchestrator
* Update src/i18n/locales/ca/embeddings.json
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* feat: add Mistral embedding provider with OpenAI Compatible Wrapper
- Implement MistralEmbedder class using OpenAI-compatible API
- Add comprehensive unit tests with 100% coverage
- Update type definitions for Mistral provider support
- Integrate Mistral option in UI components and configuration
- Add internationalization support for Mistral provider
- Fix API key storage and retrieval for embedding providers
- Update service factory to support Mistral embeddings
- Add proper error handling and validation
This implementation allows users to use Mistral's embedding models
through the existing OpenAI-compatible wrapper approach, providing
a seamless integration experience.
* feat: add Mistral embedding provider support
- Implement MistralEmbedder class with API integration
- Add Mistral models to embedding model configurations
- Update UI to include Mistral provider option
- Add comprehensive unit tests for Mistral embedder
- Update type definitions and interfaces
- Add internationalization support for Mistral provider
* fix: add missing translations for Mistral embedding provider
* fix: address PR review feedback - improve translations and add clarifying comment
feat: add batch limiting to code indexer to control memory usage
- Add MAX_PENDING_BATCHES constant (20) to limit concurrent batches
- Implement backpressure mechanism to pause file parsing when limit reached
- Prevent memory overflow during large codebase indexing
* feat: add global rate limiting for OpenAI-compatible embeddings
- Implement shared rate limit state across all embedder instances
- Add exponential backoff (5s base, up to 5 minutes max)
- Track consecutive rate limit errors with auto-reset after 60s
- Add thread-safe mutex for concurrent access
- Remove verbose logging to prevent log flooding during retries
- Add comprehensive test coverage for rate limiting behavior
This prevents multiple parallel batches from overwhelming APIs with
restrictive rate limits by coordinating delays globally.
* fix: restore original logging while keeping rate limit logging silent
- Restored all original console.warn and console.error calls that were inadvertently removed
- Only the rate limit retry warning remains silent (no console output)
- Fixed test expectation to use correct error variable
- All existing logging behavior is preserved
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
fix(embeddings): translate error messages before sending to UI
- Import t() function from i18n module
- Wrap error messages with t() translation function in _initializeEmbedder()
- Ensures proper localization of error messages in the UI
- Falls back to original message if no translation exists
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
* fix: add embedder validation to prevent misleading status indicators (#4398)
* fix: address PR feedback and fix critical issues
- Fixed settings-save flow to save before validation
- Fixed Error constructor usage in scanner.ts
- Fixed segment identification in file-watcher.ts
- Added missing translation keys for embedder validation errors
* fix: add missing Ollama translation keys
- Added missing ollama.title, description, and settings keys
- Fixed translation check failure in CI/CD pipeline
- Synchronized all 17 non-English locale files
* feat: add proactive embedder validation on provider switch
- Validate embedder connection when switching providers
- Prevent misleading 'Indexed' status when embedder is unavailable
- Show immediate error feedback for invalid configurations
- Add comprehensive test coverage for validation flow
This ensures users get immediate feedback when configuring embedders,
preventing confusion when providers like Ollama are not accessible.
* fix: improve error handling and validation in code indexing process
* refactor: extract common embedder validation and error handling logic
- Created shared/validation-helpers.ts with centralized error handling utilities
- Refactored OpenAI, OpenAI-Compatible, and Ollama embedders to use shared helpers
- Eliminated duplicate error handling code across embedders
- Improved maintainability and consistency of error handling
- Fixed test compatibility in manager.spec.ts
- All 2721 tests passing
* refactor: simplify validation helpers by removing unnecessary wrapper functions
- Removed getErrorMessageForConnectionError and inlined logic into handleValidationError
- Removed isRateLimitError, logRateLimitRetry, and logEmbeddingError wrapper functions
- Updated openai.ts and openai-compatible.ts to inline rate limit checking and logging
- Reduced code complexity while maintaining all functionality
- All 311 tests continue to pass
* fix: add missing invalidResponse i18n key and fix French translation
- Added missing 'invalidResponse' key to all locale files
- Fixed French translation: changed 'and accessible' to 'et accessible'
- Ensures proper error messages are displayed when embedder returns invalid responses
* fix: restore removed score settings in webviewMessageHandler
- Restored codebaseIndexSearchMaxResults and codebaseIndexSearchMinScore settings that were unintentionally removed
- Keep embedder validation related changes
* fix: revert unintended changes to file-watcher and scanner
- Reverted point ID generation back to using line numbers instead of segmentHash
- Restored { cause: deleteError } parameter in scanner error handling
- These changes were unrelated to the embedder validation feature
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* feat: add configurable max search results for codebase indexing (#5149)
- Add codebaseIndexSearchMaxResults to configuration schema with validation (10-1000)
- Update Qdrant client to accept maxResults parameter in search method
- Add UI slider in Experimental Settings to configure max search results
- Rename constants to DEFAULT_MAX_SEARCH_RESULTS and DEFAULT_SEARCH_MIN_SCORE for clarity
- Add translations for new setting across all 17 supported languages
- Add comprehensive test coverage for config manager, Qdrant client, and UI components
fix: settings persistence for codebase index configuration
- Add new updateCodebaseIndexConfig message type to properly merge config updates
- Update SettingsView to send entire codebaseIndexConfig object instead of just enabled flag
- Add backend handler to merge configuration updates instead of overwriting
- Add tests for the new message handler functionality
This ensures the max search results setting persists correctly when saved.
