p3: keep original URLs on RRF/dedupe; rerank=false is not a merge

CanonicalURL is the dedupe key only. Hits keep the first source's original URL, including a trailing slash. Dedupe has the same rule.
2026-09-23 16:04:45 -07:00
parent b6e1cdf825
commit 1c57845ebd
4 changed files with 36 additions and 9 deletions
@@ -79,13 +79,14 @@ func Dedupe(in []Hit) []Hit {
 		if canon == "" {
 			continue
 		}
-		h.URL = canon
 		if s, ok := seen[canon]; ok {
 			if len(h.Snippet) > len(s.h.Snippet) {
 				src := s.h.Source
+				keep := s.h.URL
 				sc := s.h.Score
 				s.h = h
 				s.h.Source = src
+				s.h.URL = keep
 				if sc > s.h.Score {
 					s.h.Score = sc
 				}