hindsight-api 0.2.1__py3-none-any.whl → 0.3.0__py3-none-any.whl

hindsight_api/admin/__init__.py

@@ -0,0 +1 @@
+# Admin CLI for Hindsight

hindsight_api/admin/cli.py

@@ -0,0 +1,252 @@
+"""
+Hindsight Admin CLI - backup and restore operations.
+"""
+
+import asyncio
+import io
+import json
+import logging
+import zipfile
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+import asyncpg
+import typer
+
+from ..config import HindsightConfig
+from ..pg0 import parse_pg0_url, resolve_database_url
+
+
+def _fq_table(table: str, schema: str) -> str:
+    """Get fully-qualified table name with schema prefix."""
+    return f"{schema}.{table}"
+
+
+# Setup logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(message)s",
+)
+logger = logging.getLogger(__name__)
+
+app = typer.Typer(name="hindsight-admin", help="Hindsight administrative commands")
+
+# Tables to backup/restore in dependency order
+# Import must happen in this order due to foreign key constraints
+BACKUP_TABLES = [
+    "banks",
+    "documents",
+    "entities",
+    "chunks",
+    "memory_units",
+    "unit_entities",
+    "entity_cooccurrences",
+    "memory_links",
+]
+
+MANIFEST_VERSION = "1"
+
+
+async def _backup(database_url: str, output_path: Path, schema: str = "public") -> dict[str, Any]:
+    """Backup all tables to a zip file using binary COPY protocol."""
+    conn = await asyncpg.connect(database_url)
+    try:
+        tables: dict[str, Any] = {}
+        manifest: dict[str, Any] = {
+            "version": MANIFEST_VERSION,
+            "created_at": datetime.now(timezone.utc).isoformat(),
+            "schema": schema,
+            "tables": tables,
+        }
+
+        # Use a transaction with REPEATABLE READ isolation to get a consistent
+        # snapshot across all tables. This prevents race conditions where
+        # entity_cooccurrences could reference entities created after the
+        # entities table was backed up.
+        async with conn.transaction(isolation="repeatable_read"):
+            with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf:
+                for i, table in enumerate(BACKUP_TABLES, 1):
+                    typer.echo(f"  [{i}/{len(BACKUP_TABLES)}] Backing up {table}...", nl=False)
+
+                    buffer = io.BytesIO()
+
+                    # Use binary COPY for exact type preservation
+                    # asyncpg requires schema_name as separate parameter
+                    await conn.copy_from_table(table, schema_name=schema, output=buffer, format="binary")
+
+                    data = buffer.getvalue()
+                    zf.writestr(f"{table}.bin", data)
+
+                    # Get row count for manifest
+                    qualified_table = _fq_table(table, schema)
+                    row_count = await conn.fetchval(f"SELECT COUNT(*) FROM {qualified_table}")
+                    tables[table] = {
+                        "rows": row_count,
+                        "size_bytes": len(data),
+                    }
+
+                    typer.echo(f" {row_count} rows")
+
+                zf.writestr("manifest.json", json.dumps(manifest, indent=2))
+
+        return manifest
+    finally:
+        await conn.close()
+
+
+async def _restore(database_url: str, input_path: Path, schema: str = "public") -> dict[str, Any]:
+    """Restore all tables from a zip file using binary COPY protocol."""
+    conn = await asyncpg.connect(database_url)
+    try:
+        with zipfile.ZipFile(input_path, "r") as zf:
+            # Read and validate manifest
+            manifest: dict[str, Any] = json.loads(zf.read("manifest.json"))
+            if manifest.get("version") != MANIFEST_VERSION:
+                raise ValueError(f"Unsupported backup version: {manifest.get('version')}")
+
+            # Use a transaction for atomic restore - either all tables are
+            # restored or none are, preventing partial/inconsistent state.
+            async with conn.transaction():
+                typer.echo("  Clearing existing data...")
+                # Truncate tables in reverse order (respects FK constraints)
+                for table in reversed(BACKUP_TABLES):
+                    qualified_table = _fq_table(table, schema)
+                    await conn.execute(f"TRUNCATE TABLE {qualified_table} CASCADE")
+
+                # Restore tables in forward order
+                for i, table in enumerate(BACKUP_TABLES, 1):
+                    filename = f"{table}.bin"
+                    if filename not in zf.namelist():
+                        typer.echo(f"  [{i}/{len(BACKUP_TABLES)}] {table}: skipped (not in backup)")
+                        continue
+
+                    expected_rows = manifest["tables"].get(table, {}).get("rows", "?")
+                    typer.echo(f"  [{i}/{len(BACKUP_TABLES)}] Restoring {table}... {expected_rows} rows")
