ely-eye/backend/src/ely_eye/migrations.py

"""Schema DDL and versioned migrations for the memory store.

A memory row must answer four questions before retrieval can trust it: whose memory
is it, where did it come from, when was it true, and in what situation may it be used.
The first version of this table answered none of them, so every consumer guessed.

Versioning uses PRAGMA user_version. A database written by the first version is
upgraded in place rather than rebuilt, because the only copy of the memory is the file.
"""

from __future__ import annotations

import json
import sqlite3

from .storage import token_equivalent, visual_token_equivalent
from .text_index import index_text

SCHEMA_VERSION = 10

ATOM_COLUMNS_V2 = """
    atom_id TEXT PRIMARY KEY,
    source_id TEXT NOT NULL REFERENCES sources(source_id) ON DELETE CASCADE,
    modality TEXT NOT NULL,
    source TEXT NOT NULL,
    ingested_at TEXT NOT NULL,
    text TEXT NOT NULL,
    image_ref TEXT,
    embedding_refs_json TEXT NOT NULL,
    layout_json TEXT,
    relations_json TEXT NOT NULL,
    trust_json TEXT NOT NULL,
    token_equivalent INTEGER NOT NULL,
    metadata_json TEXT NOT NULL,
    holder_id TEXT NOT NULL DEFAULT '',
    origin TEXT NOT NULL DEFAULT 'artifact'
        CHECK (origin IN ('self', 'observed', 'artifact', 'third_party')),
    scenario TEXT NOT NULL DEFAULT '',
    event_time TEXT,
    event_time_end TEXT,
    event_time_precision TEXT NOT NULL DEFAULT 'unknown'
        CHECK (event_time_precision IN ('instant', 'minute', 'hour', 'day', 'month', 'year', 'unknown')),
    event_time_source TEXT NOT NULL DEFAULT '',
    valid_from TEXT,
    valid_to TEXT,
    supersedes_json TEXT NOT NULL DEFAULT '[]',
    visibility_json TEXT NOT NULL DEFAULT '{}',
    retention_until TEXT,
    quarantined INTEGER NOT NULL DEFAULT 0
"""

_BASE_TABLES = """
    CREATE TABLE IF NOT EXISTS sources (
        source_id TEXT PRIMARY KEY,
        path TEXT NOT NULL,
        kind TEXT NOT NULL,
        mime TEXT NOT NULL,
        sha256 TEXT NOT NULL,
        size_bytes INTEGER NOT NULL,
        created_at TEXT NOT NULL,
        metadata_json TEXT NOT NULL
    );

    CREATE TABLE IF NOT EXISTS cartridges (
        cartridge_id TEXT PRIMARY KEY,
        name TEXT NOT NULL,
        root_path TEXT NOT NULL,
        manifest_json TEXT NOT NULL,
        dna TEXT,
        token_equivalent INTEGER NOT NULL,
        created_at TEXT NOT NULL
    );

    -- Membership lives in the live store, not only in the copied parquet, otherwise
    -- "mount this cartridge" cannot scope a query against the atoms it holds.
    CREATE TABLE IF NOT EXISTS cartridge_atoms (
        cartridge_id TEXT NOT NULL REFERENCES cartridges(cartridge_id) ON DELETE CASCADE,
        atom_id TEXT NOT NULL REFERENCES atoms(atom_id) ON DELETE CASCADE,
        added_at TEXT NOT NULL,
        PRIMARY KEY (cartridge_id, atom_id)
    );

    CREATE TABLE IF NOT EXISTS mounts (
        cartridge_id TEXT PRIMARY KEY REFERENCES cartridges(cartridge_id) ON DELETE CASCADE,
        mounted_at TEXT NOT NULL
    );

