bvandeusen
5d2d27c499
Prep prose (services/journal_prep.py): - Emit explicit "WEATHER: none available — do NOT mention weather" absent-marker so a small model can't invent partly-cloudy/temperature prose when both configured locations have empty addresses. - Replace negative-only system rule with positive-anchored guidance forbidding weather/temp/precip mentions unless a numeric WEATHER section is present; also bans echoing parenthetical labels verbatim. - Reword overdue header to "(past their due date, still open — backlog, not today's work)" and render lines as "was due <date>, N day(s) overdue" with correct singular/plural. Supersedes the wording noted in Fable task #159. - Deterministic fabricated-weather reconciler: low-false-positive regex detects fabricated weather phrasing; on trip with an empty section, regenerate once with a corrective. Persistent fabrication logs ERROR rather than mangling prose. Journal route (routes/journal.py): - Override message_count with len(messages) in _day_payload. The chat path already does this; the journal path was hitting the Conversation.to_dict() fallback to 0 because messages aren't eager-loaded on that instance. Tests: - tests/test_journal_message_count.py — pins the model-level trap and the override contract (3 cases). - tests/test_journal_prep_hardening.py — 11 cases covering the fabricated-weather reconciler and absent-marker rendering. - tests/test_journal_prep_filtering.py — updated one stale assertion. Tracks Fable task #171. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
124 lines
4.4 KiB
Python
124 lines
4.4 KiB
Python
"""Coverage for the daily-prep hardening pass.
|
|
|
|
Targets the two prep-quality defects observed via the fable MCP on
|
|
2026-05-19 (conversation #291):
|
|
|
|
1. Fabricated weather ("partly cloudy with a high of 68°F and a 15%
|
|
chance of rain") emitted with an empty weather section.
|
|
2. Self-contradictory overdue phrasing ("still on the list, not
|
|
currently due, 88 days ago"; "1 days ago").
|
|
|
|
All targets are pure sync functions — no DB / LLM needed.
|
|
"""
|
|
import datetime
|
|
|
|
from fabledassistant.services.journal_prep import (
|
|
_prose_fabricated_weather,
|
|
_render_sections_for_prompt,
|
|
_render_task_line,
|
|
)
|
|
|
|
TODAY = datetime.date(2026, 5, 19)
|
|
|
|
|
|
# ── Overdue phrasing ────────────────────────────────────────────────────────
|
|
|
|
|
|
def test_overdue_line_singular_day():
|
|
line = _render_task_line(
|
|
{"title": "Change my oil", "due_date": "2026-05-18", "days_overdue": 1},
|
|
include_due=False, include_overdue=True,
|
|
)
|
|
assert "1 day overdue" in line
|
|
assert "1 days" not in line # the old ungrammatical form is gone
|
|
|
|
|
|
def test_overdue_line_plural_days_no_contradiction():
|
|
line = _render_task_line(
|
|
{"title": "Research X", "due_date": "2026-02-20", "days_overdue": 88},
|
|
include_due=False, include_overdue=True,
|
|
)
|
|
assert "88 days overdue" in line
|
|
assert "was due 2026-02-20" in line
|
|
assert "days ago" not in line # replaced by unambiguous "overdue"
|
|
|
|
|
|
def test_overdue_section_header_is_unambiguous():
|
|
out = _render_sections_for_prompt({
|
|
"tasks_overdue": [
|
|
{"title": "Research X", "due_date": "2026-02-20", "days_overdue": 88},
|
|
],
|
|
})
|
|
assert "past their due date, still open" in out
|
|
# The phrase that the model parroted into the self-contradiction is gone.
|
|
assert "not currently due" not in out
|
|
|
|
|
|
# ── Weather absent-marker ───────────────────────────────────────────────────
|
|
|
|
|
|
def test_empty_weather_emits_explicit_none_marker():
|
|
out = _render_sections_for_prompt({
|
|
"tasks_overdue": [
|
|
{"title": "Change my oil", "due_date": "2026-05-18", "days_overdue": 1},
|
|
],
|
|
"weather": [],
|
|
})
|
|
assert "WEATHER: none available" in out
|
|
assert "Do NOT mention weather" in out
|
|
|
|
|
|
def test_present_weather_renders_data_not_marker():
|
|
out = _render_sections_for_prompt({
|
|
"tasks_due_today": [{"title": "Ship it"}],
|
|
"weather": [{
|
|
"location_label": "Home",
|
|
"forecast_json": {"daily": {
|
|
"temperature_2m_max": [70],
|
|
"temperature_2m_min": [52],
|
|
"precipitation_probability_max": [10],
|
|
}},
|
|
}],
|
|
})
|
|
assert "WEATHER:" in out
|
|
assert "none available" not in out
|
|
assert "high 70°" in out
|
|
|
|
|
|
def test_quiet_day_returns_fabrication_forbidding_text():
|
|
out = _render_sections_for_prompt({})
|
|
assert "quiet day" in out
|
|
assert "Do not invent weather" in out
|
|
|
|
|
|
# ── Fabricated-weather guard ────────────────────────────────────────────────
|
|
|
|
|
|
def test_guard_flags_the_real_observed_hallucination():
|
|
prose = (
|
|
"You have two overdue tasks. The weather today is partly cloudy "
|
|
"with a high of 68°F and a 15% chance of rain. What's on your mind?"
|
|
)
|
|
assert _prose_fabricated_weather(prose, {"weather": []}) is True
|
|
|
|
|
|
def test_guard_flags_bare_temperature_glyph():
|
|
assert _prose_fabricated_weather("Expect around 72° later.", {"weather": []}) is True
|
|
|
|
|
|
def test_guard_passes_clean_prose():
|
|
prose = "Two tasks are overdue and nothing is due today. What's on your mind?"
|
|
assert _prose_fabricated_weather(prose, {"weather": []}) is False
|
|
|
|
|
|
def test_guard_no_false_positive_on_rain_in_task_title():
|
|
# Bare "rain" must NOT trip the guard — only "chance of rain" etc. does.
|
|
prose = "Don't forget to buy rain boots and finish the training module."
|
|
assert _prose_fabricated_weather(prose, {"weather": []}) is False
|
|
|
|
|
|
def test_guard_allows_weather_when_data_present():
|
|
prose = "Home is 70°F with a 10% chance of rain."
|
|
sections = {"weather": [{"location_label": "Home"}]}
|
|
assert _prose_fabricated_weather(prose, sections) is False
|