From ffb9978ec6ea59716f690dc08d447b9b8fa6ee55 Mon Sep 17 00:00:00 2001
From: Zaki Manian <zaki@iqlusion.io>
Date: Fri, 6 Mar 2026 15:27:45 -0800
Subject: [PATCH] test(workspace): regression test for document_path in search
 results (#509)

* test(workspace): add regression test for document_path propagation through RRF

Verifies that search results carry the source document's file path
through the RRF fusion pipeline, not the document UUID. Covers the
bug fixed in PR #503 / issue #481.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Update src/workspace/search.rs

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* chore: merge main and fix formatting

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
[skip-regression-check]

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
---
 src/workspace/search.rs | 61 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)

diff --git a/src/workspace/search.rs b/src/workspace/search.rs
index d25dda09..29e21c33 100644
--- a/src/workspace/search.rs
+++ b/src/workspace/search.rs
@@ -249,6 +249,67 @@ mod tests {
         }
     }
 
+    fn make_result_with_path(chunk_id: Uuid, doc_id: Uuid, path: &str, rank: u32) -> RankedResult {
+        RankedResult {
+            chunk_id,
+            document_id: doc_id,
+            document_path: path.to_string(),
+            content: format!("content for chunk {}", chunk_id),
+            rank,
+        }
+    }
+
+    #[test]
+    fn test_rrf_propagates_document_path() {
+        // Regression test: search results must carry the source document's
+        // file path, not the document UUID. See PR #503 / issue #481.
+        let config = SearchConfig::default().with_limit(10);
+
+        let doc_a = Uuid::new_v4();
+        let doc_b = Uuid::new_v4();
+        let chunk1 = Uuid::new_v4();
+        let chunk2 = Uuid::new_v4();
+        let chunk3 = Uuid::new_v4();
+
+        let fts_results = vec![
+            make_result_with_path(chunk1, doc_a, "notes/todo.md", 1),
+            make_result_with_path(chunk2, doc_b, "journal/2024-01-15.md", 2),
+        ];
+        let vector_results = vec![
+            make_result_with_path(chunk1, doc_a, "notes/todo.md", 1),
+            make_result_with_path(chunk3, doc_b, "journal/2024-01-15.md", 2),
+        ];
+
+        let results = reciprocal_rank_fusion(fts_results, vector_results, &config);
+
+        for result in &results {
+            // The path must be a real file path, never a UUID string
+            assert!(
+                Uuid::parse_str(&result.document_path).is_err(),
+                "document_path looks like a UUID ('{}'), expected a file path",
+                result.document_path
+            );
+        }
+
+        // Verify exact paths are preserved
+        let paths: Vec<&str> = results.iter().map(|r| r.document_path.as_str()).collect();
+        assert!(
+            paths.contains(&"notes/todo.md"),
+            "missing notes/todo.md in {:?}",
+            paths
+        );
+        assert!(
+            paths.contains(&"journal/2024-01-15.md"),
+            "missing journal/2024-01-15.md in {:?}",
+            paths
+        );
+
+        // Hybrid match (chunk1) should preserve the correct path
+        let hybrid = results.iter().find(|r| r.chunk_id == chunk1).unwrap();
+        assert_eq!(hybrid.document_path, "notes/todo.md");
+        assert!(hybrid.is_hybrid());
+    }
+
     #[test]
     fn test_rrf_single_method() {
         let config = SearchConfig::default().with_limit(10);