    -- The directory of who may hold or answer a memory. A transactive system answers
    -- "who knows this?" before it answers "what is this?", and it cannot do that without
    -- an entity to point at. Contact details are free-form on purpose: the transport is
    -- whoever wired this store together, not the schema.
    CREATE TABLE IF NOT EXISTS holders (
        holder_id TEXT PRIMARY KEY,
        name TEXT NOT NULL DEFAULT '',
        kind TEXT NOT NULL DEFAULT 'person'
            CHECK (kind IN ('person', 'agent', 'service')),
        knows_about_json TEXT NOT NULL DEFAULT '[]',
        contact_json TEXT NOT NULL DEFAULT '{}',
        created_at TEXT NOT NULL,
        updated_at TEXT NOT NULL
    );

    -- What has already been folded into a rollup, one row per holder and scenario. The
    -- watermark is what makes consolidation replayable: the next pass starts where the last one
    -- stopped, so the same memory is never counted into two rollups.
    CREATE TABLE IF NOT EXISTS consolidations (
        holder_id TEXT NOT NULL,
        scenario TEXT NOT NULL DEFAULT '',
        watermark_at TEXT NOT NULL,
        rollup_atom_id TEXT NOT NULL REFERENCES atoms(atom_id) ON DELETE CASCADE,
        atom_count INTEGER NOT NULL,
        token_equivalent INTEGER NOT NULL,
        consolidated_at TEXT NOT NULL,
        PRIMARY KEY (holder_id, scenario)
    );

    -- Two memories that cannot both be current. The store records the disagreement even when no
    -- person has picked a winner; retrieval reads this table to keep the newer side instead of
    -- packing both numbers into the same prompt.
    CREATE TABLE IF NOT EXISTS conflicts (
        conflict_id INTEGER PRIMARY KEY AUTOINCREMENT,
        older_atom_id TEXT NOT NULL REFERENCES atoms(atom_id) ON DELETE CASCADE,
        newer_atom_id TEXT NOT NULL REFERENCES atoms(atom_id) ON DELETE CASCADE,
        holder_id TEXT NOT NULL,
        scenario TEXT NOT NULL DEFAULT '',
        terms_json TEXT NOT NULL,
        older_value TEXT NOT NULL,
        newer_value TEXT NOT NULL,
        detected_at TEXT NOT NULL,
        resolved_at TEXT,
        UNIQUE (older_atom_id, newer_atom_id)
    );

    CREATE TABLE IF NOT EXISTS cache_events (
        id INTEGER PRIMARY KEY AUTOINCREMENT,
        ts TEXT NOT NULL,
        layer TEXT NOT NULL,
        cache_key TEXT NOT NULL,
        event TEXT NOT NULL,
        bytes_estimate INTEGER NOT NULL,
        metadata_json TEXT NOT NULL
    );

    CREATE TABLE IF NOT EXISTS evidence_edges (
        id INTEGER PRIMARY KEY AUTOINCREMENT,
        from_atom_id TEXT NOT NULL,
        to_atom_id TEXT NOT NULL,
        relation TEXT NOT NULL,
        confidence REAL NOT NULL,
        metadata_json TEXT NOT NULL
    );

    -- How many atoms one query expression matches, remembered so the next question does not
    -- count the same rows again. Every atom write clears it, so a count is never read stale.
    CREATE TABLE IF NOT EXISTS term_df (
        term TEXT PRIMARY KEY,
        documents INTEGER NOT NULL
    );

    -- What the dense vector table was built from. vec0 cannot be altered in place, so when the
    -- model or the width changes the table is dropped and re-encoded; these three values are
    -- how the next start notices it has to.
    CREATE TABLE IF NOT EXISTS vector_index_meta (
        key TEXT PRIMARY KEY,
        value TEXT NOT NULL
    );

    -- One row, bumped by every write that changes which atoms are current. A compiled context is
    -- only true for the corpus it was compiled from, and its cache key carries this number.
    CREATE TABLE IF NOT EXISTS store_meta (
        key TEXT PRIMARY KEY,
        value TEXT NOT NULL
    );

