prowler/api/src/backend/config/django/base.py

from datetime import timedelta

from config.custom_logging import LOGGING  # noqa
from config.env import BASE_DIR, env  # noqa
from config.settings.celery import *  # noqa
from config.settings.eventstream import *  # noqa
from config.settings.partitions import *  # noqa
from config.settings.sentry import *  # noqa
from config.settings.social_login import *  # noqa
from django.core.exceptions import ImproperlyConfigured

SECRET_KEY = env("SECRET_KEY", default="secret")
DEBUG = env.bool("DJANGO_DEBUG", default=False)
ALLOWED_HOSTS = ["localhost", "127.0.0.1"]
SECURE_PROXY_SSL_HEADER = ("HTTP_X_FORWARDED_PROTO", "https")
USE_X_FORWARDED_HOST = True

# Application definition

INSTALLED_APPS = [
    "django.contrib.admin",
    "django.contrib.auth",
    "django.contrib.contenttypes",
    "django.contrib.sessions",
    "django.contrib.messages",
    "django.contrib.staticfiles",
    "django.contrib.postgres",
    "psqlextra",
    "api",
    "rest_framework",
    "corsheaders",
    "drf_spectacular",
    "drf_spectacular_jsonapi",
    "django_guid",
    "rest_framework_json_api",
    "django_celery_results",
    "django_celery_beat",
    "rest_framework_simplejwt.token_blacklist",
    "allauth",
    "django.contrib.sites",
    "allauth.account",
    "allauth.socialaccount",
    "allauth.socialaccount.providers.google",
    "allauth.socialaccount.providers.github",
    "allauth.socialaccount.providers.saml",
    "dj_rest_auth.registration",
    "rest_framework.authtoken",
    "drf_simple_apikey",
    "django_eventstream",
]

MIDDLEWARE = [
    "api.middleware.CloseDBConnectionsMiddleware",
    "django_guid.middleware.guid_middleware",
    "django.middleware.security.SecurityMiddleware",
    "django.contrib.sessions.middleware.SessionMiddleware",
    "corsheaders.middleware.CorsMiddleware",
    "django.middleware.common.CommonMiddleware",
    "django.middleware.csrf.CsrfViewMiddleware",
    "django.contrib.auth.middleware.AuthenticationMiddleware",
    "django.contrib.messages.middleware.MessageMiddleware",
    "django.middleware.clickjacking.XFrameOptionsMiddleware",
    "api.middleware.APILoggingMiddleware",
    "allauth.account.middleware.AccountMiddleware",
]

SITE_ID = 1

CORS_ALLOWED_ORIGINS = ["http://localhost", "http://127.0.0.1"]

ROOT_URLCONF = "config.urls"

TEMPLATES = [
    {
        "BACKEND": "django.template.backends.django.DjangoTemplates",
        "DIRS": [],
        "APP_DIRS": True,
        "OPTIONS": {
            "context_processors": [
                "django.template.context_processors.debug",
                "django.template.context_processors.request",
                "django.contrib.auth.context_processors.auth",
                "django.contrib.messages.context_processors.messages",
            ],
        },
    },
]

