Remove version numbers from Mistral model enum names (MistralLarge_3 → MistralLarge, MistralMedium_3_1 → MistralMedium, MistralSmall_3_2 → MistralSmall) and update display text to indicate "latest" versions. This aligns naming with the underlying "latest" API endpoints and improves maintainability.
Replace the single Replan tool with three targeted alternatives:
ReviseStep, RevisePlan, and SkipStep. This gives the orchestration
agent more precise control over plan recovery — revising only the
current step, replacing all remaining steps, or skipping a step
entirely — rather than triggering a full replan each time.
Also give the orchestration agent read access to vault files so it
can resolve execution failures without routing back to the planning
agent, and update the execution agent prompt to stop it from
attempting self-recovery (gap resolution is now the orchestrator's
responsibility).
Emit tool call start events immediately when tools begin execution,
allowing UI to display contextual "thinking" messages (e.g., "Generating
note contents..." for WriteVaultFile) before tool completion. Add
Spinner to ThoughtIndicator component for visual feedback during tool
operations.
Migrate attachment storage from base64-in-JSON to separate binary files with SHA-256 naming, add automatic garbage collection, implement lazy loading via getBase64() and getMimeType() methods, normalize text MIME types, add image resizing, and update all AI provider integrations. Fix small issue that caused the chat area to scroll down on message streaming end even when scrolled up.
- Rename toolDefinitions to aiFunctionDefinitions across all AI classes
- Add aiFunctionUsageMode property to control function calling behavior
- Implement provider-specific tool_choice/tool_config based on usage mode
- Remove AIController and create BaseAgent base class
- Update ExecutionPrompt with scope of execution guidelines
- Simplify ChatArea layout update logic by removing debounce
- Add naming service completion wait in ChatService
- Replace console.warn with Exception.warn in InputService
- Delete unused AIController.ts file
- Update all tests to use new aiFunctionDefinitions property
- Expand SystemPrompt wiki-link guidance with examples and common mistakes
- Add ResizeObserver to ChatPlanArea for dynamic height adjustments
- Improve plan completion summary prompt with more context requirements
- Add context_for_next_step parameter to CompleteStep for passing execution history
- Add context parameter to CompleteTask for preserving task completion state
- Update OrchestrationResult to handle context propagation between steps
- Add debug color differentiation for agent types (Main, Execution, Orchestration, Planning)
- Reorganize SearchTypes from Helpers to Types directory
- Add justification requirement for execution deviations
- Support reasonable deviations in orchestration plan validation
- Refactor dependency service with TryResolve utility
- Add whitespace cleanup to Semaphore class
Restructure the AI workflow from a single-agent model to a specialized
multi-agent system with distinct roles:
- Add AgentType enum (Main, Orchestration, Planning, Execution) to define
agent specializations
- Replace AIControllerService and AIFunctionService with modular agent
classes in Services/AIServices/:
- MainAgent: Handles user interaction and delegates to orchestration
- OrchestrationAgent: Coordinates plan execution and step-by-step workflow
- PlanningAgent: Creates and revises execution plans
- ExecutionAgent: Executes individual plan steps
- AIController: Base class providing common agent loop functionality
- Create specialized prompts (OrchestrationPrompt, ExecutionPrompt) for
agent-specific behavior
- Add OrchestrationResult type to communicate workflow control decisions
(continue, abort, replan)
- Introduce agent-specific function scoping:
- ExecuteWorkflow for main agent
- CompleteTask for execution agent
- CompleteStep/Replan/CancelPlan for orchestration agent
- SubmitPlan/AskUserQuestionPlanning for planning agent
- Update BaseAIClass to use agentType property instead of isPlanningAgent
boolean for model selection
- Simplify ExecutionPlan and ExecutionStep types by removing execution
state tracking (moved to agent coordination)
- Remove PlanningEnabledAppendix and ExecutionStatus enum (superseded by
agent architecture)
- Add comprehensive integration tests for agent workflows
This architecture provides better separation of concerns, clearer agent
responsibilities, and more robust plan execution with explicit orchestration
control flow.
Add distinct AskUserQuestionPlanning and AskUserQuestionExecution functions to enable user consultation during both planning and execution phases. Update system prompt to clarify when to seek user input vs. replan. Fix plan area rendering timing and improve execution flow handling.
- Add currentProvider getter to AI classes for provider access
- Enhance planning prompt to discourage over-engineering and scope creep
- Return Unknown enum instead of throwing for invalid AI functions
- Add completion reminders to execution steps
- Fix ChatPlanArea height calculation timing
- Update tests to handle Unknown function gracefully
Document the new two-agent planning workflow, including how it works, when to use it, capabilities, visualization, and planning model configuration. Add planning mode section to both README.md and help copy.
