"""MLSettings — single-row table holding ML pipeline tunables."""

from datetime import datetime

from sqlalchemy import CheckConstraint, DateTime, Float, Integer, String, func
from sqlalchemy.orm import Mapped, mapped_column

from .base import Base


class MLSettings(Base):
    __tablename__ = "ml_settings"
    # Bare name — Base.metadata's naming convention prepends ck_<table>_,
    # producing the final ck_ml_settings_singleton (matches migration 0003).
    __table_args__ = (CheckConstraint("id = 1", name="singleton"),)

    id: Mapped[int] = mapped_column(Integer, primary_key=True)
    suggestion_threshold_character: Mapped[float] = mapped_column(
        Float, nullable=False, default=0.70
    )
    # Default raised 0.50 → 0.70 on 2026-06-02 — operator-flagged 0.50
    # surfaced too many low-confidence picks; 0.70 keeps the rail
    # signal-rich while still surfacing more than the original 0.95
    # which hid almost everything. Operator-tunable via Settings → ML.
    suggestion_threshold_general: Mapped[float] = mapped_column(
        Float, nullable=False, default=0.70
    )
    centroid_similarity_threshold: Mapped[float] = mapped_column(
        Float, nullable=False, default=0.55
    )
    # Ingest floor: tagger predictions below this confidence are not stored
    # (tagger.Tagger.infer). Default 0.70 — the suggestion path already
    # filters at 0.70 and the centroid/learned path covers low-confidence
    # preferred tags, so the sub-0.70 tail is redundant weight (it had
    # bloated image_record's TOAST to ~100 GB; plan-task #764). Operator-
    # tunable via Settings → ML; must stay ≤ the suggestion thresholds.
    tagger_store_floor: Mapped[float] = mapped_column(
        Float, nullable=False, default=0.70
    )
    min_reference_images: Mapped[int] = mapped_column(
        Integer, nullable=False, default=5
    )
    # Video tagging (#747). Sample one frame every N seconds (fixed CADENCE, not a
    # fixed count) so a tag's frame-presence reflects real screen time regardless
    # of video length; cap the total so a long video can't explode into hundreds
    # of inferences (the cadence stretches past the cap). A tag is kept only if it
    # appears in >= video_min_tag_frames sampled frames (≈ that many × interval
    # seconds on screen) — duration-independent noise rejection. Operator-tunable.
    video_frame_interval_seconds: Mapped[float] = mapped_column(
        Float, nullable=False, default=4.0
    )
    video_max_frames: Mapped[int] = mapped_column(
        Integer, nullable=False, default=64
    )
    video_min_tag_frames: Mapped[int] = mapped_column(
        Integer, nullable=False, default=3
    )
    tagger_model_version: Mapped[str] = mapped_column(
        String(128), nullable=False, default="camie-tagger-v2"
    )
    embedder_model_version: Mapped[str] = mapped_column(
        String(128), nullable=False, default="siglip-so400m-patch14-384"
    )
    updated_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), nullable=False, server_default=func.now()
    )