CREATE VIRTUAL TABLE IF NOT EXISTS atom_fts USING fts5(
atom_id UNINDEXED,
source,
text,
tokenize = 'unicode61'
);
-- source and text hold text_index output, not the atom's own text: unicode61 sees one token
-- per CJK character and per identifier fragment, which is what makes those queries match.
"""

# A memory is usable now when nothing closed it, it had begun by now, its retention has not lapsed, and nobody archived it away from the current tier; unknown bounds read as visible, because silence about when a legacy row was true is not evidence that it is false.
VIEWS = """
    CREATE VIEW IF NOT EXISTS v_atoms_current AS
    SELECT * FROM atoms
    WHERE valid_to IS NULL
      AND archived_at IS NULL
      AND (valid_from IS NULL OR valid_from <= strftime('%Y-%m-%dT%H:%M:%f+00:00', 'now'))
      AND (retention_until IS NULL OR retention_until >= strftime('%Y-%m-%dT%H:%M:%f+00:00', 'now'));

    CREATE INDEX IF NOT EXISTS idx_atoms_source_id ON atoms(source_id);
    CREATE INDEX IF NOT EXISTS idx_atoms_modality ON atoms(modality);
    CREATE INDEX IF NOT EXISTS idx_atoms_holder ON atoms(holder_id);
    CREATE INDEX IF NOT EXISTS idx_atoms_scenario ON atoms(scenario);
    CREATE INDEX IF NOT EXISTS idx_atoms_valid_to ON atoms(valid_to);
    CREATE INDEX IF NOT EXISTS idx_atoms_session ON atoms(session_id);
    CREATE INDEX IF NOT EXISTS idx_atoms_archived ON atoms(archived_at);
"""

# Columns the first version lacked, in the order added; each is nullable or defaulted so an existing row keeps its meaning.
_V1_TO_V2_COLUMNS = (
    ("holder_id", "TEXT NOT NULL DEFAULT ''"),
    ("origin", "TEXT NOT NULL DEFAULT 'artifact'"),
    ("scenario", "TEXT NOT NULL DEFAULT ''"),
    ("event_time", "TEXT"),
    ("event_time_end", "TEXT"),
    ("event_time_precision", "TEXT NOT NULL DEFAULT 'unknown'"),
    ("event_time_source", "TEXT NOT NULL DEFAULT ''"),
    ("valid_from", "TEXT"),
    ("valid_to", "TEXT"),
    ("supersedes_json", "TEXT NOT NULL DEFAULT '[]'"),
    ("visibility_json", "TEXT NOT NULL DEFAULT '{}'"),
    ("retention_until", "TEXT"),
)

# Columns added after the second version, grouped by the schema version that introduced them.
_NEW_ATOM_COLUMNS: tuple[tuple[int, tuple[tuple[str, str], ...]], ...] = (
    (9, (("quarantined", "INTEGER NOT NULL DEFAULT 0"),)),
    (
        10,
        (
            ("session_id", "TEXT NOT NULL DEFAULT ''"),
            ("importance", "REAL"),
            ("recall_count", "INTEGER NOT NULL DEFAULT 0"),
            ("last_recalled_at", "TEXT"),
            ("archived_at", "TEXT"),
        ),
    ),
)


def _table_exists(connection: sqlite3.Connection, name: str) -> bool:
    row = connection.execute(
        "SELECT 1 FROM sqlite_master WHERE type = 'table' AND name = ?", (name,)
    ).fetchone()
    return row is not None


def _column_names(connection: sqlite3.Connection, table: str) -> set[str]:
    return {str(row[1]) for row in connection.execute(f"PRAGMA table_info({table})")}


def _create_v2(connection: sqlite3.Connection) -> None:
    connection.executescript(_BASE_TABLES)
    connection.execute(f"CREATE TABLE IF NOT EXISTS atoms ({ATOM_COLUMNS_V2})")


def _upgrade_v1_to_v2(connection: sqlite3.Connection) -> None:
    """Add the four memory dimensions to a first-version atoms table.

