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.

exemplars/book_single_author_yu.toml

@@ -0,0 +1,15 @@
+# Source: CMOS official citation guide (chicagomanualofstyle.org), 18th ed.
+# The canonical output is the guide's reference example verbatim.
+# Rule cited: CMOS 14.30 — place of publication no longer required in 18th ed.
+source = "CMOS official citation guide (chicagomanualofstyle.org/tools_citationguide/citation-guide-1.html)"
+type = "book"
+tags = ["book", "single-author"]
+canary = true
+messy_input = "yu, charles. interior chinatown. New York: Pantheon Books, 2020."
+expected_bibliography = "Yu, Charles. *Interior Chinatown*. Pantheon Books, 2020."
+
+[canonical]
+author = "Yu, Charles"
+title = "Interior Chinatown"
+publisher = "Pantheon Books"
+year = 2020