When a subtask completes and the parent task resumes, set skipPrevResponseIdOnce = true
to ensure the next API call sends the full conversation including the subtask result.
This fixes the issue where GPT-5 would only receive the new message without the subtask
result context when using previous_response_id.
Fixes#7251
- Remove assistantMessageParser from experiment definitions in packages/types
- Remove ASSISTANT_MESSAGE_PARSER from shared experiments configuration
- Update Task.ts to always initialize and use AssistantMessageParser
- Remove conditional logic that checked for experiment flag
- Remove unused parseAssistantMessage import
- Update test files to remove assistantMessageParser references
- All tests passing successfully
Co-authored-by: Roo Code <roomote@roocode.com>
* fix: update DeepSeek models context window to 128k
- Updated deepseek-chat and deepseek-reasoner models from 64k to 128k context window
- Updated corresponding test expectations
- Aligns with DeepSeek API documentation at https://api-docs.deepseek.com/quick_start/pricing/Fixes#7268
* feat: update deepseek-reasoner maxTokens to 64K based on official documentation
* fix: use default maxTokens values instead of maximum for DeepSeek models
- deepseek-chat: 4096 (4K default) instead of 8192 (8K max)
- deepseek-reasoner: 32768 (32K default) instead of 65536 (64K max)
- Updated tests to match new default values
- Updated description to clarify default vs max output tokens
* fix: use maximum output tokens for both DeepSeek models
- deepseek-chat: 8192 (8K max)
- deepseek-reasoner: 65536 (64K max)
- Updated tests to match maximum values
- Updated description to reflect 64K max output
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
* feat: add optional todos parameter to new_task tool with experimental setting (#6329)
- Add optional todos parameter to new_task tool for hierarchical task planning
- Implement experimental setting to optionally require todos parameter
- Add clean state-based UI rendering to avoid spurious messages
- Export and reuse parseMarkdownChecklist function
- Add comprehensive test coverage for both optional and required modes
- Maintain full backward compatibility (todos optional by default)
* fix: update new_task tool example to include todos parameter
- Updated the example in tool-use.ts to show the todos parameter
- This prevents AI confusion about whether todos is a valid parameter
- The example now demonstrates the complete tool usage pattern
* fix: make new_task tool definition dynamic based on experimental setting
- Tool description now changes based on newTaskRequireTodos setting
- When disabled: shows todos as (optional)
- When enabled: shows todos as (required) with no mention of configuration
- Added tests to verify dynamic behavior
- Ensures AI models get unambiguous instructions based on current settings
* fix: add translations for newTaskRequireTodos experimental setting
- Added translations for all 17 supported languages
- Ensures consistent UI experience across all locales
* test: update snapshots for new_task tool example with todos parameter
- Updated 13 snapshot files to reflect the new tool-use example
- All tests now pass with the updated example format
* Update src/core/tools/newTaskTool.ts
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: address PR review comments
- Replace any[] with TodoItem[] type in ExtensionStateContext.tsx for better type safety
- Remove redundant initialTodos parameter from startTask call in Task.ts (todos already set in constructor)
- Improve code clarity in newTaskTool.ts by checking provider reference early and reusing state
# Conflicts:
# src/core/task/Task.ts
# webview-ui/src/context/ExtensionStateContext.tsx
* fix: revert order of operations in startTask to fix integration test timeout
The change in order of operations (calling say() before postStateToWebview()) was causing the XML content file test to timeout. Reverting to the original order fixes the issue.
