45f51c6341496ad17f5bc819d3b0adb4c57728f1
10
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Mark Eaton
|
45f51c6341 |
v2 chunk 2c: numbered-note format support + real-draft test
Extend the v2 parser and CLI to handle [N] text footnote definitions in addition to pandoc-style [^marker]: text. The numbered format is what docx-to-text conversion of footnoted Word documents produces. The user's "Anti-Communist Formations of LIS" draft uses this format for all 107 of its notes; without this support, v2 was structurally incapable of running on real-world docx-derived inputs. src/cmos/parser.py: - Add NoteDefinition.original_prefix field so reassembly can round-trip the source's marker syntax (pandoc input → pandoc output, numbered input → numbered output) without consumers needing to know which format was matched. - Update find_notes() to populate original_prefix as "[^N]: ". - Add find_numbered_notes() targeting "[N] text" definitions. Marker must be all digits (rejects [Smith 2020], [foo], etc.); caret prefix is rejected (rejects pandoc-style cleanly). src/cmos/cli.py: - reformat_notes now auto-detects format: tries find_notes first, falls back to find_numbered_notes if no pandoc definitions found. Uses definition.original_prefix for reassembly so both formats round-trip correctly. tests/test_parser.py: - 11 new tests for find_numbered_notes covering: single/multiple definitions, multi-digit markers, line number recording, trailing whitespace stripping, ignoring pandoc/non-numeric markers, original prefix recording, and the actual Anti-Communist draft format. - 1 new test for find_notes original_prefix population. tests/test_cli.py: - 2 new tests for reformat_notes auto-detect: numbered input round- trips as numbered output, pandoc input still round-trips as pandoc. Total suite: 136/136 (was 123, +13 net new). v1 untouched, 96/96 v1 tests still passing. Real-draft validation: ran cmos format-notes against the 107-note Anti-Communist Formations of LIS draft (108 calls in parallel via the existing concurrency=8 thread pool, completed cleanly). Output saved to /tmp (not committed). All 107 notes preserved through the pipeline; ~30-40 first-occurrence full notes produced clean CMOS 18 note form; ~30 shortened-form refs correctly left unchanged; 2 real bugs surfaced for the next iteration (empty input → conver- sational reply, Ibid → empty string), plus several lower-priority issues (substantive note truncation, retry waste on shortened forms, lossy month dropping). Not addressed in this chunk per the "collect signal, don't fix" plan. |
||
|
Mark Eaton
|
87cb70b4fb |
v2 chunk 2b: cli format-notes subcommand and reformat_notes()
Wire the v2 note formatter into the CLI so it can be invoked on real markdown drafts. The format-notes subcommand mirrors v1's format subcommand: parser → formatter → reassemble, with concurrent API calls. src/cmos/cli.py: - Import find_notes and format_note_entry alongside the existing v1 imports. - Add reformat_notes(text, formatter, concurrency) that finds pandoc-style markdown footnote definitions via find_notes, formats each definition's text via the v2 note formatter (or an injected fake), and substitutes the formatted text back into the original line position. Non-definition lines preserved byte-for-byte. Returns text unchanged when no definitions found. - Register the format-notes argparse subparser with the same --concurrency flag as v1's format. - Dispatch args.command == "format-notes" to reformat_notes. - Module docstring updated to document both subcommands. tests/test_cli.py: - 7 new tests for reformat_notes covering: in-place substitution, order preservation under concurrency, prose preservation, reference markers staying verbatim, no-op on empty input, trailing newline preservation. - Extended test_python_dash_m_invocation_actually_runs_main to also assert "format-notes" appears in --help, catching accidental subcommand removal. Path B integrity: formatter.py, note_formatter.py, parser.py, linter.py, harness/score.py all unchanged. No LINTER_VERSION bump. 96/96 v1 tests still passing. Total suite: 123/123. Real-API end-to-end smoke test on a temp draft with 2 footnote definitions: both reformatted byte-for-byte, prose and headings preserved, ## Conclusion section after the notes preserved. |
||
|
Mark Eaton
|
d061f78b7f |
v2 chunk 2a iter 1: rules 6+18 — ed. invariant, expand publishers
Two prompt edits to SYSTEM_PROMPT_NOTES driven by chunk 1 smoke test
gaps on chapter_first_doyle.toml.
Rule 6 (chapter form) expanded with an explicit invariance statement:
"ed." is the canonical abbreviation regardless of editor count — do
NOT pluralize to "eds." for multiple editors. CMOS NB treats it as
an invariant abbreviation, not a number-agreeing word.
New rule 18 (publisher expansion) mirrors v1 formatter.py rule 14:
publisher names must be in full canonical form, with note-form-
specific examples ("U of Chicago Press" → "University of Chicago
Press"). Includes the same MIT Press / ALA Editions / MLA carve-out
for publishers whose canonical self-presentation legitimately uses
initials.
Two new prompt-content unit tests added to tests/test_note_formatter.py
following the v1 test_formatter.py discipline. TDD cycle: red-green-
verified end-to-end.
