ATOCore/src/atocore/models/database.py

"""SQLite database schema and connection management."""

import sqlite3
from contextlib import contextmanager
from pathlib import Path
from typing import Generator

import atocore.config as _config
from atocore.observability.logger import get_logger

log = get_logger("database")

SCHEMA_SQL = """
CREATE TABLE IF NOT EXISTS source_documents (
    id TEXT PRIMARY KEY,
    file_path TEXT UNIQUE NOT NULL,
    file_hash TEXT NOT NULL,
    title TEXT,
    doc_type TEXT DEFAULT 'markdown',
    tags TEXT DEFAULT '[]',
    ingested_at DATETIME DEFAULT CURRENT_TIMESTAMP,
    updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE TABLE IF NOT EXISTS source_chunks (
    id TEXT PRIMARY KEY,
    document_id TEXT NOT NULL REFERENCES source_documents(id) ON DELETE CASCADE,
    chunk_index INTEGER NOT NULL,
    content TEXT NOT NULL,
    heading_path TEXT DEFAULT '',
    char_count INTEGER NOT NULL,
    metadata TEXT DEFAULT '{}',
    created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE TABLE IF NOT EXISTS memories (
    id TEXT PRIMARY KEY,
    memory_type TEXT NOT NULL,
    content TEXT NOT NULL,
    project TEXT DEFAULT '',
    source_chunk_id TEXT REFERENCES source_chunks(id),
    confidence REAL DEFAULT 1.0,
    status TEXT DEFAULT 'active',
    created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
    updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE TABLE IF NOT EXISTS projects (
    id TEXT PRIMARY KEY,
    name TEXT UNIQUE NOT NULL,
    description TEXT DEFAULT '',
    status TEXT DEFAULT 'active',
    created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
    updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE TABLE IF NOT EXISTS interactions (
    id TEXT PRIMARY KEY,
    prompt TEXT NOT NULL,
    context_pack TEXT DEFAULT '{}',
    response_summary TEXT DEFAULT '',
    project_id TEXT REFERENCES projects(id),
    created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE INDEX IF NOT EXISTS idx_chunks_document ON source_chunks(document_id);
CREATE INDEX IF NOT EXISTS idx_memories_type ON memories(memory_type);
CREATE INDEX IF NOT EXISTS idx_memories_project ON memories(project);
CREATE INDEX IF NOT EXISTS idx_memories_status ON memories(status);
CREATE INDEX IF NOT EXISTS idx_interactions_project ON interactions(project_id);
"""


def _ensure_data_dir() -> None:
    _config.ensure_runtime_dirs()


def init_db() -> None:
    """Initialize the database with schema."""
    _ensure_data_dir()
    with get_connection() as conn:
        conn.executescript(SCHEMA_SQL)
        _apply_migrations(conn)
    log.info("database_initialized", path=str(_config.settings.db_path))


def _apply_migrations(conn: sqlite3.Connection) -> None:
    """Apply lightweight schema migrations for existing local databases."""
    if not _column_exists(conn, "memories", "project"):
        conn.execute("ALTER TABLE memories ADD COLUMN project TEXT DEFAULT ''")
    conn.execute("CREATE INDEX IF NOT EXISTS idx_memories_project ON memories(project)")


def _column_exists(conn: sqlite3.Connection, table: str, column: str) -> bool:
    rows = conn.execute(f"PRAGMA table_info({table})").fetchall()
    return any(row["name"] == column for row in rows)


@contextmanager
def get_connection() -> Generator[sqlite3.Connection, None, None]:
    """Get a database connection with row factory."""
    _ensure_data_dir()
    conn = sqlite3.connect(
        str(_config.settings.db_path),
        timeout=_config.settings.db_busy_timeout_ms / 1000,
    )
    conn.row_factory = sqlite3.Row
    conn.execute("PRAGMA foreign_keys = ON")
    conn.execute(f"PRAGMA busy_timeout = {_config.settings.db_busy_timeout_ms}")
    conn.execute("PRAGMA journal_mode = WAL")
    conn.execute("PRAGMA synchronous = NORMAL")
    try:
        yield conn
        conn.commit()
    except Exception:
        conn.rollback()
        raise
    finally:
        conn.close()