From 53bb2bd9e8ad52acf04833136dac6f648174e35d Mon Sep 17 00:00:00 2001
From: monsterDavid <monsterdavidliu@gmail.com>
Date: Fri, 29 May 2026 04:33:26 -0700
Subject: [PATCH] fix(metadata): preserve empty AND results across filter
 conditions (#15386)

## Summary
- Fix `meta_filter()` AND logic so an empty result from an early
condition is not overwritten when a later condition matches.
- Add regression tests for empty-first AND, successful AND intersection,
and OR behavior after an empty first condition.

Fixes incorrect `/retrieval` metadata filtering when multiple AND
conditions are used and the first condition matches no documents.

Closes #15360

## Test plan
- [x] `pytest test/unit_test/common/test_metadata_filter_operators.py
-v` (19/19 passed)
---
 common/metadata_utils.py                      |  7 ++--
 .../common/test_metadata_filter_operators.py  | 39 +++++++++++++++++++
 2 files changed, 42 insertions(+), 4 deletions(-)

diff --git a/common/metadata_utils.py b/common/metadata_utils.py
index 53af2b4eaf..591acb8053 100644
--- a/common/metadata_utils.py
+++ b/common/metadata_utils.py
@@ -41,7 +41,7 @@ def convert_conditions(metadata_condition):
 
 
 def meta_filter(metas: dict, filters: list[dict], logic: str = "and"):
-    doc_ids = set([])
+    doc_ids = None
 
     def normalize_string_values(value):
         if isinstance(value, str):
@@ -159,7 +159,7 @@ def meta_filter(metas: dict, filters: list[dict], logic: str = "and"):
             v2docs = metas[k]
             ids = filter_out(v2docs, f["op"], f["value"])
 
-        if not doc_ids:
+        if doc_ids is None:
             doc_ids = set(ids)
         else:
             if logic == "and":
@@ -169,8 +169,7 @@ def meta_filter(metas: dict, filters: list[dict], logic: str = "and"):
                     return []
             else:
                 doc_ids = doc_ids | set(ids)
-    logging.debug(f"meta_filter filters={filters}, logic={logic}, returning doc_ids={list(doc_ids)}")
-    return list(doc_ids)
+    return list(doc_ids or [])
 
 
 async def apply_meta_data_filter(
diff --git a/test/unit_test/common/test_metadata_filter_operators.py b/test/unit_test/common/test_metadata_filter_operators.py
index 23f4c2b643..fc0cca7be8 100644
--- a/test/unit_test/common/test_metadata_filter_operators.py
+++ b/test/unit_test/common/test_metadata_filter_operators.py
@@ -125,3 +125,42 @@ def test_less_than_or_equal():
     filters = [{"key": "score", "op": "≤", "value": "5"}]
 
     assert set(meta_filter(metas, filters)) == {"doc1", "doc3"}
+
+
+def test_and_logic_returns_empty_when_first_condition_matches_nothing():
+    metas = {
+        "author": {"Alice": ["doc1"]},
+        "page_count": {"40": ["doc2"], "10": ["doc3"]},
+    }
+    filters = [
+        {"key": "author", "op": "contains", "value": "Toby"},
+        {"key": "page_count", "op": ">", "value": "30"},
+    ]
+
+    assert meta_filter(metas, filters, logic="and") == []
+
+
+def test_and_logic_intersects_matching_conditions():
+    metas = {
+        "author": {"Toby Jones": ["doc1"], "Alice": ["doc2"]},
+        "page_count": {"40": ["doc1"], "10": ["doc2"]},
+    }
+    filters = [
+        {"key": "author", "op": "contains", "value": "Toby"},
+        {"key": "page_count", "op": ">", "value": "30"},
+    ]
+
+    assert meta_filter(metas, filters, logic="and") == ["doc1"]
+
+
+def test_or_logic_still_unions_after_empty_first_condition():
+    metas = {
+        "author": {"Alice": ["doc1"]},
+        "page_count": {"40": ["doc2"], "10": ["doc3"]},
+    }
+    filters = [
+        {"key": "author", "op": "contains", "value": "Toby"},
+        {"key": "page_count", "op": ">", "value": "30"},
+    ]
+
+    assert set(meta_filter(metas, filters, logic="or")) == {"doc2"}