LocalMind 1.0.31

Update assistant timestamp on first token

Make chat message timestamps observable so the UI updates when an assistant response starts streaming visible text. This sets the assistant timestamp when the first non-thinking content arrives and clarifies the Foundry Local thinking-filter TODO.

LocalMind 1.0.30

Close settings when selecting chat

Ensure the Settings panel closes even when the already-open chat is selected again, keeping chat navigation behavior consistent.

LocalMind 1.0.29

Add GitHub repository link to settings

Adds an OpenRepository command and a corresponding UI section in Settings that lets users open the LocalMind GitHub repository for source and releases.

LocalMind 1.0.28

Upgrade Microsoft AI Foundry package

Replace the WinML-specific Microsoft.AI.Foundry.Local package with Microsoft.AI.Foundry.Local version 2.0.1 while retaining the existing Microsoft.Extensions.AI dependency.

LocalMind 1.0.27

v1.0.27

Add Gemma 4 E2B IT model to FoundryLocalProvider

LocalMind 1.0.26

Bump NuGet package versions

Update FluentIcons.WinUI, Microsoft.Extensions.AI, Microsoft.Extensions.AI.OpenAI, and Microsoft.WindowsAppSDK to their latest versions.

LocalMind 1.0.25

v1.0.25

Merge branch 'main' of https://github.com/aherrick/LocalMind

LocalMind 1.0.24

Handle stale chat selection and drop model refresh

Refactors sidebar-clearing logic in `MainWindow` into a `ClearSidebarSelection()` helper and now also clears selection when `SelectedChat` points to a chat no longer present in either pinned or regular chat collections. This prevents lingering highlights when chats are removed or become invalid.

Also removes the model-picker `DropDownOpened` refresh path by deleting the XAML event handler, its code-behind method, and `ChatViewModel.RefreshModels()`, simplifying model selection behavior and avoiding implicit refresh-on-open side effects.

LocalMind 1.0.23

Refresh model picker and clear nav selection

Adds immediate model discovery when the chat model ComboBox opens by wiring DropDownOpened to ChatViewModel.RefreshModels(), so newly started providers appear without delay. Also clears both sidebar ListView selections when switching to Settings, fixing stale highlight state when OneWay SelectedItem binding does not push null reliably.

LocalMind 1.0.22

Centralize local model discovery and status polling

Introduce a shared `ModelCatalog` service that periodically refreshes all local providers, tracks available models, and publishes per-provider availability/model snapshots. Update `ILocalModelProvider` to return `LocalProviderStatus` via `GetStatusAsync`, and adapt Foundry, Ollama, and llama.cpp providers to the new contract.

Refactor `MainViewModel`, `ChatViewModel`, and `SettingsViewModel` to consume catalog-driven updates instead of doing their own provider polling. This keeps chat model lists and settings provider states in sync as providers come online/offline, while preserving selection stability and reducing duplicated refresh logic.