* fix: correct property name in updateCodebaseIndexConfig message
The frontend was sending 'config' but the backend expects 'codebaseIndexConfig'.
This mismatch was preventing the max search results setting from persisting.
* feat: refactor codebase index constants and update search result defaults
* feat(chat): add advanced settings for maximum search results configuration
* refactor: remove updateCodebaseIndexConfig and integrate max search results into saveCodeIndexSettingsAtomic
- Removed updateCodebaseIndexConfig message type and handler as per PR feedback
- Added codebaseIndexSearchMaxResults to codeIndexSettings type in WebviewMessage.ts
- Updated saveCodeIndexSettingsAtomic to save codebaseIndexSearchMaxResults
- Fixed SettingsView.tsx to use codebaseIndexEnabled message instead of updateCodebaseIndexConfig
* Delete webview-ui/src/components/settings/__tests__/ExperimentalSettings.spec.tsx
* refactor: remove updateCodebaseIndexConfig tests to streamline codebase indexing logic
* revert this
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
* fix: resolve Go duplicate references in tree-sitter queries (#5367)
- Replace broad statement captures with function-scoped queries
- Eliminates overlapping captures that caused duplicate references
- Improves search quality and indexing performance for Go projects
- Add test to validate no duplicate line ranges are captured
- Maintains backward compatibility with existing functionality
Fixes#5367
* fix: resolve Go codebase indexing with language-specific thresholds
- Update Go tree-sitter queries to capture full declarations instead of just identifiers
- Implement language-specific character thresholds (50 chars for Go vs 100 default)
- Fix inspectGo.spec.ts test to match new query behavior
- Add comprehensive test coverage for Go indexing fix
This ensures Go files are properly indexed for semantic search while preventing
duplicate references. All tests now pass.
* fix: implement universal 50-character threshold for code indexing
- Changed MIN_BLOCK_CHARS from 100 to 50 in parser.ts
- Updated tests to expect single-block captures for small Go files
- Removed language-specific threshold logic
- Fixes Go files not being indexed due to high character threshold
Fixes#5367
* test: replace Go-specific test with generic MIN_BLOCK_CHARS test
- Remove go-indexing-fix.spec.ts as requested in PR feedback
- Add generic test in parser.spec.ts to verify 50-character threshold
- Test ensures content under 50 chars is filtered, 50+ chars is indexed
- Applies to all languages, not just Go
* fix: update markdown tests for MIN_BLOCK_CHARS change from 100 to 50
* feat: add markdown support to codebase indexing (#4660)
* fix: implement chunking for large markdown sections and fix Qdrant deduplication issue (#4660)
- Modified parseMarkdownContent to chunk large sections (>1150 chars)
- Added support for chunking header-less markdown files
- Fixed _chunkTextByLines to handle oversized lines properly
- Added defensive check for parseMarkdown returning undefined
- Fixed Qdrant ID generation to use segmentHash instead of file:line
- This was the root cause: chunks were being deduplicated
- Each chunk now gets a unique ID even from the same line
- Added comprehensive tests for all edge cases
- Ensures all markdown content is properly indexed in Qdrant
* fix: remove redundant supported-extensions test file
As identified in PR review, the supported-extensions.spec.ts file only tests
the contents of an array, which is already implicitly covered by the functional
tests in parser.spec.ts. Removing this reduces maintenance overhead without
sacrificing test quality.
