Changelog

Three changes to the AI assistant tray:

1. Panel no longer closes on click-away. Users must explicitly close via the

close button or Escape key, matching the expectation that the panel stays

open while working.

2. Added drag-to-resize handle (same pattern as InfoPanel) allowing users to

widen or narrow the tray between 320-700px. Default remains 400px.

3. Active plugin context is now injected into the AI system prompt. When the

user navigates to a plugin, the AI receives the plugin's name, description,

tags, and category. Plugins can optionally set DetailedDescription on

PluginMetadata for richer context (feature list, capabilities, quick actions).

This lets the AI answer questions like "what is this plugin?" and "what can

I do here?"

SDK 1.63.0: Added PluginMetadata.DetailedDescription property.

Desktop 1.62.0.

Replace single Amount column with separate Outflow (red) and Inflow (green) columns in the account register. Add All/Outflow/Inflow filter toggle to the account selector row. Add Outflow/Inflow direction toggle button to the add transaction form (defaults to Outflow). When adding an inflow, splits use positive amount on the asset account and negative on an auto-resolved income account. The quick transaction form also gets an Outflow/Inflow toggle with visual feedback, replacing the old sign-convention watermark. Edit panel preserves original sign direction. Bump version to 3.19.0.

Replace old local model catalog (phi-3-mini, llama-1b, mistral-7b) with a

better-tiered selection: llama-3.2-3b (lightweight), qwen-2.5-7b (balanced),

qwen-2.5-14b (high quality), and qwen-2.5-32b (best local quality for 32GB+

systems). Add parameter count metadata to model info for tier detection.

Implement 3-tier intent classification prompt system: Small tier (current

terse few-shot for <5B local models, 384 tokens), Medium tier (richer

instructions with slot descriptions for 7B+ local models, 768 tokens), and

Large tier (full chain-of-thought with intent descriptions, edge case

guidance, and confidence scoring for cloud models, 1024 tokens).

IntentEngine now dynamically selects prompt tier and MaxTokens based on the

active AI provider — cloud providers get Large tier, local 7B+ get Medium,

and small local models get Small. Medium/Large tiers skip intent filtering

to give capable models the full intent set.

Add ChatML prompt template for Qwen models with proper anti-prompts. Update

PlatformDetector RAM thresholds to recommend new models. Old downloaded

models (phi-3, mistral, llama-1b) still work via backward-compatible prompt

template matching.

Remove direct LiveChartsCore.SkiaSharpView.Avalonia dependency from both

plugins. Charts now flow through AdaptiveCartesianChart and AdaptivePieChart

controls provided by PrivStack.UI.Adaptive, which owns the LiveCharts2

rc6.1 dependency.

This fixes the SourceGenChart TypeLoadException crash in Finance Reports

and makes charting available to any plugin via the existing UI.Adaptive

reference.

Finance: ReportsView.axaml uses adaptive: namespace wrappers instead of

lvc: LiveCharts controls. ViewModel series building unchanged (ISeries/Axis

types resolve transitively).

Notes: ChartBlockEditor creates AdaptiveCartesianChart/AdaptivePieChart

instead of CartesianChart/PieChart directly. ChartSeriesFactory and

ChartExportRenderer unchanged (C# types only, no XAML controls).

Finance version: 3.18.0 (unchanged)

Notes version: 1.61.0 → 1.62.0