* fix(api): update cacheReadsPrice for OpenAI GPT-4.1 models (#2887)
Set correct cacheReadsPrice (cached input price) for gpt-4.1, gpt-4.1 mini, and gpt-4.1 nano based on official OpenAI pricing. No changes to cacheWritesPrice as per current OpenAI documentation. This ensures prompt caching costs are accurately reflected for these models in cost calculations.
* Update more OpenAI cache prices
* Track cache tokens and cost correctly for OpenAI
* Update tests
---------
Co-authored-by: monotykamary <tom81094@gmail.com>
Creates a temporary ZDOTDIR to handle zsh shell integration properly while preserving user's zsh configuration. This ensures VSCode shell integration works correctly with zsh without modifying the user's existing setup.
- Add terminalZdotdir setting (disabled by default)
- Create temporary directory with proper security (sticky bit)
- Add automatic cleanup on terminal close
- Add translations for all supported languages
User confirmed fixes:
Fixes: #2205Fixes: #2129
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Added two new terminal settings:
- terminalZshOhMy: Sets ITERM_SHELL_INTEGRATION_INSTALLED=Yes for Oh My Zsh
- terminalZshP10k: Sets POWERLEVEL9K_TERM_SHELL_INTEGRATION=true for Powerlevel10k
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Added a new configuration option 'terminalZshClearEolMark' (default: true) that
sets PROMPT_EOL_MARK='' in the terminal environment. This prevents issues with
command output interpretation when the output ends with special characters like '%'.
Added translations for all supported languages.
Fixes: #2194
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Add a new configuration option that allows users to toggle the PowerShell counter workaround. This workaround adds a counter to PowerShell commands to ensure proper command execution and output capture.
The setting is disabled by default, allowing users to enable it only when needed.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Add a new configurable setting to control command execution delays in terminals.
When set to a non-zero value, this adds a sleep delay after command execution
via PROMPT_COMMAND in bash/zsh and start-sleep in PowerShell.
The default value is 0, which disables the delay completely. This setting
replaces the previous hardcoded delay of 50ms that was added as a workaround
for VSCode bug #237208.
Fixes: #2017
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* feat: Add file context tracking system
This commit adds a comprehensive file context tracking system that monitors file operations (reads, edits) by both Roo and users. The system helps prevent stale context issues and improves checkpoint management.
Key features:
- Track files accessed via tools, mentions, or edits
- Monitor file changes outside of Roo using file watchers
- Store file operation metadata with timestamps
- Trigger checkpoints automatically when files are modified
- Prevent false positives by distinguishing between Roo and user edits
The implementation includes:
- New FileContextTracker class to manage file operations
- Type definitions for file metadata tracking
- Integration with all file-related tools
- File mention tracking in the mentions system
- Improved checkpoint triggering based on file modifications
* Update src/core/context-tracking/FileContextTracker.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Update src/core/context-tracking/FileContextTracker.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* test: Add mocks for getFileContextTracker in Cline tests
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* Directly use provider rateLimitSeconds and remove uneeded default
* remove a bunch of unused rateLimitSeconds references
* rateLimitSettings field def in GlobalSettingsRecord isn't needed for migration
* Added Gemini 2.5 Pro model to Vertex AI Provider
* Adds Gemini 2.5 Pro preview model
Adds configuration for the new Gemini 2.5 Pro preview model,
including its token limits, context window size, image support, and
pricing information.
* Bedrock prompt caching
* remove whitespace only change to src/api/providers/base-provider.ts
* remove integration test that calls bedrock
* PR prep cleanup
* test file and redundant code cleanup
* updated multi-cache-point
* optimized cache strategy
* cache logic updated. commit before trying to simplify newConversationPlacements
* simplified initial cachePoint logic
* fix the missing caching params for claude 3.7 on bedrock
* undo unintentional changes to README.md files
* fix merge bug that hid use prompt cache checkbox
* prep for PR
* remove unintended changes
* revert .gitignore change
* undo unintended changes
* Issue 1998 - Unable to use ARN. https://github.com/RooVetGit/Roo-Code/issues/1998 - Simplify region extraction from Arns. Change example of ARN use from the foundational model ARN to an inference profile ARN which is what is needed.
* small updates to error message
* more flexible support for ARNs and hardening of ARN handling
* update comment on regex use for platform indipendent cosideration
* small code comment update
* remove duplicative logic to add a region to the arn when cross-region is selected
* Update README files from main branch
* improve error handling when on-demand throughput is not avialable for a foundational model
* fix prompt router bug
* minor tweaks for simplicity
* error messgae formatting
* set new version of bedrock runtime package
* fixes: 2229 - complete prompt doesn't work and appears like a no-op
* remove commented out logger.debug blocks per PR review request
* localize new prompt cache UI inputs
* single source of truth for AWS Region information
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* Browser Automation Improvements
* Added multi-tab remote Chrome support
* Added support for hover
* Properly caching remote browser host in global state
* Cleanup functions
* Updated for changes after merge
* Added www. exception for common tabs
* Update src/core/webview/ClineProvider.ts
* Revert README changes
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
- Move "Add to Context" to the top of submenu and code actions for improved accessibility
- Add line number tracking (startLine/endLine) to EditorContext and code actions
- Update templates in support-prompt.ts to include line numbers in file references
- Ensure backward compatibility with existing code
This change improves the UX by making the frequently used "Add to Context" action more accessible and enhances context awareness by tracking and displaying line numbers for selected code.