* fix: hide todos parameter from new_task tool prompt when experiment is disabled
- Modified getNewTaskDescription to completely omit todos parameter when experiment is off
- Updated tests to verify todos parameter is not shown at all when disabled
- Ensures tool prompt remains unchanged when experimental setting is disabled
- Maintains backward compatibility while providing cleaner prompt interface
* fix: update snapshots for new_task tool todos parameter
- Updated snapshots in add-custom-instructions.spec.ts
- Updated snapshots in system-prompt.spec.ts
- All tests now passing with the new todos parameter documentation
* feat: move newTaskRequireTodos from experimental to VSCode settings
- Added newTaskRequireTodos as a VSCode configuration property in src/package.json
- Added description in src/package.nls.json
- Updated newTaskTool.ts to read from VSCode configuration instead of experiments
- Removed NEW_TASK_REQUIRE_TODOS from experimental settings in src/shared/experiments.ts
- Removed newTaskRequireTodos from packages/types/src/experiment.ts
- Updated tests to use VSCode configuration mocking instead of experiments
- Removed references from experiments test file
- Maintains backward compatibility (defaults to false)
* fix: make new_task tool description dynamically reflect VSCode setting
- Updated new-task.ts to check args.settings instead of args.experiments
- Added newTaskRequireTodos to SystemPromptSettings interface
- Pass newTaskRequireTodos setting through Task.ts and generateSystemPrompt.ts
- Updated all related tests to use settings instead of experiments
- Fixed TypeScript errors in test files by adding newTaskRequireTodos property
This ensures the tool description correctly shows todos parameter as required/optional
based on the VSCode setting value, fixing the issue where Roo would try to use
new_task without the todos parameter when it was required.
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Merge Resolver <merge-resolver@roo-code.com>
Co-authored-by: Roo Code <roomote@roocode.com>
- Show VSCode warning when users under MDM policy try to leave AccountView without auth
- Add showMdmAuthRequiredNotification message type to WebviewMessage interface
- Implement handler in webviewMessageHandler to display localized warning
- Add 'Your organization requires authentication' translation in all 17 languages
- Fix translation key path to use common:mdm.info.organization_requires_auth
* feat: add "Installed" filter to Roo Marketplace
- Added installed boolean filter to ViewState interface
- Implemented UI checkbox for "Show installed only" filter
- Updated filterItems method to filter by installation status
- Added translation strings for the new filter
- Updated tests to include the new filter property
Fixes#7004
* fix: add missing translations for "Installed" filter in marketplace
- Added "filters.installed.label" and "filters.installed.description" keys
- Updated all backend marketplace.json files (src/i18n/locales/*/marketplace.json)
- Updated all frontend marketplace.json files (webview-ui/src/i18n/locales/*/marketplace.json)
- All translation checks now pass successfully
* fix: improve code quality for installed filter feature
- Replace plain HTML checkbox with UI library Checkbox component for consistency
- Add proper TypeScript typing for installedMetadata (MarketplaceInstalledMetadata)
- Optimize filterItems method to avoid unnecessary object copying
- Remove dead code for subcomponent filtering
* refactor: improve installed filter UI and functionality
- Replace checkbox with dropdown for better UX
- Place dropdown inline with search field for better layout
- Add three filter options: All Items, Installed Only, Not Installed
- Update filter logic to handle all three states
- Improve translation labels to clarify it's a filter
- Optimize filterItems method for better performance
- Add proper TypeScript types throughout
* fix: ensure both filter dropdowns have matching height
- Set both Select and Button components to h-7 for visual consistency
- Installation status dropdown and tags dropdown now have identical height
- Improved visual alignment for better UX
* chore: remove redundant useEffect in MarketplaceListView to prevent re-render loop; rely on state manager handleMessage sync
* i18n: update tri-state Installed filter translations across all locales
- Replace checkbox-based installed keys with dropdown keys:
{ label, all, installed, notInstalled }
- Updated both frontend and backend marketplace.json files for all non-English locales
- Ensures translation completeness for CI check
* i18n: change Installed option text to 'Installed' (remove 'Only') across all locales (frontend + backend)
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
* fix: omit temperature parameter when not explicitly set for OpenAI Compatible providers
- Modified OpenAiHandler to only include temperature when modelTemperature is defined
- Modified BaseOpenAiCompatibleProvider to only include temperature when modelTemperature is defined
- Added tests to verify temperature is omitted when undefined
- Updated existing tests to explicitly set temperature where needed
This allows backend services (LiteLLM, vLLM) to use their configured default temperatures
instead of being forced to use temperature=0 when "Use custom temperature" is unchecked.
