gendesign/backend/app/workers/celery_app.py
bot-backend cf7e7ec8c8
All checks were successful
CI Trade-In / changes (pull_request) Successful in 8s
CI / changes (pull_request) Successful in 9s
CI Trade-In / backend-tests (pull_request) Has been skipped
CI Trade-In / browser-tests (pull_request) Has been skipped
CI Trade-In / frontend-checks (pull_request) Has been skipped
CI / frontend-tests (pull_request) Has been skipped
CI / openapi-codegen-check (pull_request) Successful in 2m15s
CI / backend-tests (pull_request) Successful in 15m14s
fix(ptica): скраб ПДн на transaction-канале + company/message ключи (review #2749)
before_send_transaction в main.py/celery_app.py оставался на голом
scrub_sensitive_query (только URL) — Starlette-интеграция кладёт request.data
на transaction-scope так же, как на error-scope, поэтому PII продолжало течь
через transaction-канал при glitchtip_traces_sample_rate > 0 (0.05 по
умолчанию, config.py:19). Оба канала теперь на едином composed-хендлере
scrub_event (PII-scrub + URL-secret redact), вынесенном в sentry_scrub.py.

_PII_KEYS расширен до полного набора МЕРЫ (client_name/client_phone/
client_email/phone/email/name, #396) + company/message — PilotRequestInput
(app/api/v1/pilot.py) несёт оба свободнотекстовых поля, куда чаще всего
прилетают телефоны/имена/адреса.

scrub_event обёрнут в try/except (возвращает event при сбое скраба) —
sentry_sdk capture_internal_exceptions иначе только логирует и ДРОПАЕТ event
целиком, если before_send бросает исключение. Убрана мёртвая ветка
"if scrubbed is None: return None" — scrub_pii_event никогда не возвращает
None.

Тесты: новые ключи (company/message/client_phone/client_email), scrub_event
composition + exception-safety, source-grep wiring-гейт на саму строку
before_send_transaction=scrub_event в main.py/celery_app.py.
2026-08-06 21:22:57 +03:00

110 lines
4.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""Celery app — single source of truth для Celery configuration.
Beat schedule build → app/workers/beat_schedule.py.
Worker lifecycle hooks (process_init, worker_ready) → app/workers/lifecycle.py.
"""
import logging
import os
import sentry_sdk
from celery import Celery
from sentry_sdk.integrations.celery import CeleryIntegration
from sentry_sdk.integrations.httpx import HttpxIntegration
from sentry_sdk.integrations.logging import LoggingIntegration
from sentry_sdk.integrations.sqlalchemy import SqlalchemyIntegration
from app.core.config import settings
from app.observability.sentry_scrub import scrub_event
logger = logging.getLogger(__name__)
# SDK инициализируется в обоих процессах (FastAPI-сервер и Celery-воркер),
# чтобы события из тасков попадали в GlitchTip. SDK безопасен для двойного
# вызова — повторный sentry_sdk.init() в одном процессе заменяет клиента.
if settings.glitchtip_dsn:
# before_send И before_send_transaction — ОБА на scrub_event (#2457-review,
# см. app/main.py и sentry_scrub.py module docstring): до этого фикса worker
# вообще не скрабил error-события (тут before_send не было), а
# before_send_transaction был на голом scrub_sensitive_query (только URL) —
# оба канала пропускали PII.
sentry_sdk.init(
dsn=settings.glitchtip_dsn,
environment=settings.environment,
release=os.getenv("GIT_SHA") or os.getenv("SENTRY_RELEASE") or "unknown",
traces_sample_rate=settings.glitchtip_traces_sample_rate,
profiles_sample_rate=0.0,
send_default_pii=False,
before_send=scrub_event,
before_send_transaction=scrub_event,
integrations=[
CeleryIntegration(monitor_beat_tasks=True),
SqlalchemyIntegration(),
HttpxIntegration(),
LoggingIntegration(level=logging.INFO, event_level=logging.ERROR),
],
)
logger.info(
"GlitchTip SDK initialised in Celery worker (env=%s)",
settings.environment,
)
celery_app = Celery(
"gendesign",
broker=settings.redis_url,
backend=settings.redis_url,
include=[
"app.workers.tasks.scrape_kn",
"app.workers.tasks.scrape_kn_catalog_objects",
"app.workers.tasks.scrape_kn_catalog_flats",
"app.workers.tasks.refresh_analytics",
"app.workers.tasks.scrape_objective",
"app.workers.tasks.objective_etl",
"app.workers.tasks.nspd_geo",
"app.workers.tasks.nspd_sync",
"app.workers.tasks.poi_sync",
"app.workers.tasks.noise_sync",
"app.workers.tasks.utility_infrastructure_sync",
"app.workers.tasks.pzz_sync",
"app.workers.tasks.scrape_cadastre",
"app.workers.tasks.ekburg_permits_sync",
"app.workers.tasks.cbr_macro_sync",
"app.workers.tasks.rosstat_macro_sync",
"app.workers.tasks.refresh_quarter_price_index",
"app.workers.tasks.etl_newbuilding_crossload",
"app.workers.tasks.supply_layers_refresh",
"app.workers.tasks.location_refresh",
"app.workers.tasks.forecast",
"app.workers.tasks.full_report",
"app.workers.tasks.ird_harvest",
"app.workers.tasks.ekb_krt_sync",
"app.workers.tasks.gknspecial_harvest",
"app.workers.tasks.opportunity_harvest",
"app.workers.tasks.planning_harvest",
"app.workers.tasks.zone_regulation_refresh",
"app.workers.tasks.backfill_zone_regulations",
"app.workers.tasks.reservation_ingest",
"app.workers.tasks.genplan_zones_sync",
"app.workers.tasks.ekb_ppt_tep_sync",
"app.workers.tasks.krt_geometry_sync",
"app.workers.tasks.okn_objects_sync",
"app.workers.tasks.pat_subzones_load",
"app.workers.tasks.izyatie_ocr_ingest",
"app.workers.tasks.developer_registry_refresh",
"app.workers.tasks.refresh_layout_velocity",
"app.workers.tasks.riasurt_sverdl_harvest",
"app.workers.tasks.mv_sales_tracker_refresh",
"app.workers.tasks.scrape_freshness_check",
"app.workers.tasks.connection_capacity_sync",
"app.workers.tasks.gisogd_permits_sync",
],
)
celery_app.conf.timezone = "Europe/Moscow"
# Apply beat schedule (DB → fallback → hardcoded entries)
from app.workers.beat_schedule import build_beat_schedule # noqa: E402
celery_app.conf.beat_schedule = build_beat_schedule()
# Register lifecycle hooks (import for side-effect — signal decorator registration)
from app.workers import lifecycle # noqa: E402, F401