feat: redesign agents page (architectural-grid style), add image description, fix AI limits, remove dead code

- Redesign agents page with architectural-grid (8) design system:
  rounded-2xl cards, serif headings, motion tabs, dashed templates section
- Replace agent form popup with full-page detail view (SettingsView style)
  with dark planning card, section tooltips, and help button
- Hide advanced mode for slide/excalidraw generators
- Add 'describe images' action to contextual AI assistant
- Add copy button to action/resource preview with HTTP fallback
- Add delete history button to agent run log panel
- Increase AI word limit from 2000 to 5000 (reformulate + transform-markdown)
- Increase max steps slider from 25 to 50
- Fix image description error with clear model compatibility message
- Fix doubled execution count display in agent detail view
- Remove dead files: notes-list-view.tsx, notes-view-toggle.tsx
- Remove 'list' view mode from NotesViewMode type
- Add missing i18n keys (back, configuration, options, copy, cleared)

memento-note/lib/ai/services/image-description.service.ts

@@ -75,10 +75,18 @@ export async function describeImages(
   }
   const langName = langMap[language] || 'English'
 
-  // Resolve all images as base64 data URLs — skip any that can't be found
   const resolved = await Promise.all(imageUrls.map(url => resolveImageAsBase64(url)))
   const imageDataUrls = resolved.filter((d): d is string => d !== null)
 
+  if (imageDataUrls.length === 0) {
+    throw new Error('Could not load any of the provided images. Please check the image URLs.')
+  }
+
+  const buildImageContent = (dataUrl: string) => ({
+    type: 'image' as const,
+    image: dataUrl,
+  })
+
   if (isTitleMode) {
     const prompt = imageUrls.length === 1
       ? `Look carefully at this image and identify every concrete detail you can see: objects, people, animals, text, logos, colors, location/setting, actions, weather, time of day, style (photo/illustration/diagram), and any notable elements.
@@ -100,13 +108,22 @@ Respond ONLY with a JSON array: [{"title": "title1", "confidence": 0.95}, {"titl
 
     const content: any[] = [{ type: 'text', text: prompt }]
     for (const dataUrl of imageDataUrls) {
-      content.push({ type: 'image', image: dataUrl })
+      content.push(buildImageContent(dataUrl))
     }
 
-    const { text } = await generateText({
-      model,
-      messages: [{ role: 'user', content }],
-    })
+    let text: string
+    try {
+      const result = await generateText({
+        model,
+        messages: [{ role: 'user', content }],
+      })
+      text = result.text
+    } catch (e: any) {
+      if (e.message?.includes('image_url') || e.message?.includes('image') || e.message?.includes('vision') || e.message?.includes('multimodal')) {
+        throw new Error('Your AI model does not support image analysis. Please switch to a vision-capable model (e.g., gpt-4o, claude-3.5-sonnet, gemini-2.0-flash).')
+      }
+      throw e
+    }
 
     // Parse JSON response
     const jsonMatch = text.match(/\[[\s\S]*\]/)
@@ -128,13 +145,22 @@ Respond ONLY with a JSON array: [{"title": "title1", "confidence": 0.95}, {"titl
   if (imageUrls.length === 1) {
     const content: any[] = [
       { type: 'text', text: `Describe this image in detail in ${langName}. Be specific about what you see: objects, people, colors, setting, mood, text visible. Keep it under 100 words.` },
-      { type: 'image', image: imageDataUrls[0] },
+      buildImageContent(imageDataUrls[0]),
     ]
 
-    const { text } = await generateText({
-      model,
-      messages: [{ role: 'user', content }],
-    })
+    let text: string
+    try {
+      const result = await generateText({
+        model,
+        messages: [{ role: 'user', content }],
+      })
+      text = result.text
+    } catch (e: any) {
+      if (e.message?.includes('image_url') || e.message?.includes('image') || e.message?.includes('vision') || e.message?.includes('multimodal')) {
+        throw new Error('Your AI model does not support image analysis. Please switch to a vision-capable model (e.g., gpt-4o, claude-3.5-sonnet, gemini-2.0-flash).')
+      }
+      throw e
+    }
 
     return {
       descriptions: [{ index: 0, description: text.trim() }],
@@ -147,13 +173,22 @@ Respond ONLY with a JSON array: [{"title": "title1", "confidence": 0.95}, {"titl
   for (let i = 0; i < imageDataUrls.length; i++) {
     const content: any[] = [
       { type: 'text', text: `Describe this image (image ${i + 1} of ${imageDataUrls.length}) in ${langName}. Be specific: objects, people, colors, setting, text visible. Under 80 words.` },
-      { type: 'image', image: imageDataUrls[i] },
+      buildImageContent(imageDataUrls[i]),
     ]
 
-    const { text } = await generateText({
-      model,
-      messages: [{ role: 'user', content }],
-    })
+    let text: string
+    try {
+      const result = await generateText({
+        model,
+        messages: [{ role: 'user', content }],
+      })
+      text = result.text
+    } catch (e: any) {
+      if (e.message?.includes('image_url') || e.message?.includes('image') || e.message?.includes('vision') || e.message?.includes('multimodal')) {
+        throw new Error('Your AI model does not support image analysis. Please switch to a vision-capable model (e.g., gpt-4o, claude-3.5-sonnet, gemini-2.0-flash).')
+      }
+      throw e
+    }
 
     descriptions.push({ index: i, description: text.trim() })
   }

memento-note/lib/ai/services/paragraph-refactor.service.ts

@@ -56,7 +56,7 @@ export const REFACTOR_OPTIONS: RefactorOption[] = [
 export class ParagraphRefactorService {
   private languageDetection: LanguageDetectionService
   private readonly MIN_WORDS = 10
-  private readonly MAX_WORDS = 2000
+  private readonly MAX_WORDS = 5000
 
   constructor() {
     this.languageDetection = new LanguageDetectionService()