mfcli 0.2.0__py3-none-any.whl

mfcli/alembic/versions/7fcb7d6a5836_init.py

@@ -0,0 +1,167 @@
+"""init
+
+Revision ID: 7fcb7d6a5836
+Revises: 
+Create Date: 2025-12-11 22:49:37.368709
+
+"""
+from typing import Sequence, Union
+
+import sqlmodel
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '7fcb7d6a5836'
+down_revision: Union[str, Sequence[str], None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('datasheets',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('part_number', sqlmodel.sql.sqltypes.AutoString(length=100), nullable=False),
+    sa.Column('datasheet', sqlmodel.sql.sqltypes.AutoString(length=500), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_datasheets_datasheet'), 'datasheets', ['datasheet'], unique=False)
+    op.create_index(op.f('ix_datasheets_part_number'), 'datasheets', ['part_number'], unique=False)
+    op.create_table('projects',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('name', sqlmodel.sql.sqltypes.AutoString(length=45), nullable=False),
+    sa.Column('index_id', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+    sa.Column('repo_dir', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+    sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('(CURRENT_TIMESTAMP)'), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_projects_index_id'), 'projects', ['index_id'], unique=True)
+    op.create_index(op.f('ix_projects_name'), 'projects', ['name'], unique=True)
+    op.create_index(op.f('ix_projects_repo_dir'), 'projects', ['repo_dir'], unique=True)
+    op.create_table('pipeline_runs',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('project_id', sa.Integer(), nullable=True),
+    sa.Column('status', sa.Integer(), server_default='0', nullable=False),
+    sa.Column('errors', sa.Text(), nullable=True),
+    sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('(CURRENT_TIMESTAMP)'), nullable=False),
+    sa.Column('updated_at', sa.DateTime(timezone=True), server_default=sa.text('(CURRENT_TIMESTAMP)'), nullable=False),
+    sa.ForeignKeyConstraint(['project_id'], ['projects.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_pipeline_runs_project_id'), 'pipeline_runs', ['project_id'], unique=False)
+    op.create_table('files',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('pipeline_run_id', sa.Integer(), nullable=False),
+    sa.Column('name', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=False),
+    sa.Column('type', sa.Integer(), nullable=False),
+    sa.Column('sub_type', sa.Integer(), nullable=True),
+    sa.Column('mime_type', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=False),
+    sa.Column('md5', sqlmodel.sql.sqltypes.AutoString(length=32), nullable=False),
+    sa.Column('ext', sqlmodel.sql.sqltypes.AutoString(length=10), nullable=True),
+    sa.Column('path', sqlmodel.sql.sqltypes.AutoString(length=600), nullable=True),
+    sa.Column('gemini_file_id', sqlmodel.sql.sqltypes.AutoString(length=40), nullable=True),
+    sa.Column('is_datasheet', sa.Integer(), nullable=False),
+    sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('(CURRENT_TIMESTAMP)'), nullable=False),
+    sa.Column('updated_at', sa.DateTime(timezone=True), server_default=sa.text('(CURRENT_TIMESTAMP)'), nullable=False),
+    sa.ForeignKeyConstraint(['pipeline_run_id'], ['pipeline_runs.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('md5', 'pipeline_run_id', name='uq_file_md5_pipeline_run')
+    )
+    op.create_index(op.f('ix_files_ext'), 'files', ['ext'], unique=False)
+    op.create_index(op.f('ix_files_is_datasheet'), 'files', ['is_datasheet'], unique=False)
+    op.create_index(op.f('ix_files_md5'), 'files', ['md5'], unique=False)
+    op.create_index(op.f('ix_files_name'), 'files', ['name'], unique=False)
+    op.create_index(op.f('ix_files_pipeline_run_id'), 'files', ['pipeline_run_id'], unique=False)
+    op.create_index(op.f('ix_files_sub_type'), 'files', ['sub_type'], unique=False)
+    op.create_index(op.f('ix_files_type'), 'files', ['type'], unique=False)
+    op.create_table('netlists',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('pipeline_run_id', sa.Integer(), nullable=False),
+    sa.Column('created_at', sa.TIMESTAMP(timezone=True), server_default=sa.text('(CURRENT_TIMESTAMP)'), nullable=False),
+    sa.ForeignKeyConstraint(['pipeline_run_id'], ['pipeline_runs.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_netlists_pipeline_run_id'), 'netlists', ['pipeline_run_id'], unique=False)
+    op.create_table('bom',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('file_id', sa.Integer(), nullable=False),
+    sa.Column('reference', sqlmodel.sql.sqltypes.AutoString(length=100), nullable=False),
