basic-memory 0.7.0__py3-none-any.whl → 0.17.4__py3-none-any.whl

basic_memory/__init__.py

@@ -1,3 +1,7 @@
 """basic-memory - Local-first knowledge management combining Zettelkasten with knowledge graphs"""
 
-__version__ = "0.7.0"
+# Package version - updated by release automation
+__version__ = "0.17.4"
+
+# API version for FastAPI - independent of package version
+__api_version__ = "v0"

basic_memory/alembic/alembic.ini

@@ -0,0 +1,119 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = .
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library and tzdata library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to migrations/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:migrations/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+# version_path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+version_path_separator = os
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

basic_memory/alembic/env.py

@@ -1,22 +1,56 @@
 """Alembic environment configuration."""
 
+import asyncio
+import os
 from logging.config import fileConfig
 
-from sqlalchemy import engine_from_config
-from sqlalchemy import pool
+# Allow nested event loops (needed for pytest-asyncio and other async contexts)
+# Note: nest_asyncio doesn't work with uvloop, so we handle that case separately
+try:
+    import nest_asyncio
+
+    nest_asyncio.apply()
+except (ImportError, ValueError):
+    # nest_asyncio not available or can't patch this loop type (e.g., uvloop)
+    pass
+
+from sqlalchemy import engine_from_config, pool
+from sqlalchemy.ext.asyncio import AsyncEngine, create_async_engine
 
 from alembic import context
 
-from basic_memory.models import Base
-from basic_memory.config import config as app_config
+from basic_memory.config import ConfigManager
+
+# Trigger: only set test env when actually running under pytest
+# Why: alembic/env.py is imported during normal operations (MCP server startup, migrations)
+#      but we only want test behavior during actual test runs
+# Outcome: prevents is_test_env from returning True in production, enabling watch service
+if os.getenv("PYTEST_CURRENT_TEST") is not None:
+    os.environ["BASIC_MEMORY_ENV"] = "test"
+
+# Import after setting environment variable  # noqa: E402
+from basic_memory.models import Base  # noqa: E402
 
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.
 config = context.config
 
-# Set the SQLAlchemy URL from our app config
-sqlalchemy_url = f"sqlite:///{app_config.database_path}"
-config.set_main_option("sqlalchemy.url", sqlalchemy_url)
+# Load app config - this will read environment variables (BASIC_MEMORY_DATABASE_BACKEND, etc.)
+# due to Pydantic's env_prefix="BASIC_MEMORY_" setting
+app_config = ConfigManager().config
+
+# Set the SQLAlchemy URL based on database backend configuration
+# If the URL is already set in config (e.g., from run_migrations), use that
+# Otherwise, get it from app config
+# Note: alembic.ini has a placeholder URL "driver://user:pass@localhost/dbname" that we need to override
+current_url = config.get_main_option("sqlalchemy.url")
+if not current_url or current_url == "driver://user:pass@localhost/dbname":
+    from basic_memory.db import DatabaseType
+
+    sqlalchemy_url = DatabaseType.get_db_url(
+        app_config.database_path, DatabaseType.FILESYSTEM, app_config
+    )
+    config.set_main_option("sqlalchemy.url", sqlalchemy_url)
 
 # Interpret the config file for Python logging.
 if config.config_file_name is not None:
@@ -27,6 +61,14 @@ if config.config_file_name is not None:
 target_metadata = Base.metadata
 
 
+# Add this function to tell Alembic what to include/exclude
+def include_object(object, name, type_, reflected, compare_to):
+    # Ignore SQLite FTS tables
+    if type_ == "table" and name.startswith("search_index"):
+        return False
+    return True
+
+
 def run_migrations_offline() -> None:
     """Run migrations in 'offline' mode.
 