* support project-level mcp config
* switch the toasts to English
fix test
(cherry picked from commit 26941dcaae)
* add i18n for project mcp
(cherry picked from commit 792a8225c1)
* optimize McpHub.ts
* fix merge main into head
* fix project mcp
* partial update mcp config
* fix toggleToolAlwaysAllow
* Modify mcp to support project and global of the same name
* fix ut
* remove unused mcp log
* i18n for mcp
* Revert README changes
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* feat: add pinning functionality for API configurations
Added the ability to pin/unpin API configurations, enabling prioritized appearance in dropdown menus.
- modified state management to support storing pinned configurations persistently.
- Updated UI components to display and toggle pin states
- Adjusted backend handling for syncing pinned configuration states across sessions.
* refactor: add support for loading API configurations by ID
- Introduced a new method `loadConfigById` in `ConfigManager` to load API configurations using their unique ID.
- Refactored the dropdown and pin logic to work with ID
- Added tests to verify the new functionality for loading configurations by ID.
* fix: preserve existing API config ID on updates
- Ensure that the existing ID is retained when updating an API config.
- Prevents unintentional ID changes during configuration updates.
* Fix theme issues
---------
Co-authored-by: james <james@systemslogiq.com>
Co-authored-by: cte <cestreich@gmail.com>
* Code for new fetch_instructions tool
* Call parameter for fetch_instructions task, not text
* Additional places that fetch_instructions needs to be added.
* Pass necessary objects into create MCP server code
* Update snapshots to reflect changes to prompts
* Fixes from testing
* Move guidance on creating project modes to fetchable instructions
* i18n for new prompt
Translations suggested by Roo.
* Missing translation
* Another missing i18n update
* Missing Catalan translation
* Re-use content parameter on ClineSayTool
* Remove space from zh-TW translation
This is consistent with other translations
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* PR review - suggested changes to prompts
* Slightly more conservative in terms of text pruning from default prompt
* Move additional detail about mode creation into fetch_instructions instructions
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Replace hardcoded custom modes filename with GlobalFileNames constant
* Remove 'cline' prefix from mcpSettings filename
* Use GlobalFileNames.customModes in modes.ts
* replace two more `cline_mcp_settings` with `mcp_settings` in tests.
* feat: add settings file migration for new file naming convention
- Implement migrateSettings function to rename legacy settings files to new format
- Migrate cline_custom_modes.json to new custom modes filename
- Migrate cline_mcp_settings.json to new MCP settings filename
- Add TODO to remove migration code in September 2025 (6 months after implementation)
- Make activate function async to support migration on startup
* Add associated changeset
* removed unused import
* refactor: move migrateSettings to dedicated utility file
- Extract migrateSettings function from extension.ts to src/utils/migrateSettings.ts
- Update extension.ts to import and use the extracted function
- Update tests to use the real implementation
- Improve dependency injection by passing outputChannel as parameter
- Enhance maintainability by isolating temporary migration code (to be removed Sept 2025)
* Update src/extension.ts
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* feat: Add the openAiR1FormatEnabled field to enable this switch in OpenAI compatible mode to support the current QWQ and future additional classes of R1 models.
* feat: Add the openAiR1FormatEnabled field to enable this switch in OpenAI compatible mode to support the current QWQ and future additional classes of R1 models.
* fix: add miss i18n
* fix: add miss i18n
* fix: remove the redundant call
---------
Co-authored-by: xiong <yueminxiong.xym@alibaba-inc.com>
* Add Requesty OAuth flow
* New 1-click onboarding flow
* Requesty: Use correct default model info
* When called from the onboard flow, created the default profile
Glama OAuth handler changed for consistency.
* Add router images
* Shuffle the routers
* Translate
* Appease knip
---------
Co-authored-by: Daniel Trugman <dtrugman@gmail.com>
* feat read file range
feat: add file truncation with code structure preview
Add configurable line limit for large file handling with source code structure preview. This improves performance and memory usage while maintaining code readability.
Key changes:
Add maxReadFileLine setting (default: 4500) with UI controls
Create efficient line counter utility using streams
Add parseSourceCodeDefinitionsForFile for single file parsing
Show truncation notice with code structure for large files
Add comprehensive tests for new functionality
Move file extensions to shared constant
add line number
pr comment
Return definition ranges from tree-sitter
make treesitter always add line
add line number to rg search
enhance tree siter output & fix test
update snapshot
fix test
* Add translations, tweak range
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
