from datetime import datetime, timezone

from sqlalchemy import DateTime, Float, Index, Integer, Text
from sqlalchemy.orm import Mapped, mapped_column

from scribe.models import Base


class RetrievalTuningEvent(Base):
    """One row per change to a retrieval surface's floor or budget (#4102).

    WHY A TABLE AND NOT JUST THE SETTING

    The setting holds the number. It cannot hold the argument, and from this
    step onward the argument is the interesting part: the operator's decision is
    that the model moves these values, *"9 times out of 10"*, without being
    asked each time. Delegation like that is only safe if it leaves a trail the
    operator can read afterwards — what changed, from what to what, and on what
    evidence — and can disagree with.

    So `reason` is not decoration and not optional. It is the guardrail: a model
    that has to state why is a model that has to have looked, and a reason that
    turns out to be wrong is a reason someone can point at. A bare number in a
    settings row records that something moved and nothing about whether it
    should have.

    WHY `actor` IS NOT JUST `user_id`

    Both a person and a model act as the same user — the MCP tools run under the
    operator's own id — so the id cannot distinguish them. That distinction is
    exactly what an operator scanning this table wants first: "did I do this, or
    did the session?" A change the operator made themselves needs no review; one
    made on their behalf might.

    FK-FREE ON user_id, like `RetrievalLog` and `AppLog` above it: the history of
    how a surface was tuned should outlive the account that tuned it, and a
    deleted user must not cascade away the record of why a number is where it is.
    """

    __tablename__ = "retrieval_tuning_events"

    id: Mapped[int] = mapped_column(primary_key=True)
    # Declared here rather than via CreatedAtMixin because the index below
    # orders on `created_at.desc()`, which needs the column object in this class
    # body — a mixin's column is not in scope there.
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), default=lambda: datetime.now(timezone.utc)
    )
    user_id: Mapped[int | None] = mapped_column(Integer, nullable=True)

    # The surface's registry name, which is also its `retrieval_logs.source`.
    # That identity is what lets a reader put a change next to what the change
    # did; `tests/test_retrieval_surfaces.py` asserts it rather than trusting it.
    surface: Mapped[str] = mapped_column(Text, nullable=False)

    # "floor" or "budget". Text rather than an enum because rule 36 makes a new
    # CHECK value a migration, and this is a young surface that may well grow a
    # third tunable — a constraint bought nothing here except a future migration.
    dial: Mapped[str] = mapped_column(Text, nullable=False)

    # Both stored as float so one pair of columns serves both dials; a budget is
    # a whole number and reads back as one. `old_value` is nullable because the
    # first change to a surface has no stored predecessor — it moved off the
    # shipped starting point, which is a different event from moving off a value
    # somebody chose, and worth being able to tell apart.
    old_value: Mapped[float | None] = mapped_column(Float, nullable=True)
    new_value: Mapped[float] = mapped_column(Float, nullable=False)

    # "model" | "human". See the class docstring: the user id cannot tell these
    # apart, and the difference is the first thing a reviewer wants.
    actor: Mapped[str] = mapped_column(Text, nullable=False, default="model")

    # REQUIRED at the service boundary, not merely non-null here. A column that
    # is technically non-null is satisfied by "", which is how a required field
    # becomes a formality; the service refuses a blank one.
    reason: Mapped[str] = mapped_column(Text, nullable=False)

    # WHAT SPACE THIS NUMBER WAS MEASURED IN (#4104). A floor is a cosine
    # distance in one embedding model's geometry, over documents cut one
    # particular way — change either and the number describes something that
    # no longer exists.
    #
    # On the EVENT rather than beside the setting, because this table already
    # holds one row per change and `current_settings` already reads the latest
    # per dial. A parallel stamp row next to the value would be a second place
    # to keep in sync, and the two disagreeing is worse than neither.
    #
    # Both NULLABLE for the rows written before this step: those were measured
    # under something, but claiming to know which would be inventing a fact.
    # Null here means "unstamped", which is a different and honest answer from
    # naming a model that may be wrong.
    embedding_model: Mapped[str | None] = mapped_column(Text, nullable=True)
    shape_version: Mapped[int | None] = mapped_column(Integer, nullable=True)

    __table_args__ = (
        # The only read this table has: one surface's history, newest first.
        Index(
            "ix_retrieval_tuning_surface_created",
            "surface",
            created_at.desc(),
        ),
    )

    def to_dict(self) -> dict:
        return {
            "id": self.id,
            "created_at": self.created_at.isoformat() if self.created_at else None,
            "surface": self.surface,
            "dial": self.dial,
            "old_value": self.old_value,
            "new_value": self.new_value,
            "actor": self.actor,
            "reason": self.reason,
            # Null for every row written before #4104, and rendered as
            # "unstamped" rather than guessed at — see the column comments.
            "embedding_model": self.embedding_model,
            "shape_version": self.shape_version,
        }