Clarify execution vs orchestration responsibilities, eliminate conditional step patterns in planning, add explicit plan completion signal, and strengthen guidance on atomic unconditional actions with outcome-based routing.
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.
Track agent initialization, function calls, workflow transitions, and completion states across MainAgent, OrchestrationAgent, PlanningAgent, ExecutionAgent, and AIController. Remove unused window.debugServiceLog global declaration.
- 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.
Move step height measurements into updateHeight function to ensure fresh calculations on each update, preventing stale reactive declarations from causing incorrect collapsed height values
Test agent loop function calls, planning mode, execution agent, replan workflow, error handling, save callbacks, and shouldContinue flag behavior. Update mocks to use AIFunctionResponse class and rename onPlanComplete to onPlanReset.
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.
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 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.
- Wrap user messages in <message_to_title> tags to prevent prompt injection
- Expand NamePrompt with security guidelines and edge case handling
- Add 10-word limit truncation for generated titles
- Move conversation save before naming to ensure persistence
- Add comprehensive task complexity assessment framework to SystemPrompt
- Change stack limit error to warning log for better resilience
Move parseFunctionCall and parseFunctionResponse from BaseAIClass private methods to shared ResponseHelper module for better code reusability across providers and tests.
- 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
Implement extractRetryDelay methods in Claude, Gemini, and OpenAI classes to parse provider-specific retry delay headers/responses. Update StreamingService to use these delays when available, falling back to exponential backoff. Enhance ApiError to include response headers and body for retry delay extraction.
- 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
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.
- Move icon name logic to Attachment and Reference classes
- Create reusable setElementIcon Svelte action in ElementHelper
- Update ChatArea and ChatAttachments to use new icon helper
- Add visual separator and background color for message attachments
- Fix duplicate URIs in drag-and-drop file handling
- Improve attachment icon centering with flexbox layout
Replace errorMessage string with uploadErrors array in processAttachments
to provide structured error handling. Enhanced error messages to include
file names. Added getHeader helper method for case-insensitive header
lookups. Fixed Gemini upload to use contentType parameter instead of
Content-Type header.
- Add validation check for file ID after upload attempt
- Clear existing file ID before re-uploading to prevent stale IDs
- Replace Node.js Buffer with standard Uint8Array/ArrayBuffer for cross-platform compatibility
- Add missing Content-Type header for Gemini file uploads
- Update tests to use TextDecoder for ArrayBuffer inspection
Enhance WorkSpaceService.getActiveFile() to filter out excluded files using VaultService.isExclusion(), preventing access to restricted paths. Add optional allowAccessToPluginRoot parameter for cases requiring access to plugin root directory. Update test expectations to match new method signature.
- Include user's current active file path in chat requests
- Move conversation save after attachments are added
- Extract formattedRequest in suggest handler
- Add WorkSpaceService.getActiveFile() method
- Remove premature chatArea layout update
- Update unit tests
- 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 pageNumber field to ISearchSnippet and IPageText interfaces
- Update extractSnippets to process content as paginated text
- Switch PDF reading to use readPDF helper for page extraction
- Update search results to include page numbers in snippets
- Add page number assertions to VaultService tests
- Add isObserver parameter to updateChatAreaLayout for instant ResizeObserver updates
- Wrap chat area in container with top and bottom fade gradients
- Improve scroll visual feedback with gradient overlays
- Update dependencies: openai 6.15.0, svelte-check 4.3.5, @testing-library/svelte 5.2.10
Consolidate duplicate file upload and error handling code from Claude, Gemini, and OpenAI into shared `processAttachments` method in BaseAIClass. Remove unnecessary abort service wrapping from BaseAIFileService retry logic.
