Discover feeds behind aggregator-only articles

A best-effort pipeline stage after social enrichment asks Miniflux to
discover the feeds behind each aggregator-only article, validates every
result by sniffing the body, and records the survivors as feed candidates
with a per-host memo. Ranking is a shrunk mean over the linked articles'
existing telemetry and ratings. `daily-epub feeds discover` runs the same
pass over recent articles for seeding.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QVPagF6jfDv78CC5Jv2wp4

src/pipeline.rs

@@ -46,7 +46,7 @@ use crate::types::{
     Article, ArticleId, Artifact, BehindThePaper, Candidate, Colophon, Edition, Issue, IssueMeta,
     Lineup, Models, TokenUsage, reading_minutes,
 };
-use crate::{comments, dedupe, epub, http, miniflux, publish, social, world};
+use crate::{comments, dedupe, discovery, epub, http, miniflux, publish, social, world};
 
 /// One `generate` invocation's inputs — the CLI flags, already parsed (§2).
 #[derive(Debug, Clone, Default)]
@@ -449,6 +449,32 @@ async fn run_stages(
     report.counts.social_hits = enricher.enrich_all(&mut articles).await as i64;
     report.timings.record("social", elapsed_ms(stage));
 
+    // --- Stage 5b: feed discovery (feed discovery plan §4) — best effort ---
+    // Runs here because it needs the real article ids stage 4 minted and the
+    // subscription map stage 1 already loaded, and because `articles` is moved
+    // into hygiene next.
+    if config.discovery.enabled {
+        let stage = Timestamp::now();
+        match discovery::run(
+            db,
+            &client,
+            &http,
+            &config.discovery,
+            &articles,
+            &feeds,
+            Timestamp::now(),
+        )
+        .await
+        {
+            Ok(summary) => {
+                tracing::info!(%summary, "feed discovery");
+                report.counts.feed_candidates_new = summary.candidates_new as i64;
+            }
+            Err(error) => report.warn(format!("feed discovery failed: {error:#}")),
+        }
+        report.timings.record("discovery", elapsed_ms(stage));
+    }
+
     // --- Stage 6: hygiene, embeddings, and cheap signals (§8.1, §9) ---
     let stage = Timestamp::now();
     let mut personalized = admit::hygiene(