"""rule_embeddings — rules become findable by meaning (milestone 307 step 4,
decision note 3026)

Revision ID: 0089
Revises: 0088
Create Date: 2026-08-26

Rules were the only major record type with no vector, so `search` could never
return one and a rule could only ever arrive by being preloaded. That single
fact is what made every rule compete for the same always-on budget.

A sibling table rather than a generalisation of note_embeddings: the row could
have been made polymorphic, but the SEARCH could not — semantic_search_notes is
Note-specific scoping end to end, and a rule shares none of it. See the model
docstring for the full reasoning.

The vectors are DERIVED data. Nothing is backfilled here: the startup backfill
regenerates them, which is also how a chunker-version bump is handled.
"""
import sqlalchemy as sa
from alembic import op

revision = "0089"
down_revision = "0088"
branch_labels = None
depends_on = None

# Matches note_embeddings — bge-small-en-v1.5, 384-dim unit-normalized.
_EMBEDDING_DIM = 384


def upgrade() -> None:
    op.create_table(
        "rule_embeddings",
        sa.Column("rule_id", sa.BigInteger(), sa.ForeignKey("rules.id", ondelete="CASCADE"), primary_key=True),
        sa.Column("chunk_index", sa.Integer(), primary_key=True),
        sa.Column("chunk_text", sa.Text(), nullable=False),
        sa.Column("chunker_version", sa.Integer(), nullable=False),
        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
    )
    # The vector column is added by raw DDL for the same reason 0067 did it:
    # the type comes from the pgvector extension, not from SQLAlchemy's
    # type system.
    op.execute(f"ALTER TABLE rule_embeddings ADD COLUMN embedding vector({_EMBEDDING_DIM}) NOT NULL")
    # HNSW for cosine distance — matches Vector.cosine_distance (`<=>`), so the
    # search is an indexed ORDER BY ... LIMIT k rather than a full scan.
    op.execute(
        """
        CREATE INDEX ix_rule_embeddings_embedding_hnsw
            ON rule_embeddings
         USING hnsw (embedding vector_cosine_ops)
        """
    )


def downgrade() -> None:
    op.execute("DROP INDEX IF EXISTS ix_rule_embeddings_embedding_hnsw")
    op.drop_table("rule_embeddings")