feat: page-memory fine-hierarchy trim and hierarchy path slash escaping

apps/api/app/services/demo/source_catalog.py

@@ -69,7 +69,7 @@ class DemoSourceDefinition:
                 ),
                 citations=(
                     DemoCitationDefinition(
-                        section_path=("TSLA-Q4-2025-Update.pdf-->OTHER UPDATES"),
+                        section_path=("TSLA-Q4-2025-Update.pdf/OTHER UPDATES"),
                         description="xAI investment",
                         content=(
                             "On January 16, 2026, Tesla entered into an agreement "
@@ -92,7 +92,7 @@ class DemoSourceDefinition:
                 citations=(
                     DemoCitationDefinition(
                         section_path=(
-                            "TSLA-Q4-2025-Update.pdf-->SUMMARY-->"
+                            "TSLA-Q4-2025-Update.pdf/SUMMARY/"
                             "Energy generation and storage"
                         ),
                         description="Storage deployment growth",
@@ -115,7 +115,7 @@ class DemoSourceDefinition:
                 ),
                 citations=(
                     DemoCitationDefinition(
-                        section_path=("TSLA-Q4-2025-Update.pdf-->OUTLOOK-->Product"),
+                        section_path=("TSLA-Q4-2025-Update.pdf/OUTLOOK/Product"),
                         description="2026 production plans",
                         content=(
                             "Cybercab, Tesla Semi and Megapack 3 are on schedule "

apps/api/app/services/demo/source_projection.py

@@ -5,6 +5,11 @@
 from typing import Any, Protocol
 from urllib.parse import quote
 
+from shared.services.chunks.path_segments import (
+    join_document_path,
+    split_escaped_document_path,
+)
+
 _SOURCE_FILE_EXTENSIONS = (
     ".csv",
     ".doc",
@@ -241,22 +246,18 @@ def _publication_path(
     if not raw:
         return prefix
 
-    if "-->" in raw:
-        sections = [part.strip() for part in raw.split("-->")[1:] if part.strip()]
-        return "/".join([prefix, *sections]) if sections else prefix
-
     if raw.startswith("images/") or raw.startswith("tables/"):
         return f"{prefix}/Assets/{raw}"
 
-    parts = [part.strip() for part in raw.split("/") if part.strip()]
+    parts = split_escaped_document_path(raw)
     if parts and parts[0] == source.title:
-        return raw
+        return join_document_path(parts)
     if len(parts) >= 2 and parts[0] == "Default_Root":
         section_parts = parts[2:] if parts[1] == source.title else parts[1:]
-        return "/".join([prefix, *section_parts]) if section_parts else prefix
+        return join_document_path([prefix, *section_parts]) if section_parts else prefix
     if parts and _is_source_file_root(parts[0]):
         section_parts = parts[1:]
-        return "/".join([prefix, *section_parts]) if section_parts else prefix
+        return join_document_path([prefix, *section_parts]) if section_parts else prefix
     return prefix
 
 

apps/api/tests/contract/test_chunk_document_path_contract.py

@@ -89,38 +89,6 @@ def test_should_not_treat_dotted_section_titles_as_legacy_document_files() -> No
     assert children[0]["path"] == chunk_path
 
 
-def test_should_read_arrow_delimited_document_paths_as_section_paths() -> None:
-    chunk_path = "report.pdf-->Intro-->Subsection"
-
-    doc_nav = ZipResultSchemaBuilder().build_doc_nav(
-        [
-            {
-                "chunk_id": "chunk_arrow_delimited_path",
-                "type": "text",
-                "content": "arrow delimited content",
-                "path": chunk_path,
-                "metadata": {"summary": "arrow delimited summary"},
-            }
-        ],
-        "report.pdf",
-    )
-
-    sections = cast(list[dict[str, object]], doc_nav["sections"])
-    children = cast(list[dict[str, object]], sections[0]["children"])
-
-    assert (
-        section_path_from_chunk_path(
-            chunk_path,
-            source_file_name="report.pdf",
-        )
-        == "Intro / Subsection"
-    )
-    assert sections[0]["title"] == "Intro"
-    assert sections[0]["path"] == "report.pdf/Intro"
-    assert children[0]["title"] == "Subsection"
-    assert children[0]["path"] == "report.pdf/Intro/Subsection"
-
-
 def test_should_preserve_literal_arrow_text_in_slash_paths() -> None:
     chunk_path = "report.pdf/Inputs --> Outputs/Details"