fix(materialize): render a title identically in frontmatter and index

ingest-spec §4 makes the extraction title BOTH the `title` frontmatter and
the index link label — one value, two sites. The frontmatter renderer
single-lined its values while the index label was written raw, so a title
carrying a whitespace run rendered two different ways from one input:

    title: Energiforbruk 2024
    - [Energiforbruk  2024](ingest-orders.md)

Single-lining is now one named rule applied at every site that renders the
title, instead of a detail of frontmatter rendering that the index path did
not share.

No golden bytes change: no title in this repo, portfolio-optimiser or
portfolio-optimiser-claude carries a whitespace run.

Open question routed to commons, the spec owner: §5 mandates collapsing
whitespace runs in `source_query` only, while `title` is separately required
to be single-line and is already validated as such at manifest load. So
collapsing the title may be over-application — the alternative reading is
that both sites should emit it verbatim. Either reading keeps the two sites
in agreement, which is what this commit establishes; which of the two is
correct is a spec question, not ours.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WdVgowYC4LARgvNdNMiuvz

src/llm_ingestion_okf/materialize.py

@@ -49,11 +49,18 @@ class IngestResult:
     stamp: str
 
 
+def _single_line(value: str) -> str:
+    # §5: frontmatter values are single-lined — whitespace runs, including
+    # newlines, collapse to one space — because the format is line-oriented
+    # and parsing stops at the first `---` line. §4 makes the extraction
+    # title BOTH the `title` frontmatter and the index link label, so the
+    # same rule has to reach both sites or the one value renders two ways.
+    return " ".join(value.split())
+
+
 def _render_frontmatter(frontmatter: dict[str, str]) -> str:
-    # Line-oriented `key: value`; values are single-lined (whitespace runs,
-    # including newlines, collapse to one space — §5) because parsing is
-    # line-oriented and stops at the first `---` line. Insertion order.
-    return "\n".join(f"{key}: {' '.join(value.split())}" for key, value in frontmatter.items())
+    # Line-oriented `key: value`, insertion order.
+    return "\n".join(f"{key}: {_single_line(value)}" for key, value in frontmatter.items())
 
 
 def _parse_frontmatter(path: Path) -> dict[str, str]:
@@ -141,7 +148,7 @@ def _link_in_index(bundle_dir: Path, target_name: str, label: str) -> None:
     if f"]({target_name})" in body:
         return
     prefix = body if body.endswith("\n") else body + "\n"
-    index_path.write_bytes(f"{prefix}- [{label}]({target_name})\n".encode())
+    index_path.write_bytes(f"{prefix}- [{_single_line(label)}]({target_name})\n".encode())
 
 
 def materialize_bundle(
@@ -265,7 +272,8 @@ def materialize_bundle(
     # bundle_summary as its body; links are appended in extraction order.
     index_path = bundle / _INDEX_NAME
     labels_by_target = {
-        generated_filename(extraction.id): extraction.title for extraction in manifest.extractions
+        generated_filename(extraction.id): _single_line(extraction.title)
+        for extraction in manifest.extractions
     }
     if not index_path.is_file():
         _write_bytes(bundle, _INDEX_NAME, manifest.bundle_summary + "\n")

tests/test_materialize.py

@@ -124,6 +124,41 @@ def test_file_source_concept_file_exact_bytes(file_setup: tuple[Path, Path]) ->
     assert (bundle / "ingest-orders.md").read_bytes() == expected.encode("utf-8")
 
 
+def test_title_renders_identically_in_frontmatter_and_index(tmp_path: Path) -> None:
+    # §4: the title "becomes the `title` frontmatter AND the index link
+    # label" — one value, two sites, so the two MUST agree. The frontmatter
+    # renderer single-lines its values; the index label was written raw, so
+    # a title carrying a whitespace run diverged between the two.
+    src = tmp_path / "src"
+    manifest_path = write_manifest(
+        src,
+        file_manifest_data(
+            [
+                {
+                    "id": "orders",
+                    "title": "Energiforbruk  2024",
+                    "query": "orders.csv",
+                    "okf_type": "dataset",
+                    "max_rows": 100,
+                }
+            ]
+        ),
+    )
+    (src / "data").mkdir()
+    (src / "data" / "orders.csv").write_text("a,b\n1,x\n", encoding="utf-8", newline="")
+    bundle = tmp_path / "bundle"
+
+    materialize_bundle(manifest_path, bundle, ingested_at=INGESTED_AT)
+
+    concept = (bundle / "ingest-orders.md").read_text(encoding="utf-8")
+    index = (bundle / "index.md").read_text(encoding="utf-8")
+    frontmatter_title = next(
+        line.partition(":")[2].strip() for line in concept.splitlines() if line.startswith("title:")
+    )
+    index_label = index.partition("- [")[2].partition("]")[0]
+    assert frontmatter_title == index_label
+
+
 def test_result_lists_written_concept_files(file_setup: tuple[Path, Path]) -> None:
     manifest_path, bundle = file_setup
     result = materialize_bundle(manifest_path, bundle, INGESTED_AT)