Update AskUserQuestionExecution function definition and ExecutionPrompt to provide clearer guidance on when to ask users vs. report outcomes. Emphasizes resolving ambiguity at discovery point rather than passing uncertain outcomes to orchestrator.
- Remove unused agentExecutionDefinitions and gatedDefinitions methods
- Delete obsolete CreatePlan.ts (replaced by ExecuteWorkflow.ts)
- Rename PlanningAgentSystemPrompt to PlanningPrompt for consistency
- Fix orchestration agent promise returns and replan flag handling
- Make saveConversation calls async throughout AIController
- Simplify vault cache delete event handling
- Change debug logging from console.log to console.debug
- Fix function name references in execution and main agents
Restructure all AI function descriptions to use consistent "Call this function:" and "Do NOT use this function:" sections for improved clarity and scannability.
Track replan state to ensure plan doesn't complete prematurely when a replan
is requested. Also add CompletePlan to orchestration agent definitions and
update step progress callback on successful completion.
- 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
Enhance user question display with markdown rendering for better readability.
Display formatted questions with emphasis, lists, and code snippets. Adjust
input display max-height based on platform (mobile: 15vh, desktop: 30vh).
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.
- Move parseFunctionCall/parseFunctionResponse to ResponseHelper
- Enhance orphaned call/response filtering with detailed debug logs
- Add toolId to conversation content for better tracking
- Fix planning workflow execution mechanics and step numbering
- Remove unused planning agent appendix and detailedAppendixForPlanningAgent
- Add conversation save callbacks throughout AI controller loops
- Improve multi-agent function handling to avoid exceptions
- Update all tests to include toolId fields for proper filtering
- 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
- 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
Add cache control to system prompt, tools, and conversation messages to optimize API performance and reduce costs by caching frequently reused content.
Update GitHub link to point directly to project page.
Improve prompt for user suggestion during actions that require confirmation.
Update unit tests.
Bump dependency versions.
Excludes image/PDF content blocks from text extraction when
isProviderSpecificContent flag is set, avoiding unnecessary token
usage. Updates ReadVaultFiles documentation to clarify image/PDF
reading capabilities and adds system prompt guidance for handling
binary file references.
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.
- Add mobile-specific controls with Accept/Reject buttons for diff review
- Centralize user rejection/suggestion messages in AIFunctionResponse
- Update VaultService to use centralized message constants
- Style mobile buttons with proper touch targets and theme colors
- Auto-focus main view after accepting/rejecting changes on mobile
This change simplifies the patch mechanism by replacing the unified diff format with a straightforward find-and-replace approach. The PatchVaultFile function now accepts oldContent and newContent parameters instead of a diff patch string, making it more intuitive and reliable for AI agents to use.
Key changes:
- Update PatchVaultFile function signature and documentation
- Replace diff.applyPatch() with String.replace()
- Simplify error handling for content matching
- Update all tests to reflect new API
- Remove unused applyPatch method from DiffService
- Fix diff container height calculation in CSS
- Fix error notification logic in ChatService
- Fix conversation deletion order in TopBar component
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.
Move isValidJson, dateToString, and escapeRegex from Helpers to new StringTools class. Add asRegex method for parsing regex literals with /pattern/flags format. Update all imports and usages across codebase.
- Change function arguments type from `Record<string, object>` to `Record<string, unknown>`
- Add Zod schemas for all AI function arguments validation
- Improve TypeScript types across modals and services
- Add ESLint disable comments for intentional exceptions
- Fix async/await handling in modal and view lifecycle methods
- Update dependencies (@typescript-eslint 8.46.4, rollup 4.53.2, zod 4.1.12)
Remove custom interface definitions for Claude, OpenAI, and Gemini APIs in favor of importing types directly from official SDKs (@anthropic-ai/sdk, openai, @google/genai). Add openai package dependency and update StoredFunctionResponse interface to include name field.
Replace `any` types with proper TypeScript interfaces and type assertions throughout Claude, Gemini, and OpenAI implementations. Add explicit typing for streaming events, function parameters, and conversation content to improve type checking and reduce runtime errors.
- Enhance DeleteVaultFiles to handle both files and folders
- Change VaultService.delete to use vault.trash instead of permanent deletion
- Remove TFile type check to allow folder deletion
- Simplify delete method signature by removing unused force parameter
- Increase default snippet size limit from 150 to 300 characters
- Fix IPrompt to use SettingsService instead of direct plugin access
- Update all tests to reflect trash behavior and folder support
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
- 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)
- 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
- Add abort flag to prevent semaphore double-release during stop
- Stop active chats before deleting conversations to avoid state corruption
- Treat empty search terms as explicit request for all files
- 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
- Update SearchVaultFiles function to return contextual snippets instead of just file lists
- Implement snippet extraction with configurable context length (300 chars)
- Add snippet merging logic to consolidate overlapping matches
- Limit results to 20 randomly sampled matches when exceeding threshold
- Update return types across service layer to use SearchMatch/SearchSnippet
- Change regex flags to 'ig' for global case-insensitive matching
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.
- Add allowDestructiveActions parameter throughout AI request chain
- Implement edit mode UI toggle with visual indicators
- Update getQueryActions to conditionally include destructive tools
- Add blue highlight styling when edit mode is active
