server-26/drb-c2-core/tests/test_chatter_classifier.py

"""
server-26#127 — upstream dispatch-vs-chatter classifier, shadow mode.

Fixtures are real transcripts, not invented ones: pulled from
`corr_dump_9-7_0437am.json`, `corr_dump_9-7_pm.json`, `corr_dump_9-12.json`
and the hand-labeled examples in `CORRELATION_REVIEW_0907b.md` /
`CORRELATION_REVIEW_0912.md`. The "must classify False" set specifically
includes every transcript those review docs flagged as dangerous to drop —
a false positive here is a real event silently losing its scene once this
classifier ever goes live, which is a much worse failure than a missed
chatter call staying in the existing (already-working) pipeline.
"""
import pytest

from app.internal.chatter_classifier import classify_chatter


# ─────────────────────────────────────────────────────────────────────────────
# Must classify as chatter
# ─────────────────────────────────────────────────────────────────────────────

CHATTER_EXAMPLES = [
    # Bare acknowledgements / unit check-ins (CORRELATION_REVIEW_0907b.md)
    ("114 Paul.\n114 Paul, Metro Central.\n10-4.", "bare_acknowledgement"),
    ("Affirmative, in charge of 10-8. 10-8, 10-4.", "bare_acknowledgement"),
    ("6-8, you can show me 98. 10-4.", "bare_acknowledgement"),
    ("10-4, 10-4 Central, 98. 10-4, 98.", "bare_acknowledgement"),
    ("7 for Post 1 and 2, 98. Affirm.", "bare_acknowledgement"),
    ("11-Victor to Central. 11-Victor. 72-Holland, 1-5. Central.", "bare_acknowledgement"),
    # Roll call (CORRELATION_REVIEW_0907b.md / _0912.md)
    ("Post 4, Ossining. And to volunteer patrol, stand by for roll call.", "roll_call"),
    ("Headquarters to all cars, stand by for roll call.", "roll_call"),
    ("All Troop NYC Patrols, stand by for roll call.", "roll_call"),
    (
        "Car 100, roll call.\nHenry 1.\nHenry 1.\nSam 1.\nSam 1.\n45 Baker.\n"
        "45 Baker.\n11 Adam.\nAdam.\n11 Baker.\nBaker.\nStaff 1.\n1.\nStaff 2.",
        "roll_call",
    ),
    (
        "Headquarters, all cars on a roll call. Baker 1? Baker 1. Henry 1? "
        "Henry 1. Sam 2? Sam 2. 11 Adam? 11. 11 Baker? 11 Baker.",
        "roll_call",
    ),
    ("Because all cars came out for roll call.", "roll_call"),
    ("10-1. KL Cars, that concludes roll call, time is 3-31.", "roll_call"),
    # Minimal single-word / bare-code transmissions (orphan pool, all 3 dumps)
    ("10-4.", "bare_acknowledgement"),
    ("Roger.", "bare_acknowledgement"),
    ("Clear.", "bare_acknowledgement"),
    ("Affirmative.", "bare_acknowledgement"),
    ("Received.", "bare_acknowledgement"),
    ("10-8, clear. 10-4.", "bare_acknowledgement"),
    ("Post 4, 10-8. 10-4.", "bare_acknowledgement"),
    ("Central to 6 Henry.", "bare_acknowledgement"),
]


@pytest.mark.parametrize("transcript,expected_reason", CHATTER_EXAMPLES)
def test_classifies_chatter(transcript, expected_reason):
    is_chatter, reason = classify_chatter(transcript)
    assert is_chatter is True
    assert reason == expected_reason


# ─────────────────────────────────────────────────────────────────────────────
# Must NOT classify as chatter — real events, including every transcript the
# review docs specifically named as dangerous to drop.
# ─────────────────────────────────────────────────────────────────────────────

REAL_EVENT_EXAMPLES = [
    # The major "extinguishing fire" call (severity=major, tags=[extinguishing-fire])
    ("Dispatch, this is 7-4, extinguishing fire.", "extinguishing_fire"),
    # Geocoded 911-hangup call (has location_coords)
    (
        "7, Charlie. Charlie, check and advise, we've got a call for service "
        "coming over, it's going to be a 9-1-1 hangout, no voice contact. "
        "Looks like it was an automated message saying it's the Doral Hat Company.",
        "geocoded_911_hangup",
    ),
    # Pursuit updates (severity=major, tags include pursuit / low-speed-pursuit)
    ("I'm aware of that one. It's a low-speed pursuit. It's refusing to pull over.", "low_speed_pursuit"),
    (
        "1. Headquarters to 5-charlie. I'm going to say the last thing to anyone.\n"
        "2. Info, Sgt. Repeat.\n"
        "3. The SP is on a pursuit southbound on I-684. It's approaching the airport.\n"
        "4. Okay, thank you.\n5. 23-59.",
        "pursuit_i684",
    ),
    # "6 Alpha ... Pelham Station" subject check (CORRELATION_REVIEW_0907b.md's
    # own "genuinely distinct events" list) — looks like a bare check-in but
    # dispatches a unit to a specific location.
    (
        "6 Alpha, this is Central. 7 Alpha here.\n"
        "6 Alpha, can you show me on scene at Pelham Station? Stand by.",
        "pelham_station_subject_check",
    ),
    # Property-retrieval call (tags=[property-retrieval])
    (
        "Property was retrieved with a 911. Can I get a phone number? 10-4. "
        "Phone number is 214792. 214792.",
        "property_retrieval",
    ),
    # Subject check south of Maronex Station (tags=[subject-check])
    (
        "Proceed. Show me on a subject south of Maronex Station. Can I get a "
        "15 check by New York client ID?",
        "maronex_subject_check",
    ),
    # Trespassing at milepost 13.7 (tags=[trespassing])
    (
        "Can you just 10-5 that job? You came over real muffled.\n"
        "10-4, there's going to be a trespass on the tracks.\n"
        "Train 8755 reports two juveniles, one male, one female, both wearing "
        "white shirts, track three side, at milepost 13.7.",
        "trespass_milepost_13_7",
    ),
    # MVA (severity=moderate, tags=[traffic-accident])
    ("1. Train patrol 9.\n2. MVA 4, how close is it?\n3. 10-4.", "mva"),
]


@pytest.mark.parametrize("transcript,label", REAL_EVENT_EXAMPLES, ids=[l for _, l in REAL_EVENT_EXAMPLES])
def test_does_not_classify_real_events_as_chatter(transcript, label):
    is_chatter, reason = classify_chatter(transcript)
    assert is_chatter is False, f"{label}: false positive, reason={reason!r}"
    assert reason is None


# ─────────────────────────────────────────────────────────────────────────────
# Edge cases
# ─────────────────────────────────────────────────────────────────────────────

def test_empty_transcript_not_chatter():
    assert classify_chatter("") == (False, None)
    assert classify_chatter(None) == (False, None)
    assert classify_chatter("   ") == (False, None)


def test_unrecognized_content_defaults_to_not_chatter():
    # Anything containing real descriptive words the classifier doesn't
    # recognize must fall through to (False, None), not guess.
    is_chatter, reason = classify_chatter("Shots fired, officer down, requesting backup immediately.")
    assert is_chatter is False
    assert reason is None