* test: address PR review feedback
- Remove redundant test 'should handle large markdown documentation folders efficiently'
that only verified the scanner could iterate over mocked files
- Add test to verify unique point IDs are generated for each block from the same file,
ensuring the segmentHash-based ID generation prevents collisions
* fix: add segmentHash to vector point payload and refactor tests
- Add segmentHash to payload in scanner.ts to fix vector point ID generation
- Split parser.spec.ts tests into focused unit tests (mocked dependencies)
- Move integration tests to new markdownIntegration.spec.ts file
- Each test suite now has clear, distinct responsibilities
- Fixes issue #4660: vector point ID collisions for large Markdown files
* refactor: move redundant tests
* feat: enhance markdown processing with consistent chunking logic and segment hashing
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* Fix code index secret persistence with async VSCode storage
- Add async secret methods to CodeIndexConfigManager
- Implement direct VSCode secret storage access bypassing ContextProxy cache
- Update loadConfiguration to use async secret loading
- Modify webview message handler to use new async secret storage
- Add public secret methods to CodeIndexManager
- Enhance debugging throughout secret flow
This fixes the issue where API keys were saved but not loaded immediately
into services due to ContextProxy cache synchronization issues.
* Fix code index secret persistence and test failures
- Add async secret handling to CodeIndexConfigManager with new methods:
- getSecretAsync(), storeSecretAsync() for individual secrets
- loadSecretsAsync(), storeSecretsAsync() for batch operations
- Update doesConfigChangeRequireRestart() to check OpenAI Compatible modelDimension changes
- Fix all failing tests by using setupSecretMocks() helper consistently
- Update manager.spec.ts to properly mock _recreateServices to avoid real service creation
This ensures API keys and other secrets are properly loaded from VSCode's async secret storage
and that configuration changes requiring service restart are correctly detected.
* feat: improve code index settings secret handling in UI
- Show placeholder dots (••••••••••••••••) in password fields when secrets are already set
- Only send modified secret fields to prevent overwriting existing secrets with empty values
- Track which fields have been modified by the user
- Add requestCodeIndexSecretStatus message handler to check if secrets exist
- Fix console.log to handle empty string keys without errors
- Ensure changing one setting doesn't clear other unmodified secrets
* refactor: disconnect code index from unified settings system
- Rename handleExternalSettingsChange to handleSettingsChange for clarity
- Remove handleSettingsChange call from ClineProvider (not related to code index)
- Remove codebaseIndexConfig from general settings save in SettingsView
- Delete unused codebaseIndexConfig message handler
- Remove codebaseIndexConfig from WebviewMessage type definition
- Code index settings are now fully independent with their own dedicated UI
* feat: separate code index enable/disable from indexing settings
- Move 'Enable codebase indexing' toggle to global settings in Experimental section
- Keep indexing-specific settings (API keys, URLs, models) in dedicated Code Index Settings component
- Add codebaseIndexEnabled handler to webview message handler
- Update translations with new settings title and disabled message
- Ensure code index service properly responds to enable/disable changes
- Maintain backward compatibility with existing codebaseIndexConfig structure
* refactor: remove ContextProxy.getVSCodeContext() and pass ExtensionContext directly
- Updated CodeIndexConfigManager to accept vscode.ExtensionContext in constructor
- Modified CodeIndexManager to pass context directly to CodeIndexConfigManager
- Updated webviewMessageHandler to use provider.context.secrets directly
- Removed getVSCodeContext() method from ContextProxy
- Updated all related tests to reflect these changes
- Fixed CodeIndexSettings webview tests after UI changes
* refactor: streamline secret handling by removing async methods and utilizing ContextProxy directly
* feat: translations and popover component
* refactor: simplify test mocks and improve checkbox handling in CodeIndexSettings tests
* refactor: remove debug logging from CodeIndexConfigManager, CodeIndexManager, CodeIndexServiceFactory, and QdrantVectorStore
* fix: merge missing translation keys from main after rebase
- Add advancedConfigLabel, searchMinScoreLabel, searchMinScoreDescription, searchMinScoreResetTooltip keys
- Update startIndexingButton and clearIndexDataButton labels to match main
- Preserve all CodeIndexPopover translations added in this PR
* Revert "fix: merge missing translation keys from main after rebase"
This reverts commit beb1de4924ac1475731fcd06d994ddb96eb1e5fd.
* fix: add missing translation keys from main branch after rebase
- Added codeIndex.advancedConfigLabel
- Added codeIndex.searchMinScoreLabel
- Added codeIndex.searchMinScoreDescription
- Added codeIndex.searchMinScoreResetTooltip
These keys exist on main but were missing from non-English locales after rebase.
* fix: remove clickIndicatorMessage, fix toggle message type, and clean up translation key inconsistencies
* refactor: streamline settings management in CodeIndexPopover and improve secret handling
* refactor: remove debug logging from configuration checks in CodeIndexConfigManager and webviewMessageHandler
* fix: translations
* refactor: remove CodeIndexSettings component and associated tests
