citefind: the references in a bibliography, and what could not be read off them

Cuts a reference list into entries — at the note numbers where there are any,
at the layout where there are not — and reads each as far as its punctuation
allows. Fields that would not parse are named in `unsettled` rather than
guessed at, and `--prompt` asks a model about exactly those and no others.

Over 202 real reference sections from the corpus: 8,566 references, 95% with
a title, 82% with a year, 46% settling every field with no model involved.
A title is refused where the entry was never divided, so no record reports
its own text back as the work it cites.

`ibid.` is flagged and left alone — it points at a work, and the entry does
not say which. A rule of dashes is filled in, because the style defines it as
the author above.

chunkmd gains `note_starts` and `cites_something`: recognising a page of
notes and splitting one are the same knowledge, and two copies of that
pattern would drift.

crates/bindings/python/catena/__init__.py

@@ -14,9 +14,12 @@ from ._catena import (
     __version__,
     cue_windows,
     chunk_markdown,
+    citation_prompt,
     count_tokens,
+    find_citations,
     fuse_hits,
     identify,
+    merge_citation_reply,
     pack_cues,
     parse_identifier,
     parse_subtitles,
@@ -30,9 +33,12 @@ __all__ = [
     "__version__",
     "cue_windows",
     "chunk_markdown",
+    "citation_prompt",
     "count_tokens",
+    "find_citations",
     "fuse_hits",
     "identify",
+    "merge_citation_reply",
     "pack_cues",
     "parse_identifier",
     "parse_subtitles",