fix: treat [0] document references as out of range in AnswerBuilder (#12061)

Author: vidigoat

haystack/components/builders/answer_builder.py

@@ -223,13 +223,14 @@ def run(
                 )
 
                 for idx in doc_idxs:
-                    try:
-                        doc = documents[idx]
-                    except IndexError:
+                    # An explicit bounds check is needed because references are 1-based: a reference like [0]
+                    # yields idx = -1, which Python would otherwise silently resolve to the last document.
+                    if not 0 <= idx < len(documents):
                         logger.warning(
                             "Document index '{index}' referenced in Generator output is out of range. ", index=idx + 1
                         )
                         continue
+                    doc = documents[idx]
 
                     doc_meta: dict[str, Any] = dict(doc.meta or {})
                     doc_meta["source_index"] = idx + 1

releasenotes/notes/answer-builder-zero-reference-out-of-range-64aab56f8b5f65c3.yaml

@@ -0,0 +1,7 @@
+---
+fixes:
+  - |
+    AnswerBuilder now treats a ``[0]`` document reference as out of range instead of silently attaching
+    the last document. References are 1-based, so ``[0]`` produced a negative index that bypassed the
+    out-of-range guard, marking an unrelated document as ``referenced`` with a wrong ``source_index``.
+    The same applied to expanded reference ranges starting at 0 (e.g. ``[0-1]``).

test/components/builders/test_answer_builder.py

@@ -186,6 +186,38 @@ def test_run_with_documents_with_reference_pattern_and_no_match(self, caplog):
         assert len(answers[0].documents) == 0
         assert "Document index '3' referenced in Generator output is out of range." in caplog.text
 
+    def test_run_with_documents_with_zero_reference(self, caplog):
+        # References are 1-based, so [0] is out of range and must not silently
+        # resolve to the last document via a negative index.
+        component = AnswerBuilder(reference_pattern="\\[(\\d+)\\]")
+        with caplog.at_level(logging.WARNING):
+            output = component.run(
+                query="test query",
+                replies=["Answer: AnswerString[0]"],
+                meta=[{}],
+                documents=[Document(content="test doc 1"), Document(content="test doc 2")],
+            )
+        answers = output["answers"]
+        assert len(answers) == 1
+        assert len(answers[0].documents) == 0
+        assert "Document index '0' referenced in Generator output is out of range." in caplog.text
+
+    def test_run_with_zero_reference_in_expanded_range(self, caplog):
+        component = AnswerBuilder(reference_pattern="\\[([\\d\\s,-]+)\\]", expand_reference_ranges=True)
+        with caplog.at_level(logging.WARNING):
+            output = component.run(
+                query="test query",
+                replies=["Answer: AnswerString[0-1]"],
+                meta=[{}],
+                documents=[Document(content="test doc 1"), Document(content="test doc 2")],
+            )
+        answers = output["answers"]
+        assert len(answers) == 1
+        assert len(answers[0].documents) == 1
+        assert answers[0].documents[0].content == "test doc 1"
+        assert answers[0].documents[0].meta["referenced"] is True
+        assert "Document index '0' referenced in Generator output is out of range." in caplog.text
+
     def test_run_with_reference_pattern_set_at_runtime(self):
         component = AnswerBuilder(reference_pattern="unused pattern")
         output = component.run(