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

from datetime import datetime

from sqlalchemy import (
    Boolean,
    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)
    # CPU whole-image embedding (B3, operator 2026-07-02). The ml-worker's ONLY
    # processing role is the embed fallback for stacks WITHOUT a GPU agent — ON
    # by default so a fresh install works with no agent. Stacks that run the
    # agent and drop the ml-worker container turn this OFF so import hooks stop
    # queueing embed work nothing will consume (the daily GPU 'embed' backfill
    # covers those images instead).
    cpu_embed_enabled: Mapped[bool] = mapped_column(
        Boolean, nullable=False, default=True
    )
    # Video embedding (#747). Sample one frame every N seconds (fixed CADENCE, not
    # a fixed count) so coverage reflects real screen time regardless of length;
    # cap the total so a long video can't explode into hundreds of embeds. The
    # per-frame SigLIP embeddings are mean-pooled. 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
    )
    # Tagging-v2 head training (#114). The head is the suggestion source that
    # LEARNS from the operator's tags (replacing Camie + centroid). A concept
    # needs >= head_min_positives labelled images before a head is trained;
    # head_auto_apply_precision is the precision bar a head must clear (at some
    # operating point) to "graduate" into earned auto-apply. Operator-tunable.
    head_min_positives: Mapped[int] = mapped_column(
        Integer, nullable=False, default=8
    )
    head_auto_apply_precision: Mapped[float] = mapped_column(
        Float, nullable=False, default=0.97
    )
    # Earned auto-apply (#114). A graduated head fires (tags images without a
    # human) when this master switch is on AND the head has at least
    # head_auto_apply_min_positives clean labels — so a precise-looking but
    # under-supported low-N head can't spray tags across the library. ON by
    # default (operator-asked 2026-06-29: opt-OUT, not opt-in); the support +
    # measured-precision gates keep it safe, and every auto-tag is reversible.
    head_auto_apply_enabled: Mapped[bool] = mapped_column(
        Boolean, nullable=False, default=True
    )
    head_auto_apply_min_positives: Mapped[int] = mapped_column(
        Integer, nullable=False, default=30
    )
    # CCIP character-match cosine cut (#114). 0.85 default — the v1 flat 0.75
    # over-fired (high-reference characters matched a scatter of images); 0.85
    # keeps the confident single-character matches. Tunable from the agent card.
    ccip_match_threshold: Mapped[float] = mapped_column(
        Float, nullable=False, default=0.85
    )
    # CCIP auto-apply (#114). Confident matches (>= ccip_auto_apply_threshold,
    # above the suggest cut) auto-tag on a daily sweep. ON by default (opt-out);
    # single-character references + the high bar keep it safe, every tag reversible.
    ccip_auto_apply_enabled: Mapped[bool] = mapped_column(
        Boolean, nullable=False, default=True
    )
    ccip_auto_apply_threshold: Mapped[float] = mapped_column(
        Float, nullable=False, default=0.92
    )
    # Default = SigLIP 2 (so400m, 512px) for new installs (migration 0069);
    # existing libraries keep their stored value until the operator re-embeds.
    embedder_model_version: Mapped[str] = mapped_column(
        String(128), nullable=False, default="siglip2-so400m-patch16-512"
    )
    # The HF model NAME the embedder loads (server CPU embed + announced to the
    # GPU agent in the lease). Operator-settable so the embedder is a choice, not
    # a hardcode (#1190): set name + version together, then re-embed + retrain.
    embedder_model_name: Mapped[str] = mapped_column(
        String(128), nullable=False, default="google/siglip2-so400m-patch16-512"
    )
    updated_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), nullable=False, server_default=func.now()
    )