Previously, when users initiated context condensing and switched to another task before completion, the 'condensing context' indicator would persist on the new task.
This fix ensures the condensing state is properly reset in the task switching effect, preventing the indicator from appearing incorrectly on different tasks.
- Removed array slicing logic that limited messages to 500
- This eliminates array index shifting that caused Virtuoso to lose scroll position
- Virtuoso is designed to efficiently handle large lists through virtualization
- Fixes the scrollbar jumping issue reported in #7063 and #7052
Co-authored-by: Roo Code <roomote@roocode.com>
Fixes#6756
When ripgrep encounters file access errors (e.g., permission denied), it would cause the search_files tool to return empty results. Adding the --no-messages flag suppresses these error messages while still showing pattern syntax errors, allowing the search to continue and return valid results from accessible files.
Co-authored-by: Roo Code <roomote@roocode.com>
* fix: make search_files path parameter optional and clarify tool descriptions
- Made path parameter optional in search_files tool (defaults to workspace root)
- Updated search_files description with clearer examples
- Improved codebase_search description to clarify when to use path parameter
- Updated test snapshots to reflect the changes
This addresses confusion where LLMs were unnecessarily specifying paths when searching from project root
* revert: remove search_files changes, keep only codebase_search improvements
- Reverted all changes to src/core/prompts/tools/search-files.ts
- Reverted all changes to src/core/tools/searchFilesTool.ts
- Updated test snapshots to reflect the reverted search_files tool
- Kept the codebase_search tool description improvements as intended
* Update codebase-search.ts
Simplify codebase_search tool documentation
- Condensed description to eliminate repetitive explanations about user wording
- Reduced from 2 examples to 1 comprehensive example showing optional path usage
- Streamlined parameter descriptions to remove redundancy
- Maintained all critical requirements (English queries, semantic search, path optionality)
- Reduced documentation size by ~40% while preserving clarity
* fix: add workspace directory context to codebase_search path parameter
- Added ToolArgs import and parameter to getCodebaseSearchDescription function
- Updated path parameter description to include '(relative to the current workspace directory ${args.cwd})'
- Updated index.ts to pass args to getCodebaseSearchDescription
- Maintains consistency with other tool descriptions like list_files and search_files
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Hannes Rudolph <hrudolph@gmail.com>
* fix: add explicit max_output_tokens for GPT-5 Responses API
- Added max_output_tokens parameter to GPT-5 request body using model.maxTokens
- This prevents GPT-5 from defaulting to very large token limits (e.g., 120k)
- Updated tests to expect max_output_tokens in GPT-5 request bodies
- Fixed test for handling unhandled stream events by properly mocking SDK fallback
* fix: add missing translations for reasoningEffort.minimal in Indonesian and Dutch locales
* fix: correct GPT-5 response ID persistence and usage
- Renamed metadata field from 'previous_response_id' to 'response_id' for clarity
- Fixed logic to correctly use the response_id from the previous message as previous_response_id for the next request
- This resolves the 'Previous response with id not found' errors that occurred after multiple turns in the same session
* feat: add robust error handling for GPT-5 previous_response_id failures
- Automatically retry without previous_response_id when it's not found (400 error)
- Clear stored lastResponseId to prevent reusing stale IDs
- Handle errors in both SDK and SSE fallback paths
- Log warnings when retrying to help with debugging
* fix: handle GPT-5 response ID race condition with nano model
- Add promise-based synchronization for response ID persistence
- Wait for pending response ID from previous request before using it
- Resolve promise when response ID is received or cleared
- Add 100ms timeout to avoid blocking too long on ID resolution
- Properly clean up resolver on errors to prevent memory leaks
This fixes the race condition where fast nano model responses could cause
the next request to be initiated before the response ID was fully persisted.
* fix: address PR review comments for GPT-5 implementation
- Extract usage normalization helper to reduce duplication
- Suppress conversation continuity for first message (but respect explicit metadata)
- Deduplicate response ID resolver logic
- Remove dead enableGpt5ReasoningSummary option references
- DRY up GPT-5 event/usage handling with normalizeGpt5Usage helper
- Centralize default GPT-5 reasoning effort using model info
- Fix Indonesian locale minimal string misplacement
- Add clarifying comments for Developer prefix usage
- Add TODO for future verbosity UI capability gating
- Fix failing test in reasoning.spec.ts
* fix(openai-native): address Roomote inline feedback\n\n- Delegate standard GPT-5 SSE event types to shared processor to reduce duplication\n- Add JSDoc for response ID accessors\n- Standardize key error messages for GPT-5 Responses API fallback\n- Extract persistGpt5Metadata() in Task to simplify metadata writes\n- Add malformed JSON SSE parsing test\n
* fix(openai-native,gpt5): correct usage cost calc (use calculateApiCostOpenAI incl. cache); enforce 'skip once' continuity via suppressPreviousResponseId; dedupe responseId resolver on SSE 400; feat: gate reasoning.summary by enableGpt5ReasoningSummary; centralize default reasoning effort; types/ui: add ModelInfo.supportsVerbosity and gate Verbosity UI by capability; refactor: avoid duplicate usage emission in SSE done/completed
* fix(gpt5): default enableGpt5ReasoningSummary=true to preserve tests and expected behavior
* fix(gpt5): canonicalize GPT-5 metadata key to previous_response_id and align enableGpt5ReasoningSummary default docs
* fix(openai-native): remove review artifact comments and guard GPT-5 in completePrompt
