jsahnandClaude Fable 5
d9dda79282
- Per-paper summary batches are fact-checked against abstracts (verify -> revise once on major issues -> re-verify), controlled by SEBRIEF_VERIFY_ENABLED - The paper cap never drops papers already published in this week's digest (--force re-runs could otherwise erase them from every digest) - SEBRIEF_MAX_PAPERS default 40 -> 60 (observed weekly volume ~47) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
55 lines
1.7 KiB
Python
55 lines
1.7 KiB
Python
"""Settings loading: CSV splitting, validation, derived properties."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from pydantic import ValidationError
|
|
|
|
from sebrief.config import Settings
|
|
|
|
|
|
def make_settings(**overrides) -> Settings:
|
|
return Settings(_env_file=None, **overrides)
|
|
|
|
|
|
def test_defaults():
|
|
s = make_settings()
|
|
assert s.minimax_model == "MiniMax-M3"
|
|
assert s.minimax_fallback_models == ["MiniMax-M2.7", "MiniMax-M2.5"]
|
|
assert s.run_weekday == 0
|
|
assert s.run_time_kst == "07:00"
|
|
assert s.catchup_window_hours == 72
|
|
assert s.max_papers == 60
|
|
assert s.backfill_days == 7
|
|
assert s.verify_enabled is True
|
|
assert s.paper_summary_enabled is True
|
|
assert s.paper_summary_batch_size == 8
|
|
assert s.rss_feeds == []
|
|
assert s.db_path == Path("data") / "sebrief.sqlite3"
|
|
|
|
|
|
def test_csv_fields_split():
|
|
s = make_settings(
|
|
MINIMAX_FALLBACK_MODELS=" a , b ,",
|
|
SEBRIEF_RSS_FEEDS="e-Informatica|https://example.org/rss, X|https://x.example/feed",
|
|
SEBRIEF_EXTRA_BLACKLIST_ISSNS="1234-5678, 2345-6789",
|
|
)
|
|
assert s.minimax_fallback_models == ["a", "b"]
|
|
assert s.rss_feeds == ["e-Informatica|https://example.org/rss", "X|https://x.example/feed"]
|
|
assert s.extra_blacklist_issns == ["1234-5678", "2345-6789"]
|
|
|
|
|
|
def test_run_weekday_validated():
|
|
with pytest.raises(ValidationError):
|
|
make_settings(SEBRIEF_RUN_WEEKDAY="7")
|
|
assert make_settings(SEBRIEF_RUN_WEEKDAY="6").run_weekday == 6
|
|
|
|
|
|
def test_env_aliases(tmp_path):
|
|
s = make_settings(SEBRIEF_DATA_DIR=str(tmp_path / "d"), SEBRIEF_MAX_PAPERS="10")
|
|
assert s.data_dir == tmp_path / "d"
|
|
assert s.max_papers == 10
|
|
assert s.db_path == tmp_path / "d" / "sebrief.sqlite3"
|