- Add maxReadFileTokens setting to global settings schema (default: 10000)
- Update extractTextFromFile to use token counting with tiktoken
- Modify UI components to show token-based settings instead of line-based
- Update all callers of extractTextFromFile to pass the new parameter
- Add comprehensive tests for token-based truncation
- Token-based truncation takes precedence over line-based when both are set
This addresses issue #6274 by preventing context window exhaustion when
reading files with very long lines that contain many tokens.
- Replace broken command URI with onClick handler that posts message
- Command URIs don't work in webview context, must use postMessage
- Restores original working implementation from PR #5798
- Directs to autoApprove section where command permissions are configured
The bug was introduced in commit 77bc9e6f when the tooltip was updated
to use command URI instead of the working onClick pattern.
* 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>
fix: add Hugging Face API key to SECRET_STATE_KEYS and fix validation
- Added huggingFaceApiKey to SECRET_STATE_KEYS array to ensure it's properly handled as a secret
- Fixed validateModelsAndKeysProvided to check for huggingFaceModelId when validating Hugging Face provider
- This fixes the issue where the welcome view wouldn't transition to chat view after configuring Hugging Face
* 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: add jump icon for newly created files
- Add jump icon to newFileCreated tool case in ChatRow.tsx
- Matches existing pattern from readFile case for consistent UX
- Allows users to quickly open newly created files
- Fixes issue #5736
* fix: remove duplicate file path display in newFileCreated case
- Removed redundant ToolUseBlock that was showing file path twice
- Added onJumpToFile prop to CodeAccordian component to support jump icon
- Jump icon now appears in CodeAccordian header for newFileCreated files
- Maintains consistent UX with existing file operations while avoiding duplication
Fixes feedback from @daniel-lxs about duplicate elements being shown
* fix: address PR feedback for jump icon on new files
- Fix openFile message to use correct path format with './' prefix
- Remove duplicate chevron icon when jump icon is present
- Add aria-label for accessibility
- Fix styling: use mr-1 to match progressStatus icon
- Remove redundant margin style from jump icon
---------
Co-authored-by: Roo Code <roo@roocode.com>
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* feat: add Issue Fixer Orchestrator mode
* fix: allow export task history while API is active (#5324)
- Add exportAlwaysEnabled prop to TaskActions component
- Export button remains enabled when exportAlwaysEnabled is true
- Other action buttons still respect buttonsDisabled state
- Add tests to verify the new behavior
This fixes the regression where users couldn't export task history
during API operations, which is a common debugging workflow.
* fix: simplify export button to always be enabled
The export functionality is not impacted by the model streaming state,
so the button should always be enabled. Removed the unnecessary
exportAlwaysEnabled prop and simplified the implementation.
- Remove exportAlwaysEnabled prop from TaskActions
- Remove disabled attribute from export button entirely
- Update TaskHeader to remove exportAlwaysEnabled prop usage
- Update tests to reflect that export is always enabled
* fix: enable export, share, and copy buttons during API operations
- Export, share, and copy buttons now remain enabled when API is active
- Delete button still respects buttonsDisabled state for safety
- Removed unnecessary exportAlwaysEnabled prop
- Updated tests to reflect new behavior
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* fix: add character limit to prevent terminal output context explosion
- Enhanced truncateOutput function to accept character limits alongside line limits
- Character limits take priority over line limits to prevent context window explosion
- Added terminalOutputCharacterLimit setting (default: 100,000 characters)
- Updated all terminal output processing to use both limits
- Added comprehensive tests for character limit functionality
Fixes#5775
* feat: add terminal output character limit setting to UI
- Add character limit slider to Terminal Settings UI (default: 50,000)
- Update ExtensionStateContext to manage character limit state
- Add validation for positive character limit values
- Add English translation and translations for all 17 supported languages
- Connect UI to backend through proper message handling
- Character limit takes precedence over line limit to prevent memory issues
* fix: update test expectations for character limit edge cases
- Fix multi-byte character test to account for JavaScript's string length behavior
- Fix newline content test to match actual slice behavior
- Tests now correctly validate the truncateOutput function's character limit handling
---------
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
* improved chat row first pass
* big UI improvements
* working functionality
* tests working
* ok finally tests working for real!
* translations
* add back hidden flag
* remove option to skip notif
* fixed image issue
* ui fix
* put back edit flag
* oops test fix
* reduce margins
* code review
* feat: add Cmd+Shift+. keyboard shortcut for previous mode switching
- Add switchToPreviousMode function that cycles backwards through modes array
- Update handleKeyDown to detect Cmd+Shift+. keyboard combination
- Update modeShortcutText to display both next and previous mode shortcuts
- Add forPreviousMode translation key to all 18 language files
- Implements backwards mode cycling using modulo arithmetic for proper array wrapping
Fixes#5692
* fix: correct keyboard shortcut detection for Cmd+Shift+. (previous mode)
When Shift is pressed with the period key, event.key becomes ">" instead of ".".
Fixed line 1576 to check for event.key === ">" for proper Cmd+Shift+. detection.
Fixes keyboard shortcut issue reported in PR comment.
* fix: use event.code for cross-platform keyboard shortcut compatibility
- Replace event.key checks with event.code === "Period" for both shortcuts
- Fixes keyboard layout compatibility issue where Shift+Period produces different characters on non-US layouts
- Consolidates both shortcuts into a single conditional block for better maintainability
- Addresses feedback from @daniel-lxs in PR #5695
* feat: add navigation link to history tab in HistoryPreview
- Add 'View all history' link at bottom of history preview
- Include internationalization support with new translation key
- Use consistent styling with VSCode theme colors
- Navigate to history tab using switchTab message format
* feat: add viewAllHistory translation to all language files
* Tweaks and translations
* Fix test
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