+
+                    data = zf.read(filename)
+                    buffer = io.BytesIO(data)
+                    # asyncpg requires schema_name as separate parameter
+                    await conn.copy_to_table(table, schema_name=schema, source=buffer, format="binary")
+
+                # Refresh materialized view
+                typer.echo("  Refreshing materialized views...")
+                await conn.execute(f"REFRESH MATERIALIZED VIEW {_fq_table('memory_units_bm25', schema)}")
+
+        return manifest
+    finally:
+        await conn.close()
+
+
+async def _run_backup(db_url: str, output: Path, schema: str = "public") -> dict[str, Any]:
+    """Resolve database URL and run backup."""
+    is_pg0, instance_name, _ = parse_pg0_url(db_url)
+    if is_pg0:
+        typer.echo(f"Starting embedded PostgreSQL (instance: {instance_name})...")
+    resolved_url = await resolve_database_url(db_url)
+    return await _backup(resolved_url, output, schema)
+
+
+async def _run_restore(db_url: str, input_file: Path, schema: str = "public") -> dict[str, Any]:
+    """Resolve database URL and run restore."""
+    is_pg0, instance_name, _ = parse_pg0_url(db_url)
+    if is_pg0:
+        typer.echo(f"Starting embedded PostgreSQL (instance: {instance_name})...")
+    resolved_url = await resolve_database_url(db_url)
+    return await _restore(resolved_url, input_file, schema)
+
+
+@app.command()
+def backup(
+    output: Path = typer.Argument(..., help="Output file path (.zip)"),
+    schema: str = typer.Option("public", "--schema", "-s", help="Database schema to backup"),
+):
+    """Backup the Hindsight database to a zip file."""
+    config = HindsightConfig.from_env()
+
+    if not config.database_url:
+        typer.echo("Error: Database URL not configured.", err=True)
+        typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
+        raise typer.Exit(1)
+
+    if output.suffix != ".zip":
+        output = output.with_suffix(".zip")
+
+    typer.echo(f"Backing up database (schema: {schema}) to {output}...")
+
+    manifest = asyncio.run(_run_backup(config.database_url, output, schema))
+
+    total_rows = sum(t["rows"] for t in manifest["tables"].values())
+    typer.echo(f"Backed up {total_rows} rows across {len(BACKUP_TABLES)} tables")
+    typer.echo(f"Backup saved to {output}")
+
+
+@app.command()
+def restore(
+    input_file: Path = typer.Argument(..., help="Input backup file (.zip)"),
+    schema: str = typer.Option("public", "--schema", "-s", help="Database schema to restore to"),
+    yes: bool = typer.Option(False, "--yes", "-y", help="Skip confirmation prompt"),
+):
+    """Restore the database from a backup file. WARNING: This deletes all existing data."""
+    config = HindsightConfig.from_env()
+
+    if not config.database_url:
+        typer.echo("Error: Database URL not configured.", err=True)
+        typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
+        raise typer.Exit(1)
+
+    if not input_file.exists():
+        typer.echo(f"Error: File not found: {input_file}", err=True)
+        raise typer.Exit(1)
+
+    if not yes:
+        typer.confirm(
+            "This will DELETE all existing data and replace it with the backup. Continue?",
+            abort=True,
+        )
+
+    typer.echo(f"Restoring database (schema: {schema}) from {input_file}...")
+
+    manifest = asyncio.run(_run_restore(config.database_url, input_file, schema))
+
+    total_rows = sum(t["rows"] for t in manifest["tables"].values())
+    typer.echo(f"Restored {total_rows} rows across {len(BACKUP_TABLES)} tables")
+    typer.echo("Restore complete")
+
+
+async def _run_migration(db_url: str, schema: str = "public") -> None:
+    """Resolve database URL and run migrations."""
+    from ..migrations import run_migrations
+
+    is_pg0, instance_name, _ = parse_pg0_url(db_url)
+    if is_pg0:
+        typer.echo(f"Starting embedded PostgreSQL (instance: {instance_name})...")
+    resolved_url = await resolve_database_url(db_url)
+    run_migrations(resolved_url, schema=schema)
+
+
+@app.command(name="run-db-migration")
+def run_db_migration(
+    schema: str = typer.Option("public", "--schema", "-s", help="Database schema to run migrations on"),
+):
+    """Run database migrations to the latest version."""
+    config = HindsightConfig.from_env()
+
+    if not config.database_url:
+        typer.echo("Error: Database URL not configured.", err=True)
+        typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
+        raise typer.Exit(1)
+
+    typer.echo(f"Running database migrations (schema: {schema})...")
+
+    asyncio.run(_run_migration(config.database_url, schema))
+
+    typer.echo("Database migrations completed successfully")
+
+
+def main():
+    app()
+
+
+if __name__ == "__main__":
+    main()