REST_FRAMEWORK = {
    "DEFAULT_SCHEMA_CLASS": "drf_spectacular_jsonapi.schemas.openapi.JsonApiAutoSchema",
    "DEFAULT_AUTHENTICATION_CLASSES": (
        "api.authentication.CombinedJWTOrAPIKeyAuthentication",
    ),
    "PAGE_SIZE": 10,
    "EXCEPTION_HANDLER": "api.exceptions.custom_exception_handler",
    "DEFAULT_PAGINATION_CLASS": "drf_spectacular_jsonapi.schemas.pagination.JsonApiPageNumberPagination",
    "DEFAULT_PARSER_CLASSES": (
        "rest_framework_json_api.parsers.JSONParser",
        "rest_framework.parsers.FormParser",
        "rest_framework.parsers.MultiPartParser",
    ),
    "DEFAULT_RENDERER_CLASSES": ("api.renderers.APIJSONRenderer",),
    "DEFAULT_METADATA_CLASS": "rest_framework_json_api.metadata.JSONAPIMetadata",
    "DEFAULT_FILTER_BACKENDS": (
        "rest_framework_json_api.filters.QueryParameterValidationFilter",
        "rest_framework_json_api.filters.OrderingFilter",
        "rest_framework_json_api.django_filters.backends.DjangoFilterBackend",
        "rest_framework.filters.SearchFilter",
    ),
    "SEARCH_PARAM": "filter[search]",
    "TEST_REQUEST_RENDERER_CLASSES": (
        "rest_framework_json_api.renderers.JSONRenderer",
    ),
    "TEST_REQUEST_DEFAULT_FORMAT": "vnd.api+json",
    "JSON_API_UNIFORM_EXCEPTIONS": True,
    "DEFAULT_THROTTLE_CLASSES": [
        "rest_framework.throttling.ScopedRateThrottle",
    ],
    "DEFAULT_THROTTLE_RATES": {
        "dj_rest_auth": None,
        "token-obtain": env("DJANGO_THROTTLE_TOKEN_OBTAIN", default=None),
        "attack-paths-custom-query": env(
            "DJANGO_THROTTLE_ATTACK_PATHS_CUSTOM_QUERY", default="10/min"
        ),
        "health-live": env("DJANGO_THROTTLE_HEALTH_LIVE", default="120/min"),
        "health-ready": env("DJANGO_THROTTLE_HEALTH_READY", default="60/min"),
    },
}

SPECTACULAR_SETTINGS = {
    "SERVE_INCLUDE_SCHEMA": False,
    "COMPONENT_SPLIT_REQUEST": True,
    "PREPROCESSING_HOOKS": [
        "drf_spectacular_jsonapi.hooks.fix_nested_path_parameters",
    ],
    "POSTPROCESSING_HOOKS": [
        "api.schema_hooks.attach_task_202_examples",
    ],
    "TITLE": "API Reference - Prowler",
}

WSGI_APPLICATION = "config.wsgi.application"
ASGI_APPLICATION = "config.asgi.application"

DJANGO_GUID = {
    "GUID_HEADER_NAME": "Transaction-ID",
    "VALIDATE_GUID": True,
    "RETURN_HEADER": True,
    "EXPOSE_HEADER": True,
    "INTEGRATIONS": [],
    "IGNORE_URLS": [],
    "UUID_LENGTH": 32,
}

DATABASE_ROUTERS = ["api.db_router.MainRouter"]


# Password validation
# https://docs.djangoproject.com/en/5.0/ref/settings/#auth-password-validators

AUTH_USER_MODEL = "api.User"

AUTH_PASSWORD_VALIDATORS = [
    {
        "NAME": "django.contrib.auth.password_validation.UserAttributeSimilarityValidator",
    },
    {
        "NAME": "django.contrib.auth.password_validation.MinimumLengthValidator",
        "OPTIONS": {"min_length": 12},
    },
    {
        "NAME": "api.validators.MaximumLengthValidator",
        "OPTIONS": {
            "max_length": 72,
        },
    },
    {
        "NAME": "django.contrib.auth.password_validation.CommonPasswordValidator",
    },
    {
        "NAME": "django.contrib.auth.password_validation.NumericPasswordValidator",
    },
    {
        "NAME": "api.validators.SpecialCharactersValidator",
        "OPTIONS": {
            "min_special_characters": 1,
        },
    },
    {
        "NAME": "api.validators.UppercaseValidator",
        "OPTIONS": {
            "min_uppercase": 1,
        },
    },
    {
        "NAME": "api.validators.LowercaseValidator",
        "OPTIONS": {
            "min_lowercase": 1,
        },
    },
    {
        "NAME": "api.validators.NumericValidator",
        "OPTIONS": {
            "min_numeric": 1,
        },
    },
]

