"""retrieval_tuning_events carries the space each number was measured in (#4104)

Revision ID: 0104
Revises: 0103
Create Date: 2026-09-17

Milestone 416 step 6. A retrieval floor is a cosine distance in ONE embedding
model's geometry, computed over documents cut one particular way. Change the
model and every score moves at once; change the chunker and the same record
embeds different text. Either way a number chosen before the change is a
measurement of something that no longer exists — and today nothing records
which world it was chosen in, so the staleness is unknowable rather than
merely unknown.

`CHUNKER_VERSION` already solved exactly this for documents: stored per row, so
the startup backfill re-embeds precisely what is stale instead of wiping the
table. These two columns are that idea applied to the tuned numbers.

TWO COLUMNS, NOT ONE (rule 149). A reader has to be able to say WHICH half
moved: a new embedding model and a re-cut document shape invalidate the same
numbers for different reasons, and a fused `"<model>@<n>"` could only report
that something changed.

NULLABLE, and not backfilled. The rows already in this table were written
under something, but naming it would be inventing a fact — the honest value is
"unstamped", which is a different answer from a model name that might be wrong.
`current_settings` reports an unstamped dial as exactly that.
"""
import sqlalchemy as sa
from alembic import op

revision = "0104"
down_revision = "0103"
branch_labels = None
depends_on = None


def upgrade() -> None:
    op.add_column(
        "retrieval_tuning_events",
        sa.Column("embedding_model", sa.Text(), nullable=True),
    )
    op.add_column(
        "retrieval_tuning_events",
        sa.Column("shape_version", sa.Integer(), nullable=True),
    )


def downgrade() -> None:
    op.drop_column("retrieval_tuning_events", "shape_version")
    op.drop_column("retrieval_tuning_events", "embedding_model")