ingestion/internal/wiki/merge.go

@@ -41,9 +41,19 @@ func Merge(a, b Page) Page {
 	fmA, preambleA, secsA := parseSections(a.Content)
 	fmB, _, secsB := parseSections(b.Content)
 
+	// First occurrence wins on a collision — a page can already carry two
+	// on-disk sections that only differ by case or whitespace (the exact
+	// corpus drift this normalization exists to catch going forward, found
+	// pre-existing in review of PR #130): a plain last-write assignment
+	// here would silently and deterministically route every future update
+	// to whichever duplicate happens to sort last in the file, freezing
+	// the other one forever with nothing to say so.
 	idx := make(map[string]int, len(secsA))
 	for i, s := range secsA {
-		idx[normalizeHeading(s.heading)] = i
+		key := normalizeHeading(s.heading)
+		if _, exists := idx[key]; !exists {
+			idx[key] = i
+		}
 	}
 
 	for _, sB := range secsB {

ingestion/internal/wiki/merge_test.go

@@ -341,6 +341,32 @@ func TestMerge_HeadingWhitespaceDriftMatchesSameSection(t *testing.T) {
 	assert.Contains(t, got, "What about remote teams?")
 }
 
+func TestMerge_PreExistingCaseDuplicateHeadingsRouteToTheFirstOccurrence(t *testing.T) {
+	// Found in review of PR #130: normalizeHeading's idx map is built by
+	// iterating secsA with idx[normalizeHeading(s.heading)] = i -- last
+	// write wins. Before heading normalization existed, two on-disk
+	// sections differing only by case (real, pre-existing corpus drift --
+	// the exact pattern #106 itself cites) never collided, since idx keyed
+	// on the exact string. After normalization they collide, and every
+	// fresh update silently, deterministically routes to whichever
+	// duplicate happens to appear LAST in the file -- the first one is
+	// frozen forever, never receiving updates again, with nothing to say
+	// so. A Contains-only check doesn't catch this: nothing is literally
+	// deleted, a bullet just lands under the wrong of two still-present
+	// headings. Assert it lands under the FIRST occurrence instead —
+	// deterministic and matches "earliest is canonical," same reasoning
+	// as every other on-disk-wins default in this file.
+	a := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Key Claims\n\n- claim one\n\n## KEY CLAIMS\n\n- claim two\n"}
+	b := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Key Claims\n\n- claim one\n- fresh claim\n"}
+
+	got := Merge(a, b).Content
+
+	assert.Contains(t, got, "## Key Claims\n\n- claim one\n- fresh claim\n",
+		"the fresh bullet must land in the first-occurrence section, not silently route to the last duplicate")
+	assert.Contains(t, got, "## KEY CLAIMS\n\n- claim two\n",
+		"the second duplicate is untouched by this update, not merged into or overwritten")
+}
+
 func TestRefreshOwned_CommentLinesSurviveUnmangled(t *testing.T) {
 	// Third review round on PR #126: parseFrontmatterBlock dropped the
 	// sibling api package's comment guard (strings.HasPrefix(trimmed, "#")).