Add 4 AI bookkeeping features

Feature 7: Bank Rec Auto-Match — AiSuggestMatches endpoint scores uncleared
transactions vs statement ending balance; AI Auto-Match panel in Reconcile.cshtml
with confidence highlights and Apply All button.

Feature 8: Late Payment Prediction — PredictLatePayments endpoint scores open AR
customers by risk (high/medium/low) using historical avg-days-to-pay + late rate;
rendered as badge table in AR Aging view via ar-aging-ai.js.

Feature 9: Natural Language Financial Queries — FinancialQuery GET page + RunFinancialQuery
POST; 12-month context snapshot pre-loaded; answers grounded in real data with
supporting facts, follow-up suggestions, session history, and example chips.

Feature 10: Recurring Bill Detection — RunRecurringDetection scans 12 months of bills
for vendor payment patterns (monthly/quarterly/annual); card grid view in Bills/RecurringDetection.cshtml
with confidence badges, next-expected-date, and suggested actions.

Supporting: 4 new DTO groups in AccountingAiDtos.cs, 4 method signatures in
IAccountingAiService.cs, 4 implementations in AccountingAiService.cs, 4 new
AiFeatures constants, 2 new Landing page AI report cards.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/PowderCoating.Application/Interfaces/IAccountingAiService.cs

@@ -43,4 +43,33 @@ public interface IAccountingAiService
     /// Returns a ranked list of flagged items with recommended actions.
     /// </summary>
     Task<AnomalyDetectionResult> DetectAnomaliesAsync(AnomalyDetectionRequest request);
+
+    /// <summary>
+    /// Suggests which uncleared bank rec items should be marked as cleared to reconcile
+    /// a statement. Returns a ranked list of suggestions with confidence scores based on
+    /// amount/date patterns and the gap between the current cleared balance and the
+    /// statement ending balance.
+    /// </summary>
+    Task<AutoMatchResult> AutoMatchReconciliationAsync(AutoMatchRequest request);
+
+    /// <summary>
+    /// Predicts likelihood of late payment for each open AR customer using their historical
+    /// payment behavior (avg days to pay, late rate) combined with current overdue status.
+    /// Returns risk levels (high/medium/low) and estimated days to collection.
+    /// </summary>
+    Task<LatePaymentPredictionResult> PredictLatePaymentsAsync(LatePaymentPredictionRequest request);
+
+    /// <summary>
+    /// Answers a plain-English financial question (e.g. "What did we spend on powder last quarter?")
+    /// using pre-loaded company financial context. Returns a direct answer, supporting facts,
+    /// and an optional follow-up question suggestion.
+    /// </summary>
+    Task<FinancialQueryResult> AnswerFinancialQueryAsync(FinancialQueryRequest request);
+
+    /// <summary>
+    /// Analyzes 6–12 months of bill history to detect recurring payment patterns per vendor.
+    /// Returns detected patterns with frequency, typical amount, next expected date, and
+    /// suggested actions (e.g. set a reminder, create a template).
+    /// </summary>
+    Task<RecurringBillDetectionResult> DetectRecurringBillsAsync(RecurringBillDetectionRequest request);
 }