Fixes#7187
* test: update tests to match new temperature handling behavior
- Remove temperature parameter expectations from provider tests
- Tests now expect temperature to be omitted when not explicitly set
- Aligns with PR #7188 changes to fix OpenAI Compatible provider behavior
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
* feat: enable loading Roo modes from multiple files in .roo/roo_modes directory
- Add support for loading modes from .roo/roo_modes directory (both global and project)
- Implement proper precedence: project .roo/roo_modes > .roomodes > global .roo/roo_modes > settings
- Update file watchers to monitor .roo/roo_modes directories
- Preserve original source file when updating modes
- Add comprehensive tests for the new functionality
Fixes#7202
* refactor: rename .roo/roo_modes to .roo/modes for cleaner directory structure
- Changed ROO_MODES_DIR constant from "roo_modes" to "modes"
- Updated all references in CustomModesManager.ts
- Updated all test descriptions and mocks in CustomModesManager.spec.ts
- All tests passing successfully
* fix: normalize sourceFile paths to use forward slashes in exported YAML
- Fixes Windows test failure where backslashes in sourceFile paths were causing test assertions to fail
- Ensures cross-platform compatibility by normalizing all paths to use forward slashes in YAML exports
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
* fix: prevent duplicate LM Studio models with case-insensitive deduplication
- Keep both listDownloadedModels and listLoaded APIs to support JIT loading
- Implement case-insensitive deduplication to prevent duplicates
- When duplicates are found, prefer loaded model data for accurate runtime info
- Add test coverage for deduplication logic
- Addresses feedback about LM Studio's JIT Model Loading feature (v0.3.5+)
Fixes#6954
* fix: correct deduplication logic to prefer loaded models
- When a loaded model ID is found in any downloaded model key (case-insensitive)
- Remove the downloaded model and replace with the loaded model
- This ensures loaded models with runtime info take precedence
- Updated tests to verify the correct deduplication behavior
* fix: improve deduplication logic and add comprehensive test coverage
- Enhanced deduplication to use path segment matching instead of simple substring
- Prevents false positives like 'llama' matching 'codellama'
- Added comprehensive test cases for edge cases and multiple scenarios
- Maintains support for JIT Model Loading feature
* fix: add type check before calling .match() on diffItem.content
Fixes#6905 - Error during diff application "v.content.match is not a function"
- Added type check to ensure diffItem.content is a string before calling .match()
- Added comprehensive tests for handling non-string content values
- Prevents runtime errors when content is null, undefined, or other non-string types
* fix: validate content type earlier in diff parsing
- Move type check to where content is first extracted from XML
- Remove redundant check since content is now guaranteed to be string
- Add test for early content validation
* chore: remove comments
* fix: add TelemetryService mock to multiApplyDiffTool tests
* fix: add captureDiffApplicationError to TelemetryService mock
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
* fix: prevent XML entity decoding in diff tools
- Add parseXmlForDiff function with processEntities: false to preserve exact content
- Update multiApplyDiffTool to use parseXmlForDiff instead of parseXml
- Add comprehensive tests for entity handling in parseXmlForDiff
This fixes the issue where fast-xml-parser was decoding HTML entities like &
causing mismatches in diff tools when comparing against original file content.
Fixes#7107
* refactor: eliminate code duplication between parseXml and parseXmlForDiff
- Refactored parseXml to accept optional ParseXmlOptions parameter
- parseXmlForDiff now delegates to parseXml with processEntities: false
- Added explanatory comment in multiApplyDiffTool.ts about why parseXmlForDiff is used
- Improved JSDoc documentation with specific use cases for parseXmlForDiff
This maintains backward compatibility while eliminating code duplication.
parseXml continues to be used for general XML parsing (file reads, follow-up questions),
while parseXmlForDiff is specifically for diff operations where entity processing must be disabled.
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