@@ -44,29 +86,97 @@ def run_migrations_offline() -> None:
         target_metadata=target_metadata,
         literal_binds=True,
         dialect_opts={"paramstyle": "named"},
+        include_object=include_object,
+        render_as_batch=True,
     )
 
     with context.begin_transaction():
         context.run_migrations()
 
 
+def do_run_migrations(connection):
+    """Execute migrations with the given connection."""
+    context.configure(
+        connection=connection,
+        target_metadata=target_metadata,
+        include_object=include_object,
+        render_as_batch=True,
+        compare_type=True,
+    )
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_async_migrations(connectable):
+    """Run migrations asynchronously with AsyncEngine."""
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+    await connectable.dispose()
+
+
 def run_migrations_online() -> None:
     """Run migrations in 'online' mode.
 
-    In this scenario we need to create an Engine
-    and associate a connection with the context.
+    Supports both sync engines (SQLite) and async engines (PostgreSQL with asyncpg).
     """
-    connectable = engine_from_config(
-        config.get_section(config.config_ini_section, {}),
-        prefix="sqlalchemy.",
-        poolclass=pool.NullPool,
-    )
-
-    with connectable.connect() as connection:
-        context.configure(connection=connection, target_metadata=target_metadata)
-
-        with context.begin_transaction():
-            context.run_migrations()
+    # Check if a connection/engine was provided (e.g., from run_migrations)
+    connectable = context.config.attributes.get("connection", None)
+
+    if connectable is None:
+        # No connection provided, create engine from config
+        url = context.config.get_main_option("sqlalchemy.url")
+
+        # Check if it's an async URL (sqlite+aiosqlite or postgresql+asyncpg)
+        if url and ("+asyncpg" in url or "+aiosqlite" in url):
+            # Create async engine for asyncpg or aiosqlite
+            connectable = create_async_engine(
+                url,
+                poolclass=pool.NullPool,
+                future=True,
+            )
+        else:
+            # Create sync engine for regular sqlite or postgresql
+            connectable = engine_from_config(
+                context.config.get_section(context.config.config_ini_section, {}),
+                prefix="sqlalchemy.",
+                poolclass=pool.NullPool,
+            )
+
+    # Handle async engines (PostgreSQL with asyncpg)
+    if isinstance(connectable, AsyncEngine):
+        # Try to run async migrations
+        # nest_asyncio allows asyncio.run() from within event loops, but doesn't work with uvloop
+        try:
+            asyncio.run(run_async_migrations(connectable))
+        except RuntimeError as e:
+            if "cannot be called from a running event loop" in str(e):
+                # We're in a running event loop (likely uvloop) - need to use a different approach
+                # Create a new thread to run the async migrations
+                import concurrent.futures
+
+                def run_in_thread():
+                    """Run async migrations in a new event loop in a separate thread."""
+                    new_loop = asyncio.new_event_loop()
+                    asyncio.set_event_loop(new_loop)
+                    try:
+                        new_loop.run_until_complete(run_async_migrations(connectable))
+                    finally:
+                        new_loop.close()
+
+                with concurrent.futures.ThreadPoolExecutor() as executor:
+                    future = executor.submit(run_in_thread)
+                    future.result()  # Wait for completion and re-raise any exceptions
+            else:
+                raise
+    else:
+        # Handle sync engines (SQLite) or sync connections
+        if hasattr(connectable, "connect"):
+            # It's an engine, get a connection
+            with connectable.connect() as connection:
+                do_run_migrations(connection)
+        else:
+            # It's already a connection
+            do_run_migrations(connectable)
 
 
 if context.is_offline_mode():

basic_memory/alembic/migrations.py

@@ -1,6 +1,5 @@
 """Functions for managing database migrations."""
 