+    sa.Column('value', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=False),
+    sa.Column('quantity', sa.Integer(), nullable=False),
+    sa.Column('description', sqlmodel.sql.sqltypes.AutoString(length=600), nullable=False),
+    sa.Column('manufacturer', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=True),
+    sa.Column('mpn', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=True),
+    sa.Column('lifecycle_status', sqlmodel.sql.sqltypes.AutoString(length=50), nullable=True),
+    sa.Column('supplier', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=True),
+    sa.Column('supplier_part', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=True),
+    sa.Column('supplier_unit_price', sa.Float(), nullable=True),
+    sa.Column('supplier_subtotal', sa.Float(), nullable=True),
+    sa.Column('revision_id', sqlmodel.sql.sqltypes.AutoString(length=50), nullable=True),
+    sa.Column('revision_state', sqlmodel.sql.sqltypes.AutoString(length=50), nullable=True),
+    sa.Column('revision_status', sqlmodel.sql.sqltypes.AutoString(length=100), nullable=True),
+    sa.Column('datasheet', sqlmodel.sql.sqltypes.AutoString(length=500), nullable=True),
+    sa.Column('created_at', sa.TIMESTAMP(timezone=True), server_default=sa.text('(CURRENT_TIMESTAMP)'), nullable=False),
+    sa.Column('updated_at', sa.TIMESTAMP(timezone=True), server_default=sa.text('(CURRENT_TIMESTAMP)'), nullable=False),
+    sa.ForeignKeyConstraint(['file_id'], ['files.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_bom_file_id'), 'bom', ['file_id'], unique=False)
+    op.create_table('netlist_components',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('netlist_id', sa.Integer(), nullable=False),
+    sa.Column('ref_des', sqlmodel.sql.sqltypes.AutoString(length=100), nullable=False),
+    sa.Column('part_number', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=False),
+    sa.Column('bom_entry_id', sa.Integer(), nullable=True),
+    sa.ForeignKeyConstraint(['bom_entry_id'], ['bom.id'], ondelete='CASCADE'),
+    sa.ForeignKeyConstraint(['netlist_id'], ['netlists.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_netlist_components_bom_entry_id'), 'netlist_components', ['bom_entry_id'], unique=False)
+    op.create_index(op.f('ix_netlist_components_netlist_id'), 'netlist_components', ['netlist_id'], unique=False)
+    op.create_index(op.f('ix_netlist_components_part_number'), 'netlist_components', ['part_number'], unique=False)
+    op.create_table('netlist_pins',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('netlist_component_id', sa.Integer(), nullable=False),
+    sa.Column('pin', sqlmodel.sql.sqltypes.AutoString(length=100), nullable=False),
+    sa.Column('net', sqlmodel.sql.sqltypes.AutoString(length=100), nullable=False),
+    sa.ForeignKeyConstraint(['netlist_component_id'], ['netlist_components.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_netlist_pins_netlist_component_id'), 'netlist_pins', ['netlist_component_id'], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_netlist_pins_netlist_component_id'), table_name='netlist_pins')
+    op.drop_table('netlist_pins')
+    op.drop_index(op.f('ix_netlist_components_part_number'), table_name='netlist_components')
+    op.drop_index(op.f('ix_netlist_components_netlist_id'), table_name='netlist_components')
+    op.drop_index(op.f('ix_netlist_components_bom_entry_id'), table_name='netlist_components')
+    op.drop_table('netlist_components')
+    op.drop_index(op.f('ix_bom_file_id'), table_name='bom')
+    op.drop_table('bom')
+    op.drop_index(op.f('ix_netlists_pipeline_run_id'), table_name='netlists')
+    op.drop_table('netlists')
+    op.drop_index(op.f('ix_files_type'), table_name='files')
+    op.drop_index(op.f('ix_files_sub_type'), table_name='files')
+    op.drop_index(op.f('ix_files_pipeline_run_id'), table_name='files')
+    op.drop_index(op.f('ix_files_name'), table_name='files')
+    op.drop_index(op.f('ix_files_md5'), table_name='files')
+    op.drop_index(op.f('ix_files_is_datasheet'), table_name='files')
+    op.drop_index(op.f('ix_files_ext'), table_name='files')
+    op.drop_table('files')
+    op.drop_index(op.f('ix_pipeline_runs_project_id'), table_name='pipeline_runs')
+    op.drop_table('pipeline_runs')
+    op.drop_index(op.f('ix_projects_repo_dir'), table_name='projects')
+    op.drop_index(op.f('ix_projects_name'), table_name='projects')
+    op.drop_index(op.f('ix_projects_index_id'), table_name='projects')
+    op.drop_table('projects')
+    op.drop_index(op.f('ix_datasheets_part_number'), table_name='datasheets')
+    op.drop_index(op.f('ix_datasheets_datasheet'), table_name='datasheets')
+    op.drop_table('datasheets')
+    # ### end Alembic commands ###

