Scaffold CMOS 18 reformatter: harness, linter, parser, formatter, CLI

Initial phase-1 baseline of the karpathy/autoresearch-style loop.
The formatter module is the inner-loop artifact; parser and linter
are infra. The linter carries a LINTER_VERSION hash (v0.2.0) that
will force a re-baseline on any rule change.

Components:
- harness/diff.py: case-sensitive field-level substring diff
- harness/score.py: three-axis scoring (field, linter, canary exact)
- src/cmos/linter.py: 9 CMOS 18 structural rules, each Purdue/CMOS cited
- src/cmos/parser.py: locate ## Bibliography section, split entries
- src/cmos/formatter.py: prompt + OpenAI call with caller injection
- src/cmos/cli.py: cmos format path/to/draft.md
- scripts/run_loop.py: loop runner with --fake mode for no-API runs
- exemplars/: 3 canary seed exemplars (book, journal w/DOI, web),
  sourced from chicagomanualofstyle.org quick guide

Tests: 48 passing. Fake-mode baseline scalar = 0.000 on the 3 seed
exemplars (identity caller fails the linter on every rule). This is
the floor the real GPT-5 formatter needs to improve from.

rough_drafts/sample.md

@@ -0,0 +1,11 @@
+# A sample draft
+
+Here is some prose that references a few sources, none of them properly
+formatted. This file exists so we can manually verify the CLI end-to-end with
+`uv run cmos format rough_drafts/sample.md` once an OpenAI key is set.
+
+## Bibliography
+
+yu, charles. interior chinatown. New York: Pantheon Books, 2020.
+Kwon, Hyeyoung. "inclusion work: children of immigrants claiming membership in everyday life." American Journal of Sociology, Vol. 127, Issue 6, 2022, pp. 1818-1859. DOI: 10.1086/720277
+google, "privacy policy," privacy & terms, effective nov 15 2023, policies.google.com/privacy