-import asyncio
 from pathlib import Path
 from loguru import logger
 from alembic.config import Config
@@ -10,20 +9,16 @@ from alembic import command
 def get_alembic_config() -> Config:  # pragma: no cover
     """Get alembic config with correct paths."""
     migrations_path = Path(__file__).parent
-    alembic_ini = migrations_path.parent.parent.parent / "alembic.ini"
+    alembic_ini = migrations_path / "alembic.ini"
 
     config = Config(alembic_ini)
     config.set_main_option("script_location", str(migrations_path))
     return config
 
 
-async def reset_database():  # pragma: no cover
+def reset_database():  # pragma: no cover
     """Drop and recreate all tables."""
     logger.info("Resetting database...")
     config = get_alembic_config()
-
-    def _reset(cfg):
-        command.downgrade(cfg, "base")
-        command.upgrade(cfg, "head")
-
-    await asyncio.get_event_loop().run_in_executor(None, _reset, config)
+    command.downgrade(config, "base")
+    command.upgrade(config, "head")

basic_memory/alembic/versions/314f1ea54dc4_add_postgres_full_text_search_support_.py

@@ -0,0 +1,131 @@
+"""Add Postgres full-text search support with tsvector and GIN indexes
+
+Revision ID: 314f1ea54dc4
+Revises: e7e1f4367280
+Create Date: 2025-11-15 18:05:01.025405
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "314f1ea54dc4"
+down_revision: Union[str, None] = "e7e1f4367280"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Add PostgreSQL full-text search support.
+
+    This migration:
+    1. Creates search_index table for Postgres (SQLite uses FTS5 virtual table)
+    2. Adds generated tsvector column for full-text search
+    3. Creates GIN index on the tsvector column for fast text queries
+    4. Creates GIN index on metadata JSONB column for fast containment queries
+
+    Note: These changes only apply to Postgres. SQLite continues to use FTS5 virtual tables.
+    """
+    # Check if we're using Postgres
+    connection = op.get_bind()
+    if connection.dialect.name == "postgresql":
+        # Create search_index table for Postgres
+        # For SQLite, this is a FTS5 virtual table created elsewhere
+        from sqlalchemy.dialects.postgresql import JSONB
+
+        op.create_table(
+            "search_index",
+            sa.Column("id", sa.Integer(), nullable=False),  # Entity IDs are integers
+            sa.Column("project_id", sa.Integer(), nullable=False),  # Multi-tenant isolation
+            sa.Column("title", sa.Text(), nullable=True),
+            sa.Column("content_stems", sa.Text(), nullable=True),
+            sa.Column("content_snippet", sa.Text(), nullable=True),
+            sa.Column("permalink", sa.String(), nullable=True),  # Nullable for non-markdown files
+            sa.Column("file_path", sa.String(), nullable=True),
+            sa.Column("type", sa.String(), nullable=True),
+            sa.Column("from_id", sa.Integer(), nullable=True),  # Relation IDs are integers
+            sa.Column("to_id", sa.Integer(), nullable=True),  # Relation IDs are integers
+            sa.Column("relation_type", sa.String(), nullable=True),
+            sa.Column("entity_id", sa.Integer(), nullable=True),  # Entity IDs are integers
+            sa.Column("category", sa.String(), nullable=True),
+            sa.Column("metadata", JSONB(), nullable=True),  # Use JSONB for Postgres
+            sa.Column("created_at", sa.DateTime(timezone=True), nullable=True),
+            sa.Column("updated_at", sa.DateTime(timezone=True), nullable=True),
+            sa.PrimaryKeyConstraint(
+                "id", "type", "project_id"
+            ),  # Composite key: id can repeat across types
+            sa.ForeignKeyConstraint(
+                ["project_id"],
+                ["project.id"],
+                name="fk_search_index_project_id",
+                ondelete="CASCADE",
+            ),
+            if_not_exists=True,
+        )
+
+        # Create index on project_id for efficient multi-tenant queries
+        op.create_index(
+            "ix_search_index_project_id",
+            "search_index",
+            ["project_id"],
+            unique=False,
+        )
+
+        # Create unique partial index on permalink for markdown files
+        # Non-markdown files don't have permalinks, so we use a partial index
+        op.execute("""
+            CREATE UNIQUE INDEX uix_search_index_permalink_project
+            ON search_index (permalink, project_id)
+            WHERE permalink IS NOT NULL
+        """)
+
+        # Add tsvector column as a GENERATED ALWAYS column
+        # This automatically updates when title or content_stems change
+        op.execute("""
+            ALTER TABLE search_index
+            ADD COLUMN textsearchable_index_col tsvector
+            GENERATED ALWAYS AS (
+                to_tsvector('english',
+                    coalesce(title, '') || ' ' ||
+                    coalesce(content_stems, '')
+                )
+            ) STORED
+        """)
+
+        # Create GIN index on tsvector column for fast full-text search
+        op.create_index(
+            "idx_search_index_fts",
+            "search_index",
+            ["textsearchable_index_col"],
+            unique=False,
+            postgresql_using="gin",
+        )
+
+        # Create GIN index on metadata JSONB for fast containment queries
+        # Using jsonb_path_ops for smaller index size and better performance
+        op.execute("""
+            CREATE INDEX idx_search_index_metadata_gin
+            ON search_index
+            USING GIN (metadata jsonb_path_ops)
+        """)
+
+
+def downgrade() -> None:
+    """Remove PostgreSQL full-text search support."""
+    connection = op.get_bind()
+    if connection.dialect.name == "postgresql":
+        # Drop indexes first
+        op.execute("DROP INDEX IF EXISTS idx_search_index_metadata_gin")
+        op.drop_index("idx_search_index_fts", table_name="search_index")
+        op.execute("DROP INDEX IF EXISTS uix_search_index_permalink_project")
+        op.drop_index("ix_search_index_project_id", table_name="search_index")
+
+        # Drop the generated column
+        op.execute("ALTER TABLE search_index DROP COLUMN IF EXISTS textsearchable_index_col")
+
+        # Drop the search_index table
+        op.drop_table("search_index")