mfcli/alembic/versions/e0f2b5765c72_added_cascade_delete_for_models_that_.py

@@ -0,0 +1,32 @@
+"""Added cascade delete for models that did not have it
+
+Revision ID: e0f2b5765c72
+Revises: 6ccc0c7c397c
+Create Date: 2025-12-19 02:07:53.180832
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'e0f2b5765c72'
+down_revision: Union[str, Sequence[str], None] = '6ccc0c7c397c'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    pass
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    pass
+    # ### end Alembic commands ###

mfcli/alembic.ini

@@ -0,0 +1,147 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = %(here)s/alembic
+
+# 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.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+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 <script_location>/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 "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+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
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+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 module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[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

mfcli/cli/dependencies.py

@@ -0,0 +1,59 @@
+import os
+import subprocess
+import sys
+
+from pydantic import ValidationError
+
+from mfcli.utils.config import get_config
+from mfcli.utils.directory_manager import app_dirs
+from mfcli.utils.logger import get_logger
+
+logger = get_logger(__name__)
+
+
+def is_playwright_installed() -> bool:
+    try:
+        from playwright.sync_api import sync_playwright
+        with sync_playwright() as p:
+            path = p.chromium.executable_path
+            if path is None or path.strip() == "":
+                return False
+            if not os.path.exists(path):
+                return False
+            return True
+    except Exception:
+        return False
+
+
+def ensure_playwright_installed():
+    if not is_playwright_installed():
+        try:
+            subprocess.run([sys.executable, "-m", "playwright", "install"], check=True)
+        except subprocess.CalledProcessError as e:
+            logger.error("Failed to install Playwright automatically.")
+            logger.error(f"Error details: {e}")
+            logger.error("You can try installing Playwright manually by running:")
+            logger.error("    python -m playwright install")
+            logger.error("For more information, see https://playwright.dev/python/docs/intro")
+            sys.exit(1)
+def check_dependencies():
+    env_file_path = app_dirs.env_file_path
+    logger.debug(f".env file path: {env_file_path}")
+    if os.path.exists(env_file_path) and os.access(env_file_path, os.R_OK):
+        logger.debug(f".env file found: {env_file_path}")
+    else:
+        logger.error(f".env file does not exist or cannot be read: {env_file_path}")
+        logger.error("Please add your api keys to .env using .env.example in the project folder")
+        logger.error(f".env file must be in your home directory: {env_file_path}")
+        sys.exit(1)
+    try:
+        logger.debug(f"Validating .env file: {env_file_path}")
+        get_config()
+        logger.debug(f".env file validated: {env_file_path}")
+    except ValidationError as e:
+        logger.exception(e)
+        logger.error(f".env file is not formatted properly: {env_file_path}")
+    if not is_playwright_installed():
+        logger.warning("Playwright is not installed")
+        logger.debug("Installing playwright")
+        ensure_playwright_installed()

