Changelog

User message ViewModels defaulted to ChatMessageState.Loading (enum 0)

since State was never explicitly set. The history filter excluded all

Loading messages, which silently dropped every user turn. Changed filter

to only exclude assistant messages that are still loading.

The ai-vault was not in StandardVaultIds, so it was never auto-unlocked

during app startup. Keys were persisted to disk but remained locked in

memory. Adding ai-vault to StandardVaultIds ensures it's unlocked alongside

the master password, just like the connections vault.

The ContentPresenter inside the overlay Border was receiving new form

content while detached from the visual tree (Border.IsVisible=false).

On re-entry to the visual tree, Avalonia's ContentPresenter does not

re-process content that was assigned while detached, causing the form's

visual children to never attach — rendering an empty modal.

Two changes fix this:

1. Always reset overlay state (removed the IsQuickActionOverlayOpen

guard) so stale content is cleared even when the overlay appears

closed.

2. Set IsQuickActionOverlayOpen=true BEFORE assigning

QuickActionOverlayContent in the Post callback, ensuring the

ContentPresenter is live in the visual tree when it receives the

new ContentControl. This guarantees template application and visual

child attachment on every invocation.

Cloud providers (OpenAI, Anthropic, Gemini) now build full message arrays from

ConversationHistory when present, enabling multi-turn conversations. Anthropic

uses automatic prompt caching (cache_control ephemeral) for multi-turn chats,

reducing repeat input cost to 10% on cache hits. AiPersona gains a richer

cloud system prompt with memory context injection and higher token budgets.

AiMemoryService persists learned user facts to JSON at DataPaths.BaseDir,

capped at 50 entries. AiMemoryExtractor runs a fire-and-forget secondary AI

call after cloud responses to extract memorable facts. The chat VM branches:

local models get the existing minimal prompt path; cloud models get history,

memory, and no aggressive sanitization. Desktop version bumped to 1.51.0.

Introduces AiChatMessage (Role + Content) and an optional ConversationHistory

property on AiRequest for multi-turn chat support. Cloud providers can iterate

over the history to build full message arrays while local providers ignore it.

Backward-compatible — defaults to null. SDK version bumped to 1.51.0.