feat: integrate site_search fallback into Phase 1 pipeline

Build SiteSearchProvider before wave loop, chain as third fallback
after RSS + HTML when both return 0 links.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/src/services/synthesis/mod.rs

@@ -28,6 +28,7 @@ use crate::services::llm::factory::create_provider;
 use crate::services::scraper;
 use crate::services::source_scraper;
 use crate::services::feed_parser;
+use crate::services::site_search;
 
 mod helpers;
 pub(crate) use helpers::{
@@ -156,6 +157,22 @@ pub async fn run_generation_inner(
     let model_research = Arc::new(model_research);
     let classification_categories = Arc::new(classification_categories);
 
+    // Build the site search fallback provider (Brave if available, else LLM)
+    let site_search_provider = if settings.use_brave_search {
+        match resolve_brave_key(state, user_id).await {
+            Ok(key) => Arc::new(site_search::SiteSearchProvider::Brave { api_key: key }),
+            Err(_) => Arc::new(site_search::SiteSearchProvider::Llm {
+                provider: provider.clone(),
+                model: model_websearch.clone(),
+            }),
+        }
+    } else {
+        Arc::new(site_search::SiteSearchProvider::Llm {
+            provider: provider.clone(),
+            model: model_websearch.clone(),
+        })
+    };
+
     // === PHASE 1: Personalized Sources ===
     if !sources.is_empty() {
         emit_progress(tx, "sources", "Analyse des sources personnalisees...", 15);
@@ -203,6 +220,9 @@ pub async fn run_generation_inner(
                     let rss_url = source.rss_url.clone();
                     let rss_discovered_at = source.rss_discovered_at;
                     let max_l = max_links;
+                    let ss_provider = site_search_provider.clone();
+                    let ss_theme = theme.theme.clone();
+                    let ss_max_age = theme.max_age_days;
                     join_set.spawn(async move {
                         // Try RSS feed first
                         let feed_result = feed_parser::detect_and_parse_feed(
@@ -239,8 +259,30 @@ pub async fn run_generation_inner(
                             feed_parser::FeedResult::Found { .. } => {
                                 // Feed found but too few entries — keep the cache, fall back to HTML
                                 let links = source_scraper::extract_article_links(&client, &source_url, max_l).await;
+                                match links {
+                                    Ok(ref l) if l.is_empty() => {
+                                        // HTML also returned 0 links — try site search fallback
+                                        if let Some(domain) = crate::services::synthesis::extract_domain(&source_url) {
+                                            let ss_config = site_search::SiteSearchConfig {
+                                                domain,
+                                                theme: ss_theme,
+                                                max_results: max_l,
+                                                max_age_days: ss_max_age,
+                                            };
+                                            let ss_links = site_search::search(&client, &ss_config, &ss_provider).await;
+                                            if !ss_links.is_empty() {
+                                                tracing::info!(source = %source_title, links = ss_links.len(), "Site search fallback produced links");
+                                                (source_url, source_title, Ok(ss_links), None)
+                                            } else {
                                                 (source_url, source_title, links, None)
                                             }
+                                        } else {
+                                            (source_url, source_title, links, None)
+                                        }
+                                    }
+                                    _ => (source_url, source_title, links, None),
+                                }
+                            }
                             feed_parser::FeedResult::NotFound => {
                                 // No feed discovered — fall back to HTML and clear any stale cache
                                 let links = source_scraper::extract_article_links(&client, &source_url, max_l).await;
@@ -249,9 +291,31 @@ pub async fn run_generation_inner(
                                 } else {
                                     None
                                 };
+                                match links {
+                                    Ok(ref l) if l.is_empty() => {
+                                        // HTML also returned 0 links — try site search fallback
+                                        if let Some(domain) = crate::services::synthesis::extract_domain(&source_url) {
+                                            let ss_config = site_search::SiteSearchConfig {
+                                                domain,
+                                                theme: ss_theme,
+                                                max_results: max_l,
+                                                max_age_days: ss_max_age,
+                                            };
+                                            let ss_links = site_search::search(&client, &ss_config, &ss_provider).await;
+                                            if !ss_links.is_empty() {
+                                                tracing::info!(source = %source_title, links = ss_links.len(), "Site search fallback produced links");
+                                                (source_url, source_title, Ok(ss_links), update)
+                                            } else {
+                                                (source_url, source_title, links, update)
+                                            }
+                                        } else {
                                             (source_url, source_title, links, update)
                                         }
                                     }
+                                    _ => (source_url, source_title, links, update),
+                                }
+                            }
+                        }
                     });
                 }