- Add comprehensive memory service architecture mirroring CodeIndexManager pattern
- Implement temporal intelligence with fact categorization (infrastructure, architecture, debugging, pattern)
- Add memory_search tool for retrieving relevant conversation context
- Create service factory, orchestrator, and search service stubs
- Add configuration management for memory system settings
- Implement cache manager for persistent memory storage
- Define interfaces for fact extraction, conflict resolution, and temporal management
Based on detailed planning documents:
- Temporal intelligence for managing fact lifecycle
- Battle-tested patterns from mem0, Graphiti, and Potpie
- Workspace isolation for project-specific memories
- Non-invasive integration with minimal codebase changes
This is an initial implementation that provides the foundation for the conversation memory feature as described in issue #7537.
* feat: update /init command to focus only on non-obvious discoveries
- Emphasize that only non-obvious information discovered by reading files should be included
- Update all mode-specific examples to show truly non-obvious rules
- Add CRITICAL section explaining what qualifies as non-obvious
- Exclude standard patterns and framework defaults
- Focus on gotchas, hidden requirements, and counterintuitive patterns
* fix: ensure /init command checks for and updates existing AGENTS.md files
- Check for existing AGENTS.md in root directory
- Check for existing AGENTS.md in all .roo/rules-*/ directories
- Read and improve existing files rather than replacing them
- Update discovery phase to explicitly look for these files
* refactor: clean up /init command to properly handle existing AGENTS.md files
- Consolidate all AGENTS.md path checking into step 1 with CRITICAL emphasis
- Add explicit instructions for deep dive improvement of existing files
- Remove redundant mentions throughout the workflow
- Emphasize iterating and enhancing existing files, not just appending
- Add clear guidance on cleaning up outdated info and reorganizing
- Make discovery phase the single source of truth for file checking
* fix: strengthen /init command to aggressively remove obvious information
- Add explicit instructions to DELETE obvious information first
- Emphasize that files should get SHORTER, not longer
- Use stronger language: CRITICALLY EVALUATE, AGGRESSIVELY DELETE
- Make clear that standard practices must be removed even if previously included
- Add success metric: files should be more concise and valuable
- Goal is to fix the tendency to just append instead of clean up
* fix: ensure .roo directory is created in project root, not system root
CRITICAL FIX: Paths were being interpreted as absolute, causing .roo to be created at system root
- Clarify all paths are relative to PROJECT/WORKSPACE root
- Add explicit warnings that .roo must be in project root, not system root
- Update example to show proper project structure
- Add IMPORTANT notes throughout emphasizing relative paths
- Fix prevents accidental creation of /.roo at system level
* test: update built-in-commands test to match new init command content
- Replace 'mode-specific rule directories' with 'non-obvious'
- Replace 'analysis_workflow' with 'discovered by reading files'
- Tests now align with the new focus on non-obvious discoveries
Fixes#6756
When ripgrep encounters file access errors (e.g., permission denied), it would cause the search_files tool to return empty results. Adding the --no-messages flag suppresses these error messages while still showing pattern syntax errors, allowing the search to continue and return valid results from accessible files.
Co-authored-by: Roo Code <roomote@roocode.com>
* Revert "fix: prevent unnecessary MCP server refresh on settings save (#6772) (#6779)"
This reverts commit 8d05bc179b.
* fix(mcp): Revert changes causing startup issues and temporarily disable notifications
- Reverted PR #6779 which prevented unnecessary MCP server refreshes but caused startup failures
- Temporarily disabled MCP notification popups as a stopgap solution
- Added TODO comments explaining the temporary nature of disabled notifications
- This allows MCP servers to function properly while a more robust solution is developed
* test(mcp): restore mcpEnabled toggle coverage to verify delegation to McpHub
* refactor(mcp): remove info notifications during refresh; rely on UI indicator
* fix: add missing MCP error translation keys
- Added refresh_after_disable translation key
- Added refresh_after_enable translation key
- Added disconnect_servers_partial translation key
- Updated all 18 locale files with the missing keys
- Fixes the "errors.refresh_after_disable" display issue in MCP server management
* fix: remove fallback English strings from MCP error translations
As requested by @mrubens, removed the || operator and fallback English strings from:
- t("mcp:errors.disconnect_servers_partial")
- t("mcp:errors.refresh_after_disable")
- t("mcp:errors.refresh_after_enable")
The translation system will now rely solely on the localized strings without fallbacks.
* fix: translate MCP error messages to all locales
- Translated "refresh_after_disable" error message
- Translated "refresh_after_enable" error message
- Translated "disconnect_servers_partial" error message with count placeholder
- All 17 non-English locales now have proper translations instead of English text
---------
Co-authored-by: Roo Code <roomote@roocode.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
* feat: Before requesting, ensure checkpoint is initialized
* Generate a checkpoint before modifying the code
* refactor: streamline checkpoint handling and enhance getCheckpoints method
* Blocked waiting for checkpoint initialization timing to change
* cancel checkpoint restore limit
* fix: ensure checkpoint service is undefined on initialization error and improve checkpoint diff handling
* refactor: simplify checkpoint service initialization and cleanup unused variables in CheckpointMenu
* fix: prevent race condition in checkpoint service initialization
- Only assign service to cline.checkpointService after successful initialization
- Add proper cleanup on initialization failure
- Prevents service from being in inconsistent state if Git check fails
* fix: remove checkpoint save from presentAssistantMessage for update_todo_list case
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* feat: add Issue Fixer Orchestrator mode
* The `list_files` tool with `recursive: true` was returning empty results when targeting directories that start with a dot (e.g., `.roo-memory`). This happened because the recursive mode was applying a blanket exclusion pattern `!**/.*//**` that excluded all files inside any hidden directory, even when the user explicitly requested to list that directory.
