* Fix filename format in downloadTask function for markdown export
* Update src/integrations/misc/export-markdown.ts
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>
- Implemented the append_to_file tool to allow users to append content to existing files or create new ones if they do not exist.
- Updated the rules and instructions to include the new tool.
- Added tests for the append_to_file functionality, covering various scenarios including error handling and content preprocessing.
- Enhanced the experiment schema to include the new append_to_file experiment ID.
- Updated relevant interfaces and types to accommodate the new tool.
- Modified the UI to display the append_to_file tool in the appropriate sections.
* Add xAI provider
* Add model reasoning effort
* DRY this up
* Handle undefined delta
* Cleanup getModel to fix test
* Add missing translations
* Small type cleanup
* Support temperature
---------
Co-authored-by: cte <cestreich@gmail.com>
Previously, handlers for terminal output were registered after starting the process,
which could cause output to be missed for fast-executing commands that complete
before handlers are set up.
- Adds CommandCallbacks interface to register handlers upfront
- Moves handler registration before process start to ensure no output is missed
- Provides process instance in callbacks for direct control
- Adds debug logging to help diagnose timing issues
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Co-authored-by: Eric Wheeler <roo-code@z.ewheeler.org>
* 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>
Fixes Bedrock ARN validation
Updates the Bedrock ARN regex to allow alphanumeric characters, dots, hyphens, and colons in the resource ID.
This prevents validation errors when using ARNs containing those characters.
* read symbolic linked dir and files recursively
* add symlinked dir and nested symlink test case for custom-instructions
* enhance comments
* add changeset
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>
- 【What】Move the logic for generating webview HTML content from ClineProvider to a new WebviewHTMLManager class.
- 【Why】This improves code organization and maintainability by separating concerns related to webview HTML generation.
- 【Why】This allows for easier testing and modification of the HTML generation logic without affecting the ClineProvider class.