mfcli/cli/main.py

@@ -0,0 +1,192 @@
+import asyncio
+import argparse
+import os.path
+from pathlib import Path
+
+from mfcli.cli.dependencies import check_dependencies
+from mfcli.crud.project import init_project, read_project_config_file
+from mfcli.models.project_metadata import ProjectConfig
+from mfcli.utils.config import get_config
+from mfcli.utils.data_cleaner import clean_app_data
+from mfcli.utils.directory_manager import init_directory_structure
+from mfcli.utils.logger import get_logger
+from mfcli.utils.vectorizer import add_file_to_db
+from mfcli.utils.kb_lister import print_vectorized_files
+from mfcli.utils.kb_remover import remove_files_from_kb
+
+# TODO: CREATE PIP PACKAGE
+# TODO: all files go into knowledgebase
+# TODO: HEAD FILES/REMOVE LOG OUTPUT
+# TODO: DATASHEETS DO NOT NEED TO BE VECTORIZED TWICE
+# TODO: IF METADATA FILE EXISTS BUT DB PROJECT DOESN'T - CREATE IT
+
+
+cli_prog_name = "mfcli"
+
+desc = "Multifactor AI-powered pipeline to analyze hardware engineering documents like schematics and BOMs"
+
+logger = get_logger(__name__)
+
+
+def init():
+    config = get_config()
+    os.environ["GOOGLE_API_KEY"] = config.google_api_key
+
+
+def run_web_server(port: int):
+    import uvicorn
+    from fastapi import FastAPI
+    from google.adk.cli.fast_api import get_fast_api_app
+    agent_dir = str(Path(__file__).parent.parent / "agents")
+    db_dir = Path(__file__).parent.parent.parent
+    db_url = f"sqlite:///{db_dir / "sessions.db"}"
+    app: FastAPI = get_fast_api_app(
+        agents_dir=agent_dir,
+        session_service_uri=db_url,
+        allow_origins=["*"],
+        web=True
+    )
+    uvicorn.run(
+        app,
+        host="0.0.0.0",
+        port=port,
+        reload=False
+    )
+
+
+def start_pipeline(project_config: ProjectConfig):
+    from mfcli.pipeline.pipeline import run_pipeline_with_config
+    asyncio.run(run_pipeline_with_config(project_config))
+
+
+def run_cli():
+    from mfcli.utils.logger import setup_logging
+
+    setup_logging()
+    init()
+    logger.debug("Starting CLI")
+    logger.debug("Checking dependencies")
+    check_dependencies()
+    parser = argparse.ArgumentParser(
+        prog=cli_prog_name,
+        description=desc
+    )
+    sub = parser.add_subparsers(dest="command", required=True)
+    init_cmd = sub.add_parser(
+        "init",
+        help="Initialize a repo containing hardware design documents"
+    )
+    init_cmd.add_argument(
+        "--name",
+        type=str,
+        default=None,
+        help="Project name (defaults to current directory name)"
+    )
+
+    sub.add_parser(
+        "run",
+        help="Run the analysis pipeline on the current directory"
+    )
+    web_cmd = sub.add_parser(
+        "web",
+        help="Start web UI"
+    )
+    web_cmd.add_argument("--port", type=int, default=9999)
+
+    clean_cmd = sub.add_parser(
+        "clean",
+        help="Clean all mfcli app data"
+    )
+    clean_cmd.add_argument(
+        "--accept",
+        action="store_true",
+        help="Skip confirmation prompt"
+    )
+
+    add_cmd = sub.add_parser(
+        "add",
+        help="Add a file to the ChromaDB database"
+    )
+    add_cmd.add_argument(
+        "file",
+        type=Path,
+        help="Path to the file to add to ChromaDB"
+    )
+    add_cmd.add_argument(
+        "--purpose",
+        type=str,
+        default="datasheet",
+        help="Purpose/category for the file (e.g., 'datasheet', 'manual', 'specification'). Default: 'datasheet'"
+    )
+
+    sub.add_parser(
+        "ls",
+        help="List all files that have been vectorized into the ChromaDB knowledge base"
+    )
+
+    rm_cmd = sub.add_parser(
+        "rm",
+        help="Remove files from the ChromaDB knowledge base by filename or partial match"
+    )
+    rm_cmd.add_argument(
+        "filename",
+        type=str,
+        help="Full or partial filename to match (case-insensitive)"
+    )
+    rm_cmd.add_argument(
+        "--yes",
+        action="store_true",
+        help="Skip confirmation prompt and delete immediately"
+    )
+
+    configure_cmd = sub.add_parser(
+        "configure",
+        help="Interactive setup wizard to configure API keys and settings"
+    )
+    configure_cmd.add_argument(
+        "--check",
+        action="store_true",
+        help="Check existing configuration and validate API keys"
+    )
+
+    sub.add_parser(
+        "setup-mcp",
+        help="Auto-configure MCP server for Cline and Claude Code"
+    )
+
+    sub.add_parser(
+        "doctor",
+        help="Run system health checks and diagnose issues"
+    )
+
+    args = parser.parse_args()
+
+    init_directory_structure(os.getcwd())
+    if args.command == "init":
+        init_project(args.name)
+    elif args.command == "clean":
+        clean_app_data(args.accept)
+    else:
+        project_config = read_project_config_file()
+        if args.command == "run":
+            start_pipeline(project_config)
+        elif args.command == "web":
+            run_web_server(args.port)
+        elif args.command == "add":
+            add_file_to_db(project_config.name, args.file, args.purpose)
+        elif args.command == "ls":
+            print_vectorized_files(project_config.name)
+        elif args.command == "rm":
+            remove_files_from_kb(project_config.name, args.filename, confirm=not args.yes)
+        elif args.command == "configure":
+            from mfcli.utils.configurator import run_configuration_wizard, check_configuration
+            if args.check:
+                check_configuration()
+            else:
+                run_configuration_wizard()
+        elif args.command == "setup-mcp":
+            from mfcli.utils.mcp_configurator import setup_mcp_servers
+            setup_mcp_servers()
+        elif args.command == "doctor":
+            from mfcli.utils.system_check import run_system_check
+            run_system_check()