Introduce separate planning model setting to allow using different models for planning vs execution. Add visual countdown display when rate limits are hit, with improved retry delay parsing across providers (Claude, OpenAI, Gemini). Refactor settings tab into Views directory and enhance mobile layout for input controls.
- Add MAX_AGENT_DEPTH check to prevent infinite planning recursion
- Prompt user to submit plan if not provided instead of silent failure
- Clear planning mode when deactivating edit mode
- Remove inline overflow-y style in favor of CSS declaration
- Update error copy for clarity
- Remove unused deactivateEditMode method
Add new CompletePlan function with schema and validation to allow agents to explicitly signal when all execution steps are done. Update system prompt to include completion confirmation step. Refactor execution loop to recursively prompt for completion if incomplete, with MAX_EXECUTION_DEPTH limit replacing MAX_PLANNING_ITERATIONS. Remove automatic incomplete execution handling in favor of explicit agent-driven completion.
- Add planning mode toggle and AskUserQuestion function for interactive planning
- Fix Gemini cross-provider function call detection using toolId presence
- Update OpenAI naming service to handle new response format
- Improve system prompts by removing complexity gate, streamlining to action-first principle
- Add InputDisplay component and question mode to ChatInput
- Refactor execution plan error messages to show all incomplete steps
- Update tests to reflect cross-provider function call format changes
Restructure system prompt to enforce mandatory complexity evaluation before action. Replace verbose multi-step planning framework with concise gate-based decision model. Add UI for execution plan visibility. Improve planning/execution separation by blocking execution tools during planning phase. Remove cancellation indicator component. Fix conversation deletion bug preventing saves after delete. Strengthen type safety for AIFunction names. Simplify function summary format for planning agent. Update test mocks for new callback signatures.
- Add toolId matching validation for function call/response pairs
- Filter orphaned function calls and responses with warnings
- Add CancelPlan function to abort plan execution
- Fix planning response handling in execution agent
- Pass clearThoughtOnContent flag through streaming pipeline
Previously the next step description was embedded in the completion message string.
Now return it as a separate structured object with step number, description,
instruction, and optional context for better programmatic access.
- Move prompts from AIClasses to AIPrompts directory
- Replace centralized IPrompt injection with direct property setters on IAIClass
- Remove allowDestructiveActions parameter from streamRequest methods
- Add toolDefinitions, systemPrompt, and userInstruction properties to IAIClass
- Refactor AIFunctionDefinitions to static methods with agent-specific tool sets
- Add planning agent function definitions (CreatePlan, Replan, CompleteStep, SubmitPlan)
- Create AIControllerService to handle agent orchestration
- Add execution plan related copy strings and replacement utility
- Update all AI providers (Claude, Gemini, OpenAI) to use new architecture
- Move MimeTypeToFileTypes and FileTypeToMimeType mappings to dedicated FileTypeMimeTypeMapping enum file
- Add empty content validation for file attachments
- Add PDF support for Gemini
- Display attachment references in user messages with file info
- Fix OpenAI unsupported mime type message formatting
- Improve URI list handling in InputService to include text/plain
- Update chat area padding and styling for better attachment display
- Prevent drag selection on chat padding element
- Update test assertions for new unsupported mime type message format
refactor: standardize file type and MIME type handling across AI providers
Introduce centralized MimeType enum and bidirectional mappings between file types and MIME types. Update Claude, Gemini, and OpenAI implementations to use consistent MIME type validation. Add file attachment support via drag-and-drop and paste in chat input. Expand supported file type detection to include programming languages, config files, and documentation formats.
Add a new "File Monitoring Guidelines" section in plugin settings that displays provider-specific information about uploaded file retention and cleanup. The section includes a help button that opens the Plugin Guide modal and updates dynamically based on the selected AI provider (Claude, Gemini, or OpenAI). Also update help modal content with file monitoring information and fix example template link.
Add support for reading images (PNG, JPG, JPEG, WebP) and PDFs in ReadVaultFiles. Implement provider-specific formatting for binary content (Claude, OpenAI, Gemini). Update conversation structure to handle binary files separately from text responses. Add unpdf library for PDF text extraction in search.
Implement thought signature tracking for Gemini function calls to support Gemini 3 requirements. Migrate OpenAI integration from Chat Completions to Responses API with proper input/output item handling. Add cross-provider compatibility via legacy text format fallback for conversations without thought signatures or tool IDs. Improve chat auto-scroll behavior and conversation validation. Add and update AI class and conversation tests.
Replace console.error/log with Exception.log helper, improve OpenAI error handling with retryable errors, add type-safe model validation, and add new AI models (Claude Opus 4.5, Gemini 3 Pro Preview, GPT-5.1)
Implements unified diff patching as an alternative to WriteVaultFile for making targeted changes without replacing entire files. Includes new PatchVaultFile AI function, DiffService.applyPatch method, and comprehensive test coverage.
