* 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>
- Corrected error causing free models listed under openrouter to show pricing information
- Updated pre-push and pre-commit scripts to work in Windows environments when pushing to branch (windows requires npm/npx to include the ".cmd" extension to recognize and compile.
When maxReadFileLine setting was set to zero, the code would attempt to read lines with a negative end index
(maxReadFileLine - 1 = -1), causing the readLines function to reject the request.
This change:
- Checks if maxReadFileLine is greater than zero before calling readLines
- Returns an empty string when maxReadFileLine is zero
- Ensures content is only formatted with line numbers when it's not empty
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
Co-authored-by: Eric Wheeler <roo-code@z.ewheeler.org>
Add tests that validate:
- Original content with unescaped markers
- Search content with escaped markers to match unescaped markers in original content
- Proper validation of escaped search, separator, and replace markers in diff content
- Successful application of diffs with escaped markers in search content
Signed-off-by: Eric Wheeler <roo-code@z.ewheeler.org>
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>
