Changelog

Replace the barely-visible indeterminate ProgressBar + static "Thinking..." text

with an animated "Thinking." → "Thinking.." → "Thinking..." cycle (400ms per

frame) driven by a timer in AiChatMessageViewModel. The animation starts when

the message enters Loading state and stops when streaming/ready begins. Uses

italic styling for visual distinction from actual response content.

Desktop 1.63.0 → 1.63.1.

The shell-ai RAG chunk was too sparse for Duncan to explain its own

features. Expand it with detailed interaction instructions, provider

configuration details, response length behavior, and AI memory.

Add a new shell-intents RAG chunk documenting the full intent lifecycle

(signal → classification → slot extraction → execution → confirmation),

listing every available intent across all 14 plugins with descriptions

and example natural language queries.

Update APP_CONTEXT.md with a comprehensive AI & Intent System section

including a full intent catalog table, RAG explanation, and content

suggestion documentation.

This ensures Duncan can answer questions like "what are intents?",

"how do I interact with you?", and "what can you do?" with accurate,

context-aware responses from the RAG index.

Introduces ShellContentProvider implementing IIndexableContentProvider to

index shell-level features into the RAG vector index. This allows Duncan

to answer questions about global shortcuts, Universal Search, Knowledge

Graph, Dashboard, AI services, Info Panel, Cloud Sync, themes, speech

input, reminders, security, and the plugin ecosystem — without needing

plugin-specific context. Registered via CapabilityBroker so RagIndexService

discovers it alongside plugin providers during full index.

• Fix DispatcherPriority.Layout → Render (Layout doesn't exist in Avalonia)
• Revert auto-note creation from intent suggestions — intents should only

show action buttons, not auto-create notes. Auto-note stays in the

DatasetInsightOrchestrator for user-initiated insights only.

• Add Target icon (Habits plugin) and CurrencyDollar icon (Finance plugin)

to IconData with GetIcon switch cases

• Fix speech balloon arrow seam by using open path (no top-edge stroke)
• Dynamically position balloon over AI star icon instead of hardcoded margin
• Clicking balloon now opens AI tray (intents) instead of just dismissing
• Add token streaming for local LLM inference — responses appear progressively

instead of all-at-once after full generation completes

• Add StreamCompleteAsync to IAiProvider with default fallback implementation
• LocalLlamaProvider streams tokens via onToken callback during InferAsync loop
• New ChatMessageState.Streaming state for progressive content display
• Auto-create a Notes page when Duncan generates an intent suggestion insight
• Show "View Note" button alongside the intent action for quick navigation
• Handle view_page: action routing in intent suggestion message handler