Prevents attempting to apply diffs where search and replace content are identical,
which would result in no changes being made. Instead, provide a helpful error
message explaining why the operation was rejected.
Fixes: #1350
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
When previewing system instructions, getDiffStrategy was not receiving the
MULTI_SEARCH_AND_REPLACE flag, causing the instructions to show the wrong diff
strategy description. Now correctly passing the flag to ensure the proper diff
strategy description is shown in system instructions.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Provide support for escaping section markers so that the model can
add or remove lines like:
=======
by escaping them in the search or replace string:
\=======
A state machine tracks apply_diff markers appear in correct sequence:
SEARCH -> SEPARATOR -> REPLACE. Prevents syntax corruption from interleaved or
malformed blocks by validating before processing matches.
If a model tries to interleave diff markers, then the state machine will
return a response to the model like this so it can correct. testing
shows that this works on Claude 3.5, 3.7 and gemini-2.0-flash-thinking:
```xml
<error_details>
ERROR: Special marker '=======' found in your diff content at line 7:
When removing merge conflict markers like '=======' from files, you MUST escape them
in your SEARCH section by prepending a backslash (\) at the beginning of the line:
CORRECT FORMAT:
<<<<<<< SEARCH
content before
\======= <-- Note the backslash here in this example
content after
=======
replacement content
>>>>>>> REPLACE
Without escaping, the system confuses your content with diff syntax markers.
You may use multiple diff blocks in a single diff request, but ANY of ONLY the following separators that occur within SEARCH or REPLACE content must be must be escaped, as follows:
\<<<<<<< SEARCH
\=======
\>>>>>>> REPLACE
</error_details>
```
Fixes: #1557Fixes: #1408
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* feat(i18n): Enhance Translate mode guidelines
This commit improves the Translate custom mode in .roomodes by adding:
- Clear requirement to use informal speech (e.g., "du" instead of "Sie")
- Guidance on preserving domain-specific terminology in English
- New section on common translation pitfalls to avoid
- Enhanced instructions for handling placeholders in translated strings
- Guidelines for UI element translation (buttons vs. tooltips)
- Directions for handling incomplete source strings
- Rules to preserve original perspective (user→system vs system→user)
- A translator's checklist for quality assurance
These improvements ensure more consistent, accurate, and natural
translations across supported languages while preventing common
localization errors.
* use informal speech in de locales
* Fix: Enable cross-region inference for 'ap-xx' region in AwsBedrockHandler.completePrompt
* Fix: Enable cross-region inference for 'ap-xx' region in AwsBedrockHandler.createMessage
* Create itchy-waves-move.md
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Problem:
- Previous implementation incorrectly grouped context lines with matches
- Context lines were split into beforeContext/afterContext arrays, making it difficult to maintain proper line order
- Output format was inconsistent with read_file output
- Non-contiguous search results were sometimes broken or incorrectly grouped
- Example of incorrect output:
# bench/bundle-test/rollup.config.mjs
16 | file: 'dist/index-wasm.min.mjs',
17 | format: 'es',
24 | output: {
----
25 | file: 'dist/index-lite.min.mjs',
26 | format: 'es',
----
# packages/rehype/package.json
----
10 | it('run', async () => {
27 | "files": [
28 | "dist"
----
Solution:
- Replace separate context arrays with a single 'lines' array containing both matches and context
- Add isMatch flag to distinguish between match and context lines
- Improve contiguity detection by checking if line numbers are sequential
- Standardize output format to match read_file output
- Properly handle non-contiguous search results by creating new result groups
- Example of correct output:
# bench/bundle-test/rollup.config.mjs
16 | file: 'dist/index-wasm.min.mjs',
17 | format: 'es',
----
24 | output: {
25 | file: 'dist/index-lite.min.mjs',
26 | format: 'es',
----
This change ensures search results are properly grouped and displayed with the correct context.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Co-authored-by: Eric Wheeler <roo-code@z.ewheeler.org>
* 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>
* batch clear history
* catch Task not found error
* fix deleteMultipleTasksWithIds
* add i18n for batch clear history
* add i18n for history
* debug
* remove unused logs
* fix trans
* fix trans
* Cleanup
---------
Co-authored-by: aheizi <aheiz@outlook.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* fix: clarify PowerShell command completion workaround
The command completion detection approach in PowerShell requires an output
string to allow duplicate commands to execute in some versions of code.
Update the string to explicitly indicate it is a Roo PowerShell workaround,
making it clear in terminal output that this is intentional behavior rather
than a side effect.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* cleanup: improve terminal logging and error handling
No functional changes - purely improves error handling and logging clarity.
Terminal.ts:
- Handle undefined process state in setActiveStream without throwing
- Add terminal IDs to all log messages for better traceability
- Improve error message clarity in shell integration timeout
TerminalRegistry.ts:
- Reorganize shell execution event handlers for better flow
- Log shell execution events before processing for reliable debugging
- Add detailed context to terminal not found scenarios
- Include command and execution state in error messages
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* feat: make terminal shell integration timeout configurable
Users with long shell startup times were encountering "Shell Integration Unavailable" errors due to the hard-coded 4s timeout. The timeout is now configurable through Advanced Settings (1-60s).
Thanks @filthy for troubleshooting and @kiwina for suggesting making the timeout configurable.
Fixes#1654
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* critical fix: race condition that prevents command completion
Terminal running state is now managed in TerminalRegistry instead of Terminal to prevent race between stream close and shell completion.
While this race may not trigger on current VSCode versions, newer releases with additional terminal fixes may expose the issue. This proactively prevents "Shell execution end event received, but process is not running" errors.
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* fix: improve command execution path reporting
Enhance clarity of command execution context and error reporting:
- Check to see if the directory changed because of the command
- Clarify execution path message
- Add explicit message when command exits with non-zero code
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* system instructions: clarify terminal directory operations
Clear guidance for the AI system on:
- Working directory constraints
- Path handling requirements
- Tool vs terminal directory behavior
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
* test: update snapshots for system prompt working directory instructions
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
---------
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Co-authored-by: Eric Wheeler <roo-code@z.ewheeler.org>
Co-authored-by: Chris Estreich <cestreich@gmail.com>
feat: add multiple workspaces support
- Add getWorkspacePath function to centralize workspace directory path retrieval
- Use the new workspace directory retrieval logic in Cline, Mentions, ClineProvider, and WorkspaceTracker
- Update WorkspaceFile on tab switch and prevent redundant updates by checking prevWorkSpacePath
- Fix the bug that loads the contents of the previous tab when quickly switching tabs
- Optimize getWorkspacePath return value for better reliability
Co-authored-by: xiong <yueminxiong.xym@alibaba-inc.com>
* Add text-to-speech functionality
* Add speed config option to text-to-speech
* Fix test case for tts speed slider
* Fix test case for tts speed slider (really)
* Disabled error message logging in tts.ts
* ignore markdown and mermaid diagrams in TTS
* add ttsEnabled and ttsSpeed to GlobalStateKey
* fix failing webview test for save button
* Translations
* Fix tests
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
