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
@@ -97,18 +97,20 @@ func rrfMerge(lists [][]Hit) []Hit {
 	var order []string
 	for _, list := range lists {
 		for r, h := range list {
-			c := CanonicalURL(h.URL)
+			orig := h.URL
+			c := CanonicalURL(orig)
 			if c == "" {
 				continue
 			}
-			h.URL = c
 			sc := 1.0 / float64(rrfK+r+1)
 			if a, ok := seen[c]; ok {
 				a.s += sc
 				if len(h.Snippet) > len(a.h.Snippet) {
 					src := a.h.Source
+					keep := a.h.URL
 					a.h = h
 					a.h.Source = src
+					a.h.URL = keep
 				}
 				continue
 			}