Introduce a new AbortService to centralize cancellation logic across all async operations, replacing scattered AbortSignal parameters with a unified singleton service. This improves maintainability and provides consistent cancellation behavior throughout the application.
Key changes:
- Add AbortService for centralized abort signal management with automatic cleanup
- Refactor all AI providers (Claude, Gemini, OpenAI) to use AbortService instead of passing AbortSignal parameters
- Update streaming operations to use centralized abort handling
- Add CancellationIndicator component to show visual feedback during operation cancellation
- Rename ChatAreaThought to ThoughtIndicator for better semantic clarity
- Add Environment enum for consistent environment detection
- Enhance ChatService lifecycle with proper cancellation state management
- Remove scattered abort-related UI selectors and error messages in favor of dedicated indicator
- Add safeContinue() factory method to ConversationContent for internal continuations
- Update all tests to reflect new abort handling architecture
This change simplifies the API surface by removing AbortSignal parameters from method signatures while improving the user experience with clearer cancellation feedback.
Implement a comprehensive diff viewing system that allows users to review and approve/reject file changes before they're applied. The system includes event-driven architecture for managing diff lifecycle and integrates diff2html for rich visual diffs.
Key changes:
- Add DiffService for managing diff approval workflow with accept/reject/suggest actions
- Create EventService for type-safe event handling (DiffOpened/DiffClosed)
- Add DiffView component with diff2html integration for visual diff rendering
- Modify VaultService to propose changes and require confirmation before file operations
- Update FileSystemService to support optional confirmation for write operations
- Add Event enum for centralized event type definitions
- Import custom styles and diff2html styles for proper diff rendering
- Update ConversationContent validation to support optional toolId field
- Remove FileManager from dependency injection (now accessed directly from app)
- Update .gitignore to track styles.css instead of main.css
Replace console.error calls with Exception.log, implement typed API errors with automatic retry for transient failures (rate limits, server errors), add error state tracking to conversation content, and enhance system prompt with action-first operating principle, update unit tests
Add Exception helper class for consistent error handling and logging. Replace throw statements and console.error calls with Exception methods. Update service methods to return Error | T instead of mixed success/failure objects. Improve type safety in Claude.extractContents with explicit return type.
Add WikiLinks helper to VaultCacheService for managing wiki link references.
Update unit tests.
Remove 'gpt-4.1-nano' which does not support web search.
Replace Chat Completions API with OpenAI Responses API throughout codebase. Update event parsing from delta-based streaming to event-based model, restructure request format to use instructions/input instead of messages array, and revise conversation naming service to handle new response structure.
- Clarify issue reporting call-to-action in welcome message
- Add comprehensive 503 Service Unavailable error documentation
- Document common Gemini service interruptions and resolution steps
- Add shuffleArray helper function for randomized file processing
- Process files in parallel batches to improve search performance
- Implement early termination when sufficient matches are found
- Optimize snippet extraction to reduce redundant text operations
- Simplify search result structure to reduce memory overhead
- Update setting description to mention increased search time
- Fix test mocks for empty search term handling
Add validation to check for missing or empty function call IDs when
converting stored conversation history. Function calls and responses
without valid IDs are now converted to text format with [Legacy Tool Call]
and [Legacy Tool Result] prefixes to preserve context when switching
between providers.
Also improve ConversationHistoryModal initialization, add empty state
copy constant, enhance system prompt with regex pattern guidance, and
clean up formatting.
- Add AIFunction enum type to AIFunctionCall name property
- Implement fromString helper to convert string to AIFunction
- Update Claude, Gemini, and OpenAI classes to use aiFunctionFromString
- Add type safety to AIFunctionService switch statement
- Update all test files to use AIFunction enum values
- Extract hardcoded strings in HelpModalSvelte to Copy enum constants
- Update manifest version to 1.0.0 and minAppVersion to 1.9.14
- Replace placeholder author/funding URLs with actual GitHub and Buy Me a Coffee links
- Improve maintainability by centralizing UI copy in Enums/Copy.ts
- Add detailed plugin guide covering modes, references, and instructions
- Add troubleshooting section with API key and rate limit solutions
- Add privacy documentation explaining data storage and exclusions
- Make "User Instructions" text clickable to open help modal
- Support opening help modal to specific topic via initialTopic prop
- Add internal link handling to navigate from help modal to vault files
- Update About section with GitHub link and contribution info
- Filter out messages with empty content in Claude, Gemini, and OpenAI
- Insert hidden "Continue" message when last message is from assistant
- Remove function call JSON from assistant message content
- Hide empty messages in ChatArea UI
- Add GitHub link and about content to help modal
- Add comprehensive tests for message handling edge cases
