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/report.rs

@@ -67,6 +67,10 @@ pub struct StageCounts {
     pub excerpt_only: i64,
     /// Social lookups that returned a hit (§3.4).
     pub social_hits: i64,
+    /// Feed candidates recorded for the first time by the discovery stage
+    /// (feed discovery plan §4 step 3).
+    #[serde(default)]
+    pub feed_candidates_new: i64,
     /// Articles passing hygiene and eligible for personalized signals.
     pub eligible: i64,
     /// Eligible articles with a valid embedding.