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
Replace hardcoded strings in AIAgentSettingTab with Copy enum constants for better maintainability and consistency. Add new Copy entries for settings labels, descriptions, placeholders, and tooltips. Update README with comprehensive documentation and fix textarea resize behavior.
- Add titles for About, Plugin Guide, Troubleshooting, and Privacy sections
- Limit topic sidebar width to 150px with text truncation for long labels
- Apply ellipsis overflow handling to prevent layout breaking
- Add HelpModal enum entries for titles and content
- Implement HelpModalSvelte component with sidebar navigation
- Add topic selection functionality with fade transitions
- Style help modal with grid layout and custom backgrounds
- Display plugin version in modal footer
- Apply consistent spacing with conversation history modal
Add user-configurable settings for search results limit (5-40) and snippet size limit (50-1000 chars) to control AI context usage. Update VaultService to use these limits instead of hardcoded values. Include comprehensive test coverage.
- Add dropdown interface for selecting custom user instructions
- Include "No custom instructions" option to clear selection
- Highlight currently active instruction with accent border
- Auto-save selected instruction to plugin settings
- Close dropdown on click outside or focus loss
- Add keyboard navigation with arrow keys and enter
- Scroll selected instruction into view automatically
- Reset search state when chat input loses focus
Refactor SearchVaultFiles to accept array of search terms, add user instruction panel in chat input with toggle button, move user instruction path to settings (from hardcoded), improve search result interaction with mouse/keyboard support, fix async exists() method in VaultService, and create example instructions file on first launch
Introduces HTMLService to centralize HTML/DOM operations and updates
SearchTrigger, StreamingMarkdownService, and tests to use the new
service instead of directly manipulating innerHTML and DOM methods.
- Add new ListVaultFiles AI function for listing vault contents
- Remove auto-fallback to listing all files when search returns 0 results
- Improve SearchVaultFiles description to clarify it searches content
- Add listFoldersInDirectory and listDirectoryContents methods to VaultService
- Update SanitiserService to normalize empty strings to "/" (vault root)
- Add allowAccessToPluginRoot parameter to searchVaultFiles
- Update tests to reflect new search behavior and list operations
- Add DeregisterAllServices call in plugin onunload
- Update dependencies (@google/genai, svelte, vitest, eslint)
- Add tooltips to search trigger elements for better visibility
- Fix cursor detection logic for contenteditable="false" elements
- Make user messages render as HTML to support rich content
- Add default cursor style to search triggers
- Remove debug console.log statement
- Clean up unused import in SearchTrigger
Replace getNodeAtCursorPosition with getElementBeforeCursor for more robust element detection before cursor. Add cursor position validation after deletions to prevent cursor from ending up inside contenteditable="false" elements. Remove unused helper methods and reorganize code structure.
refactor: rename type interfaces to use I prefix convention
Standardize naming by adding I prefix to all interface types across the codebase (StreamChunk → IStreamChunk, SearchMatch → ISearchMatch, etc.). Also rename conversationStore.ts to ConversationStore.ts for consistency.
Register VaultCacheService as singleton dependency, add file event registration to VaultService for monitoring vault changes, implement listVaultContents method to retrieve all files and folders with exclusion filtering, and add comprehensive test coverage for new functionality.
Replace simple API provider selection with comprehensive model dropdown organized by provider (Claude, OpenAI, Gemini). Update settings schema from `apiProvider` to `model`, add AIProvider.fromModel() helper, simplify provider URLs, and fix indentation inconsistencies throughout codebase.
- Split content and functionCall into separate fields in ConversationContent
- Extract content parsing logic into dedicated methods for Claude and Gemini
- Add API error 429 handling with provider-specific user information
- Improve error messages in naming services to include response text
- Increase max_tokens for main requests and naming services
- Optimize ChatService to reduce unnecessary saves and array recreations
- Remove message key binding in ChatArea to improve performance
- Adjust chat window max-width to fixed pixel value
- Add Claude and OpenAI ConversationNamingService with API integration
- Register Claude and OpenAI naming service in dependency injection
- Add model and URL constants for naming
- Add Claude and OpenAI to AIProviderModel enum
- Implement ClaudeTokenService and OpenAITokenService
- Update service registration to handle new providers
- Install @anthropic-ai/sdk and gpt-tokenizer dependencies
- Add error handling for invalid provider selection
- Implement ITokenService interface and GeminiTokenService for token counting
- Add StatusBarService for managing status bar messages
- Extract AIProviderModel enum to centralize model configuration
- Remove unused MessageService and AIThoughtMessage classes
- Update dependency registration to include new services
- Clean up main plugin initialization and status bar handling
Implement automatic conversation title generation using Gemini API. Add IConversationNamingService interface with GeminiConversationNamingService implementation. Integrate naming service into ChatService to generate titles on first user message. Update ConversationFileSystemService to support title updates via file renaming.
- Rename DeleteVaultFile to DeleteVaultFiles with array support
- Add MoveVaultFiles function for file relocation and renaming
- Refactor file operations to return structured success/error results
- Move directory creation logic to VaultService
- Register FileManager dependency for file operations
- Fix CSS variable for interactive accent blue hover state
- Rename ReadVaultFile to ReadVaultFiles with multi-file support
- Add DeleteVaultFile function with confirmation parameter
- Update function references and error handling
- Return detailed error objects from FileSystemService
- Remove unnecessary reasoning parameter from web search function
- Update Path enum to separate root and AI agent directory
- Add filename matching to vault search results
- Use Path enum constants consistently across services
- Rename ReadFile to ReadVaultFile for consistency
- Add WriteVaultFile function for destructive operations
- Fix array concatenation bug in getQueryActions
- Return all vault files when search yields no results
- Update SearchVaultFiles description to clarify fallback behavior
- Improve error handling in writeFile to return error details
- Reorder system prompt sections for better clarity
Replace list_vault_files function with search_vault_files that performs regex-based content search instead of listing all files. Add escapeRegex helper for search term sanitization. Remove unused edit mode CSS.
