From d3c8ed62a833e7179777d3ff7a7ddf0b8d8d5972 Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Wed, 15 Apr 2026 15:10:24 +0300
Subject: [PATCH] preserve original chunk when expansion produces less content

---
 haiku_rag_slim/haiku/rag/context.py           |  6 +-
 .../haiku/rag/store/models/document_item.py   |  2 +
 tests/test_context.py                         | 62 +++++++++++++++++++
 3 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/haiku_rag_slim/haiku/rag/context.py b/haiku_rag_slim/haiku/rag/context.py
index 77836f28..a66c8b84 100644
--- a/haiku_rag_slim/haiku/rag/context.py
+++ b/haiku_rag_slim/haiku/rag/context.py
@@ -230,9 +230,11 @@ async def expand_with_items(
 
         first = original_results[0]
 
-        # If noise filtering removed all content, preserve the original
+        # Expansion should never return less content than the original chunk.
+        # This can happen when item texts are fragmented (e.g., docling splits
+        # formatted HTML list items into many small text nodes).
         expanded_content = "\n\n".join(content_parts)
-        if not expanded_content:
+        if len(expanded_content) < len(first.content):
             expanded_content = first.content
 
         final_results.append(
diff --git a/haiku_rag_slim/haiku/rag/store/models/document_item.py b/haiku_rag_slim/haiku/rag/store/models/document_item.py
index 2e93883d..ee17bf0c 100644
--- a/haiku_rag_slim/haiku/rag/store/models/document_item.py
+++ b/haiku_rag_slim/haiku/rag/store/models/document_item.py
@@ -56,6 +56,8 @@ def extract_items(
 
     Runs iterate_items() and extracts the fields needed for context expansion:
     self_ref, label, pre-rendered text, and page numbers from provenance.
+    Items are stored as docling produces them — container items (e.g., list_item)
+    may have empty text with content in their children.
     """
     items: list[DocumentItem] = []
 
diff --git a/tests/test_context.py b/tests/test_context.py
index 6635bb7a..94e062a0 100644
--- a/tests/test_context.py
+++ b/tests/test_context.py
@@ -320,3 +320,65 @@ class TestExpandWithItems:
             # with skip_noise crosses into the Introduction section which has
             # real content — so we get expanded content, not the fallback.
             assert len(expanded[0].content) > 0
+
+    async def test_fragmented_items_preserve_chunk(self, temp_db_path):
+        """When items are fragmented (e.g., list_item children), the original
+        chunk content is preserved if expansion produces less text."""
+        from haiku.rag.client import HaikuRAG
+
+        async with HaikuRAG(temp_db_path, create=True) as rag:
+            # Simulate docling's list_item structure: container with empty text,
+            # children with tiny fragments
+            items = [
+                DocumentItem(
+                    document_id="doc-1",
+                    position=0,
+                    self_ref="#/texts/0",
+                    label="section_header",
+                    text="Steps",
+                ),
+                DocumentItem(
+                    document_id="doc-1",
+                    position=1,
+                    self_ref="#/texts/1",
+                    label="list_item",
+                    text="",
+                ),
+                DocumentItem(
+                    document_id="doc-1",
+                    position=2,
+                    self_ref="#/texts/2",
+                    label="text",
+                    text="Click",
+                ),
+                DocumentItem(
+                    document_id="doc-1",
+                    position=3,
+                    self_ref="#/texts/3",
+                    label="text",
+                    text="+",
+                ),
+                DocumentItem(
+                    document_id="doc-1",
+                    position=4,
+                    self_ref="#/texts/4",
+                    label="text",
+                    text="Add a New Service",
+                ),
+            ]
+            await rag.document_item_repository.create_items("doc-1", items)
+
+            # The chunk had properly assembled content from the chunker
+            result = SearchResult(
+                content="1. Click + Add a New Service in the dashboard.",
+                score=0.9,
+                document_id="doc-1",
+                doc_item_refs=["#/texts/1", "#/texts/2", "#/texts/3", "#/texts/4"],
+            )
+            expanded = await expand_with_items(
+                rag.document_item_repository, "doc-1", [result], 10, 5000
+            )
+            assert len(expanded) == 1
+            # Expansion produces "Steps\n\nClick\n\n+\n\nAdd a New Service" = 38 chars
+            # which is less than the chunk's 46 chars — fallback preserves the chunk
+            assert expanded[0].content == result.content