    The old `time` column recorded when ingestion ran, which is the only timestamp a
    legacy row honestly has, so it is renamed rather than duplicated.
    """
    columns = _column_names(connection, "atoms")
    if "time" in columns and "ingested_at" not in columns:
        connection.execute("ALTER TABLE atoms RENAME COLUMN time TO ingested_at")
        columns = _column_names(connection, "atoms")
    if "ingested_at" not in columns:
        raise SystemExit(
            "atoms table has neither `time` nor `ingested_at`; refusing to guess which timestamp is ingestion"
        )
    for name, definition in _V1_TO_V2_COLUMNS:
        if name not in columns:
            connection.execute(f"ALTER TABLE atoms ADD COLUMN {name} {definition}")


def _recount_visual_tokens(connection: sqlite3.Connection) -> None:
    """Re-price raster atoms at 32x32 patches; a 1280x720 frame cost 18 tokens under the old rule.

    An atom whose layout carries no size keeps its stored number: there is no region to price,
    and inventing one would move a figure we cannot verify.
    """
    rows = connection.execute(
        "SELECT atom_id, text, layout_json FROM atoms WHERE modality IN ('image', 'video_frame', 'ui_screenshot')"
    ).fetchall()
    updates: list[tuple[int, str]] = []
    for row in rows:
        try:
            layout = json.loads(row["layout_json"] or "{}")
        except json.JSONDecodeError as error:
            raise SystemExit(f"atom {row['atom_id']}: its stored layout is unreadable ({error})") from error
        width = float(layout.get("w") or 0)
        height = float(layout.get("h") or 0)
        if width <= 0 or height <= 0:
            continue
        updates.append((token_equivalent(row["text"]) + visual_token_equivalent(width, height), str(row["atom_id"])))
    connection.executemany("UPDATE atoms SET token_equivalent = ? WHERE atom_id = ?", updates)


def apply(connection: sqlite3.Connection) -> None:
    """Bring the schema to SCHEMA_VERSION, in place, without losing rows."""
    version = int(connection.execute("PRAGMA user_version").fetchone()[0])
    if version > SCHEMA_VERSION:
        raise SystemExit(f"database schema is version {version}, this build understands {SCHEMA_VERSION}")
    if version == SCHEMA_VERSION:
        return

    if _table_exists(connection, "atoms"):
        connection.executescript(_BASE_TABLES)
        if version < 2:
            _upgrade_v1_to_v2(connection)
    else:
        _create_v2(connection)
    if version < 3:
        _rebuild_fts(connection)
    if version < 7:
        _recount_visual_tokens(connection)
    for target, columns in _NEW_ATOM_COLUMNS:
        if version < target:
            existing = _column_names(connection, "atoms")
            for name, definition in columns:
                if name not in existing:
                    connection.execute(f"ALTER TABLE atoms ADD COLUMN {name} {definition}")
    if version < 10:
        # CREATE VIEW IF NOT EXISTS keeps the old body, and v10 changed which rows are current, so an upgraded store must be told to look again.
        connection.execute("DROP VIEW IF EXISTS v_atoms_current")

    connection.executescript(VIEWS)
    connection.execute(f"PRAGMA user_version = {SCHEMA_VERSION}")


def _rebuild_fts(connection: sqlite3.Connection) -> None:
    """Re-index every atom through text_index: rows indexed before it existed hold raw text, and
    FTS5 cannot match 钥匙 inside a token that is a whole Chinese sentence."""
    connection.execute("DROP TABLE IF EXISTS atom_fts")
    connection.executescript(_BASE_TABLES)
    rows = connection.execute("SELECT atom_id, source, text FROM atoms ORDER BY atom_id").fetchall()
    connection.executemany(
        "INSERT INTO atom_fts(atom_id, source, text) VALUES (?, ?, ?)",
        [(row[0], index_text(row[1]), index_text(row[2])) for row in rows],
    )