- `src/services/glob/list-files.ts`
- **Modified `buildRecursiveArgs()`**: Removed the problematic `!**/.*//**` exclusion pattern for hidden directories in recursive mode
- **Enhanced `listFilteredDirectories()`**: Added `isTargetDir` parameter to distinguish between explicitly targeted directories and discovered subdirectories
- **Updated `shouldIncludeDirectory()`**: Always include explicitly targeted directories (even if hidden), while still applying ignore rules to subdirectories found during traversal
- **Before**: `list_files` with `path: ".roo-memory"` and `recursive: true` → Empty results
- **After**: `list_files` with `path: ".roo-memory"` and `recursive: true` → Returns directory contents
- **Preserved**: Hidden subdirectories discovered during traversal are still filtered out
This maintains consistency with `.gitignore` and `.rooignore` mechanisms while ensuring explicitly targeted directories are always processed.
Fixes#2992
* Update src/services/glob/list-files.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* fix: list_files recursive mode now works correctly for hidden directories
- Fixed ripgrep exclusion pattern from `!**/.*//**` to `!**/.*/**`
- Hidden directories (like .git/) now appear in recursive listings but their contents are excluded
- Contents of hidden directories are only shown when explicitly targeting that directory
- Prevents context window overflow from massive hidden directories like .git/
- Maintains consistent behavior: show directory exists, avoid flooding with contents
Fixes#2992
* fix(glob): show top-level hidden directories in list_files
- Modified list-files.ts to show hidden directories at top level
- Added test coverage for hidden directory visibility behavior
- Maintains existing functionality while fixing the .roo directory issue
Addresses PR #5176 feedback with simplified implementation
* fix(glob): include top-level files when recursively listing ignored directories
- Fix issue where files at root level of directories in DIRS_TO_IGNORE were excluded
- Add explicit include patterns (* and **/*) when targeting ignored directories
- Modify exclusion pattern to use !*/dir/** instead of !**/dir/** for target directory
- Add comprehensive test case for .roo/temp scenario
Fixes#5176
* fix(list-files): improve handling of explicitly targeted ignored directories
- Fixed issue where recursive listing would skip files in explicitly targeted directories that are in DIRS_TO_IGNORE
- When targeting a directory like 'temp' that's in the ignore list, we now skip adding exclusion patterns for it
- This ensures all files in the target directory are listed while still preventing recursion into nested directories with the same ignored name
- Also fixed path resolution to convert relative paths from ripgrep to absolute paths
* fix(tests): add missing mocks for list-files tests
* refactor: improve list-files implementation
- Remove redundant path resolution in listFilesWithRipgrep
- Convert CRITICAL_IGNORE_PATTERNS to Set for better performance
- Standardize error message format across all console.warn calls
* fix: update tests to handle cross-platform path resolution
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* 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>
* add more details
* format details better
* fix tests
* fix: address PR #6190 review feedback
- Move huggingface-models.ts to src/api/providers/fetchers/huggingface.ts
- Remove 'any' types and add proper TypeScript interfaces
- Add missing i18n keys and translations for all languages
- Replace magic numbers with named constants
- Add JSDoc documentation for HuggingFaceModel interface
- Improve error handling in API endpoint
- Update model capabilities display to match other providers
- Remove tool calling display (not used)
- Add comprehensive test coverage for new UI features
* fix: preserve HuggingFace provider details in model response
- Store raw HuggingFace models in cache to preserve provider information
- Export getCachedRawHuggingFaceModels to retrieve full model data
- Update huggingface-models.ts to return cached raw models when available
- Include provider name in model descriptions
- Always add provider-specific variants to show all available providers
- Remove console.log statements from fetcher
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* basic hugging face provider
* fetch hf models and providers
* save provider to config
* Update translations
---------
Co-authored-by: Thomas G. Lopes <26071571+TGlide@users.noreply.github.com>
* feat: auto-omit MCP content when no servers are configured
- Modify system prompt generation to detect when no MCP servers are defined
- Only include MCP sections when mode has mcp group AND servers exist
- Pass undefined mcpHub to capabilities and tools when no servers available
- Reduces system prompt verbosity when MCP functionality is not in use
* fix: add missing Uri and RelativePattern exports to VSCode mocks
- Added Uri and RelativePattern exports to global VSCode mock in __mocks__/vscode.js
- Fixed McpHub.spec.ts VSCode mock to include Uri and RelativePattern
- Fixed Task.spec.ts VSCode mock to include Uri and RelativePattern with proper TypeScript typing
- Resolves unhandled rejection errors in unit tests caused by missing VSCode API mocks
* fix: add proper TypeScript typing for RelativePattern in McpHub test mock
* fix: resolve unit test failures in PR #5889
- Fix VSCode mock onDidChangeWorkspaceFolders to accept callback parameter
- Update MCP test mocks to properly test auto-omit functionality
- Update test snapshots to reflect new MCP content omission behavior
- All core functionality tests now passing
* chore: remove package-lock.json as project uses npm
* fix: remove unrelated mock changes from PR
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.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>
