cmos dev
2bd1bdf0d4
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).
104 lines
3.0 KiB
Python
104 lines
3.0 KiB
Python
"""Tests for src/cmos/cli.py — end-to-end draft reformatting.
|
|
|
|
The CLI orchestrates parser → formatter → reassemble. Tests inject a fake
|
|
formatter so no API calls happen; the goal is to pin the glue logic, not the
|
|
LLM behavior.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from cmos.cli import reformat_draft
|
|
from cmos.parser import NoBibliographyError
|
|
|
|
|
|
def _fake_formatter(messy: str) -> str:
|
|
# Deterministic fake: return a cleaned-up marker string so the output is
|
|
# recognizable.
|
|
return f"FORMATTED({messy.strip()})"
|
|
|
|
|
|
def test_reformat_draft_rewrites_only_bibliography_section():
|
|
draft = """\
|
|
# My Paper
|
|
|
|
Some prose with citations.
|
|
|
|
## Bibliography
|
|
|
|
yu, charles. interior chinatown. 2020.
|
|
kwon, hyeyoung. inclusion work. 2022.
|
|
"""
|
|
output = reformat_draft(draft, formatter=_fake_formatter)
|
|
assert "# My Paper" in output
|
|
assert "Some prose with citations." in output
|
|
assert "FORMATTED(yu, charles. interior chinatown. 2020.)" in output
|
|
assert "FORMATTED(kwon, hyeyoung. inclusion work. 2022.)" in output
|
|
# Original messy lines must not also survive.
|
|
assert "yu, charles. interior chinatown. 2020." not in output.replace(
|
|
"FORMATTED(yu, charles. interior chinatown. 2020.)", ""
|
|
)
|
|
|
|
|
|
def test_reformat_draft_preserves_sections_after_bibliography():
|
|
draft = """\
|
|
## Bibliography
|
|
|
|
one entry.
|
|
|
|
## Appendix
|
|
|
|
appendix text.
|
|
"""
|
|
output = reformat_draft(draft, formatter=_fake_formatter)
|
|
assert "FORMATTED(one entry.)" in output
|
|
assert "## Appendix" in output
|
|
assert "appendix text." in output
|
|
|
|
|
|
def test_reformat_draft_raises_when_no_bibliography():
|
|
with pytest.raises(NoBibliographyError):
|
|
reformat_draft("## Intro\n\nno bib here.\n", formatter=_fake_formatter)
|
|
|
|
|
|
def test_reformat_draft_bibliography_heading_preserved():
|
|
draft = "## Bibliography\n\nentry.\n"
|
|
output = reformat_draft(draft, formatter=_fake_formatter)
|
|
assert "## Bibliography" in output
|
|
|
|
|
|
def test_reformat_draft_preserves_order_under_concurrency():
|
|
# With concurrent execution the formatter is called on all entries in
|
|
# parallel; the CLI must reassemble them in input order regardless of
|
|
# which call finishes first. This test uses a fake formatter that
|
|
# sleeps based on the entry content so earlier entries finish AFTER
|
|
# later ones if order were naively tied to completion.
|
|
import time
|
|
|
|
def slow_fake(messy: str) -> str:
|
|
# Entries with lower index sleep longer so they finish last.
|
|
n = int(messy.split()[-1])
|
|
time.sleep(0.05 * (5 - n))
|
|
return f"FORMATTED({messy})"
|
|
|
|
draft = """\
|
|
## Bibliography
|
|
|
|
entry 0
|
|
entry 1
|
|
entry 2
|
|
entry 3
|
|
entry 4
|
|
"""
|
|
output = reformat_draft(draft, formatter=slow_fake, concurrency=4)
|
|
# Entries must appear in input order.
|
|
lines = [l for l in output.splitlines() if l.startswith("FORMATTED(")]
|
|
assert lines == [
|
|
"FORMATTED(entry 0)",
|
|
"FORMATTED(entry 1)",
|
|
"FORMATTED(entry 2)",
|
|
"FORMATTED(entry 3)",
|
|
"FORMATTED(entry 4)",
|
|
]
|