- Rename experiment ID from smartContextTracking to smartRead
- Apply smart read logic to @ file mentions (skip files already in context)
- Add parseMentions parameters for experiments and apiConversationHistory
- Add English translation keys for SMART_READ experiment
- Fix TypeScript errors and update tests
Added new 'smartContextTracking' experiment to gate the file context
tracking optimization. When disabled (default), the read_file tools
behave as before. When enabled, files that haven't changed and still
have content in the conversation context return a short 'unchanged'
response instead of re-reading the full content.
Changes:
- Added smartContextTracking to experimentIds in packages/types
- Added SMART_CONTEXT_TRACKING to experiments.ts
- Updated simpleReadFileTool.ts to check experiment before optimization
- Updated ReadFileTool.ts to check experiment before optimization
* feat: add WorkspaceTaskVisibility type and workspaceTaskVisibility property to OrganizationCloudSettings
* refactor: create workspaceTaskVisibilitySchema and derive WorkspaceTaskVisibility type from it
---------
Co-authored-by: Roo Code <roomote@roocode.com>
* Add a way to save screenshots from the browser tool
* fix: use cross-platform paths in BrowserSession screenshot tests
* fix: validate screenshot paths to prevent filesystem escape
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Adds a new search_replace tool that performs a single search and replace
operation on a file, requiring the old_string to uniquely identify the
target text with 3-5 lines of context.
Parameters:
- file_path: Path to file (relative or absolute)
- old_string: Text to find (must be unique in file)
- new_string: Replacement text (must differ from old_string)
* fix: add Kimi, MiniMax, and Qwen model configurations for Bedrock
- Add moonshot.kimi-k2-thinking with 32K max tokens and 256K context
- Add minimax.minimax-m2 with 16K max tokens and 230K context
- Add qwen.qwen3-next-80b-a3b with 8K max tokens and 262K context
- Add qwen.qwen3-coder-480b-a35b-v1:0 with 8K max tokens and 262K context
All models configured with native tool support and appropriate pricing.
Fixes#9902
* fix: add preserveReasoning flag and update Kimi K2 context window
- Added preserveReasoning: true to moonshot.kimi-k2-thinking model
- Added preserveReasoning: true to minimax.minimax-m2 model
- Updated Kimi K2 context window from 256_000 to 262_144
These changes ensure:
1. Reasoning traces are properly preserved for both models
2. Roo correctly recognizes task completion
3. Tool calls within reasoning traces are handled appropriately
4. Context window matches AWS Console specification
* fix: update MiniMax M2 context window to 196_608 for Bedrock
Based on AWS CLI testing, the actual context window limit for MiniMax M2
on Bedrock is 196,608 tokens, not 230,000 as initially configured.
* Update packages/types/src/providers/bedrock.ts
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
