"""tag_and_embed / backfill task tests. Models aren't in CI, so we test
the pure helpers (_maxpool_predictions, _is_video) as unit tests, and the
DB-touching backfill query as an integration test with monkeypatched
inference.
"""

from pathlib import Path

import pytest

from backend.app.services.ml.tagger import TagPrediction
from backend.app.tasks.ml import _is_video, _maxpool_predictions


def test_is_video():
    assert _is_video(Path("a.mp4")) is True
    assert _is_video(Path("a.MKV")) is True
    assert _is_video(Path("a.jpg")) is False


def test_maxpool_predictions():
    f1 = {"smile": TagPrediction("smile", "general", 0.6)}
    f2 = {
        "smile": TagPrediction("smile", "general", 0.9),
        "sword": TagPrediction("sword", "general", 0.7),
    }
    merged = _maxpool_predictions([f1, f2])
    assert merged["smile"]["confidence"] == 0.9
    assert merged["sword"]["confidence"] == 0.7


@pytest.mark.integration
@pytest.mark.asyncio
async def test_backfill_enqueues_missing(db, monkeypatch):
    from backend.app.models import ImageRecord
    from backend.app.tasks import ml as ml_tasks

    calls = []
    monkeypatch.setattr(
        ml_tasks.tag_and_embed, "delay", lambda image_id: calls.append(image_id)
    )

    img = ImageRecord(
        path="/images/n.jpg", sha256="n" * 64, size_bytes=1,
        mime="image/jpeg", width=1, height=1,
        origin="imported_filesystem", integrity_status="unknown",
        tagger_predictions=None, siglip_embedding=None,
    )
    db.add(img)
    await db.commit()

    count = ml_tasks.backfill()
    assert count >= 1
    assert img.id in calls


@pytest.mark.integration
@pytest.mark.asyncio
async def test_apply_allowlist_applies_above_threshold(db):
    from sqlalchemy import select

    from backend.app.models import ImageRecord, TagAllowlist, TagKind
    from backend.app.models.tag import image_tag
    from backend.app.services.tag_service import TagService
    from backend.app.tasks import ml as ml_tasks

    tag = await TagService(db).find_or_create("autohero", TagKind.character)
    db.add(TagAllowlist(tag_id=tag.id, min_confidence=0.95))
    img = ImageRecord(
        path="/images/al.jpg", sha256="al" + "0" * 62, size_bytes=1,
        mime="image/jpeg", width=1, height=1,
        origin="imported_filesystem", integrity_status="unknown",
        tagger_predictions={
            "autohero": {"category": "character", "confidence": 0.97}
        },
    )
    db.add(img)
    await db.commit()

    n = ml_tasks.apply_allowlist_tags(tag_id=tag.id)
    assert n >= 1
    src = (
        await db.execute(
            select(image_tag.c.source)
            .where(image_tag.c.image_record_id == img.id)
            .where(image_tag.c.tag_id == tag.id)
        )
    ).scalar_one()
    assert src == "ml_auto"


@pytest.mark.integration
@pytest.mark.asyncio
async def test_apply_allowlist_skips_below_threshold(db):
    from sqlalchemy import select

    from backend.app.models import ImageRecord, TagAllowlist, TagKind
    from backend.app.models.tag import image_tag
    from backend.app.services.tag_service import TagService
    from backend.app.tasks import ml as ml_tasks

    tag = await TagService(db).find_or_create("lowconf", TagKind.character)
    db.add(TagAllowlist(tag_id=tag.id, min_confidence=0.95))
    img = ImageRecord(
        path="/images/lc.jpg", sha256="lc" + "0" * 62, size_bytes=1,
        mime="image/jpeg", width=1, height=1,
        origin="imported_filesystem", integrity_status="unknown",
        tagger_predictions={
            "lowconf": {"category": "character", "confidence": 0.40}
        },
    )
    db.add(img)
    await db.commit()
    ml_tasks.apply_allowlist_tags(tag_id=tag.id)
    applied = (
        await db.execute(
            select(image_tag.c.tag_id)
            .where(image_tag.c.image_record_id == img.id)
            .where(image_tag.c.tag_id == tag.id)
        )
    ).scalar_one_or_none()
    assert applied is None