basic_memory/alembic/versions/502b60eaa905_remove_required_from_entity_permalink.py

@@ -0,0 +1,51 @@
+"""remove required from entity.permalink
+
+Revision ID: 502b60eaa905
+Revises: b3c3938bacdb
+Create Date: 2025-02-24 13:33:09.790951
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "502b60eaa905"
+down_revision: Union[str, None] = "b3c3938bacdb"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("entity", schema=None) as batch_op:
+        batch_op.alter_column("permalink", existing_type=sa.VARCHAR(), nullable=True)
+        batch_op.drop_index("ix_entity_permalink")
+        batch_op.create_index(batch_op.f("ix_entity_permalink"), ["permalink"], unique=False)
+        batch_op.drop_constraint("uix_entity_permalink", type_="unique")
+        batch_op.create_index(
+            "uix_entity_permalink",
+            ["permalink"],
+            unique=True,
+            sqlite_where=sa.text("content_type = 'text/markdown' AND permalink IS NOT NULL"),
+        )
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("entity", schema=None) as batch_op:
+        batch_op.drop_index(
+            "uix_entity_permalink",
+            sqlite_where=sa.text("content_type = 'text/markdown' AND permalink IS NOT NULL"),
+        )
+        batch_op.create_unique_constraint("uix_entity_permalink", ["permalink"])
+        batch_op.drop_index(batch_op.f("ix_entity_permalink"))
+        batch_op.create_index("ix_entity_permalink", ["permalink"], unique=1)
+        batch_op.alter_column("permalink", existing_type=sa.VARCHAR(), nullable=False)
+
+    # ### end Alembic commands ###

