feat(index): maintain existing indexes on re-materialization (spec §6)

TDD step 6: on an existing index, managed lines whose target is an
ingest-owned file removed this run are dropped, a managed label is
refreshed in place when the extraction title changes, and every other
line — curated links, promoted-verdict links, foreign line endings — is
preserved byte for byte. Load-bearing test: a promoted verdict and its
index link survive re-ingest unchanged.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QeqhJpYQyghASjiJo5EhGg

src/llm_ingestion_okf/materialize.py

@@ -101,6 +101,36 @@ def _write_bytes(bundle_dir: Path, name: str, content: str) -> Path:
     return resolved
 
 
+def _update_index_lines(
+    index_path: Path, removed_targets: set[str], labels_by_target: dict[str, str]
+) -> None:
+    """§6 maintenance on an EXISTING index: drop managed lines whose target is
+    an ingest file removed in this run; refresh in place a managed label that
+    no longer equals the extraction title. Every other line is preserved
+    verbatim, in order — including its own line ending.
+    """
+    original = index_path.read_bytes().decode("utf-8")
+    lines = original.splitlines(keepends=True)
+    updated: list[str] = []
+    changed = False
+    for line in lines:
+        content = line.rstrip("\r\n")
+        ending = line[len(content) :]
+        match = _MANAGED_LINE_RE.match(content)
+        if match is not None:
+            target = match.group("target")
+            if target in removed_targets:
+                changed = True
+                continue
+            new_label = labels_by_target.get(target)
+            if new_label is not None and match.group("label") != new_label:
+                line = f"- [{new_label}]({target})" + ending
+                changed = True
+        updated.append(line)
+    if changed:
+        index_path.write_bytes("".join(updated).encode("utf-8"))
+
+
 def _link_in_index(bundle_dir: Path, target_name: str, label: str) -> None:
     # §6: idempotent by target — a link whose target is already present in
     # the index is never added twice.
@@ -215,8 +245,15 @@ def materialize_bundle(
     # §6 index generation — the last disk mutation. A fresh index gets
     # 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
+    }
     if not index_path.is_file():
         _write_bytes(bundle, _INDEX_NAME, manifest.bundle_summary + "\n")
+    else:
+        # Links whose target is an ingest-owned file removed this run MUST be
+        # removed; all other links — curated and promoted — are preserved.
+        _update_index_lines(index_path, owned - staged_names, labels_by_target)
     for extraction in manifest.extractions:
         _link_in_index(bundle, generated_filename(extraction.id), extraction.title)
     return IngestResult(written=written)