Reduce batch size to 10 and tighten AI price check prompt

Still seeing stubs despite MaxTokens=8192 — smaller batches and explicit
word limits in the prompt eliminate any remaining truncation risk.

- BatchSize: 15 → 10 (~1200 output tokens per batch vs. potential 3000+)
- Prompt: added 20-word cap on assumptions, 25-word cap on reasoning
- Prompt: strengthened "nothing before or after the '['" instruction
- Error log: now includes item IDs and first 300 chars of raw response
  so the next failure tells us exactly what Claude returned
- JS timing: updated batch divisor from 25 → 10 to match actual batch size

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

src/PowderCoating.Web/wwwroot/js/catalog-price-check.js

@@ -12,14 +12,14 @@
 
     // Estimate total seconds based on item count (roughly 12s per batch of 25, min 15s).
     function estimateDuration(itemCount) {
-        var batches = Math.max(1, Math.ceil(itemCount / 25));
-        return Math.max(15, batches * 12);
+        var batches = Math.max(1, Math.ceil(itemCount / 10));
+        return Math.max(15, batches * 10);
     }
 
     // Messages keyed to approximate progress milestones (0–100).
     function messageAt(pct, batchCount) {
         if (pct < 10) return 'Loading catalog items…';
-        if (pct < 20) return 'Sending items to Claude…';
+        if (pct < 20) return 'Sending items for analysis…';
         if (batchCount <= 1) {
             if (pct < 75) return 'Analyzing your catalog with AI…';
             if (pct < 92) return 'Reviewing pricing data…';