SIMPLE_JWT = {
    # Token lifetime settings
    "ACCESS_TOKEN_LIFETIME": timedelta(
        minutes=env.int("DJANGO_ACCESS_TOKEN_LIFETIME", 30)
    ),
    "REFRESH_TOKEN_LIFETIME": timedelta(
        minutes=env.int("DJANGO_REFRESH_TOKEN_LIFETIME", 60 * 24)
    ),
    "ROTATE_REFRESH_TOKENS": True,
    "BLACKLIST_AFTER_ROTATION": True,
    # Algorithm and keys
    "ALGORITHM": "RS256",
    "SIGNING_KEY": env.str("DJANGO_TOKEN_SIGNING_KEY", "").replace("\\n", "\n"),
    "VERIFYING_KEY": env.str("DJANGO_TOKEN_VERIFYING_KEY", "").replace("\\n", "\n"),
    # Authorization header configuration
    "AUTH_HEADER_TYPES": ("Bearer",),
    "AUTH_HEADER_NAME": "HTTP_AUTHORIZATION",
    # Custom serializers
    "TOKEN_OBTAIN_SERIALIZER": "api.serializers.TokenSerializer",
    "TOKEN_REFRESH_SERIALIZER": "api.serializers.TokenRefreshSerializer",
    # Standard JWT claims
    "TOKEN_TYPE_CLAIM": "typ",
    "JTI_CLAIM": "jti",
    "USER_ID_FIELD": "id",
    "USER_ID_CLAIM": "sub",
    "CHECK_REVOKE_TOKEN": True,
    # Issuer and Audience claims, for the moment we will keep these values as default values, they may change in the
    # future.
    "AUDIENCE": env.str("DJANGO_JWT_AUDIENCE", "https://api.prowler.com"),
    "ISSUER": env.str("DJANGO_JWT_ISSUER", "https://api.prowler.com"),
    # Additional security settings
    "UPDATE_LAST_LOGIN": True,
}

SECRETS_ENCRYPTION_KEY = env.str("DJANGO_SECRETS_ENCRYPTION_KEY", "")

# DRF Simple API Key settings
DRF_API_KEY = {
    "FERNET_SECRET": SECRETS_ENCRYPTION_KEY,
    "API_KEY_LIFETIME": 365,
    "AUTHENTICATION_KEYWORD_HEADER": "Api-Key",
}

# Internationalization
# https://docs.djangoproject.com/en/5.0/topics/i18n/

LANGUAGE_CODE = "en-us"
LANGUAGES = [
    ("en", "English"),
]

TIME_ZONE = "UTC"

USE_I18N = True

USE_TZ = True

# Static files (CSS, JavaScript, Images)
# https://docs.djangoproject.com/en/5.0/howto/static-files/

STATIC_URL = "static/"

# Default primary key field type
# https://docs.djangoproject.com/en/5.0/ref/settings/#default-auto-field

DEFAULT_AUTO_FIELD = "django.db.models.BigAutoField"

# Cache settings
CACHE_MAX_AGE = env.int("DJANGO_CACHE_MAX_AGE", 3600)
CACHE_STALE_WHILE_REVALIDATE = env.int("DJANGO_STALE_WHILE_REVALIDATE", 60)


TESTING = False

FINDINGS_MAX_DAYS_IN_RANGE = env.int("DJANGO_FINDINGS_MAX_DAYS_IN_RANGE", 7)


# API export settings
DJANGO_TMP_OUTPUT_DIRECTORY = env.str(
    "DJANGO_TMP_OUTPUT_DIRECTORY", "/tmp/prowler_api_output"
)
DJANGO_FINDINGS_BATCH_SIZE = env.int("DJANGO_FINDINGS_BATCH_SIZE", 1000)

DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = env.str("DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET", "")
DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID = env.str("DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID", "")
DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY = env.str(
    "DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY", ""
)
DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN = env.str("DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN", "")
DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = env.str("DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION", "")
# Storage endpoint the API and Celery workers use to talk to S3-compatible object storage
# such as MinIO. Empty means the real AWS S3 endpoint, which is unaffected.
DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL = env.str("DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL", "")
# Browser-reachable storage host used to sign download URLs. Empty means sign against the
# same endpoint the API talks to, which is what Prowler Cloud on S3 does.
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL = env.str(
    "DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL", ""
)

