- 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.
* fix: restore file truncation backward compatibility and fix regressions
Fixes#1934
- Setting maxReadFileLine=-1 provides equivalent functionality for reading entire files
- Revert to system-controlled maxReadFileLine for file truncation, fixing regressions with:
- Overridden system prompts lacking auto_truncate parameter information
- Insufficient user control over truncation behavior
- Add 'Always read entire file' checkbox for easier access to full file reading
- Update translations across all locales with improved descriptions
- Update truncation notice to be more concise
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* test: add comprehensive tests for read_file maxReadFileLine settings
- Tests behavior when maxReadFileLine is -1 (reads entire file)
- Tests behavior when maxReadFileLine >= file length (reads entire file)
- Tests behavior when maxReadFileLine is 0 (shows only definitions)
- Tests behavior when maxReadFileLine < file length (truncates content)
- Verifies exact line counts in responses
- Adds helper functions for response validation
- Includes DEBUG flag for controlled logging
---------
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Co-authored-by: Eric Wheeler <roo-code@z.ewheeler.org>
* 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>
* 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>
Forcing terminals to `cd` back to the project directory was disrupting
shell state without providing feedback to the model. This caused issues
with capturing output from subsequent commands, particularly with custom
shell prompts.
Instead of forcing directory changes, we now track terminal state
through shell integration with a fallback mechanism, and provide
explicit working directory feedback to the model. This allows terminals
to maintain their natural state while ensuring accurate command output
capture.
Changes:
- Remove forced `cd` commands that were disrupting terminal state
- Add getCurrentWorkingDirectory() method with shell integration fallback
- Add customCwd parameter to executeCommandTool for flexible directory handling
- Add requiredCwd parameter to control terminal selection behavior
- Refactor terminal selection logic for more consistent state management
- Modify environment details to include terminal working directory feedback
- Update XML schema to include optional working directory parameter in execute_command
The environment details now provide explicit feedback about terminal state:
Command executed in terminal N from '/path/to/dir'. Exit code: 0
Fixes: #1388
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