basic_memory/alembic/versions/5fe1ab1ccebe_add_projects_table.py

@@ -0,0 +1,120 @@
+"""add projects table
+
+Revision ID: 5fe1ab1ccebe
+Revises: cc7172b46608
+Create Date: 2025-05-14 09:05:18.214357
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "5fe1ab1ccebe"
+down_revision: Union[str, None] = "cc7172b46608"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+
+    # SQLite FTS5 virtual table handling is SQLite-specific
+    # For Postgres, search_index is a regular table managed by ORM
+    connection = op.get_bind()
+    is_sqlite = connection.dialect.name == "sqlite"
+
+    op.create_table(
+        "project",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("description", sa.Text(), nullable=True),
+        sa.Column("permalink", sa.String(), nullable=False),
+        sa.Column("path", sa.String(), nullable=False),
+        sa.Column("is_active", sa.Boolean(), nullable=False),
+        sa.Column("is_default", sa.Boolean(), nullable=True),
+        sa.Column("created_at", sa.DateTime(), nullable=False),
+        sa.Column("updated_at", sa.DateTime(), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("is_default"),
+        sa.UniqueConstraint("name"),
+        sa.UniqueConstraint("permalink"),
+        if_not_exists=True,
+    )
+    with op.batch_alter_table("project", schema=None) as batch_op:
+        batch_op.create_index(
+            "ix_project_created_at", ["created_at"], unique=False, if_not_exists=True
+        )
+        batch_op.create_index("ix_project_name", ["name"], unique=True, if_not_exists=True)
+        batch_op.create_index("ix_project_path", ["path"], unique=False, if_not_exists=True)
+        batch_op.create_index(
+            "ix_project_permalink", ["permalink"], unique=True, if_not_exists=True
+        )
+        batch_op.create_index(
+            "ix_project_updated_at", ["updated_at"], unique=False, if_not_exists=True
+        )
+
+    with op.batch_alter_table("entity", schema=None) as batch_op:
+        batch_op.add_column(sa.Column("project_id", sa.Integer(), nullable=False))
+        batch_op.drop_index(
+            "uix_entity_permalink",
+            sqlite_where=sa.text("content_type = 'text/markdown' AND permalink IS NOT NULL")
+            if is_sqlite
+            else None,
+        )
+        batch_op.drop_index("ix_entity_file_path")
+        batch_op.create_index(batch_op.f("ix_entity_file_path"), ["file_path"], unique=False)
+        batch_op.create_index("ix_entity_project_id", ["project_id"], unique=False)
+        batch_op.create_index(
+            "uix_entity_file_path_project", ["file_path", "project_id"], unique=True
+        )
+        batch_op.create_index(
+            "uix_entity_permalink_project",
+            ["permalink", "project_id"],
+            unique=True,
+            sqlite_where=sa.text("content_type = 'text/markdown' AND permalink IS NOT NULL")
+            if is_sqlite
+            else None,
+        )
+        batch_op.create_foreign_key("fk_entity_project_id", "project", ["project_id"], ["id"])
+
+    # drop the search index table. it will be recreated
+    # Only drop for SQLite - Postgres uses regular table managed by ORM
+    if is_sqlite:
+        op.drop_table("search_index")
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("entity", schema=None) as batch_op:
+        batch_op.drop_constraint("fk_entity_project_id", type_="foreignkey")
+        batch_op.drop_index(
+            "uix_entity_permalink_project",
+            sqlite_where=sa.text("content_type = 'text/markdown' AND permalink IS NOT NULL"),
+        )
+        batch_op.drop_index("uix_entity_file_path_project")
+        batch_op.drop_index("ix_entity_project_id")
+        batch_op.drop_index(batch_op.f("ix_entity_file_path"))
+        batch_op.create_index("ix_entity_file_path", ["file_path"], unique=1)
+        batch_op.create_index(
+            "uix_entity_permalink",
+            ["permalink"],
+            unique=1,
+            sqlite_where=sa.text("content_type = 'text/markdown' AND permalink IS NOT NULL"),
+        )
+        batch_op.drop_column("project_id")
+
+    with op.batch_alter_table("project", schema=None) as batch_op:
+        batch_op.drop_index("ix_project_updated_at")
+        batch_op.drop_index("ix_project_permalink")
+        batch_op.drop_index("ix_project_path")
+        batch_op.drop_index("ix_project_name")
+        batch_op.drop_index("ix_project_created_at")
+
+    op.drop_table("project")
+    # ### end Alembic commands ###