# HTTP Security Headers
SECURE_CONTENT_TYPE_NOSNIFF = True
X_FRAME_OPTIONS = "DENY"
SECURE_REFERRER_POLICY = "strict-origin-when-cross-origin"

DJANGO_DELETION_BATCH_SIZE = env.int("DJANGO_DELETION_BATCH_SIZE", 5000)

# Public base URL of the Prowler UI (for example https://cloud.prowler.com). Used to
# build links back to findings in outbound integrations such as Jira. Empty by
# default, so self-hosted deployments emit no links unless they configure it.
UI_BASE_URL = env.str("DJANGO_UI_BASE_URL", "").rstrip("/")

# SAML requirement
CSRF_COOKIE_SECURE = True
SESSION_COOKIE_SECURE = True

# Attack Paths
ATTACK_PATHS_SCAN_INACTIVITY_THRESHOLD_MINUTES = env.int(
    "ATTACK_PATHS_SCAN_INACTIVITY_THRESHOLD_MINUTES", 30
)
ATTACK_PATHS_SCAN_STALE_THRESHOLD_MINUTES = env.int(
    "ATTACK_PATHS_SCAN_STALE_THRESHOLD_MINUTES", 960
)  # 16h

# Minimum age (of the scan row, or of the scan id itself when the row is gone) before
# the periodic reaper will drop an orphaned temp Neo4j database. Keeps a scan that is
# still legitimately in flight from ever losing its staging database mid-run.
ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS = env.int(
    "ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS", 6
)
if ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS <= 0:
    raise ImproperlyConfigured(
        "ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS must be a positive number of hours"
    )

# Selects where the persistent attack-paths graph is stored. The scan
# temporary database is always Neo4j; only the sink is configurable.
# Valid values: "neo4j" (default, OSS and local dev), "neptune" (hosted).
ATTACK_PATHS_SINK_DATABASE = env.str("ATTACK_PATHS_SINK_DATABASE", default="neo4j")

# Lighthouse AI
# Comma-separated hostnames (or IP literals) that bypass the SSRF validation
# applied to OpenAI-compatible provider base URLs, so self-hosted deployments
# can point Lighthouse AI at internal endpoints. Empty by default: every base
# URL must resolve to a public endpoint.
LIGHTHOUSE_AI_OPENAI_COMPATIBLE_ALLOWED_HOSTS = env.list(
    "LIGHTHOUSE_AI_OPENAI_COMPATIBLE_ALLOWED_HOSTS", default=[]
)

# Orphan task recovery feature flags. The master switch is OFF by default, so task
# recovery is opt-in; enable it with DJANGO_TASK_RECOVERY_ENABLED=true. The per-group
# toggles default to enabled, so once the master is on every group recovers unless a
# group is explicitly turned off.
TASK_RECOVERY_ENABLED = env.bool("DJANGO_TASK_RECOVERY_ENABLED", False)
TASK_RECOVERY_SUMMARIES_ENABLED = env.bool(
    "DJANGO_TASK_RECOVERY_SUMMARIES_ENABLED", True
)
TASK_RECOVERY_DELETIONS_ENABLED = env.bool(
    "DJANGO_TASK_RECOVERY_DELETIONS_ENABLED", True
)


def label_postgres_connections(databases):
    """Tag each Postgres connection with ``application_name="<component>:<alias>"``
    so connections are attributable by component in ``pg_stat_activity`` (and any
    tooling that surfaces ``application_name``). The component (api / worker /
    scan / ...) is injected per process by the container entrypoint via
    ``DJANGO_APP_COMPONENT``; the alias distinguishes which pool inside the
    process owns the connection. The neo4j entry is skipped (not a Postgres
    backend). Postgres truncates ``application_name`` at 63 bytes.
    """
    component = env.str("DJANGO_APP_COMPONENT", default="api")
    for alias, config in databases.items():
        engine = config.get("ENGINE", "")
        if engine.startswith("psqlextra") or "postgresql" in engine:
            name = f"{component}:{alias}"[:63]
            config.setdefault("OPTIONS", {})["application_name"] = name