Move common OpenAI-compatible API code to ChatCompletionsAIClass base, unify retry delay extraction and tool-choice mapping across providers (Claude, Gemini, Mistral, OpenAI), fix Gemini model labels, and correct scroll state when content is not scrollable
Fix Gemini model naming in settings. Fix CHat area scroll to bottom state when clearing a conversation.
Remove slider setDynamicTooltip calls in settings UI and update project dependencies including Anthropic SDK, Google GenAI, Shikiji, and various dev dependencies to latest versions.
- Add AssetsService to manage plugin icon and banner assets
- Update sidebar, ribbon, and quick actions to use new icon
- Add plugin banner to help modal welcome section
- Update help text to reference "plugin icon" instead of "sparkles icon"
Remove deprecated model versions (Claude 4/4.5/4.6, Gemini 2.5, GPT 5.4 Pro, Mistral latest aliases) and replace with current model identifiers. Add DEFAULT_QUICK_MODEL_BY_PROVIDER configuration, update default models to use Sonnet 4.6 standard and Opus 4.8 for planning, and adjust Mistral agent to use Small model.
Move replaceCopy function from Copy enum to Helpers module to improve
separation of concerns. Add splitFrontmatter and mergeTagsIntoFrontmatter
utilities for YAML frontmatter manipulation. Remove unused Beautify prompt
and QuickActionsService. Add timeout support to Semaphore.wait(). Remove
unused Event.QuickActionsSettingsChanged. Update all imports across AI
classes, prompts, services, and tests.
Remove unused dispose method and settings subscription from BaseAIClass. Update SettingsService to track which settings changed and notify subscribers with specific changed keys. Components now only react to relevant setting changes. Export RegisterAiProvider and call it when AI provider settings change to ensure provider is re-registered with new configuration.
Replace activeDocument/activeWindow globals with Obsidian API equivalents (createFragment, createDiv, createSpan, window), update officeparser to use async API, switch diff2html import path and disable highlight option, prefix unused parameters with underscore, and update dependencies including @anthropic-ai/sdk, @google/genai, officeparser, and various dev dependencies
- Change settings from mutable to readonly with updateSettings method
- Add settings change subscription system for reactive updates
- Remove direct property mutations throughout codebase
- Make API key reactive to provider changes via subscription
- Consolidate all settings updates through single async method
- Remove unused RegisterAiProvider export and AIToolDefinitions.isGated
Implement optional drawer element hiding on mobile devices when the chat input is focused, providing more screen space for the on-screen keyboard. Elements smoothly animate away on focus and restore on blur. Includes new setting in Advanced Settings section and updates Anthropic SDK to 0.91.1.
Add settings to enable/disable quick actions in both the editor context menu and toolbar. Implement dynamic registration system that updates when settings change. Include event-driven architecture for settings changes and improve toolbar injection logic. Update dependencies to latest versions.
Introduce QuickActionsService and QuickAgent for lightweight, single-shot AI
operations. Add a dedicated quickActionModel setting alongside a new top-level
provider setting, with validation ensuring all models match the selected provider
and provider-specific defaults. Refactor FileSystemService to offer both TFile
and path-based overloads (readFile/readFilePath, writeToFile/writeToFilePath,
patchFile/patchFileAtPath). Replace window/document globals with activeWindow/
activeDocument throughout InputService and VaultkeeperAISettingTab for Obsidian
mobile compatibility.
Update linting packages to latest.
Introduce a new setting to control AI access to the web viewer tool and refactor prompt building to inject capability directives (memories, web search, web viewer) into all agent contexts. Update tool definitions to conditionally include web viewer and memory tools based on settings. Consolidate memories injection and active directives into a unified prompt builder pattern.
Add new get_web_viewer_content tool that allows AI agents to retrieve
text content or screenshots from open web views. Refactor AIToolResponse
to use AIToolResponsePayload class for structured responses with attachment
support. Update tool service to handle binary file attachments consistently
across read_vault_files and new web viewer tool.
Add memories feature allowing AI to retain vault conventions, user preferences, and established workflows across conversation sessions. Include read-only mode option, validation requiring read-before-write, and settings UI with toggle controls.
Adjusted default search and snippet size values in plugin settings.
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.
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.
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.
- Remove unused Platform import from ChatWindow
- Add grid column for mobile layout in TopBar
- Add await to tick() promise in UserInstruction
- Enhance refocusMainView with explicit focus setting in DiffView
- 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
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.
Improve component lifecycle management by converting DiffService and StatusBarService to extend Component class, ensuring proper cleanup and event handling. Add automatic service cleanup in DependencyService during deregistration.
Refine error handling in AI function responses to return error messages instead of Error objects for better serialization. Update user rejection messaging to provide clearer guidance to AI about stopping actions.
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
Add eslint-plugin-eslint-comments to require descriptions on all
disable directives. Replace generic eslint-disable comments with
specific explanations of why rules are disabled. Change `any` type
to `unknown` in DependencyService and add justification for remaining
`any` usage in StreamingMarkdownService.
- 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)
- Add mobile-specific height constraints for input buttons
- Fix message alignment to left for better readability
- Change click to mousedown for better mobile responsiveness
- Adjust top bar grid columns for mobile layout
- Update view type identifier to 'ai-agent-main-view'
- Standardize quote style to double quotes across config files
- Extract functionCall/functionResponse objects properly in Gemini
- Reset chat area state when loading conversations
- Add SanitiserService for path validation
- Prevent duplicate conversation names
- Improve chat scrolling and padding logic
- Clear streaming state on submission complete
- Add sparkles icon to MainView via getIcon() method
- Integrate StatusBarService to clean up status messages on view close
- Center view content with max-width constraint
- Apply consistent background styling to leaf content
Replace hardcoded color values and custom CSS variables with Obsidian's
built-in theme variables for backgrounds, borders, and interactive elements.
Removes unused isStreaming state and simplifies gradient background. Updates
view display text to "AI Agent".
- Updated package.json to include dependencies for rehype and remark plugins for markdown processing.
- Added default highlight.js CSS for code highlighting.
- Included KaTeX CSS for rendering mathematical expressions.
- Created markdown.css for styling markdown content in the Obsidian plugin, incorporating styles for headings, paragraphs, lists, tables, and code blocks.
- Customized highlight.js colors to match Obsidian theme.