hindsight_api/alembic/versions/f1a2b3c4d5e6_add_memory_links_composite_index.py

@@ -0,0 +1,44 @@
+"""add_memory_links_from_type_weight_index
+
+Revision ID: f1a2b3c4d5e6
+Revises: e0a1b2c3d4e5
+Create Date: 2025-01-12
+
+Add composite index on memory_links (from_unit_id, link_type, weight DESC)
+to optimize MPFP graph traversal queries that need top-k edges per type.
+"""
+
+from collections.abc import Sequence
+
+from alembic import context, op
+
+# revision identifiers, used by Alembic.
+revision: str = "f1a2b3c4d5e6"
+down_revision: str | Sequence[str] | None = "e0a1b2c3d4e5"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def _get_schema_prefix() -> str:
+    """Get schema prefix for table names (e.g., 'tenant_x.' or '' for public)."""
+    schema = context.config.get_main_option("target_schema")
+    return f'"{schema}".' if schema else ""
+
+
+def upgrade() -> None:
+    """Add composite index for efficient MPFP edge loading."""
+    schema = _get_schema_prefix()
+    # Create composite index for efficient top-k per (from_node, link_type) queries
+    # This enables LATERAL joins to use index-only scans with early termination
+    # Note: Not using CONCURRENTLY here as it requires running outside a transaction
+    # For production with large tables, consider running this manually with CONCURRENTLY
+    op.execute(
+        f"CREATE INDEX IF NOT EXISTS idx_memory_links_from_type_weight "
+        f"ON {schema}memory_links(from_unit_id, link_type, weight DESC)"
+    )
+
+
+def downgrade() -> None:
+    """Remove the composite index."""
+    schema = _get_schema_prefix()
+    op.execute(f"DROP INDEX IF EXISTS {schema}idx_memory_links_from_type_weight")

hindsight_api/alembic/versions/g2a3b4c5d6e7_add_tags_column.py

@@ -0,0 +1,48 @@
+"""add_tags_column
+
+Revision ID: g2a3b4c5d6e7
+Revises: f1a2b3c4d5e6
+Create Date: 2025-01-13
+
+Add tags column to memory_units and documents tables for visibility scoping.
+Tags enable filtering memories by scope (e.g., user IDs, session IDs) during recall/reflect.
+"""
+
+from collections.abc import Sequence
+
+from alembic import context, op
+
+# revision identifiers, used by Alembic.
+revision: str = "g2a3b4c5d6e7"
+down_revision: str | Sequence[str] | None = "f1a2b3c4d5e6"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def _get_schema_prefix() -> str:
+    """Get schema prefix for table names (e.g., 'tenant_x.' or '' for public)."""
+    schema = context.config.get_main_option("target_schema")
+    return f'"{schema}".' if schema else ""
+
+
+def upgrade() -> None:
+    """Add tags column to memory_units and documents tables."""
+    schema = _get_schema_prefix()
+
+    # Add tags column to memory_units table
+    op.execute(f"ALTER TABLE {schema}memory_units ADD COLUMN IF NOT EXISTS tags VARCHAR[] NOT NULL DEFAULT '{{}}'")
+
+    # Create GIN index for efficient array containment queries (tags && ARRAY['x'])
+    op.execute(f"CREATE INDEX IF NOT EXISTS idx_memory_units_tags ON {schema}memory_units USING GIN (tags)")
+
+    # Add tags column to documents table for document-level tags
+    op.execute(f"ALTER TABLE {schema}documents ADD COLUMN IF NOT EXISTS tags VARCHAR[] NOT NULL DEFAULT '{{}}'")
+
+
+def downgrade() -> None:
+    """Remove tags columns and index."""
+    schema = _get_schema_prefix()
+
+    op.execute(f"DROP INDEX IF EXISTS {schema}idx_memory_units_tags")
+    op.execute(f"ALTER TABLE {schema}memory_units DROP COLUMN IF EXISTS tags")
+    op.execute(f"ALTER TABLE {schema}documents DROP COLUMN IF EXISTS tags")