Real-API smoke test, 3 v2 exemplars × 2 runs each: 6/6 byte-perfect
matches (was 4/6 in chunk 1; chapter_first_doyle went 0/2 → 2/2,
book and journal still 2/2). v1 untouched, 96/96 v1 tests still
passing. Total suite: 116/116.
|
||
|
Mark Eaton
|
28ca3ac928 |
v2 chunk 1: scaffold note formatter (Path B parallel artifact)
Begin v2 (in-text citation note form) as a parallel artifact to the
v1 bibliography formatter, per the Path B architectural decision:
no shared mutable state, no shared prompt content, no v1 changes.
New artifacts:
- src/cmos/parser.py: add find_notes() / NoteDefinition /
NotesParseResult as siblings to split_bibliography(). Targets
pandoc-style markdown footnote definitions [^marker]: text.
Single-line only; multi-line continuation deferred.
- src/cmos/note_formatter.py: new module mirroring formatter.py.
17-rule SYSTEM_PROMPT_NOTES for CMOS 18 first-occurrence note
form. Reuses cmos.runtime_validator.validate() unchanged — its
structural checks all apply to note form too. Caller injection,
retry loop, and model selection mirror v1.
- tests/test_parser.py: 7 new tests for find_notes().
- tests/test_note_formatter.py: 11 new tests mirroring v1 test
discipline (no API calls, fake-caller injection, retry semantics,
prompt smoke checks).
- exemplars/notes/: new subdirectory with 3 hand-synthesized
first-occurrence note exemplars (book, journal article, chapter
in edited book). Uses expected_note as the field name (not v1's
expected_bibliography). harness/score.py:load_exemplars uses a
non-recursive glob, so the v1 canary loader does not see these —
Path B isolation is automatic.
v1 untouched. v1 canary still loads exactly 17 exemplars. Full
test suite: 96 v1 + 18 new v2 = 114 passing.
Smoke-tested all 3 v2 exemplars against real GPT-5 (not fakes),
2 runs each. book_first_yu and journal_first_kwon: 4/4 byte-perfect
on the first try. chapter_first_doyle: 0/2, surfacing two known
prompt gaps for the next iteration:
1. Publisher abbreviation not expanded ("U of Chicago Press"
preserved instead of "University of Chicago Press"). v1's
formatter.py rule 14 is missing from the v2 prompt.
2. "ed." pluralized to "eds." for multiple editors. CMOS NB
uses "ed." invariantly regardless of editor count.
Both gaps are addressable prompt edits, not architectural problems —
exactly the kind of finding the dev loop is designed to surface.
Out of scope (deferred to chunk 2 and later): CLI extension,
shortened-form generation, document reassembly, harness scoring
loop integration, v2 linter rules, real-draft testing.
|
||
|
Mark Eaton
|
22404fbd6b |
cli: add __main__ guard so python -m cmos.cli actually runs
Without `if __name__ == "__main__": sys.exit(main())` at the bottom of cli.py, `python -m cmos.cli format <path>` imports the module but never invokes main(), so the process silently exits 0 with empty stdout — indistinguishable from a successful run that produced no output. Discovered during real-draft testing on 2026-04-11. Adds a regression test that subprocesses the CLI with --help and asserts on stdout content. argparse --help exits 0 in both broken and fixed states; stdout content is the only discriminator. Both invocation paths now work: - uv run cmos format <path> (pyproject script entry) - uv run python -m cmos.cli format <path> (module invocation) |
||
|
cmos dev
|
8b14dbc9ca |
formatter: linter-guided retry to suppress GPT-5 reasoning drift
GPT-5 is a reasoning model and is not bit-deterministic even at the API level (no temperature override allowed). Variance testing in iter 7 showed ~1 in 6 loop runs hit a nondeterministic regression: in one run the magazine_mead exemplar lost its italic markers around "New Yorker" even though the exact same input had produced a clean output 5 times prior. The scoring linter caught it (rule_magazine_name_italicized) but the formatter still emitted the bad output to the user. This commit adds a runtime guardrail: - New module src/cmos/runtime_validator.py — type-independent structural sanity checks. Operates on a single candidate string with no Exemplar context, because at runtime we don't know the source type. Checks: ends with period, no Ibid., has at least one italic span (almost every CMOS bibliography entry italicizes something), balanced * and " markers. Deliberately weaker than the scoring linter; it's a fast guardrail, not a full validator. - format_bibliography_entry now retries up to DEFAULT_MAX_RETRIES (2) times when the validator rejects a candidate. Independent re-calls are usually enough because the failures are stochastic. If every attempt fails, the LAST attempt is returned (no exception) — the caller still gets something usable, and the failure surfaces through the scoring linter or human review. The retry path costs zero on the common case (1 call per entry); ~1-2% extra calls on noisy drafts. Empirical: 3 consecutive loop runs after this change are scalar 1.000 canary 1.000 (vs 5/6 clean in the variance test before). Sample is too small to claim full suppression but the signal is positive. Also adds a new exemplar journal_multiauthor_secondary_first_last.toml captured from the user's HML draft (Hasanah et al., IJIDI 2024). It exercises the case where a multi-author entry has the first author inverted and the rest in First Last form — which the iter 7 HML run got wrong on one entry. Variance testing showed the exemplar passes 6/6 in isolation, so the original HML failure was nondeterminism, not a missing rule. Keeping the exemplar regardless: it adds canary coverage of a real-world multi-author pattern, no-DOI / JSTOR-URL variant, and the year-suffix author-date holdover stripping. Tests: 85 → 95 (8 new for runtime_validator + 2 new for formatter retry). All passing. |
