Add screenshot content analysis using VLM

Features:
- ScreenshotAnalyzer class for VLM-based image analysis
- Real-time analysis during video recording
- Extract likes, comments, tags, category from screenshots
- Frontend display for category badges and tags
- Batch analysis API endpoint

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

dashboard/static/css/video-learning.css

@@ -212,6 +212,37 @@
     flex-shrink: 0;
 }
 
+/* Category Badge */
+.video-category {
+    margin-top: 0.5rem;
+}
+
+.category-badge {
+    display: inline-block;
+    padding: 0.2rem 0.5rem;
+    background-color: rgba(99, 102, 241, 0.2);
+    color: var(--primary-color);
+    border-radius: 4px;
+    font-size: 0.7rem;
+    font-weight: 500;
+}
+
+/* Tags */
+.video-tags {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 0.25rem;
+    margin-top: 0.5rem;
+}
+
+.video-tags .tag {
+    font-size: 0.65rem;
+    color: var(--text-secondary);
+    background-color: var(--bg-color);
+    padding: 0.15rem 0.4rem;
+    border-radius: 3px;
+}
+
 /* Session Complete */
 .session-complete {
     text-align: center;

dashboard/static/video-learning.html

@@ -228,6 +228,12 @@
                                     {{ formatNumber(video.comments) }}
                                 </span>
                             </div>
+                            <div class="video-category" v-if="video.category">
+                                <span class="category-badge">{{ video.category }}</span>
+                            </div>
+                            <div class="video-tags" v-if="video.tags && video.tags.length > 0">
+                                <span class="tag" v-for="tag in video.tags" :key="tag">#{{ tag }}</span>
+                            </div>
                         </div>
                     </div>
                 </div>