- Save checkpoint before adding user messages to API conversation history
- Add comprehensive tests to verify checkpoint behavior
- Handle checkpoint errors gracefully without interrupting the flow
* 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
* feat: Before requesting, ensure checkpoint is initialized
* Generate a checkpoint before modifying the code
* refactor: streamline checkpoint handling and enhance getCheckpoints method
* Blocked waiting for checkpoint initialization timing to change
* cancel checkpoint restore limit
* fix: ensure checkpoint service is undefined on initialization error and improve checkpoint diff handling
* refactor: simplify checkpoint service initialization and cleanup unused variables in CheckpointMenu
* fix: prevent race condition in checkpoint service initialization
- Only assign service to cline.checkpointService after successful initialization
- Add proper cleanup on initialization failure
- Prevents service from being in inconsistent state if Git check fails
* fix: remove checkpoint save from presentAssistantMessage for update_todo_list case
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* fix: detect Claude models by name for API protocol selection
- Modified getApiProtocol to accept modelId parameter
- Added check for 'claude' in model name (case-insensitive)
- Updated Task.ts to pass model ID to getApiProtocol
- Added comprehensive tests for the new logic
Fixes#5830
* fix: limit Claude model detection to vertex and bedrock providers only
- Modified getApiProtocol to only detect Claude models by name when provider is vertex or bedrock
- Added comprehensive unit tests for getApiProtocol function as requested in PR review
- This ensures Claude models are only auto-detected for providers that need it
* feat: add BatchDiffApproval component for multi-file diff application
- Introduced a new component `BatchDiffApproval` to handle the approval of batch changes across multiple files.
- Integrated the `BatchDiffApproval` component into `ChatRow` to display batch diff requests.
- Updated experimental settings to include a toggle for multi-file apply diff functionality.
- Enhanced localization files to support new strings related to batch changes in multiple languages.
- Updated tests to cover the new multi-file apply diff feature.
* revert this
* fix: update applyDiff parameter type to accept string or DiffItem
* refactor: keep original file name for apply diff tool
* revert this
* Update src/core/webview/__tests__/ClineProvider.test.ts
* revert this
* fix: keep the original path if the experiment is disabled
* test: add dynamic strategy selection tests for MultiSearchReplaceDiffStrategy and MultiFileSearchReplaceDiffStrategy
* fix: mock applyDiffTool module and ensure legacy tool resolves successfully in tests
* remove this
* ellipsis suggestion
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* refactor: mirror concurrent file reads
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* feat(read_file): enhance file reading capabilities with multi-file support and improved parameter handling
fix(read_file): change return to continue on approval rejection in readFileTool
Enhance readFileTool with improved error handling and validation
- Introduced a FileEntry interface for better type management.
- Added validation for start_line and end_line to ensure proper ranges.
- Implemented RooIgnore validation before processing files.
- Enhanced error handling with dedicated functions for file and global errors.
- Streamlined file reading logic to handle binary files, definitions-only mode, and line thresholds more effectively.
- Improved user feedback for empty files and read limits.
chore: update Jest snapshot for system prompt tool usage
Refactor read-file tool to support XML input format and multiple line ranges
- Updated the `getReadFileDescription` function to reflect new XML structure for file reading requests.
- Modified `readFileTool` to parse XML input, allowing multiple line ranges for each file.
- Removed old parsing logic that handled line ranges as separate parameters.
- Implemented validation for line ranges and ensured proper error handling for file access.
- Adjusted approval messaging to accommodate new line range format.
- Enhanced error handling to provide consistent feedback for file read errors.
update from KJ7LNW comment
feat: add maxConcurrentFileReads setting to enhance read_file tool performance
feat: enhance readFileTool with XML parsing and file processing state tracking
feat: enhance readFileTool to include user feedback handling and processing state tracking
chore: clean up read_file tool documentation by removing extra newlines
feat: update read_file tool tests to handle user feedback and approval states
feat: add tests for feedback message formatting and XML special character handling in read_file tool
Implement code changes to enhance functionality and improve performance
feat: increase max concurrent file reads and adjust slider range in settings
feat: increase default max concurrent file reads from 5 to 15 across settings and context management
fix(read_file): enhance legacy path handling and remove duplicate parameters
feat(read_file): enhance file description handling and add support for multiple files in messages
done poc for new ux
idea 1
* fix the test
* fix: normalize locale file formatting to use tabs
- Applied prettier formatting to all locale JSON files
- Fixed mixed indentation (spaces/tabs) to use consistent tabs
- Aligns with project's prettier configuration
* fix(settings): improve checkbox handling and slider configuration in ConcurrentFileReadsExperiment
* fix(read_file): enhance description to include partial reads support
* fix(read_file): update description for partial reads and improve example clarity
* fix: suggestions
* fix: translations
* test: update system prompt snapshots for multi-file read tool
* fix: remove batch permission question from readFile tool translations
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* [Condense] Skip condense and show error if the context grows
* update tests
* changeset
* nit: error should be nonempty
* update translations
* add more errors
* add more test cases
* update translations
* pipe error back from truncate code
* add condense_context_error ClineMessage
* fixes
* translations
* feat: Make checkpoint on new task
Ensures that invoking the `newTaskTool` always creates a checkpoint, even if no files have changed. This provides a consistent state snapshot before a sub-task is initiated.
* refactor: remove delay
---------
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
