- Add fork button to user messages in ChatRow
- Reuse existing delete message logic for truncating history
- Create new task with truncated history using existing createTaskWithHistoryItem
- No tool exposed to the model - purely user-driven functionality
- Minimal implementation as requested in issue feedback
Addresses #9790
When tools are called in parallel (e.g., update_todo_list + new_task),
the tool results accumulate in userMessageContent but aren't saved to
API history until all tools complete. When new_task triggers delegation,
the parent is disposed before these pending results are saved, causing
400 errors when the parent resumes (missing tool_result for tool_use).
This fix:
- Adds flushPendingToolResultsToHistory() method in Task.ts that saves
pending userMessageContent to API history
- Calls this method in delegateParentAndOpenChild() before disposing the
parent task
- Safe for both native/XML protocols and sequential/parallel execution
(returns early if there's nothing to flush)
* feat: add model-specific tool customization via excludedTools and includedTools
- Add excludedTools and includedTools to ModelInfo schema
- Implement applyModelToolCustomization helper to filter tools based on model config
- Integrate model tool filtering into filterNativeToolsForMode for native protocol
- Add comprehensive tests for tool customization functionality
- Wire up modelInfo through buildNativeToolsArray and Task.ts
This allows providers to override which native tools are available on a per-model basis via MODEL_DEFAULTS, enabling better control over tool selection for models with specific needs.
* feat: add customTools for opt-in only tools
- Add customTools array to ToolGroupConfig for defining opt-in only tools
- Update getToolsForMode() to exclude customTools from default tool set
- Modify applyModelToolCustomization() to include customTools only via includedTools
- Add tests for customTools functionality
- Add comprehensive documentation with usage examples
customTools allows defining tools that are NOT available by default,
even when a mode includes their group. These tools are only available
when explicitly included via a model's includedTools configuration.
This enables:
- Gradual rollout of experimental tools
- Model-specific specialized capabilities
- Safe experimentation without affecting default tool sets
* Add assertions for customTools tests per review feedback
* test: add tests for including customTools via includedTools
* Update src/core/prompts/tools/__tests__/filter-tools-for-mode.spec.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>
The pendingNewTaskToolCallId was being set AFTER startSubtask() returned.
However, startSubtask() contains a 500ms delay during which the subtask
could complete. If the subtask completed during this window, completeSubtask()
would be called before pendingNewTaskToolCallId was set, causing it to
fall through to the XML protocol path and add a text message instead of
a proper tool_result block, breaking the API conversation structure.
This fix moves the pendingNewTaskToolCallId assignment to happen BEFORE
calling startSubtask(), ensuring the ID is set before the subtask starts.
If the subtask creation fails, the pending ID is cleared.
* feat: add AWS Bedrock support for codebase indexing
- Add bedrock as a new EmbedderProvider type
- Add AWS Bedrock embedding model profiles (titan-embed-text models)
- Create BedrockEmbedder class with support for Titan and Cohere models
- Add Bedrock configuration support to config manager and interfaces
- Update service factory to create BedrockEmbedder instances
- Add comprehensive tests for BedrockEmbedder
- Add localization strings for Bedrock support
Closes#8658
* fix: add missing bedrockOptions to loadConfiguration return type
* Fix various issues that the original PR missed.
* Remove debug logs
* Rename AWS Bedrock -> Amazon Bedrock
* Remove some 'as any's
* Revert README changes
* Add translations
* More translations
* Remove leftover code from a debugging session.
* fix: add bedrock to codebaseIndexModelsSchema and update brace-expansion override
- Add bedrock provider to codebaseIndexModelsSchema type definition to fix empty model dropdown in UI
- Update pnpm override for brace-expansion from '>=2.0.2' to '^2.0.2' to resolve ESM/CommonJS compatibility issues
* Improvements to AWS Bedrock embeddings support
- Enhanced bedrock.ts embedder implementation
- Added comprehensive test coverage in bedrock.spec.ts
- Updated config-manager.ts for better Bedrock configuration handling
- Improved service-factory.ts integration
- Updated embeddingModels.ts with Bedrock models
- Enhanced CodeIndexPopover.tsx UI for Bedrock options
- Added auto-populate test for CodeIndexPopover
- Updated pnpm-lock.yaml dependencies
* Restore openrouter config
* Remove debug log
* Fix config-manager.spec.ts unit test.
* Add translations for "optional"
* Revert unnecessary change related to open ia embedder
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Co-authored-by: Smartsheet-JB-Brown <jb.brown@smartsheet.com>
* feat: store reasoning in conversation history for all providers
* refactor: address review feedback
- Move comments inside else block
- Combine reasoning checks into single if block
- Make comments more concise
* refactor: make comments more concise
* Fix preserveReasoning flag to control API reasoning inclusion
Changes:
1. Removed hardcoded <think> tag logic in streaming
- Previously hardcoded reasoning into assistant message text
- Now passes reasoning to addToApiConversationHistory as parameter
2. Updated buildCleanConversationHistory to respect preserveReasoning flag
- When preserveReasoning: true → reasoning block included in API requests
- When preserveReasoning: false/undefined → reasoning stripped from API
- Reasoning stored in history for all cases
3. Added temporary debug logs to base-openai-compatible-provider.ts
- Shows preserveReasoning flag value
- Logs reasoning blocks in incoming messages
- Logs <think> tags in converted messages sent to API
* Fix: Use api.getModel() directly instead of cachedStreamingModel
Addresses review comment: cachedStreamingModel is set during streaming but
buildCleanConversationHistory is called before streaming starts. Using the
cached value could cause stale model info when switching models between requests.
Now directly uses this.api.getModel().info.preserveReasoning to ensure we
always check the current model's flag, not a potentially stale cached value.
* Clean up comments in Task.ts
Removed outdated comment regarding model's preserveReasoning flag.
* fix: remove unnecessary reasoningBlock variable in task reasoning logic