||
|
cmos dev
|
2bd1bdf0d4 |
cli: parallelize formatter calls with thread pool
reformat_draft now uses concurrent.futures.ThreadPoolExecutor with a default of 8 workers. OpenAI SDK calls are synchronous but network- bound, so threads release the GIL during I/O and give real speedup. ThreadPoolExecutor.map preserves input order regardless of completion order, so output is deterministic. Empirical: HML draft (134 entries) went from ~25 min serial to 1m55s with concurrency=12. ~12x speedup; further increases hit OpenAI rate limits. CLI gains a --concurrency flag (default 8) for tuning per draft size / rate limit headroom. concurrency=1 forces serial execution for debugging. New test asserts that order is preserved when concurrent calls finish out of input order (uses a sleep-by-index fake formatter). |
||
|
cmos dev
|
1b11a03a0b |
judge: LLM-as-judge triage for canary failures (advisory only)
Add harness/judge.py and scripts/triage.py. The judge reads the latest loop run from logs/runs.jsonl, finds canary failures (exact_match=False but fields/linter passed), and asks GPT-5 to classify each as "regression", "variant", or "unclear" with CMOS 18 section citations. CRITICAL: verdicts are ADVISORY ONLY. They are written to logs/triage.jsonl and never feed back into the loop scalar. Using the judge as ground truth would let the formatter-LLM optimize against a judge-LLM from the same model family, inviting shared-bias drift. Design: - harness/judge.py: Verdict dataclass, build_judge_prompt, parse_verdict (handles code fences and normalizes unknown labels to "unclear"), judge() with caller-injection seam matching cmos.formatter. Uses the same _is_reasoning_model branching to skip temperature for gpt-5/o*. Judge model is separately overridable via CMOS_JUDGE_MODEL env var (defaults to OPENAI_MODEL, which defaults to gpt-5). - scripts/triage.py: CLI that walks runs.jsonl, locates a target run (default: latest), filters canary failures, calls judge on each, appends a verdict record to logs/triage.jsonl. --dry-run available for offline testing. Exits 0 with a note when there are no failures. Tests: 6 new unit tests covering prompt building, JSON parsing (including code-fence stripping and unknown-label normalization), and caller injection. No real API calls in the test suite. Validated on iter 3's run (canary 0.286, 10 failures): - 8 correctly flagged as regressions, each with a cited CMOS section (14.72, 14.76, 14.128, 14.190, 14.206, 14.212, 14.267, ...). - 2 flagged as variants: "Kindle" vs "Kindle edition" (CMOS 14.159– 14.161 allows flexibility) and "The New Yorker" vs "New Yorker" (CMOS 14.191 — leading "The" is optional). These surface that the formatter's current rules 17 and 18 are stricter than CMOS strictly requires; documenting here but not acting on yet. |
||
|
cmos dev
|
fe5e071066 |
linter: expand to 21 rules covering all 8 source types (v0.3.0)
Close the defense-in-depth gap flagged after iter 6: chapter, magazine,
newspaper, social_media, podcast, and video exemplars had ZERO applicable
linter rules, so their 100% linter pass rate was trivially true. Every
exemplar now has 3-6 structural rules firing.
Bump LINTER_VERSION to v0.3.0. Per harness discipline, this invalidates
prior run logs' scores for cross-version comparison (they stay in the
log as history). The re-baseline run still scores scalar 1.000, canary
1.000 on all 14 exemplars — formatter was already producing output that
matches the new structural conventions, so tightening the linter didn't
surface any regressions.
New rules (12):
- chapter_book_title_italicized
- chapter_in_book_marker
- magazine_name_italicized
- newspaper_name_italicized
- periodical_comma_before_date (magazine + newspaper; not journal)
- social_media_post_quoted
- social_media_platform_comma_date
- podcast_series_italicized
- podcast_episode_quoted
- podcast_format_label
- video_title_quoted (in quotes, NOT italicized)
- video_format_label
Extended:
- article_title_quoted now covers journal, magazine, newspaper,
and accepts ?/! as terminal punctuation
Each rule has a positive + negative unit test with the CMOS/Purdue source
cited in the docstring. Tests: 48 → 78 (30 new).
Per-exemplar applicable-rule counts after this change:
book 4 journal 5-6 web 3
chapter 4 magazine 5 social 4
podcast 5 video 4 newspaper 5
|
||
|
cmos dev
|
4cad38ef30 |
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. |