feat: add enrichment parameter to gather_search_context() replacing weak metadata query

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

src/ai/insight_generator.rs

@@ -512,13 +512,19 @@ impl InsightGenerator {
         timestamp: i64,
         location: Option<&str>,
         contact: Option<&str>,
+        enrichment: Option<&str>,
     ) -> Result<Option<String>> {
         let tracer = global_tracer();
         let span = tracer.start_with_context("ai.context.search", parent_cx);
         let search_cx = parent_cx.with_span(span);
 
-        // Build semantic query from metadata
-        let query_text = format!(
+        // Use enrichment (topics + photo description + tags) if available;
+        // fall back to generic temporal query.
+        let query_text = if let Some(enriched) = enrichment {
+            enriched.to_string()
+        } else {
+            // Fallback: generic temporal query
+            format!(
                 "searches about {} {} {}",
                 DateTime::from_timestamp(timestamp, 0)
                     .map(|dt| dt.format("%B %Y").to_string())
@@ -527,7 +533,8 @@ impl InsightGenerator {
                 contact
                     .map(|c| format!("involving {}", c))
                     .unwrap_or_default()
-        );
+            )
+        };
 
         let query_embedding = match self.ollama.generate_embedding(&query_text).await {
             Ok(emb) => emb,
@@ -948,6 +955,7 @@ impl InsightGenerator {
                 timestamp,
                 location.as_deref(),
                 contact.as_deref(),
+                None, // enrichment — wired up in Task 5
             )
             .await
             .ok()